ABSTRACT
Abstract
Systems and methods managing, by an orchestrator, a plurality of agents to generate a response to an input. The orchestrator employs one or more multimodal models such as a large language models to process or deconstruct the prompt into a series of instructions for different agents. Each agent employs one or more machine-learning models to process disparate inputs or different portions of an input associated with the prompt. The system generates, by the orchestrator, a natural language summary of the structured and unstructured data records. The system formulates output and transmits the natural language summary of the data records.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
The present application claims the benefit of U.S. Provisional Patent Application Ser. No. 63/433,124 filed Dec. 16, 2022 and entitled âUnbounded Data Model Query Handling and Dispatching Action in a Model Driven Architecture,â U.S. Provisional Patent Application Ser. No. 63/446,792 filed Feb. 17, 2023 and entitled âSystem and Method to Apply Generative AI to Transform Information Access and Content Creation for Enterprise Information Systems,â and U.S. Provisional Patent Application Ser. No. 63/492,133 filed Mar. 24, 2023 and entitled âIterative Context-based Generative Artificial Intelligence,â each of which is hereby incorporated by reference herein.
TECHNICAL FIELD
This disclosure pertains to generative artificial intelligence and machine learning. More specifically, this disclosure pertains to enterprise generative artificial intelligence architectures.
BACKGROUND
Artificial intelligence (AI) is a branch of computer science for the development of software that allows computer systems to perform tasks that imitate human cognitive intelligence, such as visual perception, speech recognition, decision-making, and language translation. Traditional approaches for storing and retrieving information typically involves databases and applications to index search and locate specific files.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 depicts a diagram of an example logical flow of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 2 depicts a diagram of an example layered architecture and environment of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 3 depicts a diagram of an example architecture of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 4 depicts a diagram of an example network system for enterprise generative artificial intelligence according to some embodiments.
FIG. 5 depicts a diagram of an example enterprise generative artificial intelligence system according to some embodiments.
FIG. 6 depicts a flowchart of an example generative artificial intelligence unstructured data and structured data retrieval process.
FIG. 7 depicts a diagram of an example logical flow of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 8 A depicts a flowchart of an example iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIGS. 8 B-C depict flowcharts of example non-iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIG. 9 depicts a flowchart of an example iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIG. 10 depicts a flowchart of an example generative artificial intelligence process using unstructured data and structured data according to some embodiments.
FIG. 11 depicts a flowchart of an example generative artificial intelligence process using unstructured data and structured data according to some embodiments.
FIG. 12 depicts a flowchart of an example of a non-iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIG. 13 depicts a flowchart of an example of a generative artificial intelligence process using structured data according to some embodiments.
FIG. 14 depicts a flowchart of an example operation of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 15 is a diagram of an example computer system for implementing the features disclosed herein according to some embodiments.
DETAILED DESCRIPTION
Generative AI is an artificial intelligence technology that uses machine learning algorithms to perform tasks that imitate human cognitive intelligence and generate content. Content can be in the form of text, audio, video, images, and more. Content in enterprise computing environments is typically spread across disparate data sources that may be incompatible, siloed, and access controlled. Supporting efficient search capabilities is further complicated in circumstance that require subject matter expertise or context specific knowledge.
An architecture for enterprise generative AI is disclosed herein to transform interactions with enterprise information that fundamentally change the human-computer interaction (HCI) model for enterprise software. Enterprises running sensitive workloads in both cloud-native, on premise, or air-gapped environments can implement enterprise generative AI architecture to generate enterprise-wide insights using tool to rapidly locate and retrieve with agents that develop and coordinate complex operations in response to simple intuitive input. The enterprise generative AI architecture enables enterprise users to ask open-ended, multi-level, context specific questions that are processed used generative AI with machine learning to understand the request, identify relevant information, and generate new context specific insights with predictive analysis. The enterprise generative AI architecture supports simplified human-computer-interactions with intuitive natural language interface as well as advanced accessibility features for adaptable forms of input including but not limited to text, audio, video, images, and more.
Conventional generative artificial intelligence processes are computationally inefficient, often present faulty or biased information, cannot effectively handle different types of inputs and outputs, fail to effectively leverage disparate data sources with different data formats, and fail to interact effectively with other machine learning systems or effectively leverage information across different domains. These problems, as well as those discussed above, are addressed by the enterprise generative artificial intelligence systems and processes discussed herein. More specifically, enterprise generative artificial intelligence systems can efficiently provide more accurate and reliable results than conventional generative artificial intelligence solutions while consuming fewer computing resources and requiring shorter processing times. Furthermore, enterprise generative artificial intelligence systems can employ various models that effectively provide cross-domain functionality. Enterprise generative artificial intelligence systems can further use a combination of agents and tools to efficiently process a wide variety of inputs received from disparate data sources (e.g., having different data formats) and return results in a common data format (e.g., natural language).
The enterprise generative artificial intelligence architecture includes an orchestrator agent (or, simply, orchestrator) that supervises, controls, and/or otherwise administrates many different agents and tools. Orchestrators can include one or more machine learning models and can execute supervisory functions, such as routing inputs (e.g., queries, instruction sets, natural language inputs or other human-readable inputs, machine-readable inputs) to specific agents to accomplish a set of prescribed tasks (e.g., retrieval requests prescribed by the orchestrator to answer a query). Machine learning models can include some or all of the different types or modalities of models described herein (e.g., multimodal machine learning models, large language models, data models, statistical models, audio models, visual models, audiovisual models, etc.). Agents can include one or more multimodal models (e.g., large language models) to accomplish the prescribed tasks using a variety of different tools. Different agents can use various tools to execute and process unstructured data retrieval requests, structured data retrieval requests, API calls (e.g., for accessing artificial intelligence application insights), and the like. Tools can include one or more specific functions and/or machine learning models to accomplish a given task (or set of tasks).
Agents can adapt to perform differently based on contexts. A context may relate to a particular domain (e.g., industry) and an agent may employ a particular model (e.g., large language model, other machine learning model, and/or data model) that has been trained on industry-specific datasets, such as healthcare datasets. The particular agent can use a healthcare model when receiving inputs associated with a healthcare environment and can also easily and efficiently adapt to use a different model based on different inputs or context. Indeed, some or all of the models described herein may be trained for specific domains in addition to, or instead of, more general purposes. The enterprise generative artificial intelligence architecture leverages domain specific models to produce accurate context specific retrieval and insights.
The orchestrator manages the agents to efficiently process disparate inputs or different portions of an input. For example, an input may require the system to access and retrieve data records from disparate data sources (e.g., unstructured datastores, structured datastores, timeseries datastores, and the like), database tables from different types of databases, and machine learning insights from different machine learning applications. The different agents can each separately, and in parallel, handle each of these requests, greatly increasing computational efficiency.
Agents can process the disparate data returned by the different agents and/or tools. For example, large language models typically receive inputs in natural language format. The agents may receive information in a non-natural language format (e.g., database table, image, audio) from a tool and transform it into natural language describing the tool output in a format understood by large language models. A large language model can then process that input to âanswer,â or otherwise satisfy the initial input.
FIG. 1 depicts a diagram 100 of an example logical flow of an enterprise generative artificial intelligence system according to some embodiments. As shown, an initial input 102 is received by the system from either a user (e.g., a natural language input) or another system (e.g., a machine-readable input).
