57 results about "Specific knowledge" patented technology

Systems, methods, and computer-readable media provide a context-specific prompt to answer a user query. The systems, methods, and computer-readable media determine a context based on content of a natural language request and / or determine a role of a user who submitted the natural language request. Additionally or alternatively, templates or RAG sources that will be used for prompt generation may include financials domain-specific knowledge or other domain-specific knowledge or insights. Inclusion of this additional information in the prompt enhances the context to promote more accurate results from a large language model. In one embodiment, the prompt templates are created from various RAG sources, such as payables, general ledger, receivables, and asset management, containing structured data and information specific to the financial domain, enterprise, or other domain, which helps craft accurate prompts. A prompt is generated that identifies a subset of available fields and other selected information based on the role or other context. The prompt template may contain domain-specific knowledge uses a relevant domain or enterprise information to drive relevant results, and an executable query is generated by a large language model based on the prompt. The executable query causes data to be retrieved from a database to generate a result, and information is displayed based at least in part on the result.

Techniques for constraining the results of a generative language model to valid information using knowledge-grounded documentation. A generative language model may generate invalid results, including compound entities and incorrect entity relations. The techniques include, for a given user inquiry, determining a set of documented information, from a particular knowledge base, that corresponds to the user inquiry. The techniques further include determining a subgraph from a knowledge graph representing the knowledge base, as well as determining a trie data structure representation of the set of documented information. The user inquiry and subgraph are provided as input to a trained generative language model for generating a response to the user inquiry. The techniques include using the trie data structure to validate that the generated response corresponds to real information from the set of documented information.

The present disclosure relates to a technique for addressing an issue to be resolved associated with an electronic document. The method discloses accessing an actionable portion associated with a particular knowledge domain of the electronic document and associated context. Further, retrieve data from data sources to provide additional information related to the particular knowledge domain and the associated context. Then structuring the retrieved data to produce a subset of organized data and determine the issue to be resolved related to the electronic document. Further, generate data elements associated with the issue to be resolved and map dependency relationships between data elements. Also, determine test goals associated with the issue to be resolved based on the dependency relationships. Thereafter, determine corresponding test cases associated with resolution and determines actionable test steps related to the issue to be resolved based on the corresponding test cases associated with the electronic document.

An AI-based response generation chatbot system that acts as a digital replica of a person or expert, rather than being the expert itself, interacts with a user while being entirely guided by the information provided to it, without revealing its AI nature and the source of information. The AI-based response generation chatbot system includes a knowledge database initialized with knowledge documents containing expert knowledge with a specific viewpoint. The knowledge documents are compiled into a vector database through chunking and embedding techniques and are converted into unique topic-specific knowledge chunks in a machine-readable format. The compiled vector database further incorporates the Retrieval Augmented Generation (RAG) framework, enabling the retrieval of relevant information from the vector database and then using the retrieved information to frame accurate and contextually relevant responses aligned with user queries.

The invention discloses a personalized learning portrait construction method fusing multi-source data and state updating, and belongs to the field of student portrait construction. The method comprises the steps of firstly collecting learning behavior data of a student, calculating a mastering probability value of the student for each knowledge point in a knowledge graph based on a preset evaluation model, and mapping the mastering probability value into an explicit mastering state; active interaction behaviors of the students are monitored in real time, the self-evaluation mastering state is deduced, and whether correction of the explicit mastering state of the specific knowledge points is triggered or not is judged according to the state difference degree; and taking the corrected mastering state of the knowledge point as an updating trigger point, calculating an expected influence quantity of the mastering state change of the corrected knowledge point on the associated knowledge point based on the topological structure of the knowledge graph, and updating the mastering state of the associated knowledge point according to the expected influence quantity, thereby generating an updated personalized learning portrait. According to the method, the mastering state of the associated knowledge points is dynamically and intelligently updated, and a solid technical support is provided for self-adaptive learning path recommendation.

