A stock screening and star rating method and system based on a quantization model

Abstract

The present invention provides a stock screening and star rating method and system based on a quantitative model, which belongs to the field of data processing technology, and specifically includes: determining potential search targets in stocks based on the user's search keywords and the search keywords with associated search times, obtaining the search keywords of historical users at different potential search targets, and the similarity between the search keywords of the user and the search keywords with associated search times, determining the user's historical reference users by using the similarity, and determining the star rating results of different stocks and the user's matching search targets by using a quantitative model according to the matching between different stocks and the search keywords of the historical reference users, thereby improving the matching accuracy of the search results.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to a stock screening and star rating method and system based on a quantitative model. Background Art

[0002] To implement stock screening, the invention patent application CN202310750041.1, "A Stock Screening Method and System," obtains stock information to be retrieved, converts the stock information into a digital vector, and obtains a first semantic vector. The matching between the first semantic vector and the stock information is used to determine a total score, allowing users to select target stocks based on the total score. However, this method has the following technical drawbacks:

[0003] In the process of screening stocks based on the user's search results, the existing technical solutions ignore the adjustment of the user's search keywords. Since the specific user is not familiar with the keywords of the search target, he may determine the stock through multiple searches within a certain period of time. As a result, the search target matching the user's search keyword may have been pushed and determined to be mismatched. If the search keyword cannot be identified and adjusted, the matching accuracy of the search results cannot be guaranteed.

[0004] In response to the above technical problems, this application specifically provides a stock screening and star scoring method and system based on a quantitative model. Summary of the Invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] Specifically, in a first aspect, the present application provides a stock screening and star rating method based on a quantitative model, which specifically includes:

[0007] S1 determines the search keyword of the user in the current search data, takes the number of searches by the user within a preset time as the reference search number, and proceeds to the next step when it is determined that there is a related search number in the reference search number based on the matching of the search keyword with the reference search number for different stocks;

[0008] S2: determining a matching search target of the user's search keyword, and determining potential search targets in the stock based on the user's search keyword and the search keywords of the associated search times when a deviation of the user's search keyword is determined based on the push data of the matching search target in the associated search times;

[0009] S3 obtains search keywords of historical users at different potential search targets, and their similarities with the user's search keywords and the search keywords associated with the number of searches, and determines historical reference users of the user using the similarities;

[0010] S4 determines the rating and star results of different stocks and the matching search target of the user using a quantitative model according to the matching status of different stocks with the search keywords of the historical reference user.

[0011] The beneficial effects of the present invention are:

[0012] By matching the push data of the search target in the associated search times, it is determined whether there is a deviation in the user's search keyword, thereby realizing the identification of the deviation of the search keyword from the push situation in the associated search times, avoiding the technical problem of low accuracy of the search results caused by the single use of the user's search keyword when the user's search keyword has a deviation. At the same time, it also realizes the differentiated search push processing of the user based on the deviation identification processing results, ensuring the accuracy of the push processing.

[0013] Based on the matching of different stocks with the search keywords of historical reference users, a quantitative model is used to determine the rating and star results of different stocks, avoiding the technical problem of low accuracy of search processing results caused by traditional reliance on user search keywords. It realizes the determination of stock rating and star results from the search keywords of historical reference users, ensuring the reliability and accuracy of push processing of matching search targets.

[0014] A further technical solution is that the search keyword is determined based on the parsing result of the user's search data.

[0015] A further technical solution is that the matching status of the search keyword with the reference search times in different stocks is determined based on the stocks for which both the search keyword of the current search data and the search keyword with the reference search times exist.

[0016] A further technical solution is that the method for determining the number of associated searches is:

[0017] Determining, based on the matching of the search keywords of the reference search times in different stocks, whether different search keywords of the current search data and the different search keywords in the reference search times coexist in different stocks;

[0018] Determine the number of stocks that exist simultaneously with different search keywords currently being searched by using the coexistence condition, and use the number as the number of associated stocks;

[0019] Based on the sum of the numbers of associated stocks of different search keywords of the current search data, a total of associated stocks is determined, and according to the total of associated stocks, it is determined whether the reference search number is the associated search number of the current search data.

[0020] A further technical solution is that when the total number of associated stocks is greater than a preset threshold value of the number of associated stocks, the reference search times is determined to be the associated search times of the current search data.

