950results about "Semantic tool creation" patented technology

The invention discloses a method for analyzing a matching degree between a demand and an output result based on text semantics. The method comprises the following steps: step 1, labeling a data set; step 2, technical document preprocessing; 3, training and predicting a single-parameter model; 4, integrating prediction results of the multi-parameter model; the method has the beneficial effects thatthe method is simple; deep learning and the NLP technology are applied to the field of project association degree calculation of enterprise project management for the first time. Calculating an association matching degree between the two projects according to project requirements and result description; the associated project positioning difficulty is effectively reduced; meanwhile, the demand side can be helped to quickly and efficiently locate high-quality projects adapting to the demand of the demand side; time and resource investment for achievement screening and matching are greatly reduced, the association matching degree between projects is calculated by means of text data of existing project achievement technical documents and project declaration guidelines, and then large enterprises are assisted in screening high-quality projects with the high matching degree in the project bidding and tendering link.

The invention discloses a credit text analysis method and a credit object auditing method and device, and relates to the technical field of knowledge maps. A specific embodiment of the method comprises the steps of obtaining a target credit card text, wherein the target credit card text comprises at least one target element; a target semantic template corresponding to the target credit document text is obtained, the target semantic template comprises a statement template and an upper sharing hierarchy of the statement template, the statement template comprises at least one target slot position, and the target slot position corresponds to the target element; obtaining a full-link slot position of the target credit card text according to the statement template and the upper sharing hierarchy; and matching the target semantic template with the target credit text to obtain a target slot value corresponding to the full-link slot position. According to the implementation mode, the slot position and the slot value corresponding to the element in the credit card can be automatically obtained, and the related content in the credit card text can be analyzed.

Technology is disclosed for programmatically generating procedures based on historical conversation records and providing the procedures to users to resolve similar issues. In one implementation, an input instruction is generated to cause a language model to determine resolved historical conversation records from historical conversation records. A second input instruction is generated to cause a language model to generate procedure documents from the resolved historical conversation records. The second input instruction includes the resolved historical conversation records and a procedure generation prompt instructing the second language model to (1) extract one or more issues from each resolved historical conversation record, (2) generate a corresponding issue description of each issue, (3) generate a corresponding step-by-step procedure resolving each issue, and (4) generate a corresponding issue resolution description for each issue. The procedure documents are stored in a knowledge base to provide the step-by-step procedures to users to resolve similar issues.

The application discloses a kind of based on ocean fishery big model and digital twinning deep sea aquaculture system and anti storm intelligent operation and maintenance method, belong to the field of ocean, including: multi-source heterogeneous information high-fidelity acquisition module, for collecting environment and working condition data;Knowledge graph and big model cognitive module, through retrieval enhancement generation realizes semantic understanding and causal reasoning;Digital twinning simulation verification module, establishes "environment-structure-operation-biology" coupling model and carries out virtual deduction and risk assessment;Multi-agent collaborative decision-making module, through interaction, cognition, coordination and four types of intelligent agents carry out task arrangement and resource scheduling;Execution and feedback closed loop module, realizes instruction issuing and online correction.The application solves the problems of data fusion difficulty, decision lag, weak collaborative control and lack of physical simulation verification in complex sea conditions, can identify extreme sea condition risk in advance and generate verified risk avoidance strategy, significantly improve the safety of deep sea aquaculture facilities.

The application provides an event-driven AR visualization assembly system and a construction and editing method thereof, comprising the following steps: S1, constructing an assembly process knowledge graph based on a Neo4j graph database; S2, establishing an augmented reality assembly AR material model, extending and developing an augmented reality construction engine based on a C# language, and realizing a model conversion module; S3, defining augmented reality visualization assembly visual guidance content, extending and developing the augmented reality construction engine based on the C# language, and realizing a visualization node editor; S4, editing and associating node elements in a visualization node editing mode through the visualization node editor, defining AR visualization guidance elements, trigger events, demonstration animations and control logic; and S5, generating an augmented reality assembly guidance program. The application can improve the construction efficiency of the augmented reality auxiliary assembly program and reduce the construction period of the augmented reality guidance program.

