Search

CN-121981663-A - Business processing method, device, equipment and medium based on large model

CN121981663ACN 121981663 ACN121981663 ACN 121981663ACN-121981663-A

Abstract

The application relates to a business processing method, a business processing device, business processing equipment and a storage medium based on a large model. Analyzing input content of a user through a large model to obtain intention information and entity information of the input content, inquiring a knowledge graph based on the intention information and the entity information, determining a matching result with the input content and current information of the user, generating a processing flow list and pre-filling information by utilizing a service engine according to the matching result and the current information of the user, and generating guide information according to the processing flow list and the pre-filling information to feed back to the user. Through accurate analysis of user input of the large model, accuracy of intention recognition and entity extraction is improved, foundation is laid for personalized business processing, dynamic association and real-time updating of policy information are achieved through query knowledge graphs, business guiding accuracy and timeliness are guaranteed, a business engine automatically generates a flow list and prefilled information, repeated input and manual query of a user are reduced, and business handling efficiency is improved.

Inventors

  • HE AO
  • YIN RONGRONG

Assignees

  • 香港城市大学(东莞)

Dates

Publication Date
20260505
Application Date
20251208

Claims (10)

  1. 1. A business processing method based on a large model, the method comprising: Analyzing the input content of a user through a large model to obtain intention information and entity information of the input content; Inquiring a knowledge graph based on the intention information and the entity information, and determining a matching result with the input content and current information of a user; generating a processing flow list and pre-filling information by using a service engine according to the matching result and the current information of the user; and generating guide information to be fed back to the user according to the processing flow list and the pre-filling information.
  2. 2. The business processing method based on big model as claimed in claim 1, wherein analyzing the input content of the user through the big model to obtain the intention information and the entity information of the input content comprises: If the input content comprises voice information, converting the voice information into text information; Preprocessing the text information to obtain a preprocessed text; Carrying out semantic analysis on the preprocessed text by using an intention classification module of the large model to obtain intention information of the input content; and carrying out entity analysis on the preprocessed text by using a named entity recognition module of the large model to obtain entity information of the input content.
  3. 3. The business processing method based on the big model as claimed in claim 1, wherein the determining the matching result with the input content and the user current information based on the intention information and the entity information query knowledge-graph comprises: generating standardized query parameters based on the intention information and the entity information; performing multi-level matching query operation in a service knowledge graph based on the query parameters, obtaining policy rule nodes related to the query parameters, and outputting a policy matching list based on the policy rule nodes; Invoking a user data interface to acquire current information of a user based on the user entity information in the query parameters; and screening out policy items conforming to the current state of the user from the policy matching list based on the current information of the user as the matching result.
  4. 4. The business processing method of claim 3, wherein said performing a multi-level matching query operation in a business knowledge graph based on said query parameters to obtain policy rule nodes related to the query parameters comprises: splitting the query parameters into intention dimension parameters and constraint dimension parameters; Based on the intention dimension parameters, matching is carried out in policy classification nodes of the business knowledge graph, and primarily matched policy classification nodes are output; And based on the constraint dimension parameters, matching is carried out in the nodes subordinate to the preliminarily matched policy class nodes, and the policy rule nodes related to the query parameters are obtained.
  5. 5. The business processing method based on big model as claimed in claim 1, wherein said generating a process flow list and pre-filled information by using a business engine based on said matching result and said user current information comprises: extracting structural description information representing application conditions and material requirements from the matching result; determining satisfied conditions and missing information of a user according to the current information of the user; Generating a processing flow information list according to the structural description information, the satisfied conditions and the missing information; and extracting data fields for automatic filling as the pre-filling information based on the processing flow list and the current information of the user.
  6. 6. The business processing method based on big model as claimed in claim 1, wherein before generating the guiding information to be fed back to the user according to the process flow list and the pre-filling information, the method further comprises: and checking the processing flow list and the prefill information based on the current information of the user.
  7. 7. The business processing method based on big model as claimed in claim 1, wherein the method further comprises: and uploading the user current information, the processing flow list, the pre-filling information and the guide information to a blockchain.
  8. 8. A business processing apparatus based on a large model, the apparatus comprising: The analysis module is used for analyzing the input content of the user through the large model to obtain intention information and entity information of the input content; the query module is used for querying a knowledge graph based on the intention information and the entity information, and determining a matching result with the input content and current information of a user; the first generation module is used for generating a processing flow list and prefill information by utilizing a service engine according to the matching result and the current information of the user; and the second generation module is used for generating guide information according to the processing flow list and the pre-filling information and feeding the guide information back to the user.
  9. 9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; A processor for implementing the business processing method based on big model as claimed in any one of claims 1 to 7 when executing the program stored on the memory.
  10. 10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the business processing method based on big model of any of claims 1 to 7.

Description

Business processing method, device, equipment and medium based on large model Technical Field The present application relates to the field of large models, and in particular, to a business processing method, apparatus, device and storage medium based on a large model. Background At present, most of the existing college digital systems are information islands, such as data splitting among educational administration, finance and academic systems, and teachers and students need to repeatedly submit information when transacting cross-department business, so that the operation is complex and errors are prone to occur. In addition, the natural language understanding capability of the system is insufficient, the extraction accuracy of application such as intelligent customer service and the like to the consultation intention of teachers and students and entity information is low, and most consultations still need manual intervention for answering, so that efficient automatic response cannot be realized. For example, when teachers and students consult with the prize application business, the system cannot accurately identify the specific intention of the application material consultation or the process consultation, and also cannot accurately grasp key entity information such as the prize name, and thus the business handling efficiency is low. Therefore, how to improve the business handling efficiency has become a technical problem to be solved by those skilled in the art. Disclosure of Invention In view of the foregoing, the present application provides a business processing method, device, equipment and storage medium based on a large model, and aims to solve the above technical problems. In a first aspect, the present application provides a business processing method based on a large model, the method comprising: Analyzing the input content of a user through a large model to obtain intention information and entity information of the input content; Inquiring a knowledge graph based on the intention information and the entity information, and determining a matching result with the input content and current information of a user; generating a processing flow list and pre-filling information by using a service engine according to the matching result and the current information of the user; and generating guide information to be fed back to the user according to the processing flow list and the pre-filling information. In a second aspect, the present application provides a business processing device based on a large model, the business processing device based on the large model comprising: The analysis module is used for analyzing the input content of the user through the large model to obtain intention information and entity information of the input content; the query module is used for querying a knowledge graph based on the intention information and the entity information, and determining a matching result with the input content and current information of a user; the first generation module is used for generating a processing flow list and prefill information by utilizing a service engine according to the matching result and the current information of the user; and the second generation module is used for generating guide information according to the processing flow list and the pre-filling information and feeding the guide information back to the user. In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; a memory for storing a computer program; and the processor is used for realizing the steps of the business processing method based on the large model according to any one of the embodiments of the first aspect when executing the program stored in the memory. In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, implements the steps of the business processing method based on large models according to any of the embodiments of the first aspect. Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: According to the application, the input content of the user is analyzed through the large model, the intention information and the entity information of the input content are obtained, the knowledge graph is queried based on the intention information and the entity information, the matching result with the input content and the current information of the user are determined, the processing flow list and the pre-filling information are generated by utilizing the service engine according to the matching result and the current information of the user, and the guiding information is generated according to the processing flow