53 results about "Subject-matter expert" patented technology

Digital model platform that enables the streamlined creation and management of digital twins and physical twins by leveraging external feedback and artificial intelligence (AI) is disclosed. Methods and systems for a model collaboration platform that facilitate the integration of external feedback, whether from physical, virtual, or human sources, into the streamlined design, validation, verification, certification, assembly, operations, and maintenance processes of complex systems. Updated results are output to those external sources, including physical twins, other digital twins or models and simulations, and / or human users. External feedback includes feedback data from physical prototypes and their environment, virtual prototypes, simulations, and subject-matter experts. Embodiments are directed to integrating external feedback into the assembly and system-level assessment of digital twins, physical twins, digital threads, and the iterative design of constituting digital engineering models, including constructing, maintaining, and improving digital engineering models for the design, validation, verification, certification, operations, and maintenance of complex systems.

The present disclosure herein addresses the problem of synthesizing a series of documents and extracting or summarizing meaningful information or content embedded as tacit knowledge in the series of documents. The embodiment of the present disclosure provides a system and method for tacit knowledge generation using large language model (LLM) in document synthesis. The method of the present disclosure performs intelligent document generation orchestrating a generative artificial intelligence solution workflow. In the present disclosure, tacit knowledge of subject matter experts in a knowledge base or in a series of documents is extracted. Further a content capturing the tacit knowledge is generated leveraging a large language models (LLMs) framework as the underlying architecture. The system of the present disclosure is artificial intelligence (AI) accelerated, cloud agnostic, latency defined, and security enabled.

Embodiments described herein relate to systems and methods for providing a recommendation panel for a graphical user interface of an issue tracking platform. The system and methods can include causing display of the recommendation panel in the issue-view graphical user interface. The recommendation panel can include a first section including a set of one or more selectable link objects, where each selectable link object associated with a respective content item identified for the request type; a second section including a link to a user profile of a subject matter expert user, where the subject matter expert user selected based on a subject matter determined using the issue data; and a third section including suggested action narrative. The suggested action narrative can be determined using a generative response received from the generative output engine in response to the prompt.

A platform for creating, managing, and deploying digital twins of human experts through automated behavioral capture and analysis. The platform employs a data collection system that monitors and processes digital interactions, communications, and work patterns to create AI-powered digital representations of subject matter experts. These digital twins maintain the knowledge, decision-making patterns, and communication style of the original subject while preserving privacy and confidentiality boundaries. The platform includes systems for managing multiple instances of digital twins across different organizations, with capabilities for instance-level learning and knowledge integration. A comprehensive licensing and rights management system enables controlled distribution of expert digital twins while ensuring appropriate privacy and security controls are in place. The platform maintains continuous compliance monitoring and privacy enforcement across all twin instances, allowing for scalable deployment of expert knowledge while maintaining security and confidentiality requirements.

A computer-implemented method for serving a large language model (LLM) application via a serverless function router communicative with multiple endpoints that each have a set of subject matter expert models stored thereon is provided. The computer-implemented method includes receiving a prompt, querying a database comprising multiple datasets for an indication as to which one of the multiple datasets has a highest level of similarity with the prompt, recognizing one of the multiple endpoints as having the set of the expert models stored thereon which have a closest match with the one of the multiple datasets and routing the prompt to the one of the multiple endpoints having the set of the expert models stored thereon which have the closest match with the one of the multiple datasets.

Business rules are currently not documented and are present only as knowledge with subject matter experts (SMEs). The knowledge can be lost with time if it is not extracted or recorded. Existing techniques are unable to extract tacit knowledge and to retain the domain flavor in extracted information. Present disclosure provides a method and a system for extracting tacit knowledge from historical data. The system represents each point in historical data as a large dimensional hyperspace which contains all unstructured information where tacit knowledge can exist. Then, system maps large dimensional hyperspace to smaller dimensional hyperspace using pre-trained large language model (LLM). Thereafter, system, based on the series of downstream tasks, generates a feedback loop to optimally compute dimension of the smaller dimensional hyperspace. Once reduced dimensional space containing effective tacit knowledge information is available, system performs a downstream task based on the extracted tacit knowledge using another pre-trained LLM.

Methods and apparatuses for automatically identifying subject matter experts related to search results and displaying user identifications for the subject matter experts along with the search results are described. A search system may identify the subject matter experts based on the content of the search results, metadata associated with the search results, and various interactions including user-document interactions in which a user has created, edited, shared, or commented on a document. As the search system will only surface search results for which the user of the search system that submitted the search query has permission to access and the identification of the subject matter experts is determined based on the search results, the search system may prevent the inadvertent display of unauthorized information.