The application provides a knowledge graph-based information query method and device, equipment and a storage medium. The method comprises: constructing a target entity vector of a to-be-queried text according to an entity word in the to-be-queried text and an entity type corresponding to the entity word; determining a target query mode corresponding to the target entity vector, and obtaining a graph feature item corresponding to the target query mode; wherein the target query mode is used to indicate a query process of the to-be-queried text in a knowledge graph; associating the entity word to the corresponding graph feature item by using the target query mode; generating a corresponding graph query statement according to the target query mode and the graph feature item associated with the entity word; and querying the knowledge graph according to the graph query statement to obtain a corresponding first query result. The method provides the accuracy of the query result.

Autonomous generation includes generating, with a large language model (LLM), an action list for performing an extraction task from at least one website. Generating the action list may include for each action in the action list performing operations. The operations include capturing current webpage data including a screenshot of a current webpage and a set of interactable widgets, obtaining, using an LLM processing the current webpage data, a next action attribute set, adding the next action attribute set, and performing the next action. Autonomous generation also includes traversing the action list to filter out at least one superfluous action, generating, after filtering, a set of machine executable instructions from the action list, and storing the set of machine executable instructions associated with a task identifier. Autonomous generation also includes executing the set of machine executable instructions to extract a data element from the at least one website.

The invention discloses an ontology recognition method and device oriented to a decision knowledge graph, and the method comprises the steps: carrying out the ontology knowledge extraction of text data of a decision-related field, and obtaining an ontology text set; the ontology text set comprises an attribute text set and a rule text set of each ontology; the attribute text set comprises various attribute texts; the rule text set comprises various rule texts; preprocessing the ontology text set to obtain a preprocessed text data set; performing ontology type identification processing on the text data set of each ontology in the preprocessed text data set to obtain a type identification result of each ontology; the type of the ontology comprises a fact type ontology, a rule type ontology and a decision type ontology.

The application discloses a kind of individualized AI execution system and method based on cloud vectorization memory, it is related to artificial intelligence, cloud computing and automation execution field.The application constructs global user vector library in cloud, carries out unified vectorization coding, storage and management to the user data, behavior data, scene data collected to multiple terminals;Receive execution request from different terminals, generate global consistent individualized execution strategy based on cloud vector similarity retrieval;The individualized execution strategy is issued to the corresponding terminal, or directly completes API scheduling, process arrangement, task execution, RPA automation operation, automated payment, order settlement, aggregation payment processing in cloud;Task execution result and user feedback are updated to cloud global vector library synchronously, realize cross-device memory unification and iterative optimization.The application is suitable for multiple terminal cooperation, local life service, take-out delivery, payment aggregation, enterprise automation and the like scene, protection range covers cloud system, terminal, method and storage medium, infringement feature is clear, easy to take evidence, with strong commercial and right protection value.

The application provides a kind of intelligent matching recommendation method for supply and demand of exhibition, it is related to data processing technical field, the method obtains the static profile, dynamic behavior and category attention characteristic vector of supply and demand, and respectively calculates static profile correlation coefficient P, dynamic behavior resonance index D and category attention characteristic vector coupling degree B.And the supply and demand potential energy evaluation model is built to calculate the first supply and demand potential energy matching degree G, and high potential matching pair is identified accordingly.For high potential matching pair, the method dynamically adjusts the basic weight of P, D and B, generates adaptive weight, and finally uses adaptive weight for weighted summation to generate the second matching degree M, and sorts and recommends based on M value.The application realizes the contextual adaptive adjustment of matching logic through multi-source data fusion and dynamic weight mechanism, improves the commercial value and accuracy of recommendation result, and improves the user decision efficiency.

