6 results about "Entity–relationship model" patented technology

The present invention discloses a method and device for entity-relationship joint extraction based on a lightweight self-attention mechanism. The method comprises obtaining target sentence data and inputting the target sentence data into an entity classification model; classifying all subsequences of the target sentence data using the entity classification model to obtain entity sequences and non-entity sequences; obtaining any pair of entity pairs in the entity sequence and inputting the entity pairs and the word combinations between the entity pairs into a relationship classification model; and generating entity-relationship joint classification results using the entity-relationship joint extraction model; wherein the entity-relationship joint extraction model includes a Bert encoder, an entity classification model, and a relationship classification model. The present invention has low complexity, can improve the performance of entity-relationship models, and can be widely applied in the field of artificial intelligence technology.

The invention provides a three-phase asynchronous motor database construction method and system, and the method comprises the steps: obtaining the source data of a three-phase asynchronous motor, and the source data comprises the common parameters, geometric dimensions and performance parameters of the motor; analyzing a data dependency relationship among the common parameters, the geometric dimensions and the performance parameters to determine a determination condition of each data set; creating a plurality of correlative data tables based on the data dependency relationship, wherein the data tables comprise a geometric dimension table group for storing geometric dimensions of the motor and a performance parameter table for storing performance parameters of the motor; and constructing an entity-relationship model of the database based on the association relationship among the plurality of data tables, and generating an SQL statement for data query. According to the technical scheme provided by the invention, structured and standardized storage of the motor data is realized, data redundancy is remarkably reduced, data reusability and query efficiency are improved, and industrial digital application is effectively supported.

The application discloses a multi-level emergency command intelligent decision-making method and system based on a knowledge graph. The method comprises the following steps: S1, extracting the exclusive features of text modalities, visual modalities and space-time modalities from multi-source heterogeneous data in the whole scene of multi-level emergency command; S2, constructing a cross-modal attention fusion network to output multi-modal fusion features; S3, constructing a multi-modal joint entity relationship Transformer model, taking the multi-modal fusion features as input, and outputting standardized entity-relation triplets; S4, based on the entity-relation triplets, constructing a three-level hierarchical knowledge graph; S5, generating an emergency decision-making scheme by using a three-layer reasoning framework, and outputting the decision-making comprehensive confidence of the scheme; and S6, according to a preset emergency response level, combining the decision-making comprehensive confidence, and executing corresponding human-machine collaborative rules. In this way, intelligent sensing, accurate judgment, collaborative decision-making, efficient disposal and closed-loop optimization of the whole life cycle of an emergency event are realized.

The invention relates to the technical field of data processing, and discloses a data accounting method and device, equipment and a medium, and the method comprises the steps: obtaining to-be-accounting business list data, and carrying out the standardization processing of the business list data based on an entity relation model, and obtaining a list data set; the list data set comprises an insurance type element, an account set type element and an accounting element; constructing a screening rule tree based on the list data set, executing database retrieval operation in a head node of the screening rule tree, and screening to obtain a target data subset; grouping each node in the target data subset through a graph neural network model to obtain an accreditation data group corresponding to each preset accounting criterion; and mapping accreditation data groups corresponding to the preset accounting criteria into a preset list to be accreditated, and generating an accounting data set corresponding to the business list data. The method can be applied to financial science and technology or medical care service program systems, and the accuracy and efficiency of data accounting can be improved.

This application provides a method and apparatus for generating a knowledge graph for cross-layer data processing activities. The method includes: defining entities and relationships corresponding to the business logic layer, data operation layer, and technical implementation layer, as well as cross-layer relationships between entities in adjacent layers; generating an entity-relationship model based on entities, relationships, and cross-layer relationships; extracting entity data from the data processing activity documents corresponding to the business logic layer, data operation layer, and technical implementation layer to obtain entity-relationship data; and generating a knowledge graph based on the entity-relationship model and entity-relationship data. This application achieves full-link association analysis through three-layer cross-layer entity modeling, forming a structured, traceable, high-quality knowledge graph. This provides accurate reference and data support for risk analysis of data processing behavior, helping to quickly identify abnormal operations and potential risks.

The invention discloses a video polyphonic ringtone recommendation method and system based on an LLM and a knowledge graph, and the method comprises the steps: processing historical polyphonic ringtone service data based on an LLM algorithm, and obtaining the service data corresponding to a plurality of polyphonic ringtone categories; based on a knowledge graph algorithm, establishing a three-layer knowledge graph model according to the business data; the three-layer knowledge graph model comprises an entity relation model, a semantic paragraph relation model and a document relation model; according to an input text of a to-be-recommended user, based on the three-layer knowledge graph model, determining a recommendation demand of the to-be-recommended user; and screening out a plurality of recommended video polyphonic ringtones corresponding to the to-be-recommended user from a candidate polyphonic ringtone database according to the recommendation demand. Therefore, more accurate and reasonable video polyphonic ringtone recommendation can be performed according to the user characteristics, the satisfaction degree of the user to the recommendation result is improved, and the efficiency and response accuracy of the video polyphonic ringtone customer service are improved.