An orchestrator agent (or, simply, orchestrator) can pre-process the input in step 104 . Pre-processing can include, for example, acronym handling, translation handling, punctuation handling, input identification (e.g., identifying different portions of the input 102 for processing by different agents). The orchestrator can use a multimodal model (e.g., large language model) to further process the input 102 to create a plan for determining a result (step 112 ) for the input. The plan may include a prescribed set of tasks, such as structured data retrieval tasks, unstructured data retrieval tasks, timeseries processing tasks, visualization tasks, and the like. In some embodiments, the plan can designate which tools 108 should be used to execute the tasks, and the orchestrator can select the agents based on the designated tools. In some embodiments, the plan can designate which agents should be used to execute the tasks, and the agents can independently designate which tools 108 should be used to execute the tasks.
Continuing the example of FIG. 1 , the orchestrator routes the pre-processed input to agents 106 for further processing. More specifically, the orchestrator may use one or more multimodal models (e.g., language, video, audio, statistical models, etc.), and/or other machine learning models, to interpret the input 102 to select appropriate agents 106 and appropriate tools 108 . For example, the orchestrator may determine that a first portion of the input requires a database query, while another portion of the input requires an API call. The orchestrator can appropriately route the first portion of the input to the appropriate agent 106 - 1 (e.g., a structured data retrieval agent) and route the second portion of the input to another agent 106 - 2 (e.g., API agent). There could be any number of such agents 106 accessing any number of different tools 108 . The orchestrator may also instruct the agents 106 to operate in parallel and/or serially.
The agents 106 can select the appropriate tools 108 to accomplish a set of prescribed tasks (e.g., tasks prescribed by the orchestrator). The tools 108 can make the appropriate function calls to retrieve disparate data records among other functions. As used herein, data records can include unstructured data records (e.g., documents and text data that is stored on a file system in a format such as PDF, DOCX, .MD, HTML, TXT, PPTX, image files, audio files, video files, application outputs, and the like), structured data records (e.g., database tables or other data records stored according to a data model or type system), timeseries data records (e.g., sensor data, artificial intelligence application insights), and/or other types of data records (e.g., access control lists). The agents</figure-ca
CROSS-REFERENCE TO RELATED APPLICATIONS
The present application claims the benefit of U.S. Provisional Patent Application Ser. No. 63/433,124 filed Dec. 16, 2022 and entitled âUnbounded Data Model Query Handling and Dispatching Action in a Model Driven Architecture,â U.S. Provisional Patent Application Ser. No. 63/446,792 filed Feb. 17, 2023 and entitled âSystem and Method to Apply Generative AI to Transform Information Access and Content Creation for Enterprise Information Systems,â and U.S. Provisional Patent Application Ser. No. 63/492,133 filed Mar. 24, 2023 and entitled âIterative Context-based Generative Artificial Intelligence,â each of which is hereby incorporated by reference herein.
TECHNICAL FIELD
This disclosure pertains to generative artificial intelligence and machine learning. More specifically, this disclosure pertains to enterprise generative artificial intelligence architectures.
BACKGROUND
Artificial intelligence (AI) is a branch of computer science for the development of software that allows computer systems to perform tasks that imitate human cognitive intelligence, such as visual perception, speech recognition, decision-making, and language translation. Traditional approaches for storing and retrieving information typically involves databases and applications to index search and locate specific files.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 depicts a diagram of an example logical flow of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 2 depicts a diagram of an example layered architecture and environment of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 3 depicts a diagram of an example architecture of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 4 depicts a diagram of an example network system for enterprise generative artificial intelligence according to some embodiments.
FIG. 5 depicts a diagram of an example enterprise generative artificial intelligence system according to some embodiments.
FIG. 6 depicts a flowchart of an example generative artificial intelligence unstructured data and structured data retrieval process.
FIG. 7 depicts a diagram of an example logical flow of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 8 A depicts a flowchart of an example iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIGS. 8 B-C depict flowcharts of example non-iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIG. 9 depicts a flowchart of an example iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIG. 10 depicts a flowchart of an example generative artificial intelligence process using unstructured data and structured data according to some embodiments.
FIG. 11 depicts a flowchart of an example generative artificial intelligence process using unstructured data and structured data according to some embodiments.
FIG. 12 depicts a flowchart of an example of a non-iterative generative artificial intelligence process using unstructured data according to some embodiments.
FIG. 13 depicts a flowchart of an example of a generative artificial intelligence process using structured data according to some embodiments.
FIG. 14 depicts a flowchart of an example operation of an enterprise generative artificial intelligence system according to some embodiments.
FIG. 15 is a diagram of an example computer system for implementing the features disclosed herein according to some embodiments.
DETAILED DESCRIPTION
Generative AI is an artificial intelligence technology that uses machine learning algorithms to perform tasks that imitate human cognitive intelligence and generate content. Content can be in the form of text, audio, video, images, and more. Content in enterprise computing environments is typically spread across disparate data sources that may be incompatible, siloed, and access controlled. Supporting efficient search capabilities is further complicated in circumstance that require subject matter expertise or context specific knowledge.
An architecture for enterprise generative AI is disclosed herein to transform interactions with enterprise information that fundamentally change the human-computer interaction (HCI) model for enterprise software. Enterprises running sensitive workloads in both cloud-native, on premise, or air-gapped environments can implement enterprise generative AI architecture to generate enterprise-wide insights using tool to rapidly locate and retrieve with agents that develop and coordinate complex operations in response to simple intuitive input. The enterprise generative AI architecture enables enterprise users to ask open-ended, multi-level, context specific questions that are processed used generative AI with machine learning to understand the request, identify relevant information, and generate new context specific insights with predictive analysis. The enterprise generative AI architecture supports simplified human-computer-interactions with intuitive natural language interface as well as advanced accessibility features for adaptable forms of input including but not limited to text, audio, video, images, and more.
Conventional generative artificial intelligence processes are computationally inefficient, often present faulty or biased information, cannot effectively handle different types of inputs and outputs, fail to effectively leverage disparate data sources with different data formats, and fail to interact effectively with other machine learning systems or effectively leverage information across different domains. These problems, as well as those discussed above, are addressed by the enterprise generative artificial intelligence systems and processes discussed herein. More specifically, enterprise generative artificial intelligence systems can efficiently provide more accurate and reliable results than conventional generative artificial intelligence solutions while consuming fewer computing resources and requiring shorter processing times. Furthermore, enterprise generative artificial intelligence systems can employ various models that effectively provide cross-domain functionality. Enterprise generative artificial intelligence systems can further use a combination of agents and tools to efficiently process a wide variety of inputs received from disparate data sources (e.g., having different data formats) and return results in a common data format (e.g., natural language).
The enterprise generative artificial intelligence architecture includes an orchestrator agent (or, simply, orchestrator) that supervises, controls, and/or otherwise administrates many different agents and tools. Orchestrators can include one or more machine learning models and can execute supervisory functions, such as routing inputs (e.g., queries, instruction sets, natural language inputs or other human-readable inputs, machine-readable inputs) to specific agents to accomplish a set of prescribed tasks (e.g., retrieval requests prescribed by the orchestrator to answer a query). Machine learning models can include some or all of the different types or modalities of models described herein (e.g., multimodal machine learning models, large language models, data models, statistical models, audio models, visual models, audiovisual models, etc.). Agents can include one or more multimodal models (e.g., large language models) to accomplish the prescribed tasks using a variety of different tools. Different agents can use various tools to execute and process unstructured data retrieval requests, structured data retrieval requests, API calls (e.g., for accessing artificial intelligence application insights), and the like. Tools can include one or more specific functions and/or machine learning models to accomplish a given task (or set of tasks).