The application provides a kind of instruction driving machine task planning method and system based on knowledge model, and the specific knowledge of field is structuredly represented by knowledge model, and the object of class level, instance level of field knowledge and its logical relationship are represented;Further, the semantics of instruction is understood, and then the task planning problem represented by instruction is normalized, specifically including task planning object and its mutual constraint relationship;On this basis, further consider the space-time constraint between task objects and the measurement and evaluation of task efficiency.Finally, through atlas and visual graph display, give the pareto optimal scheme under multi-dimension, support intelligent or man-machine interactive decision, realize man-machine interaction in task planning, and output field-specific reliable scheme based on natural language.

Disclosed herein are systems and method for using machine learning to generate / provide supplemental information material for a presentation. In an aspect, presentation material associated with the presentation is analyzed using a knowledge model to identify one or more elements in the presentation material, the one or more elements being associated with one or more concepts related to the presentation and / or related to a specific knowledge area of the knowledge model. For each element of the one or more elements, supplemental information material related to a concept associated with that element is created. A table that links each element of the one or more elements with corresponding supplemental information material is generated. The table links each element in the one or more elements with a position of that element in the presentation material.

An improved knowledge graph for augmenting queries in a retrieval augmented generation system for generative artificial intelligence is constructed using entity data comprising information regarding a first entity of a first entity type and a second entity of a second entity type, the first and second entity types being defined by a domain-specific ontology for a knowledge domain. Relationship data for the knowledge graph comprises information regarding relationships between the first and second entities using relationship definitions from the domain-specific ontology. The knowledge graph is constructed by adding nodes corresponding to the entities and edges corresponding to the relationships. In some examples, the graph is used to identify cybersecurity threats applicable to a specific context.

The application provides an enhanced structured federated graph learning method, and belongs to the technical field of deep learning.The method comprises customer contribution evaluation, parameter adjustment and knowledge forgetting;the customer contribution evaluation evaluates customer contribution by using a reputation theory;the parameter adjustment adjusts key parameters by using an attention mechanism and an entropy weight method, reduces aggregation errors and optimizes global model performance;the knowledge forgetting processes data forgetting requests by combining soft confusion and hard confusion loss, and ensures that specific knowledge is forgotten without affecting overall performance.The application solves the data isolation problem in large-scale graph data training, and solves the problem of non-independent and identically distributed data and diversified local model features;even if the reliability of participants is low, the accuracy can still be guaranteed;and specific knowledge is removed from the client and propagated to the global model, which well responds to the forgetting request proposed by the user.The application significantly improves the accuracy of the global model, and better maintains the model precision after meeting the forgetting request.

The embodiment of the invention relates to a context-aware and stateless deep learning auto-tuning framework. Systems and methods are provided for improving auto-tuning procedures using stateless processing with a remote key value store. For example, the system may implement task launchers, schedulers, and agents to launch, schedule, and execute decomposed auto-tuning phases, respectively. Scheduling policies implemented by the scheduler may perform operations beyond simple scheduling policies (e.g., FIFO-based scheduling policies), which may result in high queuing latency. By utilizing auto-tuning domain-specific knowledge, queuing latency is reduced and resource utilization is improved compared to conventional systems.

The invention relates to a bilingual network threat intelligence relation extraction-oriented large language model optimization method and system, and the method comprises the steps: generating an enhanced data set according to an example set, and combining the example set and the enhanced data set to form a training set; the performance of a plurality of LLMs models is tested under various conditions, task performance and instruction following ability are extracted based on the relation of the models on a Chinese and English data set, and a basic model is screened out. And carrying out fine tuning on the screened model by adopting LoRA, and correcting the output by the LoRA through two trainable weight matrixes and by introducing an increment updating item containing task specific knowledge. Generating a dynamic instruction with a cluster exclusive feature for each test sample based on cluster affiliation, retaining a part of candidate examples with the highest correlation, screening out a part of examples with the highest correlation from the training set, constructing a sample subset under redundancy constraints, and performing cluster classification; and finally, fusing the cluster exclusive instruction with the demonstration examples for enhancing diversity in the sample subset by the cue word.