This invention belongs to the field of data processing technology, specifically relating to a method and system for generating maintenance strategies for bridge collision avoidance facilities based on knowledge graphs. The method includes: constructing a physical topology map of the collision avoidance facilities, obtaining the stiffness weights of connecting edges and initializing node parameters; collecting strain and stress data sequences of the collision avoidance units, and calculating the rheological damage index of the collision avoidance units using a dynamic time warping algorithm; constructing a force transmission probability matrix, and obtaining the comprehensive structural risk value of the collision avoidance units through iterative calculation; and calculating the maintenance urgency index by combining the position weight coefficients and service duration of the collision avoidance units to generate a dynamic maintenance strategy. This invention, by constructing a physical topology map reflecting the physical connection relationships between collision avoidance units, and combining the calculation of hysteresis energy consumption and stress transmission deduction of viscoelastic materials, can accurately identify latent transmitted damage and assess the degree of material rheological aging, thus achieving intelligent maintenance of bridge collision avoidance facilities.

The application discloses a test document full life cycle management and tracing method and device, a terminal and a storage medium, and relates to the software test field. The method comprises the following steps: constructing a unified data model comprising test document entities, associated dimension entities and associated relationship entities; dynamically capturing data and creating or updating the associated relationship entities in response to test life cycle events; constructing and maintaining a global associated graph; and generating an associated path view or a change influence domain report according to a tracing request or a change event. The method also comprises the following steps: maintaining a test document entity version evolution history and processing associated relationships. The device comprises data model construction, dynamic association execution, associated graph construction and tracing analysis modules. The application achieves test document full life cycle management and tracing, and can clearly present entity association relationships and accurately evaluate change influences.

The application relates to a knowledge-driven multi-agent cooperative reactor scheme demonstration system and a design method, medium and equipment thereof, the system comprising: a knowledge internalization unit for converting unstructured and semi-structured documents into a dynamic knowledge source which can be queried and utilized by a model in real time; a knowledge structuring unit for extracting core entities, relationships and attributes from the knowledge source and constructing a professional knowledge graph of a reactor design field; and a knowledge application unit for constructing intelligent agents and a collaborative working mechanism of multi-professional intelligent agents based on the knowledge source and the knowledge graph, and constructing an intelligent question and answer interface. Through automatic knowledge management and intelligent agent collaborative work, the application significantly reduces the time and effort of manual intervention and improves the efficiency of reactor scheme demonstration.

Embodiments of the present application disclose an information recommendation method, device, equipment, system and storage medium. In the method, first, medical text materials of a target object are acquired. Then, symptom entities in the medical text materials are determined. Next, based on the medical text materials, symptom entity feature information and context feature information corresponding to the symptom entities are extracted. Then, the symptom entity feature information and the context feature information are fused to obtain fusion features corresponding to the symptom entities. Finally, information is recommended based on the fusion features corresponding to the symptom entities in the medical text materials. By extracting the symptom entity feature information and the context feature information corresponding to the symptom entities from the medical text materials, richer symptom-related semantics is used as the basis for the recommended information. Compared with the prior art, the technical solution of the present application enriches the basis category of the recommended information, improves the utilization rate of information in the medical text materials, and thus makes the recommended information more accurate.

The application discloses a knowledge graph construction method and device of a promotion path, wherein the method comprises the following steps: step S1, combing core concepts related to the promotion path and semantic relations thereof, constructing a basic knowledge framework, and creating an ontology model based on the basic knowledge framework; step S2, setting mapping rules between ontology data and a graph database, and mapping the ontology model to the graph database; step S3, collecting multi-source information, performing knowledge extraction on the multi-source information to obtain knowledge triples and constructing entities, and constructing a knowledge graph by comprehensively combining the ontology model and the entities; and step S4, performing retrieval and correlation analysis based on the knowledge graph, forming promotion path instances, dynamically updating the promotion path instances to the knowledge graph, and obtaining a promotion path knowledge graph. The promotion path knowledge graph is obtained based on dynamic updating of the knowledge graph.