A system and method for expert-assisted generative AI prompt response adaptation within a computer-populated environment includes a user interface for enabling a user to pose and send user queries and display answers to the user query. A bot answer system is configured to retrieve relevant context in response to the user query. A generative model is configured to provide answers upon the user interface based on retrieved relevant context data in response to the user query. A feedback integration system is configured to provide subject matter expert feedback on at least one of the user query and the answer in real-time. The bot answer system and the feedback integration system are partitioned from one another and direct partitioned data flows through a convergent embedding creation process for storing embeddings in a vector database supporting a knowledge base. The subject matter expert feedback ensures continual improvement of a knowledge base.

Arrangements for machine learning-based dynamic learning are provided. In some examples, audio data associated with a plurality of calls may be received and analyzed to identify a topic and sub-topic of each call and metadata of each call. Feedback data may also be received. A machine learning model may be executed by inputting, to the model, the identified topic and sub-topic and metadata of each call, and the feedback data, to output one or more topics or sub-topics of concern. A plurality of ongoing calls may be monitored to identify an ongoing call related to one of: a topic or sub-topic of concern. A plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern and are available may be identified and joined, via respective computing devices, to the ongoing call in a dynamic learning session.

Examples described herein provide a method of knowledge authentication for artificial intelligence aided decision making. The method includes receiving knowledge from a subject expert and authenticating the knowledge based on structured decision making information. The method also includes generating an efficiency index for separate use of knowledge, wherein the efficiency index measures the order and efficiency of the decisions and methods taken to solve the problem. The method also includes storing the authenticated knowledge and an efficiency index, wherein the authenticated knowledge represents a proprietary technology that can be distributed at a deterministic level with respect to its availability. The method also includes generating a response to the user query using the authenticated knowledge and efficiency index using the trained machine learning model.

An action generation process involves one or more processors receiving a request from a user via a conversational interface; one or more processors receiving building subsystem data for one or more building subsystems in a building; one or more processors retrieving domain expert data; one or more processors determining an anomaly of one or more building subsystems based on the domain expert data and the building subsystem data; one or more processors generating a recommendation to resolve the anomaly based on fault detection and diagnosis (FDD) data related to a fault identified in one or more building subsystems; and one or more processors generating a response to the request based on the recommendation using a generative large language model.the FDD data and the subject matter expert data.

A computerized-method for automatically generating a two-part readable Suspicious Activity Report (SAR) from high-dimensional data in tabular form is provided herein. The computerized-method may include receiving high-dimensional data in tabular form of evidence financial transactions to be reported under Anti Money Laundering (AML) regulations. Then, displaying the received data to a Subject Matter Expert (SME) for ordering each displayed transaction in a predefined construction; Then, training one or more Natural Language Generation (NLG) translation models, for each transaction type, according to a deep learning model. Then, operating the one or more NLG translation models on each transaction type to generate for each transaction type a narrative of SAR; Then, operating a prebuilt summary model on the generated narrative of SAR of each transaction type to generate a summary of the plurality of narratives of SAR; and combining the plurality of narratives of SAR and the summary to one SAR.

Various methods and processes, apparatuses or systems, and media for enabling skill-based contract assignment for completing a particular project are disclosed. A processor trains a model on a set of known criteria data, a plurality of dimensions data, and volume data; and receives a request, via a user interface, from a user to assign the contract for completing the project by selecting criteria determining data. The model applies a weight to the selected criteria determining data; generates a forced-rank list of subject matter experts (SMEs) with rankings and contact information; and transmits the forced-rank list to the user interface. The processor receives user input from the user, via the user interface, establishing an agreement to select an SME from the forced-rank list; transmits an electronic message to the selected SME to accept the agreement; and sets the agreement into a contract on a blockchain to ensure accuracy and encryption.

Computer-implemented methods for a Kubernetes root cause analysis system. Aspects include receiving a keyword from a preprocessor of a Kubernetes root cause analysis system. Aspects further include determining a degree of similarity for the keyword. Aspects also include determining a membership approximation for the keyword in a labeled gravid fuzzy rough set of a multifaceted knowledge corpus based on the degree of similarity for the keyword. Aspects include receiving a determination associated with the membership approximation for the keyword from a subject matter expert. Aspects further include performing a membership action using the keyword on the labeled gravid fuzzy rough set.