Methods, systems, and computer storage media for providing domain-integrated contextual response management using a domain-integrated contextual response engine in an artificial intelligence (AI) system are described. Domain-integrated contextual response management is a systematic approach that combines specific industry knowledge with contextual understanding to generate accurate, relevant, and specific industry-tailored responses to user queries. Domain-integrated contextual response management further includes fine-tuning models for Retrieval-Augmented Generation (RAG) tasks using customer-specific data based on a two-fold approach involving skill distillation and knowledge distillation (i.e., skill distillation from a more powerful model like Large Language Model “LLM” and knowledge distillation from domain-specific data). Domain-integrated contextual response management also includes creating a synthetic dataset that enables smaller models (e.g., domain-integrated contextual response models) to effectively manage RAG tasks while incorporating domain-specific knowledge. Domain-integrated contextual response management further ensures that the domain-integrated contextual response models can retrieve relevant information, support citations, and decline out-of-domain (OOD) questions.

The invention relates to a tunnel fire intelligent decision support method and device and a medium. The method comprises the following steps: constructing an ontology layer comprising a concept knowledge graph, a fact knowledge graph and a standard knowledge graph; the method comprises the following steps: acquiring tunnel fire related multi-source heterogeneous data, and extracting a structured triple and text semantics; using a graph database as a core storage medium, instantiating the structured triad into nodes, relationships and attributes according to the constructed ontology layer, and using text semantics as attributes or nodes to mount in a knowledge graph corresponding to the ontology layer; the method comprises the following steps: acquiring a natural language question input by a user, identifying a core intention, converting the natural language question into a standard graph query statement aiming at a specific knowledge graph level based on the type of the core intention, performing retrieval in a corresponding knowledge graph, generating a fire decision support answer according to a retrieval result, and outputting the fire decision support answer. Compared with the prior art, the method has the advantages that the efficiency and scientificity of tunnel disaster prevention design and emergency decision making are remarkably improved, and the like.

The invention belongs to the technical field of information, and particularly relates to a method for learning specific industry knowledge in a large model pre-training stage. Comprising the following steps of 1, cleaning and processing industry data; 2, pre-training industry knowledge; and step 3, knowledge increment pre-training. The method has the beneficial effects that the knowledge expression of the constructed industry is about 4.6 T, and the effect score in a downstream system generation task is improved by about 10% when the method is compared with a standard NST learning method. The specific content is as follows: for pre-trained industry knowledge, about 4.6 T data is constructed through ocr, data cleaning, manual annotation and the like;

The present disclosure provides a measurement application control unit for a measurement application, comprising: a primary database interface configured to be coupled to a primary database, where the primary database is configured to store generic knowledge data about the measurement application; a secondary database interface configured to couple to at least one secondary database, where the at least one secondary database is configured to store specific knowledge data about the measurement application; the system includes a primary database, at least one secondary database, a text-based input interface configured to receive a text-based user request for a measurement application to be executed, a request processor coupled to the primary database, the at least one secondary database, and the text-based input interface, the request processor is configured to retrieve and output database entries from the primary database and the at least one secondary database, the similarity of the database entries to the text-based user requests being above a predetermined threshold.

This invention discloses a method and system for constructing a knowledge graph for personalized health consultation, relating to the field of medical information processing technology. The method includes: acquiring user static profile data and generating user feature vectors; based on a global medical knowledge graph, calculating node relevance scores using user feature vectors to filter and generate a user-specific knowledge subgraph; acquiring user dynamic health data, converting it into temporary nodes, and establishing associations with the specific knowledge subgraph to generate a personalized fusion knowledge graph; receiving user consultation questions and performing multi-hop reasoning on the personalized fusion knowledge graph to obtain reasoning paths; generating personalized consultation answers based on the reasoning paths and answer templates; removing temporary nodes after the session ends, and updating the specific knowledge subgraph when the user's static profile changes. This invention constructs a personalized knowledge graph by fusing user static features and dynamic data, achieving accurate and efficient health consultation services, significantly improving the personalization of answers and reasoning efficiency.