The application relates to an organization name recognition and abbreviation standardization method and equipment based on deep semantic understanding, which comprises the following steps: data cleaning and data labeling are performed on collected news text data; a double-module semantic network model suitable for organization name recognition and abbreviation standardization is constructed and trained; a standard organization name vector library is constructed; the news text data to be recognized is input into the trained model, semantic alignment is performed between the recognized organization abbreviation and the full name of the organization in the standard organization name vector library, and mixed similarity calculation is performed. Through the combination of a deep semantic coding network and a global pointer structure, high-precision recognition of organization names in news text is realized; the application reduces the dependence on artificial rules, can still maintain high recognition accuracy and stability in a complex text environment, improves overall retrieval efficiency and matching precision, and has good expansibility and practical application value.

The application discloses an assembly progress detection method and system based on few-shot vision and RAG. The core of the method is: through a large language model to analyze the assembly process procedure, automatically extract the process logic and part attribute to construct a lightweight knowledge graph; at the same time, extract the part diagram in the procedure, combine a small amount of real part samples to train the target detection model, and generate a part detection model. In the assembly process, the system tracks the part state in real time, when the key working condition state transition of the core component is detected, the dynamic graph RAG mechanism is triggered, the context semantics of the current process and the SOP guidance are retrieved, and they are fused with the real-time assembly picture, and input into the multimodal large language model for end-to-end process integrity and compliance reasoning. Finally, the reasoning result is mapped to the digital twin system to realize error-proofing warning and closed-loop control. The application realizes rapid changeover in high complexity assembly scene and intelligent monitoring with deep process understanding.

This invention relates to a method for fusion of heterogeneous knowledge in the power industry, comprising: obtaining first triples containing entity relations from the ontology layers of at least two knowledge graphs; classifying the entity relations in the first triples into synonym relations and inclusion relations according to relation aggregation prompts by a language model; merging entity relations belonging to synonym relations; obtaining second triples containing entity attributes or relation attributes from the ontology layers of at least two knowledge graphs; classifying the attributes in the second triples into synonym attributes and non-synonymous attributes according to attribute aggregation prompts by a language model; merging entity attributes or relation attributes belonging to synonym attributes; obtaining entities from the instance layers of at least two knowledge graphs and dividing them into several data blocks; determining whether there are duplicate entities according to entity alignment prompts by a language model; and merging duplicate entities.

This invention discloses an expert relearning reasoning question-answering method combined with a gating network. It uses a pre-trained language model for scoring and preprocessing to obtain the question context and reasoning graph. Finally, through an expert network, it deeply learns the semantic features of two representation forms and dynamically adjusts the contribution of the two representation forms to answer prediction using a gating network. Experimental results demonstrate that the proposed method is effective for question-answer prediction. By comprehensively considering the different contributions of the question text representation and the reasoned knowledge graph representation to answer prediction, the prediction accuracy can be improved. Experiments on public datasets also show good results, indicating that the method is not only applicable to fixed question-answer prediction but also has a certain generalization ability.

The application discloses a domain knowledge triple extraction method, system, medium and equipment, and relates to the technical field of knowledge engineering.The domain knowledge triple extraction method and system provided by the application can provide high-quality and efficient data support for triple extraction by analyzing and converting the obtained domain professional text into a structured vector knowledge base which can be efficiently searched, then the domain professional text is subjected to quantitative calculation and fusion screening, the initial entities of domain core high-frequency words which have global high frequency and cross-text universality are mined, the problem of "local optimum and global deviation" caused by traditional single word frequency is avoided, non-core term interference is effectively avoided, and the stability, relevance and efficiency of iterative extraction are improved, and further, the high-frequency word initial entities are subjected to closed-loop iteration through iterative RAG algorithm combined with the structured vector knowledge base, accurate extraction of the large model and iterative correlation entities, the explicit and implicit semantic correlation triples in the text can be mined layer by layer, the strong relevance and structural integrity of the extracted triples are ensured, and the professionalism and accuracy of the model in extracting triples are improved.

