Article alias mining method and system, electronic equipment and readable storage medium
A technology for items and aliases, applied in the field of information processing, can solve problems such as difficulty in accurately locating target items
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0102] A method of item alias mining based on user comments, such as figure 1 As shown, the item alias mining method includes:
[0103] Step 10, reverse association and acquisition of all retrieval keywords of the accessed items within a preset time period;
[0104] Step 20, obtaining the retrieval volume of each retrieval keyword within a preset time period;
[0105] Step 30, judging whether the retrieval amount of each retrieval keyword is greater than a preset threshold, if so, then execute step 40; if not, it means that the retrieval keyword cannot be used as a candidate word for the item;
[0106] Step 40, using search keywords greater than a preset threshold as candidate words;
[0107] Step 50, obtaining the comment data of the item;
[0108] Step 60, for each candidate word, obtain the degree of relevance between the candidate word and the item according to the comment data;
[0109] Step 70, determine whether the degree of association is greater than a preset thre...
Embodiment 2
[0128] The item alias mining method based on user comments in this embodiment is further improved on the basis of Example 1. It is not difficult to understand that if a candidate word appears in a high proportion in the comments of the corresponding model, the words that appear in other comments The proportion is very low, and this candidate word is more likely to refer to this item. Therefore, if Figure 5 As shown, before step 60, the item alias mining method also includes:
[0129] Step 51, obtaining the first search volume of the candidate word within a preset time period;
[0130] Correspondingly, such as Figure 6 As shown, step 64 is replaced with step 64-1 in step 60, specifically including:
[0131] Step 64-1. Obtain the degree of relevance according to the proportion and the first search volume.
[0132] For example, the following formula can be used to calculate the correlation degree:
[0133]
[0134] Among them, a is the total number of comments, b is the ...
Embodiment 3
[0136]The item alias mining method based on user comments in this embodiment is further improved on the basis of Example 1. If the candidate word itself is a rare word but appears a lot in the comments of the item, this word is likely to refer to Substitute this item, such as Figure 7 As shown, before step 60, the item alias mining method also includes:
[0137] Step 52, obtaining the standard name of the item;
[0138] Step 53, obtaining the second search volume of the standard name within a preset time period;
[0139] Correspondingly, such as Figure 8 As shown, step 64 is replaced with step 64-2 in step 60, specifically including:
[0140] Step 64-2, obtain the degree of association according to the proportion, the first search volume and the second search volume.
[0141] For example, the following formula can be used to calculate the correlation degree:
[0142]
[0143] Among them, d is the second search amount;
[0144] In this example, if Figure 9 As shown...
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