46 results about "Knowledge use" patented technology

The invention discloses an operation and maintenance knowledge intelligent question and answer interaction method, device and equipment based on an LLM large model. According to the method, questions of operation and maintenance personnel are received through a natural language interaction interface, semantics are analyzed through a pre-trained LLM, candidate answers are generated, the accuracy of the answers is verified in combination with a dynamic operation and maintenance knowledge graph (including equipment model and fault code mapping, a historical case library and a real-time updating knowledge base), and finally a verification result is returned. The device comprises an input module, a processing module, a verification module and an output module, the processing module integrates domain knowledge fine tuning and real-time data integration functions, and the verification module supports multi-source data fusion and confidence evaluation. The platform adopts a multi-tenant architecture, supports visual diagnosis, automatic equipment operation and knowledge use report generation, and ensures that data cannot be tampered through a block chain 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.

The invention discloses an RAG-based Deepseek-R1 dialogue question-answering method, which is characterized by comprising the following steps: carrying out knowledge base preprocessing, collecting information from a data source, converting the information into a uniform format, carrying out text analysis, partitioning, information extraction and labeling, vectorizing text data and storing the vectorized text data in a vector database; storing the preprocessed text data and the vectorized representation thereof by adopting a distributed vector database; receiving a question input by a user, understanding and rewriting the question, performing retrieval from the knowledge base by utilizing vectorization coding and similarity calculation, and optimizing a retrieval result through a reordering model; and based on the retrieved background knowledge, a Deepseek-R1 model is used to generate a natural language answer, and the natural language answer is output to the user after optimization and adjustment.

The invention provides a passive domain adaptive sample forgetting method based on sample sensitivity, and aims to solve the problems that model training is interfered by sample noise and the cross-domain adaptability is poor in a distributed data environment, the method obtains a pure training set by calculating the sample sensitivity of a source domain and screening out samples influencing the model training according to a threshold value, and the sample sensitivity of the source domain is calculated. The method comprises the steps of processing source domain data, training a teacher model by using the processed source domain data, generating a pseudo tag for unmarked data of a target domain, guiding student model learning, transmitting knowledge of the teacher model through a knowledge distillation technology, and aggregating client model parameters by using a federal learning framework, so that data privacy can be protected, and the performance of the model in the target domain can be enhanced. Experiments verify that the method can effectively realize passive domain adaptation, improve the adaptability and accuracy of the model in the target domain, and provide a better model training solution for related fields.

The invention discloses an electric vehicle charging compatible fault diagnosis method based on a knowledge graph, and the method comprises the following steps: constructing the knowledge graph, carrying out the fault diagnosis reasoning, and updating the knowledge graph, and the construction of the knowledge graph comprises the following steps: collecting multi-source data in the charging process of an electric vehicle, knowledge extraction is performed by applying a natural language processing technology and a data mining algorithm, knowledge from different sources is fused, a knowledge graph is constructed in a graph form, nodes represent entities, edges represent relationships between the entities, and attributes are attached to the nodes or the edges. According to the method, the knowledge graph is constructed, the electric vehicle charging multi-source data is comprehensively collected, knowledge is extracted and fused by using natural language processing and a data mining algorithm, and during fault diagnosis reasoning, input data is preprocessed based on combination of rules and machine learning, for example, abnormal value detection by using Z-score, missing value filling by using linear interpolation and the like.

The invention discloses a topic analysis method based on a large language model. The method comprises the following steps: performing data preprocessing on dialogue content; performing topic classification on the preprocessed dialogue contents, and collecting contents belonging to the same topic together; discussion objects, abbreviations and key phrases appearing in the content are extracted, and additional background knowledge is collected; summarizing contents under the topic by using a large language model to form a topic name and a topic abstract; and performing the same processing on a plurality of topics in the dialogue process to form a topic analysis report of the discussion content. Important information can be efficiently and accurately extracted, and a topic report is formed.

The invention discloses a federal remote sensing large model training method and system based on low-rank self-adaption. The method comprises the following steps: performing personalized heterogeneous data knowledge learning by using respective remote sensing data, a pre-trained large model and a local low-rank self-adaption model; using the trained local low-rank self-adaptive model parameters to initialize global shared low-rank self-adaptive model parameters, performing collaborative federal training based on the pre-trained large model and the global shared low-rank self-adaptive model, and learning global remote sensing task domain knowledge; after alignment of local heterogeneous data knowledge and global remote sensing task knowledge is realized in a different-rank alignment fusion mode, a federated remote sensing large model composed of parameters of a pre-trained large model and an aligned local low-rank adaptive model is output, so that the parameter quantity and communication overhead uploaded by federated training are greatly reduced, efficient training of the model is ensured, and the reliability of the model is improved. And self-adaptive alignment of local heterogeneous data and global remote sensing tasks is also realized, and the universality and robustness of the model are ensured.