[0021] A further technical solution is that, when the user does not have an associated number of searches, the same number of search keywords of the current search data and the keywords of the stock are used to determine the rating and star results of different stocks based on the proportion of the number of keywords of the stock, and the stocks with rating and star results greater than the preset rating are used as the user's matching search target.

[0022] A further technical solution is to use a quantitative model to determine the rating and star rating results of the stock, specifically including:

[0023] Using a quantitative model to determine the average value of stock keyword matching coefficients for different historical reference users;

[0024] The average value of the stock keyword matching coefficients of different historical reference users is used to determine the rating and star result of the stock.

[0025] A further technical solution is to determine the rating result of the stock based on the average value of the stock keyword matching coefficients of different historical reference users, specifically including:

[0026] The average value of the stock keyword matching coefficients with different historical reference users is used as the scoring result;

[0027] The star rating of the stock is determined based on the preset star rating corresponding to the rating result.

[0028] A further technical solution is that the star rating results include one star, two stars and three stars.

[0029] A further technical solution is that the user's matching search target is stocks whose star rating results are greater than a preset rating.

[0030] In a second aspect, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned quantitative model-based stock screening and star scoring method when running the computer program.

[0031] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0034] Figure 1 It is a flowchart of a stock screening and star rating method based on a quantitative model;

[0035] Figure 2 is a flow chart of a method for determining the number of associated searches;

[0036] Figure 3 is a flow chart of a method for determining potential search targets in stocks;

[0037] Figure 4 is a flow chart of a method for determining a user's historical reference user;

[0038] Figure 5 This is a flowchart of a method for determining a stock's star rating result. DETAILED DESCRIPTION

[0039] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0040] In this application, the push status of the user's search target in the associated search times is utilized to realize the situation where the search target of the user's search keyword has been pushed in different associated search times but has not been matched. Then, the user's search keyword that is associated with the user's search keyword can be used to search for the matching search target and determine the star rating results, thereby ensuring the accuracy of the search processing results.

[0041] Example 1

[0042] like Figure 1 As shown, this application provides a stock screening and star scoring method based on a quantitative model, which specifically includes:

[0043] S1 determines the search keyword of the user in the current search data, takes the number of searches by the user within a preset time as the reference search number, and proceeds to the next step when it is determined that there is a related search number in the reference search number based on the matching of the search keyword with the reference search number for different stocks;

[0044] It should be noted that, based on the different search keywords of the current search data and the different search keywords in the reference search times that exist simultaneously in different stocks, the number of stocks that have the different search keywords of the current search is determined, and is used as the number of associated stocks. The search keywords whose number of associated stocks is greater than the preset associated number threshold are used as associated keywords. When the associated keywords of the current search data account for more than 0.6 of the search keywords, the reference search times are determined to be the associated search times of the current search data.

[0045] S2: determining a matching search target of the user's search keyword, and determining potential search targets in the stock based on the user's search keyword and the search keywords of the associated search times when a deviation of the user's search keyword is determined based on the push data of the matching search target in the associated search times;

[0046] Specifically, when the matching search targets have all been pushed in the associated search times, it is determined that there is a deviation in the user's search keywords, and reference keywords are constructed based on the search keywords of the user's current search data and the search keywords of the associated search times. The potential search targets in stocks are stocks whose matching number of reference keywords is greater than the preset reference keyword number.

[0047] S3 obtains search keywords of historical users at different potential search targets, and their similarities with the user's search keywords and the search keywords associated with the number of searches, and determines historical reference users of the user using the similarities;

[0048] Historical reference users are historical users who have the same number of search keywords and reference keywords in different potential search targets, and whose proportion of the number of reference keywords is greater than 0.5.

[0049] S4 determines the rating and star results of different stocks and the matching search target of the user using a quantitative model according to the matching status of different stocks with the search keywords of the historical reference user.

[0050] The stock keyword matching coefficient with different historical reference users is determined based on the number of matches between the stock and the search keywords of historical reference users in potential search targets, and the proportion of the number of search keywords of historical reference users in potential search targets. The stock rating result is determined based on the average value of the stock keyword matching coefficients with different historical reference users.

[0051] Furthermore, the search keyword is determined based on the parsing result of the user's search data.

