Keyword recommendation method and device
A recommendation method and keyword technology, applied in the Internet field, can solve the problems of limited information coverage, inaccurate recommendation results, and inability to meet user needs, and achieve the effect of large search range and improved accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0073] Reference figure 1 , Shows a flowchart of the steps of a keyword recommendation method according to the first embodiment of the present invention.
[0074] The keyword recommendation method of this embodiment may include the following steps:
[0075] Step 101: Receive query information and divide the query information into at least one query keyword.
[0076] The keyword recommendation method of this embodiment can be applied to a search engine, where the search engine can be any applicable search engine, such as an independent search engine, a search engine embedded in an application, etc., such as Baidu search and Google search. , 360 search, Sogou search, etc. When a user needs to search for information in a search engine, first enter the query information that needs to be queried. After the search engine receives the query information, it does not directly make recommendations based on the query information, but further divides the query information into at least one quer...
Embodiment 2
[0086] Reference figure 2 , Shows a flowchart of the steps of a keyword recommendation method in the second embodiment of the present invention.
[0087] The keyword recommendation method of this embodiment may include the following steps:
[0088] Step 201: Obtain historical search items for which an association relationship needs to be created, and for each obtained historical search item, respectively determine historical search items associated with the current historical search item.
[0089] The search engine saves the relevant information of each historical search item. Among them, the historical search items may be related. Therefore, you can first obtain the historical search items that need to create an association relationship, and then determine the obtained historical search items separately The historical search item associated with the current historical search item is determined and the association relationship of the current historical search item is created.
[0090...
Embodiment 3
[0155] Reference Image 6 , Shows a structural block diagram of a keyword recommendation device according to the third embodiment of the present invention.
[0156] The keyword recommendation device of this embodiment may include the following modules:
[0157] The dividing module 601 is configured to receive query information and divide the query information into at least one query keyword;
[0158] The search module 602 is used to find historical search items including query keywords as matching historical search entries, and obtain historical search entries associated with the matching historical search entries as associated historical search entries; wherein, matching historical search entries and associated historical search entries All include at least one keyword;
[0159] The selection module 603 is configured to select keywords whose relevance to the query keyword meets the set relevance condition from the matching history search items and the associated history search items ...
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