Automobile repair knowledge entity network construction method, device and equipment
A technology of network construction and entity structure, applied in semantic tool creation, unstructured text data retrieval, etc., can solve the problems of scarcity of maintenance personnel, high threshold of auto repair industry, and high cost of auto repair
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0102] The following introduces Embodiment 1 of a method for constructing an auto repair knowledge entity network provided by the present application, see figure 1 , embodiment one includes:
[0103] Step S101: Obtain structured auto repair data.
[0104] It should be noted that this embodiment takes structured auto repair data as input and extracts auto repair knowledge from it, but in actual scenarios, the input may be auto repair texts, such as massive auto repair manuals or auto repair web pages. In this case, structured auto repair text can be obtained by performing preprocessing operations such as word segmentation and filtering stop words on the text. Therefore, obtaining the structured auto repair data in this embodiment is only an implementation manner, which is not limited in this application.
[0105] Step S102: Perform entity recognition on the structured auto repair data, and determine a plurality of auto repair entities in the structured auto repair data.
[0...
Embodiment 2
[0113] like image 3 As shown, the second embodiment of a method for constructing an auto repair knowledge entity network provided by this application specifically includes:
[0114] Step S201: Obtain structured auto repair data, classify it, and mark the structured auto repair data according to the classification result.
[0115] In fact, step S201 can be used as a preprocessing step, specifically including: pre-dividing the structured auto repair data into the following four types according to the data content type: conceptual type, inspection type, maintenance type, and disassembly type, and according to the structured The data content type of auto repair data, adding type marks for structured auto repair data.
[0116] The purpose of classifying structured auto repair data based on data content type is to improve the efficiency of subsequent extraction of auto repair knowledge. The principle is that structured auto repair data with different data contents contain differen...
Embodiment 3
[0129] Specifically, embodiment three includes:
[0130] Step S301: Obtain structured auto repair data.
[0131] Step S302: Determine the type of the data content. If it is a conceptual type, go to step S303. If it is an inspection type, go to step S304. If it is a maintenance type, go to step S305. If it is a disassembly type, go to step S306. What needs to be explained here is that the following four steps are different. Therefore, the same parameter may have different meanings in different steps. For details, please refer to the explanation of the meaning of the parameter in its own step.
[0132] Step S303: Carry out entity recognition for auto repair parts nouns and auto repair phenomenon nouns, and obtain a sequence {x 1 ,x 2 ,...,x m}. And extract the relationship entity pairs of each auto repair entity to obtain a sequence including multiple relationship entity pairs The relationship entity pair reflects the following information: the relationship between auto re...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com