The invention relates to a converter steelmaking knowledge graph construction method and device and computer equipment, and the method comprises the steps: constructing an ontology hierarchy according to collected multi-source heterogeneous data, then carrying out corresponding knowledge extraction on different types of data based on an ontology hierarchy structure, employing a similarity calculation hierarchical clustering method based on TF-IDF and SBERT, and carrying out knowledge extraction on different types of data; and converter steelmaking knowledge is processed and fused, so that the data quality of the knowledge graph is ensured. Multi-source knowledge dispersed in a technical document, an operation manual, an enterprise informatization database and the like is systematically integrated to form a structured knowledge base, which has positive influence on improving information retrieval and knowledge utilization and acquisition processes of converter steelmaking and provides solid knowledge data support for subsequent implementation of converter intelligent steelmaking.

The invention discloses a method and a system for automatically generating a video based on multi-agent unstructured knowledge, and relates to the technical field of video automatic generation based on knowledge processing, and through a data source weight evaluation mechanism and a content semantic similarity calculation method, repeated or contradictory knowledge fragments are automatically identified, a disputed knowledge unit list is established, and the video is automatically generated according to the disputed knowledge unit list. And analyzing the matching degree of the dispute content and the preset script by adopting a semantic vector similarity algorithm. And for the recognized dispute knowledge points, a standby knowledge replacement algorithm is applied to retrieve replacement contents with high confidence from a reliable knowledge base, a knowledge unit replacement operation is executed, and high-quality video output with dispute identification is generated, so that the content accuracy and credibility of the multi-source knowledge fusion video are effectively improved. According to the method, a whole-process quality control system from knowledge identification to video generation is established, intelligent matching of knowledge credibility evaluation and a video content presentation mode is realized, and practical deployment of the technology is restricted.

Various embodiments are generally directed to embodiments discussed herein. An example system includes a processor, and a memory having instructions stored therein. The instructions include a discovery module, a mapping module, an assignment module, a tracking module, a chunking module and an evolution module. When the instructions are executed by the processor, the instructions cause the processor to: monitor, by using the discovery module, documents within document repositories and communications in one or more communication media; identify, by using the discovery module, ideas in the monitored documents and communications; map, using the mapping module, knowledge within an enterprise based on the monitored documents and communications; provide, using the tracking module, tracking and management of the identified ideas; chunk, using the chunking module, the monitored documents and communications to provide context of the identified ideas; and track, using the evolution module, progression of the identified ideas over time.

The present invention provides a knowledge-aware sequence-to-tree mathematical word problem solving system for processing and reasoning on the word problem text to be analyzed to obtain a corresponding mathematical expression, which is characterized in that it includes: a problem encoding module that encodes the word problem text to be analyzed using a predetermined first neural network to obtain an encoded problem vector; an entity graph construction module that retrieves the word problem text to be analyzed in a predetermined external knowledge base containing common sense information to obtain a corresponding entity triple, and constructs an entity graph based on the entity triple; a knowledge representation generation module that obtains a knowledge representation recognizing knowledge using a predetermined second neural network based on the encoded problem vector and the entity graph; and a tree-shaped decoding module that generates a mathematical expression tree using a predetermined third neural network based on the encoded problem vector and the knowledge representation. This system integrates common sense information not present in the word problem, thereby improving the accuracy of the mathematical expression.

This invention discloses an AI-based intelligent question-answering method, device, electronic device, and product for games, relating to the field of intelligent question-answering technology. The AI-based intelligent question-answering method for games includes: identifying entity objects in game consultation text through part-of-speech tagging; performing similarity matching between the game consultation text and various question templates in a pre-built question template library to obtain a target question template with the highest matching degree; constructing a graph database query statement based on the question type corresponding to the target question template and the entity objects in the game consultation text; querying data from a pre-built graph database based on game knowledge using the graph database query statement; and generating a response text for the game consultation text based on the query results. The AI-based intelligent question-answering method, device, electronic device, and product disclosed in this invention ensure that the generated response content corresponds to the user's intended question, improving the accuracy of intelligent question-answering for games.