The application discloses a table information extraction method, device and equipment of a PDF format pipeline single-line diagram document and a medium, relates to the pipeline engineering field, and comprises the following steps: converting a PDF format pipeline single-line diagram document with an arbitrary layout into a target pipeline single-line diagram in an image format, cutting out region of interest images corresponding to a material table, a design parameter table and a project table from the target pipeline single-line diagram according to a template matching algorithm; removing irrelevant content, drawing auxiliary lines and extracting table information from the region of interest image corresponding to the material table to obtain material table data; identifying text blocks from the region of interest images corresponding to the design parameter table and the project table, determining the row and column attribution relationship and the entity mapping relationship between the semantic entities based on the semantic entities, semantic categories and position information of the text blocks, integrating the semantic entities to obtain design table data / project table data; and standardizing non-standardized table headers in the extracted table data and converting the non-standardized table headers into an excel table file.

Methods and systems are presented for providing a knowledge bot configurable to interact with users across multiple domains. The knowledge bot includes at least a text-based search engine and a semantic-based search engine. Each of the search engine is configured to retrieve documents from a corpus of documents based on the user query. The user query is in a natural language format. The retrieved documents may be ranked according to how relevant the documents are to the user query. A subset of the documents is used as the search results based on the ranking. The search results from the search engine are combined with the user query to generate a prompt for an artificial intelligence model. Based on the prompt, a response in the natural language format is generated by the artificial intelligence model.

Embodiments of the present application disclose an information extraction method and device, electronic equipment and storage medium. The method comprises: obtaining document information of a target document, and an entity classification model and an entity association model which have been trained; the entity classification model comprises a feature representation network and an entity classification network; inputting the document information into the feature representation network to obtain document features, and inputting the document features into the entity classification network to obtain an entity category of each document object in the target document; inputting key position features corresponding to key position entities and value position features corresponding to value position entities in the document features into the entity association model to obtain key-value pair relationships between each document object under the key position entities and each document object under the value position entities; and extracting at least two document objects with the key-value pair relationships as structured information from the target document, so as to effectively extract structured information from various documents.

The application provides a system and method for optimizing maintenance procedures using natural language interaction and structured knowledge representation. The system includes a natural language processing module, a knowledge graph, a database, a retrieval analysis module, and an interactive user interface. With the system, maintenance personnel do not need to manually search for various types of maintenance information, do not need to be very familiar with the content of the information, can use the context-aware maintenance guidance provided by the system to gradually narrow down the possible causes of the fault and ultimately lock the fault cause, and can perform processing according to the repair scheme provided by the system. Therefore, the system greatly reduces the experience requirements for maintenance personnel and the familiarization procedures for various types of information related to repair experience, saves the time of maintenance personnel for repeatedly searching various types of information, and improves the accuracy and work efficiency of the maintenance personnel for troubleshooting.

This application provides a material sourcing method and system. The method includes: crawling external data; constructing a supply chain knowledge graph based on the external data and internal enterprise data to obtain upstream and downstream relationships; acquiring user tracking data and constructing user behavior sequences based on the user tracking data; inputting the supply chain knowledge graph and user behavior sequences into a supply chain graph and user behavior fusion model for training; constructing and training a dual-tower model of materials and keywords based on historical retrieval data, converting all materials into material vectors; the dual-tower model includes a supply chain graph and user behavior fusion model and a keyword model; inputting keywords into the keyword model to obtain keyword vectors; calculating the similarity between the keyword vectors and all material vectors; and selecting at least one material with the highest similarity as the material sourcing result. This application enables rapid discovery of substitutes and new products in the material database, improving product price transparency and reducing procurement costs and related expenses.