Agents can adapt to perform differently based on contexts. A context may relate to a particular domain (e.g., industry) and an agent may employ a particular model (e.g., large language model, other machine learning model, and/or data model) that has been trained on industry-specific datasets, such as healthcare datasets. The particular agent can use a healthcare model when receiving inputs associated with a healthcare environment and can also easily and efficiently adapt to use a different model based on different inputs or context. Indeed, some or all of the models described herein may be trained for specific domains in addition to, or instead of, more general purposes. The enterprise generative artificial intelligence architecture leverages domain specific models to produce accurate context specific retrieval and insights.
The orchestrator manages the agents to efficiently process disparate inputs or different portions of an input. For example, an input may require the system to access and retrieve data records from disparate data sources (e.g., unstructured datastores, structured datastores, timeseries datastores, and the like), database tables from different types of databases, and machine learning insights from different machine learning applications. The different agents can each separately, and in parallel, handle each of these requests, greatly increasing computational efficiency.
Agents can process the disparate data returned by the different agents and/or tools. For example, large language models typically receive inputs in natural language format. The agents may receive information in a non-natural language format (e.g., database table, image, audio) from a tool and transform it into natural language describing the tool output in a format understood by large language models. A large language model can then process that input to âanswer,â or otherwise satisfy the initial input.
FIG. 1 depicts a diagram 100 of an example logical flow of an enterprise generative artificial intelligence system according to some embodiments. As shown, an initial input 102 is received by the system from either a user (e.g., a natural language input) or another system (e.g., a machine-readable input).
An orchestrator agent (or, simply, orchestrator) can pre-process the input in step 104 . Pre-processing can include, for example, acronym handling, translation handling, punctuation handling, input identification (e.g., identifying different portions of the input 102 for processing by different agents). The orchestrator can use a multimodal model (e.g., large language model) to further process the input 102 to create a plan for determining a result (step 112 ) for the input. The plan may include a prescribed set of tasks, such as structured data retrieval tasks, unstructured data retrieval tasks, timeseries processing tasks, visualization tasks, and the like. In some embodiments, the plan can designate which tools 108 should be used to execute the tasks, and the orchestrator can select the agents based on the designated tools. In some embodiments, the plan can designate which agents should be used to execute the tasks, and the agents can independently designate which tools 108 should be used to execute the tasks.
Continuing the example of FIG. 1 , the orchestrator routes the pre-processed input to agents 106 for further processing. More specifically, the orchestrator may use one or more multimodal models (e.g., language, video, audio, statistical models, etc.), and/or other machine learning models, to interpret the input 102 to select appropriate agents 106 and appropriate tools 108 . For example, the orchestrator may determine that a first portion of the input requires a database query, while another portion of the input requires an API call. The orchestrator can appropriately route the first portion of the input to the appropriate agent 106 - 1 (e.g., a structured data retrieval agent) and route the second portion of the input to another agent 106 - 2 (e.g., API agent). There could be any number of such agents 106 accessing any number of different tools 108 . The orchestrator may also instruct the agents 106 to operate in parallel and/or serially.
The agents 106 can select the appropriate tools 108 to accomplish a set of prescribed tasks (e.g., tasks prescribed by the orchestrator). The tools 108 can make the appropriate function calls to retrieve disparate data records among other functions. As used herein, data records can include unstructured data records (e.g., documents and text data that is stored on a file system in a format such as PDF, DOCX, .MD, HTML, TXT, PPTX, image files, audio files, video files, application outputs, and the like), structured data records (e.g., database tables or other data records stored according to a data model or type system), timeseries data records (e.g., sensor data, artificial intelligence application insights), and/or other types of data records (e.g., access control lists). The agents 106 can transform the disparate data records into a common format (e.g., natural language format) that can be post-processed (step 110 ) by a large language model (e.g., the same or different large language model that performed the pre-processing). More specifically, post-processing can take tool outputs (and/or transformed tool outputs) and generate a final result (step 112 ) that satisfies the initial input. For example, the orchestrator may use one or more large language models to determine the result. If the orchestrator determines there is not enough information to satisfy the initial input, the orchestrator can iteratively repeat some or all of the above steps until a stopping condition is satisfied and/or there is enough information to generate a final result (step 112 ).
FIG. 2 depicts a diagram 200 of an example layered architecture and environment of an enterprise generative artificial intelligence system (e.g., enterprise generative artificial intelligence system 402 ) according to some embodiments. In the example of FIG. 2 , the enterprise generative artificial intelligence system architecture and environment includes a hierarchy of layers. More specifically, the hierarchy of layers includes an input layer 202 , a supervisory layer 210 , an agent layer 220 , an agent and tool layer 230 , a tool and data model layer 250 , and an external layer 280 . It will be appreciated that these layers are shown by way of example, and other examples can include any number of such layers (e.g., any number of layers 220 and 230 ).
The input layer 202 represents a layer of the enterprise generative artificial intelligence system architecture that receives an input (e.g., a query, complex input, instruction set, and/or the like) from a user or system. For example, an interface module of the enterprise generative artificial intelligence system may receive the input.
The supervisory layer 210 represents a layer of the enterprise generative artificial intelligence system architecture that includes one or more large language models (e.g., of an orchestrator module) that can develop a plan for responding to the input received in the input layer 202 . A plan can include a set of prescribed tasks (e.g., retrieval tasks, API call tasks, and the like). In one example, the supervisory layer 210 can provide pre-processing and post-processing functionality described herein as well as the functionality of the orchestrators and comprehension modules described herein. The supervisory layer 210 can coordinate with one or more of the subsequent layers 220 - 280 to execute the prescribed set of tasks.
The agent layer 220 represents a layer of the enterprise generative artificial intelligence system architecture that includes agents that can execute the prescribed set of tasks. In the example of FIG. 2 , the agent layer 220 includes a machine learning insight agent 222 , an information retrieving agent 224 , a dashboard agent 226 , and an optimizer agent 228 . Each of the agents 224 - 228 can include a large language model that provides reasoning functionality for accomplishing their assigned portion of the prescribed set of tasks. More specially, the agents 224 - 228 can instruct the agents and tools of subsequent layers (e.g., layer 230 ), of which there could be any number, to execute the tasks. For example, the machine learning insight agent 222 can instruct the text processing tool 232 to perform a text processing task (e.g., transform an artificial intelligence application output into natural language), an image processing tool 234 to perform an image processing task (e.g., generate a natural language summary of an image outputted from artificial intelligence application), a timeseries tool 236 to obtain summarize timeseries data (e.g., timeseries data output from an artificial intelligence application), and an API tool 238 to perform an API call task (e.g., execute an API call to trigger or access an artificial intelligence application).
The information retrieving agent 224 may cooperate with, and/or coordinate, several different agents to perform retrieval tasks. For example, the information retrieving agent 224 may instruct an unstructured data retriever agent 240 to receive unstructured data records, a structured data retriever agent 242 to retrieve structured data records, and a type system retriever agent 244 to obtain one or more data models (or subsets of data models) and/or types from a type system. The type system provides compatibility across different data formats, protocols, operating languages, disparate systems, etc. Types can encapsulate data formats for some or all of the different types or modalities described herein (e.g., multimodal, text, coded, language, statistical, audio, visual, audiovisual, etc.). For example, a data model may include a variety of different types (e.g., in a tree or graph structure), and each of the types may describe data fields, operations, functions, and the like. Each type can represent a different object (e.g., a real-world object, such as a machine or sensor in a factory) or system (e.g., computing cluster, enterprise datastores, file systems), and each type can include a large language model context that provides context for the large language model to design or update a plan. For example, the context may include a natural language summary or description of the type (e.g., a description of the represented object, relationships with other types or objects, associated methods and functions, and the like). Types can be defined in a natural language format for efficient processing by large language models. The type system retriever agent 244 may traverse the data model 254 to retrieve a subset of the data model 254 and/or types of the data model 254 . The structured data retriever agent 242 can then use that retrieved information to efficiently retrieve structured data from a structured data source (e.g., a structured data source that is structured or modeled according to the data model 254 ).