The application discloses an operation and maintenance knowledge intelligent question and answer interaction method, device and equipment based on an LLM large model. The method receives a question from an operation and maintenance personnel through a natural language interaction interface, analyzes semantics by using a pre-trained LLM to generate a candidate answer, verifies the accuracy of the answer in combination with a dynamic operation and maintenance knowledge graph (containing a device model and fault code mapping, a historical case library and a real-time updating knowledge base), and finally returns a verification result. The device contains an input module, a processing module, a verification module and an output module, wherein the processing module integrates field knowledge fine-tuning and real-time data set functions, and the verification module supports multi-source data fusion and confidence evaluation. The platform adopts a multi-tenant architecture, supports visual diagnosis, automatic device operation and knowledge usage report generation, and ensures that data cannot be tampered with through blockchain technology.

The application discloses a kind of based on knowledge verification's trusted question and answer method, including the following steps: identifying and eliminating the reference and omission content in user's asking question, restating user's asking question, and extracting the keyword expressing user's intention.Use the keyword set after restating as query, retrieve relevant articles, calculate the relevance score of the content retrieved and the asking question, and filter out the highest relevance score multi-modal knowledge.Generating multi-modal statements about search results, multi-round, multi-path verification and reasoning are carried out on the multi-modal statements.The authenticity of the iterated multi-modal statements is verified, and the filtered and verified knowledge and evidence are integrated to generate the final trusted user reply.Compared with the prior art, the application can eliminate references and omissions by injecting associated historical context information during the question representation process, and obtain trusted multi-modal knowledge using retrieval enhancement and self-checking mechanisms, thereby more accurately answering the questions asked by the user.

The present invention discloses a method for constructing an emergency inspection knowledge base driven by knowledge fusion, belonging to the fields of emergency management and information technology. Specifically, it includes: collecting and preprocessing emergency inspection data from different data sources, extracting and representing emergency inspection knowledge using relation extraction methods and semantic web technologies, and constructing an emergency inspection knowledge graph through knowledge fusion strategies; classifying and coding the knowledge in the emergency inspection knowledge graph according to emergency inspection requirements, and formulating a classification vocabulary; conducting knowledge reasoning based on the emergency inspection knowledge graph, constructing an intelligent question-answering system and an emergency inspection process, and forming an emergency inspection knowledge base; optimizing and improving the knowledge base through functional testing, performance testing, and user feedback; the present invention improves the efficiency and accuracy of emergency inspections.

The application discloses a method and system for automatically generating a video based on unstructured knowledge of multiple agents, relates to the technical field of video automatic generation based on knowledge processing, and automatically identifies repeated or contradictory knowledge fragments through a data source weight evaluation mechanism and a content semantic similarity calculation method, establishes a controversial knowledge unit list, and adopts a semantic vector similarity algorithm to analyze the matching degree of controversial content and a preset script.For the identified controversial knowledge points, a backup knowledge replacement algorithm is used to retrieve high-confidence replacement content from a reliable knowledge base, a knowledge unit replacement operation is performed, a high-quality video output with a controversial identifier is generated, and the content accuracy and reliability of the multi-source knowledge fusion video are effectively improved.The application realizes a whole-process quality control system from knowledge identification to video generation, realizes intelligent matching of knowledge reliability evaluation and video content presentation mode, and restricts practical deployment of the technology.

One or more embodiments of the specification disclose a data security grading method and device, electronic equipment and storage medium. The method comprises: inputting a target data set into a knowledge extraction module of a data grading model for knowledge extraction, obtaining first knowledge corresponding to the target data set, which contains entity data, relationship data and attribute data; using a knowledge representation module of the data grading model, performing entity relationship prediction on the first knowledge to obtain second knowledge; inputting the second knowledge into a knowledge fusion module of the data grading model for knowledge fusion processing, merging the second knowledge with a similarity greater than a threshold to obtain third knowledge corresponding to the target data set; inputting the third knowledge into a knowledge graph module of the data grading model, and using a hierarchical knowledge graph previously constructed in the knowledge graph module to divide the data security level of the third knowledge to obtain a hierarchical result of the security level corresponding to the target data set.

The present invention belongs to the technical field of large language model security, and discloses a large language model security detection method based on automatic generation of a knowledge graph. The method includes the following steps: preprocessing a data set containing different dangerous prompt words for the security detection direction, and replacing the dangerous behaviors in the initial prompt words with low-resource languages; using a prompt word template to automatically explore the dangerous knowledge encoded inside a large language model by means of the large language model, and using the large language model to construct a detection knowledge graph; converting the structured information in the detection knowledge graph into natural language text; designing a two-level security evaluator to determine whether the security protection of the large language model can be bypassed. The present invention attempts to bypass the security protection of the large language model to be tested after preprocessing the initial prompt words and nesting the templates, so as to evaluate the security performance of the large language model by whether the model generates a detection knowledge graph and the specific content.