[0052] Specifically, the matching status of the search keyword with the reference search times in different stocks is determined based on the stocks in which both the search keyword of the current search data and the search keyword with the reference search times exist.

[0053] Specifically, such as Figure 2 As shown, the method for determining the number of associated searches is:

[0054] Determining, based on the matching of the search keywords of the reference search times in different stocks, whether different search keywords of the current search data and the different search keywords in the reference search times coexist in different stocks;

[0055] Determine the number of stocks that exist simultaneously with different search keywords currently being searched by using the coexistence condition, and use the number as the number of associated stocks;

[0056] Based on the sum of the numbers of associated stocks of different search keywords of the current search data, a total of associated stocks is determined, and according to the total of associated stocks, it is determined whether the reference search number is the associated search number of the current search data.

[0057] Furthermore, when the total number of associated stocks is greater than a preset threshold number of associated stocks, the reference search times is determined to be the associated search times of the current search data.

[0058] It should also be noted that when the user does not have an associated search number, the same number of search keywords of the current search data and the stock keywords are used to determine the star rating results of different stocks based on the proportion of the number of keywords of the stock, and the stocks with star rating results greater than the preset rating are used as the user's matching search target.

[0059] In another possible embodiment, the method for determining the number of associated searches is:

[0060] Determining, based on the matching of the search keywords of the reference search times in different stocks, whether different search keywords of the current search data and the different search keywords in the reference search times coexist in different stocks;

[0061] Determine the number of stocks that exist simultaneously with different search keywords currently being searched by using the coexistence condition, and use the number as the number of associated stocks, and use the search keywords whose number of associated stocks is greater than a preset associated number threshold as associated keywords;

[0062] Based on the proportion of the associated keywords of the current search data in the search keywords, it is determined whether the reference search times are the associated search times of the current search data.

[0063] Furthermore, when the proportion of the associated keywords of the current search data in the search keywords is greater than the preset associated keyword proportion, the reference search number is determined to be the associated search number of the current search data.

[0064] In another possible embodiment, the method for determining the number of associated searches is:

[0065] Using the same number of search keywords of the current search data and the keywords of the stock, and the stocks whose keyword ratio in the stock is greater than the preset keyword ratio as matching search targets, when the same number of matching search targets and matching search targets of the reference search number is greater than the preset search target number, determining the reference search number as the associated search number of the current search data;

[0066] When the number of the matching search targets that is the same as the number of the matching search targets of the reference search times is not greater than the preset number of search targets:

[0067] Obtaining a ratio of the identical number in the matching search targets of the current search data, and when the ratio of the identical number in the matching search targets of the current search data is greater than a preset identical number ratio, determining the reference search number as the associated search number of the current search data;

[0068] When the proportion of the identical number in the matching search targets of the current search data is not greater than the preset identical number proportion:

[0069] Determining, based on the matching of the search keywords of the reference search times in different stocks, whether different search keywords of the current search data and the different search keywords in the reference search times coexist in different stocks;

[0070] The number of stocks that exist simultaneously for different search keywords in the current search is determined by using the coexistence condition, and the number of stocks is used as the number of associated stocks. When the sum of the numbers of associated stocks for different search keywords in the current search data is greater than a preset threshold value of the number of associated stocks, the reference search number is determined to be the number of associated searches for the current search data.

[0071] When the sum of the number of stocks associated with different search keywords in the current search data is not greater than the preset threshold of the number of associated stocks:

[0072] When there is no search keyword with a number of associated stocks greater than a preset associated number threshold, it is determined that the reference search number does not belong to the associated search number of the current search data;

[0073] The search keyword with the number of associated stocks greater than a preset associated number threshold is used as the associated keyword. When the proportion of the associated keywords of the current search data in the search keywords is greater than the preset associated keyword proportion, the reference search number is determined to be the associated search number of the current search data.

[0074] When the proportion of the associated keywords of the current search data in the search keywords is greater than the proportion of the preset associated keywords:

[0075] The correlation coefficient between the current search data and the reference search times is determined based on the number of stocks associated with different associated keywords of the current search data, and the correlation coefficient is used to determine whether the reference search times are the associated search times of the current search data.

[0076] Furthermore, when the correlation coefficient is greater than a preset correlation coefficient threshold, the reference search times are determined to be the correlation search times of the current search data.

