Lexical item weight labeling method and device
A term and weight technology, applied in the field of network search, can solve problems such as unsatisfactory results, and achieve the effect of improving the quality of search sorting, improving results, and improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] refer to figure 1 , which shows a flow chart of the steps of an embodiment of a weight labeling method for terms of the present application, which may specifically include the following steps:
[0049] Step 110, acquiring each term whose weight is to be determined.
[0050] In the embodiment of the present invention, word segmentation is performed on all user search terms in the search log, and then the obtained word segmentation results are used as terms to be weighted. For example, in the search log, there is a search term of "good-looking movie", and the word segmentation results are three terms of "good-looking", "of", and "movie".
[0051] Certainly, the term items whose weights are to be determined can be generated in various ways, for example, word segmentation is performed on the document to be searched, and then the term items are extracted. The object to be searched for example describes a video page on a video website, a product page on an e-commerce platfo...
Embodiment 2
[0067] refer to figure 2 , which shows a flow chart of the steps of an embodiment of a weight labeling method for terms of the present application, which may specifically include the following steps:
[0068] Step 210, acquiring each term whose weight is to be determined.
[0069] This step is the same as step 110 in the first embodiment, and will not be described in detail here.
[0070] Step 220, extracting the term feature of each term; the term feature includes a term search feature, and the term search feature is acquired through the search log.
[0071] In the embodiment of the present invention, for each term, its feature of the term may be extracted in combination. Wherein, the term search feature in the term feature can be extracted through the search log. Of course, features can also be extracted for the term itself.
[0072] For search logs, take a video website as an example. The user logs in to the webpage of the video website in the client, and then the user...
Embodiment 3
[0110] refer to image 3 , which shows a flow chart of the steps of an embodiment of a weight labeling method for terms of the present application, which may specifically include the following steps:
[0111] Step 310, acquiring a term training set; the term training set includes terms and the term search weights corresponding to the terms.
[0112] The word segmentation is performed on the document collection, and the result after word segmentation is a term set, and a certain number of terms in the term set are extracted as a data set, and the certain number can be greater than 100. Then manually label each term in this data set, mark the search term weight of this term, and use the marked data set as a training set to train the term search weight labeling model. In practical applications, the term items in the training set can be obtained from the document collection to be searched, search logs and other materials that can provide the search task, which is not limited in t...
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