Method and device for processing hot search list

Abstract

The application discloses a kind of hot search list processing method and device, it is related to artificial intelligence intelligent service technical field, wherein the method includes: according to the identity information and operating behavior data when all users use application to search, determine multiple hot search keywords, the label of each user and the label of each hot search keyword;According to the label determines operating behavior type and hot search keyword type;According to investment risk operating behavior type and hot search keyword type determines the weight value of each hot search keyword;According to the weight value of each hot search keyword generates hot search list recommendation strategy;According to the strategy, different special hot search list is generated for the user of different operating behavior type;After a preset period, the number of clicks of special hot search list is detected, when the number of clicks is less than preset value, the strategy is readjusted;According to the strategy of readjustment, special hot search list is regenerated.The application can improve the update frequency and use rate of hot search list, and then improve user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence intelligent service, and in particular to a hot search list processing method and device. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the application recited in the claims. The description herein does not constitute admission that the subject matter disclosed herein is prior art to the present application.

[0003] With the rapid development of Internet technology, network resources are increasingly abundant, and search has become one of the indispensable methods for people to quickly obtain information.

[0004] Currently, the hot search list is usually formed by querying the search times of search words within a certain period of time. The hot search list has been applied to many scenarios, such as social, shopping, financial, news, etc. APP. However, unlike these APPs, for financial tool class APP, users often only search for a few commonly used functions, and the search frequency is low, the data source is single, which leads to low update frequency of the list. At the same time, it is also impossible to provide personalized lists for different customers. In addition, for financial tool class applications with low search scene usage rate, the usage rate of the hot search list is also low. SUMMARY

[0005] The embodiments of the present application provide a hot search list processing method for financial tool class applications, which generates different exclusive hot search lists for users of different operation behavior types based on the identity information and operation behavior of users searching using financial tool class applications, improves the update frequency and usage rate of the hot search list of the financial tool class application, and the method comprises:

[0006] According to the identity information and operation behavior data of all users searching using the application, a plurality of hot search keywords are determined, and the label of each user and the label of each hot search keyword are determined.

[0007] According to the label of each user and the label of each hot search keyword, the operation behavior type and the hot search keyword type are determined.

[0008] According to the operation behavior type and the hot search keyword type, the weight value of each hot search keyword is determined; according to the operation behavior type and the hot search keyword type, the weight value of each hot search keyword is determined, including: according to the investment risk operation behavior type and the hot search keyword type, the weight value of each hot search keyword is determined.

[0009] According to the weight value of each hot search keyword, a recommendation strategy of the hot search list is generated; according to the recommendation strategy of the hot search list, different exclusive hot search lists are generated for users of different operation behavior types.

[0010] After a preset period of time, the number of clicks of the exclusive hot search list is detected, and when the number of clicks is less than a preset value, the recommendation strategy of the hot search list is readjusted; and different exclusive hot search lists are generated for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list.

[0011] In one embodiment, the identity information includes a financial institution to which the user subscribes and geographical location information; and the operation behavior data includes a search keyword input by the user, a search frequency and a click frequency.

[0012] In one embodiment, the method for processing the hot search list of the financial tool application further includes: adjusting the hot search keyword and / or the weight value of the hot search keyword according to actual needs of operation of the financial tool application to obtain an adjusted hot search keyword and / or weight value of the hot search keyword.

[0013] According to the weight value of each hot search keyword, a recommendation strategy of the hot search list is generated; and different exclusive hot search lists are generated for users of different operation behavior types according to the recommendation strategy of the hot search list, including: generating a recommendation strategy of the hot search list according to the adjusted hot search keyword and / or weight value of the hot search keyword; and generating different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list.

[0014] In one embodiment, the method for processing the hot search list of the financial tool application further includes: displaying different exclusive hot search lists for users of different operation behavior types.

[0015] In one embodiment, the method for processing the hot search list of the financial tool application further includes: forming a popular keyword library according to the plurality of hot search keywords.