The dashboard agent 226 may be configured to generate one or more visualizations and/or graphical user interfaces, such as dashboards. For example, the dashboard agent 226 may execute tools 252 - 5 and 252 - 6 to generate dashboards based on information retrieved by the other agents and/or information output by the other agents (e.g., natural language summaries of associated tool outputs).
The optimizer agent 228 may be configured to execute a variety of different prescriptive analytics functions and mathematical optimizations 252 - 7 to assist in the calculation of answers for various problems. For example, the large language model 206 may use the optimizer agent 228 to generate plans, determine a set of prescribed tasks, determine whether more information is needed to generate a final result, and the like.
The tool and data model layer 250 is intended to represent a layer of the enterprise generative artificial intelligence system architecture that includes tools 252 and the data model 254 . The agents 240 - 242 can execute the tools 252 to retrieve information from various applications and datastores 282 in the external layer 280 (e.g., external relative to the enterprise generative artificial intelligence system). The tools 252 may include connectors that can connect to systems and datastore that are external to the enterprise generative artificial intelligence system.
FIG. 3 depicts a diagram 300 of an example architecture of an enterprise generative artificial intelligence system (e.g., enterprise generative artificial intelligence system 402 ) according to some embodiments. In the example of FIG. 3 , the enterprise generative artificial intelligence system can ingest disparate data, such as unstructured data 302 , structured data (e.g., tables) 304 , sensor data 306 , and access control information 308 . The data may be received via one or more artificial intelligence data pipelines 310 . Data may be ingested according an object model (or, data model) 312 , and an embedding model 314 (e.g., a ColBERT implementation) may be used to generate embeddings from the ingested data and persisted and/or virtualized in various datastores 318 . The datastores 318 can include vector datastores (e.g., FAISS implementation), metadata datastores, virtualized datastores, distributed file systems, key value datastores, and features stores (e.g., that stores embeddings as features for various models described herein). Database engines and timeseries engines 316 can also be used to persist and/or virtualize data within the datastores 318 .
In the example of FIG. 3 , the enterprise generative artificial intelligence system includes a variety of different agents 326 - 339 . These are shown by way of example, and various embodiments may include different agents instead of, or in addition to, the agents 326 - 339 . Further details regarding the agents and other features of enterprise generative artificial intelligence systems can be found with reference to FIG. 5 and the other figures presented herein.
In the example of FIG. 3 , the enterprise generative artificial intelligence system includes an orchestrator 342 with a fine-tuned large language model. The orchestrator 342 and/or agents 326 - 339 may include and/or access task-specific large language models 348 - 356 , as well as external or third-party large language models 340 in some embodiments. The orchestrator 342 can utilize various underlying platform services tools, such as run-time hardware profiles 368 , end- end retraining 370 , logging and monitoring 372 , prompt registry 374 , model registry 376 , hosted JUPYTER environment 378 , access management controls 380 , and/or the like.
In some embodiments, a user query 362 and/or other inputs may be received by an application hosting an application engine 360 which can communicate with a low latency engine 358 to provide the input, or a transformed input, to the orchestrator 342 . The orchestrator 342 may utilize the various agents, large language models, and other features to generate an accurate and reliable (e.g., without hallucination) answer to the user query 362 .
In some embodiments, only a portion of the architecture depicted in FIG. 3 may be deployed in an external environment (e.g., a customer hosted environment or a customer cloud environment). For example, a portion of the architecture may be deployed in an external environment while some or all of the other portions remain in an internal environment (e.g., the internal hosted environment and/or associated cloud environment of the entity providing the enterprise generative artificial intelligence system).
FIG. 4 depicts a diagram 400 of an example network system for enterprise generative artificial intelligence according to some embodiments. In the example of FIG. 4 , the network system includes an enterprise generative artificial intelligence system 402 , enterprise systems 404 - 1 to 404 -N (individually, the enterprise system 404 , collectively, the enterprise systems 404 ), external systems 406 - 1 to 406 -N (individually, the external system 406 , collectively, the external systems 406 ), and a communication network 408 .
The enterprise generative artificial intelligence system 402 may function to iteratively and non-iteratively generate machine learning model inputs and outputs to determine a final output (e.g., âanswerâ or âresultâ) in response to an initial input (e.g., provided by a user or another system). In some embodiments, functionality of the enterprise generative artificial intelligence system 402 may be performed by one or more servers (e.g., a cloud-based server) and/or other computing devices. The enterprise generative artificial intelligence system 402 may be implemented using a type system and/or model-driven architecture.
In various implementations, the enterprise generative artificial intelligence system 402 can provide a variety of different technical features, such as effectively handling and generating complex natural language inputs and outputs, generating synthetic data (e.g., supplementing customer data obtained during an onboarding process, or otherwise filling data gaps), generating source code (e.g., application development), generating applications (e.g., artificial intelligence applications), providing cross-domain functionality, as well as a myriad of other technical features that are not provided by traditional systems. As used herein, synthetic data can refer to content generated on-the-fly (e.g., by large language models) as part of the processes described herein. Synthetic data can also include non-retrieved ephemeral content (e.g., temporary data that does not subsist in a database), as well as combinations of retrieved information, queried information, model outputs, and/or the like.
In some embodiments, the enterprise generative artificial intelligence system 402 can provide and/or enable an intuitive non-complex interface to rapidly execute complex user requests with improved access, privacy, and security enforcement. The enterprise generative artificial intelligence system 402 can include a human computer interface for receiving natural language queries and presenting relevant information with predictive analysis from the enterprise information environment in response to the queries. For example, the enterprise generative artificial intelligence system 402 can understand the language, intent, and/or context of a user natural language query. The enterprise generative artificial intelligence system 402 can execute the user natural language query to discern relevant information from an enterprise information environment to present to the human computer interface (e.g., in the form of an âanswerâ).
In some embodiments, generative artificial intelligence models (e.g., large language models of an orchestrator) of the enterprise generative artificial intelligence system 402 can interact with agents (e.g., retrieval agents, retriever agents) to retrieve and process information from various data sources. For example, data sources can store data records and/or segments of data records which may be identified by the enterprise generative artificial intelligence system 402 based on embedding values (e.g., vector values associated with data records and/or segments). Data records can include tables, text, images, audio, video, code, application outputs (e.g., predictive analysis and/or other insights generated by artificial intelligence applications), and/or the like.
In some embodiments, the enterprise generative artificial intelligence system 402 can generate context-based synthetic output based on retrieved information from one or more retriever models. For example, retriever models (e.g., retriever models or a retrieval agent) can provide additional retrieved information to the large language models to generate additional context-based synthetic output until context validation criteria is satisfied. Once the validation criteria are satisfied, the enterprise generative artificial intelligence system 402 can output the additional context-based synthetic output as a result or instruction set (collectively, âanswersâ).
In various embodiments, the enterprise generative artificial intelligence system 402 provides transformative context-based intelligent generative results. For example, the enterprise generative artificial intelligence system 402 can process inputs from enterprise users using a natural language interface to rapidly locate, retrieve, and present relevant data across the entire corpus of an enterprise's information systems.
