An intelligent analysis method and system for standardizing home appliance service order information, an electronic device, and a storage medium
By identifying and optimizing entities in users' natural language orders, and combining the BERT model and rule engine, structured service prompt labels are generated, solving the problem that intelligent customer service systems cannot understand natural language orders, and improving the automation and user experience of the service platform.
CN122287607APending Publication Date: 2026-06-26BEIJING SHANSHAN INTERNET FUTURE TECHNOLOGY CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING SHANSHAN INTERNET FUTURE TECHNOLOGY CO LTD
- Filing Date
- 2026-04-01
- Publication Date
- 2026-06-26
AI Technical Summary
Technical Problem
Existing intelligent customer service systems are unable to effectively understand and parse users' natural language orders, resulting in incomplete and inaccurate order information, which limits the automation level of the service platform and the user experience.
Method used
By identifying target basic entities, confidence entities, reliability entities, and conflict handling, and combining the BERT model and rule engine, user needs are identified and optimized to generate structured service prompt labels.
Benefits of technology
It enables a deep understanding of users' complex intentions, ensures that no key service elements are missed, and improves the operational efficiency and user satisfaction of the skills service platform.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122287607A_ABST
Abstract
This invention discloses a standardized intelligent parsing method for home appliance service order information, comprising: determining target basic entities and confidence entities based on the matching degree and existence confidence of each preset basic entity in the order text; determining the corresponding target characteristic entities based on the confidence entities; determining reliability entities based on the matching degree, existence confidence, and preset reliability threshold; determining the conflict degree based on the cosine similarity between any two valid entities; determining the corrected score of valid entities based on the basic score and conflict degree of valid entities; using valid entities that meet the conditions as the decision result and outputting conflict warning and conflict handling information; and generating service prompt tags based on preset tag templates. This invention can convert unstructured natural language orders into standard service prompt tags, allowing service engineers to intuitively obtain user requests and precautions. This invention also discloses a system, electronic device, and storage medium for implementing the above method.
Need to check novelty before this filing date? Find Prior Art