[0016] According to the label of each user and the label of each hot search keyword, the operation behavior type and the hot search keyword type are determined, including: according to the label of each user and the label of each hot search keyword in the popular keyword library, the operation behavior type and the hot search keyword type are determined.

[0017] In one embodiment, the number of labels of each user is a plurality, and the number of labels of each hot search keyword is a plurality.

[0018] Embodiments of the present application also provide a processing device for a hot search list of a financial tool application, which is used to generate different exclusive hot search lists for users of different operation behavior types when the users use the financial tool application to search, improve the update frequency and usage rate of the hot search list of the financial tool application, and the device includes:

[0019] The analysis unit is configured to determine a plurality of hot search keywords based on identity information and operation behavior data of all users searching using the application.

[0020] The classification unit is configured to determine operation behavior types and hot search keyword types based on the labels of each user and the labels of each hot search keyword.

[0021] The weight determination unit is configured to determine a weight value of each hot search keyword based on the operation behavior types and the hot search keyword types.

[0022] The strategy and hot search list generation unit is configured to generate a recommendation strategy of a hot search list based on the weight value of each hot search keyword, and generate different exclusive hot search lists for users of different operation behavior types based on the recommendation strategy of the hot search list.

[0023] The real-time updating unit is configured to detect a click number of the exclusive hot search list after a preset period of time, readjust the recommendation strategy of the hot search list when the click number is less than a preset value, and generate different exclusive hot search lists for users of different operation behavior types based on the readjusted recommendation strategy of the hot search list.

[0024] In an embodiment, the identity information includes a financial institution signed by a user and geographical location information, and the operation behavior data includes a search keyword input by the user, a search number, and a click number.

[0025] In an embodiment, the processing device of the hot search list of the financial tool application further includes an adjustment unit configured to adjust the hot search keywords and / or the weight values of the hot search keywords based on actual needs of operation of the financial tool application to obtain adjusted hot search keywords and / or weight values of the hot search keywords.

[0026] The strategy and hot search list generation unit is configured to generate a recommendation strategy of a hot search list based on the weight value of each hot search keyword, and generate different exclusive hot search lists for users of different operation behavior types based on the recommendation strategy of the hot search list.

[0027] In an embodiment, the processing device of the hot search list of the financial tool application further includes a display unit configured to display different exclusive hot search lists for users of different operation behavior types.

[0028] In an embodiment, the processing device of the hot search list of the financial tool application further includes a forming unit configured to form a popular keyword library based on the plurality of hot search keywords.

[0029] The classification unit is specifically configured to determine the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword in the hot word library.

[0030] In one embodiment, the number of labels of each user is multiple, and the number of labels of each hot search keyword is multiple.

[0031] The embodiment of the application further provides a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the processing method of the hot search list of the financial tool application when executing the computer program.

[0032] The embodiment of the application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the processing method of the hot search list of the financial tool application when executed by a processor.

[0033] The embodiment of the application further provides a computer program product, which includes a computer program, and the computer program implements the processing method of the hot search list of the financial tool application when executed by a processor.

[0034] Compared with the prior art, the processing method of the hot search list of the financial tool application has the beneficial technical effects that:

[0035] Firstly, according to the identity information and operation behavior data of all users when searching by using the application, the multiple hot search keywords, the label of each user and the label of each hot search keyword are determined, and the operation behavior type and the hot search keyword type are determined according to the label of each user and the label of each hot search keyword, so as to lay a foundation for improving the update frequency and the use rate of the hot search list in the future.

[0036] Secondly, since it is the processing method of the hot search list of the financial tool application, the weight value of each hot search keyword is determined based on the investment risk operation behavior type and the product class hot search keyword type, which also lays a foundation for improving the update frequency and the use rate of the hot search list in the future.