As discussed elsewhere herein, the enterprise generative artificial intelligence system 402 can handle both machine-readable inputs (e.g., compiled code, structured data, and/or other types of formats that can be processed by a computer) and human-readable inputs. Inputs can also include complex inputs, such as inputs including âand,â âorâ, inputs that include different types of information to satisfy the input (e.g., data records, text documents, database tables, and artificial intelligence insights), and/or the like. In one example, a complex input may be âHow many different engineers has John Doe worked with within his engineering department?â This may require the enterprise generative artificial intelligence system 402 to identify John Doe in a first iteration, identify John Doe's department in a second iteration, determine the engineers in that department in a third iteration, then determine in a fourth iteration which of those engineers John Doe has interacted with, and then finally combine those results, or portions thereof, to generate the final answer to the query. More specifically, the enterprise generative artificial intelligence system 402 can use portions of the results of each iteration to generate contextual information (or, simply, context) which can then inform the subsequent iterations.
The enterprise systems 404 can include enterprise applications (e.g., artificial intelligence applications), enterprise datastores, client systems, and/or other systems of an enterprise information environment. As used herein, an enterprise information environment can include one or more networks (e.g., cloud, on premise, air-gapped or otherwise) of enterprise systems (e.g., enterprise applications, enterprise datastores), client systems (e.g., computing systems for access enterprise systems). The enterprise systems 404 can include disparate computing systems, applications, and/or datastores, along with enterprise-specific requirements and/or features. For example, enterprise systems 404 can include access and privacy controls. For example, a private network of an organization may comprise an enterprise information environment that includes various enterprise systems 404 . Enterprise systems 404 can include, for example, CRM systems, EAM systems, ERP systems, FP&A systems, HRM systems, and SCADA systems. Enterprise systems 404 can include or leverage artificial intelligence applications and artificial intelligence applications may leverage enterprise systems and data. Enterprise systems 404 can include data flow and management of different processes (e.g., of one or more organizations) and can provide access to systems and users of the enterprise while preventing access from other systems and/or users. It will be appreciated that, in some embodiments, references to enterprise information environments can also include enterprise systems, and references to enterprise systems can also include enterprise information environments. In various embodiments, functionality of the enterprise systems 404 may be performed by one or more servers (e.g., a cloud-based server) and/or other computing devices.
The external systems 406 can include applications, datastores, and systems that are external to the enterprise information environment. In one example, the enterprise systems 404 may be a part of an enterprise information environment of an organization that cannot be accessed by users or systems outside that enterprise information environment and/or organization. Accordingly, the example external systems 406 may include Internet-based systems, such as news media systems, social media systems, and/or the like, that are outside the enterprise information environment. In various embodiments, functionality of the external systems 406 may be performed by one or more servers (e.g., a cloud-based server) and/or other computing devices.
The communications network 408 may represent one or more computer networks (e.g., LAN, WAN, air-gapped network, cloud-based network, and/or the like) or other transmission mediums. In some embodiments, the communication network 408 may provide communication between the systems, modules, engines, generators, layers, agents, tools, orchestrators, datastores, and/or other components described herein. In some embodiments, the communication network 408 includes one or more computing devices, routers, cables, buses, and/or other network topologies (e.g., mesh, and the like). In some embodiments, the communication network 408 may be wired and/or wireless. In various embodiments, the communication network 408 may include local area networks (LANs), wide area networks (WANs), the Internet, and/or one or more networks that may be public, private, IP-based, non-IP based, air-gapped, and so forth.
FIG. 5 depicts a diagram of an example enterprise generative artificial intelligence system 402 according to some embodiments. In the example of FIG. 5 , the enterprise generative artificial intelligence system 402 includes a management module 502 , an orchestrator module 504 , a retrieval agent module 506 - 1 , an unstructured data retriever agent module, 506 - 2 , a structured data retriever agent module 506 - 3 , a type system retriever agent module 506 - 4 , a machine learning insight module 506 - 5 , a timeseries processing agent 506 - 6 , an API agent module 506 - 7 , a math agent module 506 - 8 , a visualization agent module 506 - 9 , a code generation agent module 506 - 10 , an unstructured data retrieval tool 508 - 1 , an structured data retrieval tool 508 - 2 , a text processing tool module 508 - 3 , an image processing tool module 508 - 4 , a timeseries processing tool module 508 - 5 , an API tool module 508 - 6 , a visualization tool module 508 - 7 , an optimizer tool module 508 - 8 , a filter tool module 508 - 9 , a projections tool module 508 - 10 , a group tool module 508 - 11 , an order tool module 508 - 12 , a limit tool module 508 - 13 , code generation tool module 508 - 14 , a comprehension module 510 , a chunking module 512 , an enterprise access control module 514 , an artificial intelligence traceability module 516 , a parallelization module 520 , model generation module 522 , a model deployment module 524 , a model optimization module 526 , an interface module 528 , a communication module 530 , vector datastore(s) 540 , model registry datastore(s) 550 , feature datastore(s) 560 , and enterprise generative artificial intelligence system datastore(s) 570 .
The management module 502 can function to (e.g., create, read, update, delete, or otherwise access) data associated with the enterprise generative artificial intelligence system 402 . The management module 502 can store or otherwise manage or store in any of the datastores 540 - 570 , and/or in one or more other local and/or remote datastores. It will be appreciated that that datastores can be a single datastore local to the enterprise generative artificial intelligence system 402 and/or multiple datastores remote to the enterprise generative artificial intelligence system 402 . In some embodiments, the datastores described herein comprise one or more local and/or remote
CLAIMS
Claims ( 20 )
What is claimed is:
1. A method comprising:
managing, by an orchestrator, a plurality of agents to generate a response to an input, wherein the orchestrator employs one or more multimodal models to process or deconstruct a prompt into a series of instructions for different agents, wherein each agent employs one or more machine-learning models to process disparate inputs or different portions of an input associated with the prompt;
instructing, by the orchestrator, retrieval requests related to the input to the one or more agents of the plurality of agents;
receiving, from the one or more agents of the plurality of agents, data from multiple data domains based on instructions from the orchestrator;
analyzing, by the orchestrator, the received data to formulate one or more responses to the prompt, wherein the orchestrator provides additional retrieval requests to the one or more agents to retrieve additional data to satisfy a context validation criteria associated with the input;
wherein the orchestrator generates intermediate instructions associated with the additional retrieval requests to the plurality of agents, wherein the intermediate instructions comprise portions of the input, questions about the input generated by the one or more multimodal models, and follow-up questions about answers generated by the one or more multimodal models; and
wherein at least one agent of the one or more agents instantiates a tool to perform one or more operations on the instruction, the retrieved data, and the intermediate instructions; and
outputting, by the orchestrator based on the intermediate instructions and the one or more operations performed by the tool, a validated response of the one or more responses to the input that satisfies context validation criteria and a portion of data retrieved by the one or more agents related to the input.
2. The method of claim 1 , wherein outputting the portion of data retrieved by the one or more agents related to the input includes a source citation for the at least a portion of the validated response.
3. The method of claim 1 , wherein the context validation criteria includes a threshold for identifying source material from an enterprise data system that corroborate the response.
4. The method of claim 1 , wherein managing the plurality of agents comprises iterative processing or multiple instructions from the orchestrator.
5. The method of claim 1 , wherein the retrieving the data from multiple data domains includes time series data, structured data, and unstructured data.
6. The method of claim 1 , wherein the operation includes at least one of calculation, translation, formatting, visualization.
7. The method of claim 1 , wherein the one or more agents are trained on different domain specific machine-learning models.
8. The method of claim 1 , wherein at least one agent employs a type system to unify incompatible data from disparate data sources.
