Intelligent sorting method for retrieval results

Abstract

The invention provides an intelligent sorting method for retrieval results, belongs to the technical field of information processing, and realizes intelligent sorting of the retrieval results through the steps of text standardization processing, importance calculation, result sorting and the like on the retrieval results, thereby improving the efficiency and accuracy of information retrieval.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a search result intelligent sorting method. Background Art

[0002] With the rapid development of the Internet, the amount of information people can access is growing exponentially. In the era of information explosion, search engines have become the main tool for people to obtain information.

[0003] When users search for information through search engines or other search tools, they often get thousands of relevant results. However, not all results are useful to users; on the contrary, a large amount of irrelevant or low-quality content will seriously interfere with the user experience. Therefore, how to quickly filter out the content that best meets user needs from massive data has become an urgent problem to be solved.

[0004] Traditional sorting methods are often based on factors such as keyword matching and web page weight, but this method ignores key information such as users' specific needs and historical search records, resulting in unsatisfactory sorting results.

[0005] Some existing search result ranking algorithms are usually based on traditional factors such as keyword matching and page link analysis. Although they can improve user experience to a certain extent, they still have many shortcomings, such as the inability to accurately capture the user's actual intentions and the lack of personalized recommendation mechanisms. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a method for intelligent sorting of retrieval results, aiming to improve the efficiency and accuracy of information retrieval and provide users with result sorting that better meets their needs.

[0007] The technical solution of the present invention is:

[0008] A search result intelligent sorting method, characterized in that:

[0009] Intelligent sorting of search results is achieved by performing text standardization, text importance calculation, text sorting, and result output steps on the search results.

[0010] The main feature is that it combines semantic understanding and user behavior analysis to optimize the display order of search results.

[0011] Furthermore,

[0012] Text normalization, including:

[0013] Standardize the search text and result text to ensure that all text data are in a unified format.

[0014] Going further,

[0015] This includes removing all invisible characters such as spaces, tabs, and line breaks from the text, as well as converting the text to half-width.

[0016] Furthermore,

[0017] Text importance calculation, including:

[0018] ① Segment the search text to obtain several search keywords, save the search keyword results, and calculate the proportion of each search keyword in all search keywords in the user's history. key ;

[0019] ② Perform word segmentation on the text of the search results to obtain the result text keywords, and calculate the length of the text before word segmentation L and the length of each result keyword after word segmentation L respectively. key And the frequency N of occurrence in the current text;

[0020] ③ Calculate the proportion of each result keyword in the result text R key =L key *N / L;

[0021] ④ For the keywords that are common in the search keywords and the result keywords, combined with the proportion of the user's current search keywords in the historical search keywords P key , get the importance of each common keyword, that is, I key =P xey *R key .

[0022] Sum the importance of each common keyword to get the total importance of each search result under the current search keyword. all_key =∑I key .

[0023] Furthermore,

[0024] Text sorting, including:

[0025] The importance I calculated based on each search result all_key Sort the search results in descending order.

[0026] Furthermore,

[0027] Result output:

[0028] Highlight the keywords that appear in the search results and mark the corresponding keywords with the user's proportion of all historical search keywords. key , combined with the sorting results, and displayed to the user.

[0029] The beneficial effects of the present invention are

[0030] The intelligent sorting method and system of search results of the present invention realizes intelligent sorting of search results by performing text standardization processing, importance calculation, result sorting and other steps on the search results. The method not only improves the efficiency and accuracy of information retrieval, but also provides users with a result sorting that better meets their needs, greatly improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the workflow of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0033] The present invention provides a method for intelligently sorting a large number of search results, which combines semantic understanding and user behavior analysis to optimize the display order of search results. The method realizes intelligent sorting of search results by performing text standardization processing, importance calculation, result sorting and other steps on the search results, thereby improving the efficiency and accuracy of information retrieval.

[0034] include:

[0035] (1) Text standardization:

[0036] Standardize the search text and result text, including removing all invisible characters such as spaces, tabs, line breaks, etc. in the text and converting the text to half-width, to ensure that all text data is in a unified mode.

[0037] (2) Importance calculation:

[0038] ① Segment the search text to obtain multiple search keywords, save the search keyword results, and calculate the proportion of each search keyword in all search keywords in the user's history. key

[0039] ② Perform word segmentation on the text of the search results to obtain the result text keywords, and calculate the length of the text before word segmentation L and the length of each result keyword after word segmentation L respectively. key And the frequency N of occurrence in the current text;

[0040] ③ Calculate the proportion of each result keyword in the result text R key =Lkey *N / L;

[0041] ④ For the keywords that are common in the search keywords and the result keywords, combined with the proportion of the user's current search keywords in the historical search keywords P key , get the importance of each common keyword, that is, I key =P key *R key

[0042] ⑤ Sum the importance of each common keyword to obtain the total importance of each search result under the current search keyword I all_key =∑I key ;

[0043] (3) Result sorting:

[0044] The importance I calculated based on each search result all_key Sort the search results in descending order.

[0045] (4) Result output:

[0046] Highlight the keywords that appear in the search results and mark the corresponding keywords with the user's proportion of all historical search keywords. key , combined with the sorting results, and displayed to the user.

[0047] The above description is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, and is not used to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for intelligently sorting search results, characterized in that: Intelligent sorting of search results is achieved by performing text standardization, text importance calculation, text sorting, and result output steps on the search results.

2. The method according to claim 1, characterized in that Combine semantic understanding and user behavior analysis to optimize the display order of search results.

3. The method according to claim 1, characterized in that: Text normalization, including: Standardize the search text and result text to ensure that all text data are in a unified format.

4. The method according to claim 3, characterized in that This includes removing all invisible characters such as spaces, tabs, and line breaks from the text, as well as converting the text to half-width.

5. The method according to claim 3 or 4, characterized in that: Text importance calculation, including: ① Segment the search text to obtain several search keywords, save the search keyword results, and calculate the proportion of each search keyword in all search keywords in the user's history. key ; ② Perform word segmentation on the text of the search results to obtain the result text keywords, and calculate the length of the text before word segmentation L and the length of each result keyword after word segmentation L respectively. key And the frequency N of occurrence in the current text; ③ Calculate the proportion of each result keyword in the result text R key =L key *N / L; ④ For the keywords that are common in the search keywords and the result keywords, combined with the proportion of the user's current search keywords in the historical search keywords P key , get the importance of each common keyword, that is, I key =P key *R key .

6. The method according to claim 5, characterized in that Sum the importance of each common keyword to get the total importance of each search result under the current search keyword. all_key =∑I key .

7. The method according to claim 6, characterized in that Text sorting, including: The importance I calculated based on each search result all_key Sort the search results in descending order.

8. The method according to claim 7, characterized in that Result output: Highlight the keywords that appear in the search results and mark the corresponding keywords with the user's proportion of all historical search keywords. key , combined with the sorting results, and displayed to the user.

Images