[0037] Thirdly, a recommendation strategy of the hot search list is generated according to the weight value of each hot search keyword; different exclusive hot search lists are generated for users of different operation behavior types according to the recommendation strategy of the hot search list; after a preset period of time, the number of clicks of the exclusive hot search list is detected, and when the number of clicks is less than a preset value, the recommendation strategy of the hot search list is readjusted; different exclusive hot search lists are generated for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list, which realizes that different exclusive hot search lists are generated for users of different operation behavior types based on the recommendation strategy, avoids the case that the list content seen by all users is the same, and at the same time, the hot search list is updated in real time based on the effect of the detection recommendation strategy, so that the hot search list of the user can be quickly affected, and therefore the update frequency and the usage rate of the hot search list are improved.

[0038] In summary, the processing scheme of the hot search list of the financial tool application provided by the embodiment of the application improves the update frequency and the usage rate of the hot search list of the financial tool application, and further improves the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor. In the drawings:

[0040] Figure 1 The flowchart of the processing method of the hot search list of the financial tool application in the embodiment of the application;

[0041] Figure 2 The flowchart of the processing method of the hot search list of the financial tool application in another embodiment of the application;

[0042] Figure 3 The flowchart of the processing method of the hot search list of the financial tool application in another embodiment of the application;

[0043] Figure 4 The structural diagram of the processing device of the hot search list of the financial tool application in the embodiment of the application;

[0044] Figure 5 The structural diagram of the processing device of the hot search list of the financial tool application in another embodiment of the application;

[0045] Figure 6 The structural diagram of the processing device of the hot search list of the financial tool application in another embodiment of the application. DETAILED DESCRIPTION

[0046] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, further detailed descriptions of the embodiments of the present application will be given below with reference to the drawings. Herein, the illustrative embodiments of the present application and their descriptions are used to explain the present application but not to limit the present application.

[0047] At present, the hot search list has been applied to various scenes and formed a certain focus. The formation is mainly through the search engine collecting the search times of all search words in a period of time, and then sorting the search words by times. First, unlike social APPs, users of tool APPs usually only search for commonly used functions, and the search frequency is low, so there may be a situation that the change rate of hot search content is low, i.e. the update rate is low, the user experience is poor, and the enthusiasm of customers to use the hot search list cannot be effectively mobilized. Second, there may be a situation that the list content seen by all users is the same, which is not conducive to mining the content attributes of the hot search list, and the traffic value is low. Third, since the hot search list relies on search frequency for sorting, some keywords that are frequently searched in a short time but have a low total frequency may not be able to quickly affect the hot search list, and the current most popular content cannot be directly reflected. Finally, the hot search list usually needs to be manually controlled again, and simple times statistics sorting is not conducive to flexible maintenance of hot search data by the operation department, and the operation cost is high.

[0048] Since the inventors have considered the above technical problems, a hot search list processing scheme for a financial tool application is proposed. Based on the identity information and search operation behavior of customers, the scheme not only forms a flexible and personalized hot search list, but also improves the update frequency of the hot search list for applications with low search scene usage rate, improves the usage rate of the hot search list of users, thereby strengthening the flow guiding effect and conversion ability of the hot search list, improving the traffic value, and improving the user experience. The hot search list processing scheme for the financial tool application will be described in detail below.

[0049] Figure 1 The flowchart of the hot search list processing method for the financial tool application in the embodiments of the present application is shown in Figure 1 The method comprises the following steps:

[0050] Step 101: determining a plurality of hot search keywords according to the identity information and operation behavior data of all users when searching using the application, the label of each user and the label of each hot search keyword;

[0051] Step 103: determining the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword;

[0052] Step 105: determining the weight value of each hot search keyword according to the operation behavior type and the hot search keyword type; determining the weight value of each hot search keyword according to the operation behavior type and the hot search keyword type, including: determining the weight value of each hot search keyword according to the investment risk operation behavior type and the hot search keyword type;

[0053] Step 107: generating a recommendation strategy of the hot search list according to the weight value of each hot search keyword; generating different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list;

[0054] Step 109: detecting the click number of the exclusive hot search list after a preset period of time, and readjusting the recommendation strategy of the hot search list when the click number is less than a preset value; generating different exclusive hot search lists for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list.

