Question sentence template automatic generation method and apparatus
An automatic generation and question sentence technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve the problem of poor maintainability and self-learning, not involving automatic template generation Coverage and other issues to increase generalization ability, ensure completeness, and achieve the effect of answer matching
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0061] figure 1 It is a flow chart of the method for automatically generating question sentence templates provided by the embodiment of the present invention. Such as figure 1 As shown, the question template automatic generation method that the embodiment of the present invention provides, comprises the following steps:
[0062] 101. Prepare question log corpus.
[0063] Specifically, the question log corpus is obtained, and the question log corpus is preprocessed, including but not limited to punctuation removal, illegal symbol removal, word case conversion, and the like.
[0064] 102. Perform word segmentation and part-of-speech tagging on the log corpus.
[0065] Specifically, the log corpus is segmented in combination with the word segmentation method of the industry dictionary. According to different needs or industries, different types of industry dictionaries can be created. Especially when it comes to specific vertical industries, using the word segmentation method...
Embodiment 2
[0074] figure 2 It is a flow chart of the method for automatically generating question sentence templates provided by Embodiment 2 of the present invention. Such as figure 2 As shown, the question template automatic generation method that the embodiment of the present invention provides, comprises the following steps:
[0075] 201. Obtain question log corpus, and perform preprocessing on the question log corpus, including but not limited to removing punctuation marks, removing illegal symbols, and converting word case.
[0076] It should be noted that the acquisition method of the question log corpus here can adopt any possible acquisition method in the prior art, which is not particularly limited in the embodiment of the present invention; the process or method of realizing the preprocessing of the log corpus is not limited to the above content, either. Any possible technical means or manners in the prior art may be adopted, which will not be described here one by one.
...
Embodiment 3
[0105] image 3 It is a structural schematic diagram of the device for automatically generating question templates provided by Embodiment 3 of the present invention. Such as image 3 As shown, the question template automatic generating device that the embodiment of the present invention provides, comprises:
[0106] Preparation module 1 is used to prepare question log corpus. Specifically, the preparation module 1 includes an acquisition module and a preprocessing module, the acquisition module is used to obtain the question log corpus, and the preprocessing module is used to preprocess the question log corpus, including label symbol removal, illegal symbol removal , Word case conversion.
[0107] Word segmentation and part-of-speech tagging module 2, used for word segmentation and part-of-speech tagging. Specifically, according to different needs or industries, different types of industry dictionaries can be created, especially when it comes to specific vertical industrie...
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