The application provides a pre-training language model construction method, system and device, relates to the fields of artificial intelligence technology and semantic processing, and mainly comprises the following steps: based on a knowledge graph, a subgraph with a triple as a node unit is constructed; based on entity and relation description text, both are encoded through a conventional pre-training language model to obtain entity representation vectors and relation representation vectors; for the entity representation vectors and the relation representation vectors corresponding to the subgraph, modeling relation information is carried out based on a graph self-attention neural network, and the parameters of the graph neural network and the entity vectors are updated through a prediction link task; the parameters of the model are updated based on a contrast learning technology; and the parameters of the model are fine-tuned for a specific task. The scheme overcomes the problem that entity in the equipment field is sparse and a conventional pre-training language model cannot sufficiently learn entity semantics, and the updated pre-training language model has better understanding and reasoning capabilities in the application of the equipment field.

Various embodiments of the present disclosure provide hallucination mitigation techniques for text-to-code conversions that improves the functionality of a computer in various aspects. The techniques comprise receiving a text-based file that defines a set of standards for a prediction domain; generating, using a machine learning model, a decision tree based on (i) the text-based file and (ii) a decisioning prompt for the text-based file; generating, using the machine learning model, computer programmable code for the set of standards based on the decision tree and a code conversion prompt for the decision tree; and providing the computer programmable code to implement an automated task for the prediction domain.

The present application relates to the technical field of deep learning and knowledge graph, specifically to a cultural relic time sequence knowledge graph completion method based on dynamic message passing, which comprises the following steps: obtaining cultural relic time sequence knowledge graph information to be completed; constructing a cultural relic time sequence knowledge graph completion model based on a message passing graph neural network and dynamic convolution; and using the cultural relic time sequence knowledge graph completion model to complete the cultural relic time sequence knowledge graph. The cultural relic time sequence knowledge graph completion model effectively aggregates entity neighborhood information and semantic information at different time nodes by introducing a dynamic relationship representation and a time decay weight mechanism. The method fuses a comprehensive time encoding mechanism of multi-granularity time information, accurately captures global features of time information through periodic encoding and feature fusion, and effectively improves the expression of time information in time sequence knowledge graph completion. The dynamic convolution operation is used to construct deep interaction among entities, relationships and time, which can efficiently capture complex time dependency relationships among the three.

This application relates to the field of semantic analysis technology, specifically to a method and system for extracting audit anomaly semantics from unstructured data. The method includes: acquiring a benchmark graph and a benchmark database and their entity mentions; obtaining the strings of entity mentions based on their positions; acquiring an audit candidate set of strings from the benchmark database; determining a matching score based on the consistency of audit roles, and then filtering the candidate entity set; encoding the candidate entities, their audit role sets, entity mentions, and strings to obtain the probability distribution of entity mentions and candidate entities, and determining the audit role consistency score based on the probability distribution; classifying the association between entity mentions and candidate entities based on the overall magnitude of the audit role consistency score, and applying different audit rules to each category; and extracting audit anomaly semantics using the audit rules. This application improves the accuracy and efficiency of semantic extraction.

The application provides an industrial operation and inspection large model system and method and electronic equipment, relates to the technical field of industrial operation and inspection, and comprises an intention recognition submodel: identifying an operation and inspection question based on an operation and inspection inquiry sentence, and determining whether the operation and inspection question exists in a question and answer library; a first interaction submodel: used for the operation and inspection question existing in the question and answer library, and outputting an operation and inspection question answer; and a second interaction submodel: used for the operation and inspection question not existing in the question and answer library, searching in a knowledge graph based on the operation and inspection question, and outputting an operation and inspection question answer. Through the above manner, the operation and inspection question of a user can be efficiently and accurately answered, and the accuracy and objectivity of the conversation of the model are improved.