[0055] The processing method of the hot search list of the financial tool application provided by the embodiment of the application works as follows: determining a plurality of hot search keywords, a label of each user and a label of each hot search keyword according to identity information and operation behavior data of all users when searching using the application; determining an operation behavior type and a hot search keyword type according to the label of each user and the label of each hot search keyword; determining the weight value of each hot search keyword according to the operation behavior type and the hot search keyword type; determining the weight value of each hot search keyword according to the operation behavior type and the hot search keyword type, including: determining the weight value of each hot search keyword according to the investment risk operation behavior type and the hot search keyword type; generating a recommendation strategy of the hot search list according to the weight value of each hot search keyword; generating different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list; detecting the click number of the exclusive hot search list after a preset period of time, and readjusting the recommendation strategy of the hot search list when the click number is less than a preset value; generating different exclusive hot search lists for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list.

[0056] Compared with the prior art that cannot provide personalized hot search lists for different customers and has low update frequency and use rate of the hot search list, the processing method of the hot search list of the financial tool application provided by the embodiment of the application has the beneficial technical effects that:

[0057] First, a plurality of hot search keywords, a label of each user and a label of each hot search keyword are determined according to identity information and operation behavior data of all users when searching using the application; an operation behavior type and a hot search keyword type are determined according to the label of each user and the label of each hot search keyword, the operation behavior type and the hot search keyword type are determined by using the label technology, which lays a foundation for subsequently improving the update frequency and use rate of the hot search list.

[0058] Secondly, since it is the processing scheme of the hot search list of the financial tool type APP, the weight value of each hot search keyword is determined based on the investment risk operation behavior type and the product type hot search keyword type, which lays a foundation for improving the update frequency and usage rate of the hot search list in the future.

[0059] Thirdly, the recommendation strategy of the hot search list is generated according to the weight value of each hot search keyword; different exclusive hot search lists are generated for users of different operation behavior types according to the recommendation strategy of the hot search list; after a preset period of time, the number of clicks of the exclusive hot search list is detected, and when the number of clicks is less than a preset value, the recommendation strategy of the hot search list is adjusted again; different exclusive hot search lists are generated for users of different operation behavior types according to the recommendation strategy of the hot search list after the adjustment, which realizes that different exclusive hot search lists are generated for users of different operation behavior types based on the recommendation strategy, avoids the case that all users see the same list content, and at the same time, the hot search list is updated in real time based on the detection of the effect of the recommendation strategy, so that the hot search list of the user can be quickly affected, thereby improving the update frequency and usage rate of the hot search list.

[0060] In summary, the processing scheme of the hot search list of the financial tool type application provided by the embodiment of the application improves the update frequency and usage rate of the hot search list of the financial tool type application, and further improves the user experience. The processing method of the hot search list of the financial tool type application will be described in detail below.

[0061] First of all, for the convenience of understanding, steps 101 to 103, i.e., search data collection and statistics, label classification, are introduced together.

[0062] In specific implementation, before the above step 101, it can also include: obtaining identity information and operation behavior data of all users using the financial tool type application for searching. In this obtaining step, the search engine of the financial tool type application collects all user search conditions, i.e., identity information (pre-authorized user identity information) and operation behavior data when using the financial tool type application for searching. The operation behavior data can include search keywords (such as AA credit card activities, BB financial product, etc.), search times, click times, and user identity information. The identity information can include information such as the signing branch (financial institution) and the geographic location, and this step 1 can be realized by a search information obtaining module, see the obtaining unit mentioned below.

[0063] In the implementation, in the step 101, according to the obtained information (identity information and operation behavior data of all users using the financial tool application to search), the result statistical analysis is performed to understand the high search keywords (hot search keywords) of the users in a branch / region, and a hot keyword library is formed. In an embodiment, the processing method of the hot search list of the financial tool application can further include: forming a hot keyword library according to the hot search keywords, to facilitate the subsequent convenient and flexible processing of the hot search list. Then, in the step 103, the operation behavior type and the hot search keyword type are determined according to the label of each user and the label of each hot search keyword. The determination can include: determining the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword in the hot keyword library.