[0077] Specifically, the matching search targets of the user's search keywords are the same number of search keywords of the current search data and the stock keywords, and the number of the stock keywords accounts for a greater proportion than the preset keyword number.

[0078] Specifically, determining that there is a deviation in the user's search keyword includes:

[0079] When the matching search targets have all been pushed in the associated search times, it is determined that there is a deviation in the user's search keyword.

[0080] It should be noted that if Figure 3 As shown, the method for determining the potential search targets in the stocks is:

[0081] Constructing reference keywords based on the search keywords of the user's current search data and the search keywords associated with the number of searches;

[0082] Based on the number of matches between different stocks and the reference keywords, potential search targets in the stocks are determined.

[0083] Furthermore, the potential search targets among the stocks are stocks whose matching number of reference keywords is greater than the preset number of reference keywords.

[0084] Optionally, the method for determining potential search targets in the stocks is:

[0085] Constructing reference keywords based on the search keywords of the user's current search data and the search keywords associated with the number of searches;

[0086] Determining matching reference keywords for the stocks based on matching conditions between different stocks and reference keywords;

[0087] According to the matching condition between the matching reference keyword and the current search data and the associated search times, it is determined whether the stock is a potential search target.

[0088] It should be noted that when the matching search keyword exists in the current search data and the number of associated searches for the matching search keyword is greater than a preset threshold of associated searches, the stock is determined to be a potential search target.

[0089] Optionally, the method for determining potential search targets in the stocks is:

[0090] Constructing reference keywords based on the search keywords of the user's current search data and the search keywords associated with the number of searches;

[0091] Based on the matching conditions between different stocks and reference keywords, when the number of reference keywords matched by the stock does not meet the requirement, it is determined that the stock does not belong to the potential search target;

[0092] When the number of reference keywords matched by the stock meets the requirement:

[0093] Using the reference keywords matched with the stock as matching reference keywords, and when the number of the matching reference keywords is greater than a preset number of matching reference keywords, determining that the stock is a potential search target;

[0094] When the number of the matching reference keywords is not greater than the preset number of matching reference keywords:

[0095] When the matching reference keyword is not in the current search data, it is determined that the stock is not a potential search target;

[0096] When the matching reference search term is in the current search data:

[0097] Obtaining a ratio of the number of matching reference keywords of the stock in the search keywords of the current search data, and determining that the stock is a potential search target when the ratio of the number of matching reference keywords of the stock in the search keywords of the current search data is greater than a preset ratio threshold;

[0098] When the proportion of the matching reference keywords of the stock in the search keywords of the current search data is not greater than the preset proportion threshold:

[0099] When the number of associated searches for a matching search keyword is greater than a preset associated search number threshold, the stock is determined to be a potential search target;

[0100] When the number of associated searches for a matching search keyword is not greater than the preset associated search threshold:

[0101] The stock matching coefficient of the stock is determined based on the proportion of the matching reference keywords in the search keywords of the current search data and the proportion of the matching reference keywords in the search keywords of different associated search times, and the stock matching coefficient of the stock is used to determine whether the stock is a potential search target.

[0102] Furthermore, when the stock matching coefficient of the stock is greater than a preset stock matching coefficient threshold, the stock is determined to be a potential retrieval target.

[0103] Specifically, such as Figure 4 As shown, the method for determining the user's historical reference user is:

[0104] Constructing reference keywords based on the search keywords of the user's current search data and the search keywords associated with the number of searches;

[0105] Based on the search keywords of historical users at different potential search targets, determining the number of matches between the search keywords of the historical users and the reference keywords;

[0106] The number of matches between the historical user's search keyword and the reference keyword is used to determine whether the historical user is a historical reference user of the user.

[0107] Furthermore, when the number of matches between the search keyword of the historical user and the reference keyword is greater than a preset matching number threshold, the historical user is determined to be a historical reference user of the user.

[0108] Optionally, the method for determining the historical reference user of the user is:

[0109] S31 constructs a reference keyword based on the search keyword of the user's current search data and the search keyword of the associated search times, determines the number of matches between the historical user's search keyword and the reference keyword based on the search keywords of different potential search targets, and determines a basic matching coefficient using the proportion of the number of matches in the reference keyword and the distribution of the number of matches in different associated search times and current search data;

[0110] S32 determines the target matching coefficient of the historical user at different potential search targets based on the number of matches between the historical user's search keyword and the reference keyword at different potential search targets, and determines the comprehensive target matching coefficient of the historical user based on the target matching coefficient at different potential search targets;

[0111] S33 determines a user matching coefficient between the historical user and the user based on an average value of the comprehensive target matching coefficient and the basic matching coefficient of the historical user, and uses the user matching coefficient to determine whether the historical user is a historical reference user of the user.