9. A system comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the system to perform:
managing, by an orchestrator, a plurality of agents to generate a response to an input, wherein the orchestrator employs one or more multimodal models to process or deconstruct a prompt into a series of instructions for different agents, wherein each agent employs one or more machine-learning models to process disparate inputs or different portions of an input associated with the prompt;
instructing, by the orchestrator, retrieval requests related to the input to the one or more agents of the plurality of agents;
receiving, from the one or more agents of the plurality of agents, data from multiple data domains based on instructions from the orchestrator;
analyzing, by the orchestrator, the received data to formulate one or more responses to the prompt, wherein the orchestrator provides additional retrieval requests to the one or more agents to retrieve additional data to satisfy a context validation criteria associated with the input;
wherein the orchestrator generates intermediate instructions associated with the additional retrieval requests to the plurality of agents, wherein the intermediate instructions comprise portions of the input, questions about the input generated by the one or more multimodal models, and follow-up questions about answers generated by the one or more multimodal models; and
wherein at least one agent of the one or more agents instantiates a tool to perform one or more operations on the instruction, the retrieved data, and the intermediate instructions; and
outputting, by the orchestrator based on the intermediate instructions and the one or more operations performed by the tool, a validated response of the one or more responses to the input that satisfies context validation criteria and a portion of data retrieved by the one or more agents related to the input.
10. The system of claim 9 , wherein outputting the portion of data retrieved by the one or more agents related to the input includes a source citation for the at least a portion of the validated response.
11. The system of claim 9 , wherein the context validation criteria includes a threshold for identifying source material from an enterprise data system that corroborate the response.
12. The system of claim 9 , wherein managing the plurality of agents comprises iterative processing or multiple instructions from the orchestrator.
13. The system of claim 9 , wherein the retrieving the data from multiple data domains includes time series data, structured data, and unstructured data.
14. The system of claim 9 , wherein the operation includes at least one of calculation, translation, formatting, visualization.
15. The system of claim 9 , wherein the one or more agents are trained on different domain specific machine-learning models.
16. The system of claim 9 , wherein at least one agent employs a type system to unify incompatible data from disparate data sources.
17. A non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to perform:
managing, by an orchestrator, a plurality of agents to generate a response to an input, wherein the orchestrator employs one or more multimodal models to process or deconstruct a prompt into a series of instructions for different agents, wherein each agent employs one or more machine-learning models to process disparate inputs or different portions of an input associated with the prompt;
instructing, by the orchestrator, retrieval requests related to the input to the one or more agents of the plurality of agents;
receiving, from the one or more agents of the plurality of agents, data from multiple data domains based on instructions from the orchestrator;
analyzing, by the orchestrator, the received data to formulate one or more responses to the prompt, wherein the orchestrator provides additional retrieval requests to the one or more agents to retrieve additional data to satisfy a context validation criteria associated with the input;
wherein the orchestrator generates intermediate instructions associated with the additional retrieval requests to the plurality of agents, wherein the intermediate instructions comprise portions of the input, questions about the input generated by the one or more multimodal models, and follow-up questions about answers generated by the one or more multimodal models; and
wherein at least one agent of the one or more agents instantiates a tool to perform one or more operations on the instruction, the retrieved data, and the intermediate instructions; and
outputting, by the orchestrator based on the intermediate instructions and the one or more operations performed by the tool, a validated response of the one or more responses to the input that satisfies context validation criteria and a portion of data retrieved by the one or more agents related to the input.
18. The non-transitory computer readable medium of claim 17 , wherein outputting the portion of data retrieved by the one or more agents related to the input includes a source citation for the at least a portion of the validated response.
19. The non-transitory computer readable medium of claim 17 , wherein the context validation criteria includes a threshold for identifying source material from an enterprise data system that corroborate the response.
20. The non-transitory computer readable medium of claim 17 , wherein managing the plurality of agents comprises iterative processing or multiple instructions from the orchestrator.
US18/542,536
2022-12-16
2023-12-15
Enterprise generative artificial intelligence architecture
Active
US12111859B2
( en )
Priority Applications (11)
Application Number
Priority Date
Filing Date
Title
PCT/US2023/084462
WO2024130219A1
( en )
2022-12-16
2023-12-15
Enterprise generative artificial intelligence architecture
US18/542,536
US12111859B2
( en )
2022-12-16
2023-12-15
Enterprise generative artificial intelligence architecture
GB2519764.1A
GB2644574A
( en )
2023-05-01
2024-04-30
Enterprise generative artificial intelligence anti-hallucination and attribution architecture
US18/651,650
US20240370709A1
( en )
2023-05-01
2024-04-30
Enterprise generative artificial intelligence anti-hallucination and attribution architecture
PCT/US2024/027118
WO2025170605A1
( en )
2023-05-01
2024-04-30
Enterprise generative artificial intelligence anti-hallucination and attribution architecture
CN202480044238.6A
CN121548824A
( en )
2023-05-01
2024-04-30
Enterprise Generative AI Anti-Illusion and Attribution Architecture
DE112024001874.2T
DE112024001874T5
( en )
2023-05-01
2024-04-30
ENTREPRENEURIAL GENERATIVE ARTIFICIAL INTELLIGENCE ANTI-HALLUCINATION AND ASSIGNMENT ARCHITECTURE
US18/822,035
US20240419713A1
( en )
2022-12-16
2024-08-30
Enterprise generative artificial intelligence architecture
US18/967,625
US20250094474A1
( en )
2022-12-16
2024-12-03
Interface for agentic website search
US18/991,198
US20250124069A1
( en )
2022-12-16
2024-12-20
Agentic artificial intelligence for a system of agents
US18/991,274
US20250131028A1
( en )
2022-12-16
2024-12-20
Agentic artificial intelligence with domain-specific context validation
Applications Claiming Priority (4)
Application Number
Priority Date
Filing Date
Title
US202263433124P
2022-12-16
2022-12-16
US202363446792P
2023-02-17
2023-02-17
US202363492133P
2023-03-24
2023-03-24
US18/542,536
US12111859B2
( en )
2022-12-16
2023-12-15
Enterprise generative artificial intelligence architecture
Related Child Applications (2)
Application Number
Title
Priority Date
Filing Date
US18/651,650
Continuation-In-Part
US20240370709A1
( en )
2023-05-01
2024-04-30
Enterprise generative artificial intelligence anti-hallucination and attribution architecture
US18/822,035
Continuation
US20240419713A1
( en )
2022-12-16
2024-08-30
Enterprise generative artificial intelligence architecture
Publications (2)
Publication Number
Publication Date
US20240202225A1
US20240202225A1 ( en )
2024-06-20
US12111859B2
true
US12111859B2 ( en )
2024-10-08
Family
ID=91472672
Family Applications (10)
Application Number
Title
Priority Date
Filing Date
US18/542,481
Active
US12265570B2
( en )
2022-12-16
2023-12-15
Generative artificial intelligence enterprise search
US18/542,583
Pending
US20240202539A1
( en )
2022-12-16
2023-12-15
Generative artificial intelligence crawling and chunking
US18/542,572
Pending
US20240202464A1
( en )
2022-12-16
2023-12-15
Iterative context-based generative artificial intelligence
US18/542,536
Active
US12111859B2
( en )
2022-12-16
2023-12-15
Enterprise generative artificial intelligence architecture
US18/542,676
Pending
US20240202600A1
( en )
2022-12-16
2023-12-16
Machine learning model administration and optimization
US18/822,035
Pending
US20240419713A1
( en )
2022-12-16
2024-08-30
Enterprise generative artificial intelligence architecture
US18/967,625
Pending
US20250094474A1
( en )
2022-12-16
2024-12-03
Interface for agentic website search
US18/991,198
Pending
US20250124069A1
( en )
2022-12-16
2024-12-20
Agentic artificial intelligence for a system of agents
US18/991,274
Pending
US20250131028A1
( en )
2022-12-16
2024-12-20
Agentic artificial intelligence with domain-specific context validation
US19/060,273
Pending
US20250190475A1
( en )
2022-12-16
2025-02-21
Generative artificial intelligence enterprise search
Family Applications Before (3)
Application Number
Title
Priority Date
Filing Date
US18/542,481
Active
US12265570B2
( en )
2022-12-16
2023-12-15
Generative artificial intelligence enterprise search
US18/542,583
Pending
US20240202539A1
( en )
2022-12-16
2023-12-15
Generative artificial intelligence crawling and chunking
US18/542,572
Pending
US20240202464A1
( en )
2022-12-16
2023-12-15
Iterative context-based generative artificial intelligence
Family Applications After (6)
Application Number
Title
Priority Date
Filing Date
US18/542,676
Pending
US20240202600A1
( en )
2022-12-16
2023-12-16
Machine learning model administration and optimization
US18/822,035
Pending
US20240419713A1
( en )
2022-12-16
2024-08-30
Enterprise generative artificial intelligence architecture
US18/967,625
Pending
US20250094474A1
( en )
2022-12-16
2024-12-03
Interface for agentic website search
US18/991,198
Pending
US20250124069A1
( en )
2022-12-16
2024-12-20
Agentic artificial intelligence for a system of agents
US18/991,274
Pending
US20250131028A1
( en )
2022-12-16
2024-12-20
Agentic artificial intelligence with domain-specific context validation
US19/060,273
Pending
US20250190475A1
( en )
2022-12-16
2025-02-21
Generative artificial intelligence enterprise search
Country Status (4)
Country
Link
US
( 10 )
US12265570B2
( en )
EP
( 5 )
EP4634830A1
( en )
CN
( 5 )
CN120615194A
( en )
WO
( 5 )
WO2024130222A1
( en )
Cited By (16)
* Cited by examiner, â Cited by third party
Publication number
Priority date
Publication date
Assignee
Title
US20240386038A1
( en )
*
2023-05-16
2024-11-21
Microsoft Technology Licensing, Llc
Embedded attributes for modifying behaviors of generative ai systems
US20240386041A1
( en )
*
2023-05-18
2024-11-21
Elasticsearch B.V.