The invention provides a knowledge base semantic retrieval vector model suitability evaluation method and device based on reinforcement learning, and solves the problems disclosed in the background technology. A reinforcement learning mechanism is introduced, a query generation process is modeled into an intelligent agent, and the intelligent agent is enabled to interact with an evaluation environment and autonomously learn to generate high-value queries capable of maximumly distinguishing different model performances, so that deeper and more accurate evaluation of model suitability is realized. By introducing a reinforcement learning mechanism, the fundamental transformation from traditional static and open-loop evaluation to dynamic and closed-loop intelligent evaluation is realized. According to the method, a general test set is abandoned, and the evaluation query with the highest distinction degree can be adaptively generated aiming at a specific knowledge base, so that the performance difference between different vector models can be more efficiently and deeply revealed. The method is high in automation and objectivity, guarantees the fairness and reliability of an evaluation result, and finally provides unprecedented intelligent and data-driven decision support for a user to select an optimal model.

This invention discloses a method and system for predicting the results of traditional Chinese medicine (TCM) consultations in urology using a large language model, belonging to the technical field of large language modeling. This invention preprocesses disease description data and obtains self-correlation parameters between the disease description data; then, based on the large language model, it constructs a prediction model; outputting core keyword data describing lesions enables the prediction of specific causes in consultations, improving accuracy; by recording feedback data related to the core keyword data in real time; inputting the feedback data into a self-correcting model and outputting adjustment values; and adjusting the parameters within the large language model in real time based on the adjustment values, through continuous use and adjustment based on feedback data, the prediction model for a specific knowledge domain in urology is further refined, thereby further improving the accuracy of predicting specific causes in consultations.

The application discloses a process intelligent improvement method based on building block units and a manufacturing industry engineering promotion system. The method comprises the following steps: constructing a three-layer knowledge base comprising a general knowledge base, a factory-specific knowledge base and an improvement case result base; adapting the model to the factory through two-stage training and continuous learning; segmenting the process video shot by the on-site personnel into at least one building block unit, wherein the building block unit is the smallest indivisible independent operation segment; extracting the action features of each building block unit and comparing them with the standard template to calculate the deviation quantization value; when the deviation exceeds the preset threshold, matching the waste type and retrieving similar historical cases to generate an improvement scheme; adopting at least one level of human-computer interaction, wherein the first level is confirmed or interactively modified by the on-site personnel and then submitted, and the second level is audited and approved by the industrial engineering department and then executed; after execution, the video is shot again to verify the effect, and the case is automatically stored in the warehouse; the stored case is used for pushing similar problems, training new people and introducing new products. The application realizes fine-grained quantization, low-cost adaptation, case reuse and controllable closed loop of process improvement.

The application provides a large language model dynamic routing method and related device; a query request is received; a first model is called to generate a candidate answer and a interference answer according to the query request; reasoning is performed according to a reasoning request to obtain a reasoning result, a first frequency of occurrence of the candidate answer and a second frequency of occurrence of the interference answer are determined; a mastery score of the first model for a knowledge point corresponding to the query request is calculated according to the first frequency and the second frequency; when the mastery score is higher than a confidence threshold, the candidate answer is output; when the mastery score is lower than the confidence threshold, a second model is called to output a target answer according to the query request, and the reasoning ability of the second model is higher than that of the first model; without relying on a bottom layer probability data interface, the mastery degree of a lightweight model for specific knowledge is accurately evaluated, thereby realizing accurate dynamic routing, reducing API calling cost, and preventing illusion answer output.