[0112] Furthermore, when the user matching coefficient is greater than a preset user matching coefficient threshold, the historical user is determined to be a historical reference user of the user.

[0113] Optionally, the above step S31 includes the following contents:

[0114] S311: Based on the search keywords of the user's current search data and the search keywords of the associated search times, a reference keyword is constructed. Based on the search keywords of historical users of different potential search targets, the number of matches between the historical user's search keywords and the reference keywords is determined. If the number of matches between the historical user's search keywords and the reference keywords does not meet the requirement, it is determined that the historical user does not belong to the user's historical reference user. If the number of matches between the historical user's search keywords and the reference keywords meets the requirement, the process proceeds to step S312.

[0115] At step S312, when the number of matches between the historical user's search keyword and the reference keyword is greater than the preset search keyword match number threshold, the historical user is determined to be a historical reference user of the user; and when the number of matches between the historical user's search keyword and the reference keyword is not greater than the preset search keyword match number threshold, the process proceeds to step S313.

[0116] S313 determines a basic matching coefficient based on the proportion of the number of matches in the reference keyword, the number of associated searches, and the distribution of the current search data. When the basic matching coefficient is greater than a preset basic matching coefficient threshold, it is determined that the historical user belongs to the user's historical reference user. When the basic matching coefficient is not greater than the preset basic matching coefficient threshold, the process proceeds to step S314.

[0117] S314: When the basic matching coefficient is less than the matching coefficient preset value, it is determined that the historical user belongs to the historical reference user of the user; when the basic matching coefficient is not less than the matching coefficient preset value, the process proceeds to step S32.

[0118] Optionally, the above step S32 includes the following contents:

[0119] S321 determines the target matching coefficient of the historical user at different potential search targets based on the number of matches between the historical user's search keyword and the reference keyword at different potential search targets. If there is no potential search target whose matching target coefficient meets the requirement, it is determined that the historical user does not belong to the reference historical user of the user. If there is a potential search target whose matching target coefficient meets the requirement, the process proceeds to step S322.

[0120] S322: When the number of potential search targets that meet the requirements of the matching target coefficient is greater than the preset number of potential targets, it is determined that the historical user belongs to the reference historical user of the user; when the number of potential search targets that meet the requirements of the matching target coefficient is not greater than the preset number of potential targets, the process proceeds to step S323;

[0121] S323 determines the comprehensive target matching coefficient of the historical user based on the target matching coefficients of different potential retrieval targets. When the comprehensive target matching coefficient of the historical user meets the requirements, it is determined that the historical user belongs to the reference historical user of the user. When the comprehensive target matching coefficient of the historical user does not meet the requirements, proceed to step S33.

[0122] Specifically, such as Figure 5 As shown, the method for determining the star rating result of the stock is:

[0123] According to the matching conditions between different stocks and the search keywords of the historical reference user, determining the number of matches between the stocks and the search keywords of the historical reference user in the potential search target;

[0124] Determining the stock keyword matching coefficients of stocks and different historical reference users based on the number of matches with the search keywords of the historical reference user in the potential search target and the proportion of the number of search keywords of the historical reference user in the potential search target;

[0125] The stock's rating and star rating results are determined using a quantitative model based on the stock keyword matching coefficients with different historical reference users.

[0126] Furthermore, the quantitative model is used to determine the rating and star rating of the stock, specifically including:

[0127] Using a quantitative model to determine the average value of stock keyword matching coefficients for different historical reference users;

[0128] The average value of the stock keyword matching coefficients of different historical reference users is used to determine the rating and star result of the stock.

[0129] It should be noted that the stock rating result is determined based on the average value of the stock keyword matching coefficients of different historical reference users, specifically including:

[0130] The average value of the stock keyword matching coefficients with different historical reference users is used as the scoring result;

[0131] The star rating of the stock is determined based on the preset star rating corresponding to the rating result.

[0132] Furthermore, the star rating results include one star, two stars and three stars.