[0064] In the implementation, in the step 101, according to the obtained information (identity information and operation behavior data of all users using the financial tool application to search), the label of each user and the label of each hot search keyword are also determined. The step 101 can be implemented by a result statistical module, as mentioned in the analysis unit below. Then, in the step 103, the operation behavior type and the hot search keyword type are determined according to the label of each user and the label of each hot search keyword, that is, the user behavior (operation behavior) and the keywords (hot search keywords) in the hot keyword library are classified by the labels (user labels and hot search keyword labels). The step 103 can be implemented by a label classification module, as mentioned in the classification unit below. The specific label content can be the signing branch (financial institution), the region (geographical location information), and the hot search keyword type (function, product, commodity, activity, etc.). A single user and a single search keyword can have one or more labels. Preferably, the number of labels of each user can be multiple, and the number of labels of each hot search keyword can be multiple, which can further improve the accuracy of the processing of the hot search list. In order to facilitate understanding, three examples are given below: 1. If the behavior of user A is to frequently search for credit card activities, and the signing bank is Beijing Branch, then the user label of user A is “Beijing Branch”, “credit card”, and “activity”, and the corresponding operation behavior type can be “Beijing Branch”, “credit card”, and “activity”; 2. If the keyword is “Magic City of Benefits”, the label of the keyword can be “activity” and “Shanghai Branch”, and the corresponding hot search keyword type can be the activity type keyword; 3. The label of the keyword “BlackRock” can be “product”, “Guangdong region”, and “Jiangsu region”, and the corresponding hot search keyword type can be the product type keyword.

[0065] Secondly, the steps 105 and 106, that is, the related steps of determining the weight value, are introduced.

[0066] In a specific implementation, in step 105, determining the weight value of each hot search keyword according to the operation behavior type and the hot search keyword type can include: determining the weight value of each hot search keyword according to the investment risk operation behavior type and / or the product category hot search keyword type. Specifically, the search list seen by users of different operation behavior types can be maintained specially. Scene one: customers with labels such as "credit card" and "activity" can increase the weight of activity keywords or make special recommendations, such as increasing the ranking weight or placing the "brushing credit card to get a discount" keyword at the top. Scene two: if the customer label has an investment risk type (investment risk operation behavior type) label, then relevant investment and financial products can be flexibly recommended in the hot search list according to the risk type of different customers. If the customer risk type is conservative, then the weight of low-risk product display can be increased, such as a money fund type product; if the customer risk type is stable, then the weight of low-risk product display can be increased, such as a bond type product and a medium-risk financial product; if the customer risk type is aggressive, then the weight of high-risk product display can be increased, such as a medium-high-risk fund product. Scene three: different types of loan products can be flexibly recommended according to the identity of the customer. If the customer has a "farmer" label, then the weight of farmer loan product display can be increased; if the customer has a "small and micro enterprise owner" label, then the weight of small and micro enterprise loan product display can be increased.

[0067] In one embodiment, as shown in Figure 2 the processing method of the hot search list of the financial tool application can further include step 106: adjusting the hot search keyword and / or the weight value of the hot search keyword according to the actual needs of the operation of the financial tool application to obtain an adjusted hot search keyword and / or weight value of the hot search keyword; then in subsequent step 107, generating a dedicated hot search list of the financial tool application for users of different operation behavior types according to the weight value of each hot search keyword can include: generating a recommendation strategy for the hot search list according to the adjusted hot search keyword and / or weight value of the hot search keyword; and generating different dedicated hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list.

[0068] In a specific implementation, in step 106, adjusting the hot search keyword and / or the weight value of the hot search keyword according to the actual needs of the operation of the financial tool application to obtain an adjusted hot search keyword and / or weight value of the hot search keyword adds the flexible control weight of the manual participation of the operation personnel, further improves the precision of the processing of the hot search list of the financial tool application, and can provide more personalized hot search lists for different users. The following examples are given for illustration.