Regarding the technology of automatically generating code using generation AI based on specifications, we want to provide technology that enables generation AI to generate code that better conforms to the specifications. [Solution] The code generation device 100 includes a prompt generation unit 110 that generates a second prompt indicating a second specification and second reference information when a first automatically generated code generated based on an inference model 50 and a first prompt indicating a first specification is committed to a version control tool 51, a first finalized code generated by modifying the first automatically generated code based on the first specification is committed to the version control tool 51, and a second reference information relating to the knowledge used by the inference model 50 when generating code is generated based on the first specification, a first conforming code, a first non-conforming code, and a first corrected code.

The invention discloses an automatic driving reinforcement teaching learning method, device and equipment, a medium and a product. The method comprises the following steps: in a simulation platform, constructing a reinforcement learning abstract environment containing a state, an action and a reward function based on an automatic driving scene; obtaining multi-source trajectory data in the reinforcement learning abstract environment, wherein the multi-source trajectory data comprises a preset teaching state transition trajectory, a different-orbit state transition trajectory and a same-orbit state transition trajectory; clustering the multi-source trajectory data to obtain a clustering result, performing probabilistic sampling according to the clustering result, and constructing a mixed experience playback pool; and carrying out automatic driving reinforcement teaching learning based on the mixed experience playback pool. According to the scheme, teaching knowledge used in imitation learning is integrated into a traditional reinforcement learning method, and the sampling and utilization mode of a probabilistic sampling optimization sample is combined, so that the learning ability of the traditional reinforcement learning method is kept, and meanwhile, the automatic driving learning process is more stable.

The invention belongs to the field of motor engineering, and particularly relates to an inference type prior knowledge construction method and device for motor parameter identification, and the method comprises the steps: obtaining basic physical constraint prior based on multi-source parallel data of a target motor; performing cross-task learning on the multi-source parallel data of the target motor between different motor types and different working conditions to obtain hot start prior; based on one or two of basic physical constraint priori and hot start priori, obtaining non-independent identically distributed adaptation priori; collaborative iterative optimization is carried out on the non-independent identically distributed adaptation priori, and enhanced non-independent identically distributed adaptation priori is obtained; the basic physical constraint priori, the hot start priori and the enhanced non-independent identically distributed adaptation priori are integrated, and inference type priori knowledge used for motor parameter identification is obtained; according to the method, reasoning type priori knowledge with physical reasonability, cross-domain adaptability and reasoning reliability can be obtained, and the generalization ability and efficiency of the AI model in a motor parameter identification scene are improved.

This invention discloses a project compliance audit method and system based on collaborative reasoning using an expert knowledge base and a large model. First, a large model is used to analyze a collection of laws and regulations and audit practice documents, automatically extracting compliance audit-related knowledge. Then, this compliance audit-related knowledge is used to construct an expert knowledge base comprising a legal and regulatory knowledge base, an audit case library, an audit experience library, an audit practice library, and a compliance audit rule library. This invention achieves the function of automatically constructing and dynamically expanding the expert knowledge base by extracting legal and regulatory knowledge and audit knowledge using a large model. Furthermore, the reliability of the expert knowledge base and factual data is ensured through a confidence level mechanism and human-machine collaborative verification. Simultaneously, the use of audit evidence traceability chain information enables full-link traceability from audit conclusions to original evidence, greatly improving knowledge conversion efficiency and enhancing the interpretability and reliability of compliance audits, making it suitable for widespread promotion and use.

The present invention discloses an entity and relationship linking method based on abstract semantic representation in knowledge base question answering, which includes two main steps: (1) entity linking for mentions in natural language questions based on abstract semantic representation. The present invention introduces entities and their descriptions in Wikipedia as external knowledge, uses a dual encoder to preliminarily screen a large number of entities in the knowledge base, and then uses a cross encoder to rank and score entity mentions in the question to determine the corresponding knowledge base entities. (2) Relationship linking for the relationship representation substructure in the semantic parsing graph based on the entity linking result and the abstract semantic representation of the question. The present invention uses a cross encoder to match, score, and rank the relationship substructure in the semantic parsing graph and the candidate relationship set, and then combines with a local dictionary to select the knowledge base relationships after preliminary screening using a dual encoder. Through the flexible use of the encoder, the accuracy of entity linking and relationship linking is further improved.