A system for an automated processing of user queries based on Subject Matter Expert (SME) data and deterministic tree data including a processor of a query processing server (QPS) node configured to host a machine learning (ML) module coupled to a chatbot module and connected to at least one user-entity node and to a plurality SME-nodes over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire a user query request comprising classifier data from the at least one user-entity node; parse the user query request to extract a plurality of key classifying features; capturing user communications' data with at least one SME from the chatbot module; query a local database to retrieve local historical SMEs'-related data and the deterministic tree data based on the plurality of key classifying features and the user communications' data; generate at least one classifier feature vector based on the plurality of the key classifying features, the user communications' data and the local historical SMEs'-related data and the deterministic tree data; provide the at least one classifier feature vector to the ML module configured to generate a user query processing predictive model for producing at least one query routing parameter; and generate a query routing verdict based on the at least one query routing parameter and route the user query to a target SME.

Various systems and methods are presented herein regarding automatically identifying one or more entities to for assignment to resolving an issue and / or removing an entity from a group of entities assigned to resolve the issue. The issue can relate to an information technology / computer-based environment. The entities can be subject matter experts, having expertise identified to be related to the issue. A summary of the issue and activity relating to resolving the issue can be automatically generated and supplied to an entity who is being onboarded after the project is underway to resolve the issue. By implementing automated assignment / removal of entities, efficiency of the resolution is improved.

An process analysis computing system receives input data that identifies a subject-matter expert (SME) process, such as an SME process that requires detailed information regarding a very large quantity of information about the SME process. In the process analysis computing system, a scenario selection engine extracts process factors and user factors from the input data. Based on the process factors and user factors, the scenario selection engine determines initial schedule data describing event stages and milestone stages included in the SME process, and also generates user-specific process schedule data based on a modification of the initial schedule data. A user-specific execution engine in the process analysis computing system receives the user-specific process schedule data. Based on a milestone stage dependency in the user-specific process schedule data, the process analysis computing system controls access to a requested resource associated with the SME process.

A system automatically identifies wait times for a subject matter expert (SME). The system includes a cloud server in communication with an agent computer, an SME computer, and a database for storing presence data associated with the SME computer. Over a first period of time, the processor receives the presence data associated with the SME computer; stores the presence data in the database; and trains a custom machine learning network. The processor receives an input from the agent computer requesting contact with the SME computer, and solicits a status from the SME computer. If the status is not “Available”, the processor, using the trained custom machine learning network, predicts a wait time after which the status will be “Available” and reports the predicted wait time to the agent computer. If the status is “Available”, the system establishes a communication link between the agent computer and the SME computer.

To provide a computer-implemented method for serving a large language model (LLM) application via a serverless function router communicative with multiple endpoints that each have a set of subject matter expert models stored thereon.SOLUTION: A computer-implemented method includes: receiving a prompt; querying a database comprising multiple datasets for an indication as to which one of the multiple datasets has a highest level of similarity with the prompt; recognizing one of the multiple endpoints as having the set of expert models stored thereon which have a closest match with the one of the multiple datasets; and routing the prompt to the one of the multiple endpoints having the set of the expert models stored thereon which have the closest match with the one of the multiple datasets.SELECTED DRAWING: Figure 3

In one implementation, a device uses a large language model-based agent to identify a task to correct an issue in a network. The device makes a determination that the large language model-based agent cannot complete the task. The device identifies, based on the determination, a subject matter expert to help complete the task. The device sends a request to the subject matter expert to complete the task.

An action generation method includes receiving, by one or more processors, a query from a user via a dialog interface; receiving, by the one or more processors, building subsystem data for one or more building subsystems in the building; retrieving, by the one or more processors, subject expert data; determining, by the one or more processors, anomalies of the one or more building subsystems based on the subject expert data and the building subsystem data; generating, by the one or more processors, a suggestion for resolving the anomaly based on fault detection and diagnosis (FDD) data related to the fault determined in the one or more building subsystems; and generating, by the one or more processors, a response to the query based on the suggestions, the FDD data, and the subject expert data using the generative large language model.

The present disclosure discloses a system that includes a transceiver and a processor. The transceiver may be configured to receive information associated with a facility. The processor may be communicatively coupled to the transceiver. The processor may be configured to obtain information from the transceiver, provide an interactive platform to train users and serve as a subject matter expert; determine a probability of a hazard based on the information, provide remediation recommendations, and generate a hazard report based on the determination of the probability of the hazard in the facility. Included is an Interactive Medical Reference System (“system”) that includes an app for patients / doctors that operates on the same principle. The system aims to also take the place of trainers by being interactive thereby serving as a training tool and identify hazards or potentially detrimental healthcare treatment plans.