A system and method for building a predictive machine learning model. The method comprises parsing the text of a document review protocol to extract at least one description of at least one concept to be tagged, and tagging at least a portion of the multiple documents to create multiple tagged documents by applying a language model to the multiple documents, wherein tagging at least a portion of the multiple documents further comprises querying the language model with at least one query generated based on the extracted at least one description, building at least one classifier machine learning model based on the extracted at least one description, and training at least one classifier machine learning model using a training set, wherein the training set comprises multiple tagged documents.

To provide a system for achieving highly accurate task processing while suppressing resource consumption, and for facilitating model customization reflecting knowledge unique to a user.SOLUTION: A system comprising: means for maintaining a base model; means for generating a small derivative model optimized for a specific task; means for providing the small derivative model based on a request from a user; means for receiving user specific knowledge and data and customizing the model; means for storing the customized model; means for distributing the customized model to other users; means for tracking usage of the customized model; means for calculating and providing compensation to the user based on the tracking data; and means for using the model in an offline environment.SELECTED DRAWING: Figure 1

The invention provides a collaborative innovation platform based on a DIKWP model and a TRIZ theory, and belongs to the technical field of artificial intelligence and innovative design. The platform takes an artificial consciousness operating system (AI-OS) as a core architecture, and deeply fuses data-information-knowledge-intelligence-intention (DIKWP) five-layer semantic storage and a TRIZ algorithm library reasoning solving function: when a user submits an innovation demand or a technical problem, the platform firstly uses a DIKWP model to perform hierarchical analysis on problem semantics, and identifies potential contradictions and key targets; and then a built-in TRIZ contradiction solving engine and a causal chain analysis engine are matched with corresponding conflict models and inventive principles, and an innovative solution is automatically generated. When the scheme is generated, a general problem solving thought is converted into an executable scheme in combination with domain knowledge, and an inference chain of semantic conversion, a TRIZ principle and a result is output for explanation and verification. The platform also supports plug-in extension, and can be in butt joint with an industry-specific knowledge graph, simulation software and external AI service to enhance the solving capability of problems in specific fields. Compared with the prior art, the method has the advantages that the target-driven semantic closed-loop analysis and the TRIZ algorithm are combined, the value alignment of the solution and the user intention is realized, the process can be explained, the robust iterative optimization capability is realized, the innovation threshold is remarkably reduced, and the problem solving efficiency is improved.

The invention relates to the technical field of information retrieval and machine learning, and provides a domain-to-entity adaptive document rearrangement method, which comprises the following steps of: inputting a plurality of discrimination sample pairs into a rearrangement model to calculate comprehensive correlation scores, and sorting to obtain a corresponding document rearrangement result; the rearrangement model comprises the steps of pre-training a rearrangement module to output a semantic basic correlation score; the domain / entity identification module generates domain weight parameters of a plurality of target domains through a classification network and determines corresponding company entities, and the combined adaptive adjustment module performs sparse selection on low-rank adaptive branches corresponding to the plurality of target domains and performs incremental feature modeling on a discrimination sample pair based on a started low-rank matrix; generating a corresponding incremental correlation score; the reordering execution module is used for ordering the comprehensive correlation scores and outputting results, a specific knowledge base or retrieval implementation does not need to be limited, flexible butt joint with an existing retrieval assembly can be achieved, and the method has the advantages of being fast in convergence, low in cost and the like in the aspects of cross-subject migration and entity-level adaptation.

The application discloses a task-specific enhanced hybrid expert model and a training method, relates to the technical field of hybrid expert models, and provides general knowledge support and outputs base features first, is connected with the base model through a residual injection mode, learns and outputs task-specific features, then generates activation strength based on input Prompt global features, filters and aggregates expert outputs, then respectively fine-tunes task-specific knowledge of independent fine-tuning task experts and binary classification head recognition ability, and finally activates experts through a double-path judgment, superimposes and aggregates outputs through residual injection to obtain a final result. Through the general expert module based on the pre-training stage, the scheme increases the task expert directional enhancement paradigm in the fine-tuning stage, realizes the accurate improvement of specific task performance under the premise that the general ability of the model is not damaged during fine-tuning, and supports the rapid fusion of multiple task version fine-tuning experts.

