Scenarized merchant recall method and device, electronic equipment and readable storage medium
A business and scene technology, applied in business, electrical digital data processing, instruments, etc., to improve adaptability, reduce time and labor costs, and take into account precision and recall.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0028] A scene-based merchant recall method provided by the embodiment of the present invention is introduced in detail.
[0029] refer to figure 1 , shows a flow chart of the steps of a scenario-based merchant recall method in an embodiment of the present invention.
[0030] Step 110, acquire a given scene word, and expand the given scene word into a keyword set including N words, where N is a natural number.
[0031] In practical applications, if merchants are recalled directly based on given scene words, the recall rate is low. Therefore, in the embodiment of the present invention, in order to improve the recall rate, after the given scene words are acquired, the given scene words may be expanded into a keyword set including N words. Wherein, N is a natural number. Generally speaking, a given scene word for the same scene may specifically include at least one word, and the specific value of N may be preset according to requirements, which is not limited in this embodimen...
Embodiment 2
[0064] A scene-based merchant recall method provided by the embodiment of the present invention is introduced in detail.
[0065] refer to figure 2 , shows a flow chart of the steps of a scenario-based merchant recall method in an embodiment of the present invention.
[0066] Step 210, train the LDA model through the pre-selected high-quality merchant reviews and generate a word-topic matrix.
[0067] In order to be able to generate high-precision and high-recall results, it is first necessary to describe the given scene from all directions, and it is necessary to expand the given scene words into a set of keywords with relevance weights, so we chose to consider the global context and divergence Stronger LDA (Latent Dirichlet Allocation) model. The LDA model is a document topic generation model, also known as a three-layer Bayesian probability model, which includes a three-layer structure of words, topics, and documents. Then, the corresponding word-topic matrix can be gen...
Embodiment 3
[0170] A scene-based merchant recall device provided by an embodiment of the present invention is introduced in detail.
[0171] refer to image 3 , shows a schematic structural diagram of a scenario-based merchant recall device in an embodiment of the present invention.
[0172] Keyword set expansion module 310, is used for obtaining given scene word, and described given scene word is expanded into the keyword set that comprises N words, and N is a natural number;
[0173]An initial seed merchant determining module 320, configured to determine an initial seed merchant from platform merchants based on each keyword in the keyword set;
[0174] A high-precision seed merchant determination module 330, configured to filter the initial seed merchants according to the set of keywords to obtain high-precision seed merchants;
[0175] The final recall merchant confirmation module 340 is configured to determine the final recall merchant of the given scene word according to the high-p...
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