Here describes a process for interfacing with a control system coupled to one or more devices. The system comprises a first module configured to receive a first data representation of at least one input alarm from the control system and associated data tags corresponding to said one or more devices. A second module configured to process said first data representation using at least one language model, where said at least one language model is adapted to convert said first data representation into a second data representation based on the associated data tags; and a third module configured to output the second data representation in response to at least one input to the control system.

Examples described herein provide a method for knowledge authentication for artificial intelligence-assisted decision making. The method includes receiving knowledge from a subject matter expert and authenticating the knowledge based on structured decision-making information. The method further includes generating an efficiency index for individual uses of the knowledge, wherein the efficiency index measures a sequence and efficiency of decisions and approaches taken towards solving a problem. The method further includes storing authenticated knowledge and the efficiency index, wherein the authenticated knowledge represents know-how that can be distributed with a level of certainty about its usability. The method further includes generating, using a trained machine learning model, a response to a user query using the authenticated knowledge and the efficiency index.

A method for generating an optimal set of parameters for a design project of a product, in which subject matter experts, working with an artificial intelligence module, select a number of fundamental measurement factors that are related to a group of fundamental prime measurements, all of which in the aggregate comprise a product profile matrix. The fundamental measurement factors are weighted and scored so that the resulting matrix reflects the various aspect of the proposed design. Through an iterative process, the fundamental measurement factors are modified until the product profile matrix provides a set of satisfactory scores that yields an acceptably low risk in proceeding with the selected design.

Various methods and processes, apparatuses or systems, and media for enabling skill-based contract assignment for completing a particular project are disclosed. A processor trains a model on a set of known criteria data, a plurality of dimensions data, and volume data; and receives a request, via a user interface, from a user to assign the contract for completing the project by selecting criteria determining data. The model applies a weight to the selected criteria determining data; generates a forced-rank list of subject matter experts (SMEs) with rankings and contact information; and transmits the forced-rank list to the user interface. The processor receives user input from the user, via the user interface, establishing an agreement to select an SME from the forced-rank list; transmits an electronic message to the selected SME to accept the agreement; and sets the agreement into a contract on a blockchain to ensure accuracy and encryption.

This disclosure relates generally to predicting proficiency level of a person from resume. The proficiency levels obtained using state-of-the-art methods tends to overestimate proficiency. Moreover, the estimated proficiency levels do not satisfy several constraints that are considered key by subject matter experts. Embodiments of the present disclosure extract skills and other related information automatically from resume and capture skill related information in terms of a feature vector. A skill estimation function is learned to predict the proficiency level of the skill from the feature vector using any one of two models. A first model is learned using a constraint loss function to combine label information with domain specific constraints and a second model is learned using a clustering based technique. The disclosure predicts skill proficiency using only resume and can be used for predicting proficiency level of skills of employees from their resumes, for suitable job recommendations from job portal.

A platform for creating, managing, and deploying digital twins of human experts through automated behavioral capture and analysis. The platform employs a data collection system that monitors and processes digital interactions, communications, and work patterns to create AI-powered digital representations of subject matter experts. These digital twins maintain the knowledge, decision-making patterns, and communication style of the original subject while preserving privacy and confidentiality boundaries. The platform includes systems for managing multiple instances of digital twins across different organizations, with capabilities for instance-level learning and knowledge integration. A comprehensive licensing and rights management system enables controlled distribution of expert digital twins while ensuring appropriate privacy and security controls are in place. The platform maintains continuous compliance monitoring and privacy enforcement across all twin instances, allowing for scalable deployment of expert knowledge while maintaining security and confidentiality requirements.

Here describes a process for interfacing with a control system coupled to one or more devices. The system comprises a first module configured to receive a first data representation of at least one input alarm from the control system and associated data tags corresponding to said one or more devices. A second module configured to process said first data representation using at least one language model, where said at least one language model is adapted to convert said first data representation into a second data representation based on the associated data tags; and a third module configured to output the second data representation in response to at least one input to the control system.

A computer-implemented method for serving a large language model (LLM) application via a serverless function router communicative with multiple endpoints that each have a set of subject matter expert models stored thereon is provided. The computer-implemented method includes receiving a prompt, querying a database comprising multiple datasets for an indication as to which one of the multiple datasets has a highest level of similarity with the prompt, recognizing one of the multiple endpoints as having the set of the expert models stored thereon which have a closest match with the one of the multiple datasets and routing the prompt to the one of the multiple endpoints having the set of the expert models stored thereon which have the closest match with the one of the multiple datasets.