The system according to this embodiment aims to provide specific knowledge and know-how regarding the installation of mobile phone base stations in condominium buildings and to generate the best possible solutions. [Solution] The system according to the embodiment comprises a generation unit, a provision unit, and a posting unit. The generation unit learns from past project data and generates the best solution for a specific problem. The provision unit provides the solution generated by the generation unit to the construction company. The posting unit posts the knowledge acquired by engineers and construction staff participating in the platform, contributing to an integrated knowledge database.

The application discloses a Web-based disaster monitoring and early warning spatio-temporal process dynamic evolution visualization method, and specifically comprises the following steps: constructing an expression model to describe disaster component elements and disaster processes as the basis for constructing a disaster spatio-temporal expression ontology, then taking the expression ontology as the top-level guide for constructing a knowledge graph, extracting specific knowledge from a large number of real three-dimensional models to construct a disaster knowledge graph, and designing a disaster data self-adaptive organization mode and a visualization data scheduling optimization mechanism to improve the compactness and relevance of data in a Web partition. The expression model and the disaster knowledge graph enable the computer to understand disaster elements and the multidimensional relationship between them, thereby realizing dynamic adjustment and optimization of three-dimensional data, effectively reducing the overhead of complex disaster scene loading and rendering, and realizing high-fluency and low-time-consumption three-dimensional display of disaster spatio-temporal process dynamic evolution.

A system for automated preparation of healthcare claim appeal documents is disclosed herein that comprises a knowledge base containing expert-derived rules that associate denial characteristics with appeal approaches. An analysis component receives claim denial notifications and extracts denial characteristics including reason codes and claim attributes. An inference engine applies the expert-derived rules to select an appeal strategy for the current denial. A document assembly component generates appeal documents by retrieving corresponding templates, populating them with claim-specific information, and incorporating argument content from the selected strategy. An outcome recording component receives appeal outcome data and associates it with the applied expert-derived rules. The system automates expert appeal strategies by encoding domain-specific knowledge about effective approaches in the knowledge base and applying this knowledge through the inference engine.

System and method for generating disambiguated terms in automatically generated transcriptions including instructions within a knowledge domain and employing the system are disclosed. Exemplary implementations may: obtain a set of transcripts representing various speech from users; obtain indications of correlated correct and incorrect transcriptions of spoken terms within the knowledge domain; obtain a vector generation model that generates vectors for individual instances of the transcribed terms in the set of transcripts that are part of the lexicography of the knowledge domain; use the vector generation model to generate the vectors such that a first set of vectors and a second set of vectors are generated that represent the instances of the first correctly transcribed term and the first incorrectly transcribed term, respectively; and train the vector generation model to reduce spatial separation of vectors generated for instances of correlated correct and incorrect transcriptions of spoken terms within the knowledge domain.

This invention provides an AR remote assistance method and system for the installation and debugging of communication equipment. By constructing a three-in-one collaborative architecture of AR smart terminal, expert collaboration platform, and cloud service brain, it achieves remote immersive assistance throughout the entire process of communication equipment installation and debugging. The method includes: the AR smart terminal collecting first-person perspective data and environmental information from the site, and uploading it to the cloud service brain via ultra-low latency transmission technology; the cloud service brain achieving spatial positioning and virtual-real overlay based on multi-source fusion SLAM technology, and completing equipment identification, instrument reading extraction, and fault diagnosis through AI models; the expert collaboration platform supporting multi-user collaborative annotation and real-time interaction, combined with guidance pushed from a communication industry-specific knowledge base; and achieving three-dimensional spatial consistency of multi-terminal virtual annotations through spatial anchor point sharing technology. This invention solves the problems of poor immersion, inaccurate information transmission, and low utilization of expert resources in traditional remote assistance, improving the efficiency and accuracy of communication equipment installation and debugging.