[0069] In implementation, the operation personnel can maintain the search list seen by the users of a branch or a region, especially for some branch or region exclusive content, which can be recommended by increasing the sorting weight or the way of top. Scene one: if a branch in Guangdong province launches a one-yuan gift activity, the search frequency of the activity name "one-yuan gift" increases greatly in a short time, and all are the customers of the Guangdong branch, then the operation personnel can directly recommend the keyword "one-yuan gift" to the customers of the Guangdong branch in the hot search list, and only the customers of the branch can see this keyword in the hot search list. Although the search frequency may not be enough to enter the hot word range globally, but it can affect the hot search list of the corresponding customers in this way. Scene two: if the Guangzhou branch plans to hold a tea tasting activity for VIP customers, the operation personnel can directly recommend the activity keyword to the VIP customers located in the Guangzhou region in the hot search list to improve the activity exposure rate and participation level. Clicking can jump to the activity details and show the nearby available sites, one-click direct connection improves customer experience.

[0070] In implementation, the operation personnel can also add the list keywords individually according to the needs, that is, adjust the keywords. Scene one: if a branch plans to carry out a card binding gift activity, the branch customer can see the keyword in the hot search list, which helps to increase the promotion and improve the operation effect. Scene two: for example, a new fund product is planned to be launched in the bank, and during the collection stage, the customer attention is also the highest, the operation personnel can set the fund as the hot search list first, which can quickly attract customer attention, achieve the effect of attracting customers, and help reduce the time cost of customers, and directly click to jump.

[0071] In implementation, through the introduction of the above embodiments, the hot search keyword type mentioned in the embodiment of the present application can include an activity type hot search keyword type and a product type hot search keyword type. The above steps 105 and 106 can be realized by a background management end module, see the weight determination unit and the adjustment unit below.

[0072] Thirdly, the above step 107 is introduced, that is, the final sorting of the list according to the weight of the keyword determined in the above step, that is, generating the list, that is, generating different exclusive hot search lists for different operation behavior types of users according to the weight value. The step 107 can be realized by a result sorting module, see the hot search list generation unit improved below. The step 107 is described in detail as follows.

[0073] 1. First, the search frequency is taken as the default sorting value, and all keywords in the hot word library are sorted according to this sorting value, and the keywords with higher frequency are sorted in front.

[0074] 2. Based on the search volume ranking value, adjusted keywords will have their weight value increased. This weight value can be adjusted to raise or lower the keyword's ranking. Weight values ​​are divided into [0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100], with higher numbers indicating higher weight.

[0075] 3. When finalizing the ranking, two values ​​will be considered. The weight value will be prioritized, followed by the search frequency ranking value. Operators can manually increase the weight of a single keyword or multiple keywords to improve ranking or place them at the top. To place a keyword at the top, set its weight value to 100. For example, if the keyword "account" has 1000 searches and a weight of 0 (unadjusted), while the keyword "balance" has 1000 searches but a weight increased by 10 (adjusted), then "balance" will rank ahead of "account." When weights are equal, ranking will be based on search frequency.

[0076] Next, let's introduce step 109 above.

[0077] In practice, click statistics for the trending search list are added to assess the effectiveness of the strategy. Based on the client's click activity on the trending search list, if there are no clicks for an extended period, the recommendation strategy is considered ineffective, and other trending search content is recommended; if clicks are made, the trending search list recommendation strategy is considered effective, and related content is continued to be recommended according to this strategy. The relevant recommendation strategies mentioned in steps 107 and 109 can be found in the related description in step 106 above.

[0078] Finally, we introduce step 110, which can be implemented through a result display module, see the display unit mentioned below.

[0079] In one embodiment, such as Figure 3 As shown, the method for processing the trending search list of the above-mentioned financial tool applications may also include step 110: displaying different exclusive trending search lists for users with different types of operational behaviors.