Private artificial intelligence (ai) searching on a database using a large language model
US20250015973A1
( en )
*
2023-12-20
2025-01-09
Beijing Baidu Netcom Science Technology Co., Ltd.
Service provision methods, devices, electronic equipment and media for large model scenes
US20250165231A1
( en )
*
2023-11-21
2025-05-22
Hitachi, Ltd.
User-centric and llm-enhanced adaptive etl code synthesis
US12405985B1
( en )
*
2024-12-12
2025-09-02
Dell Products L.P.
Retrieval-augmented generation processing using dynamically selected number of document chunks
US20250323951A1
( en )
*
2024-04-12
2025-10-16
Cisco Technology, Inc.
Compliance-based multi-factor authorization
US20250363125A1
( en )
*
2024-05-22
2025-11-27
Airia LLC
Management of Connector Services and Connected Artificial Intelligence Agents for Message Senders and Recipients
US12499145B1
( en )
2024-12-19
2025-12-16
The Bank Of New York Mellon
Multi-agent framework for natural language processing
JP7795840B1
( en )
*
2025-07-31
2026-01-08
æ ªå¼ä¼ç¤¾D4All
Information processing system, information processing method, information processing program, and AI agent
US12547681B2
( en )
2024-06-10
2026-02-10
Airia LLC
Deriving input restrictions for artificial intelligence agents
US12554620B2
( en )
2022-12-26
2026-02-17
Augstra Llc
Integrated AI-driven system for automating IT and cybersecurity operations
US12561335B2
( en )
2024-07-12
2026-02-24
Glean Technologies, Inc.
Automated expert detection
US20260079982A1
( en )
*
2024-09-16
2026-03-19
Salesforce, Inc.
Semantic search for prompt builder system
US12585658B1
( en )
*
2024-03-01
2026-03-24
Google Llc
Generating augmented output sequences by a neural network using external databases
US20260119267A1
( en )
*
2024-10-31
2026-04-30
Xhilon LLC
Workload distribution and execution platform for tasks such as artificial intelligence tasks
EP4742101A1
( en )
*
2024-11-08
2026-05-13
Fisher Scientific Company, L.L.C.
Rapidly deployable agentic reasoning platform
Families Citing this family (144)
* Cited by examiner, â Cited by third party
Publication number
Priority date
Publication date
Assignee
Title
US12001462B1
( en )
*
2023-05-04
2024-06-04
Vijay Madisetti
Method and system for multi-level artificial intelligence supercomputer design
US11989507B2
( en )
*
2021-08-24
2024-05-21
Unlikely Artificial Intelligence Limited
Computer implemented methods for the automated analysis or use of data, including use of a large language model
US12189787B2
( en )
*
2022-05-31
2025-01-07
As0001, Inc.
Systems and methods for protection modeling
US12236491B2
( en )
2022-05-31
2025-02-25
As0001, Inc.
Systems and methods for synchronizing and protecting data
US12333612B2
( en )
2022-05-31
2025-06-17
As0001, Inc.
Systems and methods for dynamic valuation of protection products
US12177242B2
( en )
2022-05-31
2024-12-24
As0001, Inc.
Systems and methods for dynamic valuation of protection products
US12244703B2
( en )
2022-05-31
2025-03-04
As0001, Inc.
Systems and methods for configuration locking
US12047400B2
( en )
2022-05-31
2024-07-23
As0001, Inc.
Adaptive security architecture based on state of posture
US20240340301A1
( en )
2022-05-31
2024-10-10
As0001, Inc.
Adaptive security architecture based on state of posture
US12596813B2
( en )
2023-01-19
2026-04-07
Citibank, N.A
Autonomous agent observation and control
US20240289365A1
( en )
*
2023-02-28
2024-08-29
Shopify Inc.
Systems and methods for performing vector search
US20240296295A1
( en )
*
2023-03-03
2024-09-05
Microsoft Technology Licensing, Llc
Attribution verification for answers and summaries generated from large language models (llms)
US12511437B1
( en )
*
2023-03-07
2025-12-30
Trend Micro Incorporated
Chat detection and response for enterprise data security
US20240311559A1
( en )
*
2023-03-15
2024-09-19
AIble Inc.
Enterprise-specific context-aware augmented analytics
US20240330597A1
( en )
*
2023-03-31
2024-10-03
Infobip Ltd.
Systems and methods for automated communication training
WO2024211603A1
( en )
*
2023-04-04
2024-10-10
Sight Machine, Inc.
Natural language interface for monitoring of manufacturing processes
US20240338387A1
( en )
*
2023-04-04
2024-10-10
Google Llc
Input data item classification using memory data item embeddings
US12373494B2
( en )
*
2023-04-20
2025-07-29
Qualcomm Incorporated
Speculative decoding in autoregressive generative artificial intelligence models
US12199936B2
( en )
*
2023-04-21
2025-01-14
M3G Technology, Inc.
Multiparty communication using a large language model intermediary
US12614080B2
( en )
*
2023-04-30
2026-04-28
Box, Inc.
Using sample question embeddings to choose between an LLM interfacing model and a non-LLM interfacing model
US12511282B1
( en )
2023-05-02
2025-12-30
Microstrategy Incorporated
Generating structured query language using machine learning
WO2024228909A1
( en )
*
2023-05-03
2024-11-07
Microsoft Technology Licensing, Llc
Collaborative development of machine learning models on specific concepts
US12625901B2
( en )
*
2023-05-23
2026-05-12
Palantir Technologies Inc.