[0133] Optionally, the user's matching search target is a stock whose star rating result is greater than a preset rating.

[0134] Example 2

[0135] In a second aspect, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned quantitative model-based stock screening and star scoring method when running the computer program.

[0136] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0137] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0138] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A stock screening and star rating method based on a quantitative model, characterized in that: Specifically include: Determine the search keyword of the user in the current search data, use the number of searches by the user within a preset time as a reference search number, and proceed to the next step when it is determined that there is a related search number in the reference search number based on the matching of the search keyword with the reference search number for different stocks; Determining matching search targets for the user's search keyword based on push data of the matching search targets in the associated search times; when all matching search targets have been pushed in the associated search times, i.e., when it is determined that there is a deviation in the user's search keyword, constructing reference keywords based on the search keywords of the user's current search data and the search keywords of the associated search times; and determining potential search targets in the stocks based on the number of matches between different stocks and the reference keywords, wherein the potential search targets in the stocks are stocks for which the number of matches between the reference keywords is greater than a preset number of reference keywords; Obtaining search keywords of historical users at different potential search targets, similarities between the search keywords of the user and the search keywords associated with the number of searches, and determining historical reference users of the user using the similarities; Based on the matching of different stocks with the search keywords of the historical reference user, a quantitative model is used to determine the rating and star results of different stocks and the matching search target of the user. The matching search target of the user is the stock whose rating and star results are greater than the preset rating.

2. The stock screening and star rating method based on a quantitative model according to claim 1, characterized in that: The search keyword is determined based on the analysis result of the user's search data.

3. The stock screening star rating method based on a quantitative model according to claim 1, characterized in that: The matching status of the search keyword with the reference search times in different stocks is determined based on the stocks in which both the search keyword of the current search data and the search keyword with the reference search times exist.

4. The method for stock screening and scoring based on a quantitative model according to claim 1, wherein: The method for determining the number of associated searches is: Determining, based on the matching of the search keywords of the reference search times in different stocks, whether different search keywords of the current search data and the different search keywords in the reference search times coexist in different stocks; Determine the number of stocks that exist simultaneously with different search keywords currently being searched by using the coexistence condition, and use the number as the number of associated stocks; Based on the sum of the numbers of associated stocks of different search keywords of the current search data, a total of associated stocks is determined, and according to the total of associated stocks, it is determined whether the reference search number is the associated search number of the current search data.

5. The method for stock screening and scoring based on a quantitative model according to claim 4, characterized in that: When the total number of associated stocks is greater than a preset threshold value of the number of associated stocks, the reference search number is determined to be the associated search number of the current search data.

6. The method for stock screening and scoring based on a quantitative model according to claim 1, wherein: When the user does not have an associated search number, the same number of search keywords of the current search data and the keywords of the stock are used to determine the star rating results of different stocks based on the proportion of the number of keywords of the stock, and the stocks with star rating results greater than the preset rating are used as the user's matching search target.

7. The method for stock screening and scoring based on a quantitative model according to claim 1, wherein: The method for determining the star rating result of the stock is: According to the matching conditions between different stocks and the search keywords of the historical reference user, determining the number of matches between the stocks and the search keywords of the historical reference user in the potential search target; Determining the stock keyword matching coefficients of stocks and different historical reference users based on the number of matches with the search keywords of the historical reference user in the potential search target and the proportion of the number of search keywords of the historical reference user in the potential search target; The stock's rating and star rating results are determined using a quantitative model based on the stock keyword matching coefficients with different historical reference users.

8. The method for stock screening and scoring based on a quantitative model according to claim 7, wherein: The quantitative model is used to determine the rating and star rating of the stock, including: Using a quantitative model to determine the average value of stock keyword matching coefficients for different historical reference users; The average value of the stock keyword matching coefficients of different historical reference users is used to determine the rating and star result of the stock.

9. The method for stock screening and scoring based on a quantitative model according to claim 8, wherein: The stock rating is determined based on the average value of the stock keyword matching coefficients of different historical reference users, specifically including: The average value of the stock keyword matching coefficients with different historical reference users is used as the scoring result; The star rating of the stock is determined based on the preset star rating corresponding to the rating result.

10. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, it executes a stock screening star scoring method based on a quantitative model as described in any one of claims 1-9.

Images