17. Abstract of description Provided in the embodiments of the present application are a knowledge base processing method and apparatus, and a computer device, a medium and a program product. The knowledge base processing method comprises: receiving a sharing credential of a shared knowledge base; in response to an access operation on the sharing credential, displaying the shared knowledge base, which is shared, wherein the shared knowledge base comprises at least one knowledge file; receiving question information for the shared knowledge base; and displaying answer information for the question information, wherein the answer information is obtained by means of performing answer generation on the question information on the basis of the knowledge file in the shared knowledge base. By means of the embodiments of the present application, the knowledge utilization rate of a knowledge base can be increased.

The present disclosure discloses a knowledge extraction method, system, device and storage medium. The knowledge extraction method comprises: obtaining and processing text data describing an object to determine a plurality of sentences and an object category corresponding to each sentence; generating a syntax relationship template for each sentence, the syntax relationship template comprising the part of speech of each word and the dependency relationship between the words; generating a syntax tree corresponding to each sentence through syntax analysis; matching the syntax relationship template and the syntax tree, and if the match is consistent, generating a candidate knowledge using the matched syntax subtree; using a knowledge prediction model to predict whether the candidate knowledge is correct knowledge; and using a knowledge classification model to process the predicted correct knowledge to identify the knowledge category corresponding to each piece of knowledge. The knowledge extracted according to the present scheme has the characteristics of low redundancy and high accuracy.

This application provides a method, apparatus, device, and computer storage medium for constructing a tag tree. The tag tree construction method includes: obtaining a tag tree construction request, the construction request including an object to be analyzed; parsing the construction request to determine key request information, the key request information including at least one of the following: the modal type of the object to be analyzed, and the field type corresponding to the construction request; determining associated tag knowledge corresponding to the construction request based on the key request information; and processing the construction request and associated tag knowledge using a tag tree generation model to generate a target tag tree corresponding to the construction request. In this embodiment, the associated tag knowledge is determined based on the key request information. Since the key tag knowledge can fully understand and operate on the professional terms and implicit knowledge corresponding to the object to be analyzed, the quality and efficiency of tag tree construction are effectively guaranteed when generating the target tag tree based on the associated tag knowledge.

The invention discloses a kernel data multi-modal knowledge graph construction method, and relates to the technical field of knowledge graphs. The kernel data multi-modal knowledge graph construction method comprises the following steps: S1, acquiring multi-modal data in the field of kernel science and technology, wherein the multi-modal data comprises text modal data and image modal data; s2, constructing a multi-modal knowledge graph ontology of the kernel data; s3, integrating target detection, relation prediction and character recognition technologies for the image modal data to realize automatic extraction of entities, relations and attributes; s4, extracting structured knowledge from the text modal data by adopting a rule-based method; and S5, realizing fusion of the image knowledge and the text knowledge through entity alignment, and storing a fusion result into a graph database to complete construction of the kernel data multi-modal knowledge graph. By adopting the multi-modal knowledge graph construction method for the kernel data, deep fusion and knowledge mining of the kernel data can be realized, and data support is provided for multi-modal question answering, retrieval and recommendation application of the kernel data.

The invention discloses a knowledge base construction and use method and device for a trusted data space, equipment and a medium, and relates to the field of artificial intelligence, and the method comprises the steps: carrying out the sensitive grading of a target knowledge block, obtaining a corresponding first grading result, carrying out the vectorization of the target knowledge block through employing different types of preset large models according to the first grading result, and obtaining a second grading result; obtaining target vector data, and constructing a target knowledge base based on the target vector data; vectorizing the knowledge query request to obtain a query request vector, and determining target data corresponding to the query request vector from each constructed target knowledge base; performing sensitivity grading on the target data to obtain a corresponding second grading result, and inputting the target data into a preset large model according to the second grading result to obtain a corresponding reasoning result; and determining a request result corresponding to the knowledge query request by using the reasoning result, and returning the request result to the knowledge user. Different knowledge bases are connected together, and the knowledge retrieval range is widened.

The invention discloses a recommendation method and device based on a knowledge graph, a medium and equipment, and relates to the technical field of recommendation based on the knowledge graph. Comprising the following steps: inputting a to-be-recommended knowledge graph into a recommendation model, learning a basic principle score of a triple in the to-be-recommended knowledge graph through a rational perception masking mechanism module, and weighting the triple by using the basic principle score; based on the weighted triple, obtaining user embedding by using a neighbor aggregation method; an average value of basic principle scores of all knowledge triples related to the project is obtained through a knowledge perception comparison mechanism module, and sampling is performed based on the average value to enhance the knowledge graph; an original knowledge base is divided into a plurality of sub-graphs through a local weighted smoothing mechanism module, and local information of direct neighbors is coded to node embedding, so that aggregation relation knowledge for item coding is learned while semantic independence is kept, and embedding representation is obtained; and performing item recommendation based on the similarity of the embedded representation.