Machine learning and language model-assisted geospatial data analysis and visualization
US12417352B1
( en )
2023-06-01
2025-09-16
Instabase, Inc.
Systems and methods for using a large language model for large documents
US20250225804A1
( en )
*
2023-06-01
2025-07-10
Fusemachines, Inc.
Method of extracting information from an image of a document
US20240419912A1
( en )
*
2023-06-13
2024-12-19
Microsoft Technology Licensing, Llc
Detecting hallucination in a language model
US20240427807A1
( en )
*
2023-06-23
2024-12-26
Crowdstrike, Inc.
Funnel techniques for natural language to api calls
US20250005060A1
( en )
*
2023-06-28
2025-01-02
Jpmorgan Chase Bank, N.A.
Systems and methods for runtime input and output content moderation for large language models
US20250013963A1
( en )
*
2023-07-06
2025-01-09
Praisidio Inc.
Intelligent people analytics from generative artificial intelligence
US12216694B1
( en )
*
2023-07-25
2025-02-04
Instabase, Inc.
Systems and methods for using prompt dissection for large language models
US12417359B2
( en )
*
2023-08-02
2025-09-16
Unum Group
AI hallucination and jailbreaking prevention framework
US20250046025A1
( en )
*
2023-08-03
2025-02-06
Wells Fargo Bank, N.A.
Smart digital interactions with augmented reality and generative artificial intelligence
US20250053835A1
( en )
*
2023-08-07
2025-02-13
Trunk Tools, Inc.
Methods and systems for generative question answering for construction project data
US12425382B2
( en )
*
2023-08-17
2025-09-23
International Business Machines Corporation
Cross-platform chatbot user authentication for chat history recovery
US12314301B2
( en )
*
2023-08-24
2025-05-27
Microsoft Technology Licensing, Llc.
Code search for examples to augment model prompt
US20250077238A1
( en )
*
2023-09-01
2025-03-06
Microsoft Technology Licensing, Llc
Pre-approval-based machine configuration
US20250086439A1
( en )
*
2023-09-07
2025-03-13
Accenture Global Solutions Limited
Platform for enterprise adoption and implementation of generative artificial intelligence systems
US12468894B2
( en )
*
2023-09-08
2025-11-11
Maplebear Inc.
Using language model to generate recipe with refined content
JP7441366B1
( en )
*
2023-09-19
2024-02-29
æ ªå¼ä¼ç¤¾æ±è
Information processing device, information processing method, and computer program
US12332925B2
( en )
*
2023-10-05
2025-06-17
Nasdaq, Inc.
Systems and methods of chained conversational prompt engineering for information retrieval
US12579159B2
( en )
*
2023-10-23
2026-03-17
Intuit Inc.
File extraction and vectorization for onboarding with LLM
US12326895B2
( en )
*
2023-11-07
2025-06-10
Notion Labs, Inc.
Enabling an efficient understanding of contents of a large document without structuring or consuming the large document
US12625869B2
( en )
*
2023-11-09
2026-05-12
Microsoft Technology Licensing, Llc
Generative AI-driven multi-source data query system
EP4557122A1
( en )
*
2023-11-14
2025-05-21
Atos France
Method and computer system for managing electronic documents
JP2025083119A
( en )
*
2023-11-20
2025-05-30
Ｌï½ï½ï½ ã¤ãã¼æ ªå¼ä¼ç¤¾
Information processing device, information processing method, and information processing program
US20250165714A1
( en )
*
2023-11-20
2025-05-22
Microsoft Technology Licensing, Llc
Orchestrator with semantic-based request routing for use in response generation using a trained generative language model
US12493754B1
( en )
2023-11-27
2025-12-09
Instabase, Inc.
Systems and methods for using one or more machine learning models to perform tasks as prompted
US12361089B2
( en )
*
2023-12-12
2025-07-15
Microsoft Technology Licensing, Llc
Generative search engine results documents
US20250209282A1
( en )
*
2023-12-21
2025-06-26
Fujitsu Limited
Data adjustment using large language model
US20250209053A1
( en )
*
2023-12-23
2025-06-26
Qomplx Llc
Collaborative generative artificial intelligence content identification and verification
US20250209138A1
( en )
*
2023-12-23
2025-06-26
Cognizant Technology Solutions India Pvt. Ltd.
Gen ai-based improved end-to-end data analytics tool
US20250225263A1
( en )
*
2024-01-04
2025-07-10
Betty Cumberland Andrea
AI-VERS3-rolling data security methodology for continuous security control of artificial intelligence (AI) data
US12450217B1
( en )
2024-01-16
2025-10-21
Instabase, Inc.
Systems and methods for agent-controlled federated retrieval-augmented generation
US12608545B2
( en )
*
2024-01-19
2026-04-21
Salesforce, Inc.
Validating generative artificial intelligence output
US20250258879A1
( en )
*
2024-02-09
2025-08-14
Fluidityiq, Llc
Method and system for an innovation intelligence platform
US12430333B2
( en )
*
2024-02-09
2025-09-30
Oracle International Corporation
Efficiently processing query workloads with natural language statements and native database commands
US20250265253A1
( en )
*
2024-02-15
2025-08-21
Cisco Technology, Inc.
Automatic retrieval augmented generation with expanding context
US20250265529A1
( en )
*
2024-02-21
2025-08-21
Sap Se
Enabling natural language interactions in process visibility applications using generative artificial intelligence (ai)
US20250272501A1
( en )
*
2024-02-27
2025-08-28
Salesforce, Inc.
Systems And Methods For Generative Language Model Database System Communication Channel Integration
US20250272344A1
( en )
*
2024-02-28
2025-08-28
International Business Machines Corporation
Personal search tailoring
US12124932B1
( en )
2024-03-08
2024-10-22
Seekr Technologies Inc.
Systems and methods for aligning large multimodal models (LMMs) or large language models (LLMs) with domain-specific principles
US12293272B1
( en )
*
2024-03-08
2025-05-06
Seekr Technologies, Inc.
Agentic workflow system and method for generating synthetic data for training or post training artificial intelligence models to be aligned with domain-specific principles
US12182678B1
( en )
*
2024-03-08
2024-12-31
Seekr Technologies Inc.
Systems and methods for aligning large multimodal models (LMMs) or large language models (LLMs) with domain-specific principles
US20250284719A1
( en )
*
2024-03-11
2025-09-11
Microsoft Technology Licensing, Llc
Machine cognition workflow engine with rewinding mechanism
US20250292016A1
( en )
*
2024-03-15
2025-09-18
Planetart, Llc
Filtering Content for Automated User Interactions Using Language Models
US20250298792A1
( en )
2024-03-22
2025-09-25
Palo Alto Networks, Inc.
Grammar powered retrieval augmented generation for domain specific languages
US20250307238A1
( en )
*
2024-03-29
2025-10-02
Microsoft Technology Licensing, Llc
Query language query generation and repair
US12260260B1
( en )
*
2024-03-29
2025-03-25
The Travelers Indemnity Company
Digital delegate computer system architecture for improved multi-agent large language model (LLM) implementations
US12488136B1
( en )
2024-03-29
2025-12-02
Instabase, Inc.
Systems and methods for access control for federated retrieval-augmented generation
US20250315856A1
( en )
*
2024-04-03
2025-10-09
Adobe Inc.
Generative artificial intelligence (ai) content strategy
US20250328550A1
( en )
*
2024-04-19
2025-10-23
Western Digital Technologies, Inc.
Entity relationship diagram generation for databases
US20250328525A1
( en )
*