[0080] In practice, step 110 can be implemented through a result display module, as shown in the display unit below. This display unit shows different exclusive trending lists to users with different types of operation behaviors, that is, to intuitively present personalized exclusive lists to users, thereby further improving the user experience.

[0081] In summary, the advantages of the method for processing trending topics for financial tool applications provided in this embodiment of the invention are:

[0082] 1. Through collecting search data, the customer identity, operation behavior and search keywords are classified according to the label, the personalized hot search list is realized, the users are classified according to the region, the signed branch, the frequently searched content and the like, the exclusive hot search list is formed, the user demand is more fitted, the browsing, clicking and conversion of the hot search list are helped to improve, and the traffic value is realized.

[0083] 2. The personalized list, the hot search list seen by each person is possibly different, the exclusive list content providing and display are realized.

[0084] 3. The artificial regulation mechanism is joined, the list maintenance is more flexible, changeable and controllable, the operation efficiency of the operation personnel is effectively helped to improve, the characteristic list can be flexibly created according to the demand, and the operation effect is strengthened.

[0085] 4. The effect that the global hot search list can be quickly influenced through the low-frequency and important keywords is realized.

[0086] The embodiment of the application also provides a hot search list processing device of a financial tool application, as described in the following embodiment.

[0087] Figure 4 The structure diagram of the hot search list processing device of the financial tool application in the embodiment of the application is shown as shown in Figure 1. Figure 4 The device comprises:

[0088] An analysis unit 01 is used for determining a plurality of hot search keywords according to the identity information and operation behavior data when all users use the financial tool application to search, the label of each user and the label of each hot search keyword.

[0089] A classification unit 03 is used for determining the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword.

[0090] A weight determination unit 05 is used for determining the weight value of each hot search keyword according to the operation behavior type and the hot search keyword type.

[0091] The strategy and hot search list generation unit 07 is configured to generate a recommendation strategy of a hot search list according to the weight value of each hot search keyword, and generate different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list.

[0092] The real-time updating unit 09 is configured to detect the number of clicks of the exclusive hot search list after a preset period of time, readjust the recommendation strategy of the hot search list when the number of clicks is less than a preset value, and generate different exclusive hot search lists for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list.

[0093] At present, the popular search list commonly used in the market is based on massive user search data, and the search popularity of a keyword is calculated through a certain data mining method to form a ranking list, which further leads users to pay attention to related information. If user identity information such as a user's opening bank, region, and daily search behavior are analyzed when the hot search list is counted, the content of the hot search list can be flexibly and effectively regulated to form an exclusive characteristic list, quickly attract user interest clicks, and improve user experience. In view of the above problems, the inventors propose a processing device for a hot search list of a financial tool application. When the device works: the analysis unit 01 determines a plurality of hot search keywords according to the identity information and operation behavior data of all users using the financial tool application to search, and determines the label of each user and the label of each hot search keyword; the classification unit 03 determines the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword; the weight determination unit 05 determines the weight value of each hot search keyword according to the investment risk operation behavior type and the hot search keyword type; the strategy and hot search list generation unit 07 generates a recommendation strategy of a hot search list according to the weight value of each hot search keyword, and generates different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list; and the real-time updating unit 09 detects the number of clicks of the exclusive hot search list after a preset period of time, readjusts the recommendation strategy of the hot search list when the number of clicks is less than a preset value, and generates different exclusive hot search lists for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list.

[0094] In summary, compared with the prior art which cannot provide personalized hot search lists for different customers and has low update frequency and use rate of the hot search list, the processing method for a hot search list of a financial tool application provided in the embodiments of the present application can generate different exclusive hot search lists for users of different operation behavior types based on the identity information and operation behavior of the users using the financial tool application to search, improve the update frequency and use rate of the hot search list, and further improve the user experience. The processing device for a hot search list of a financial tool application is described in detail below.

[0095] In actual implementation, the processing device for the hot search list provided by the embodiment of the present application can further include an acquisition unit configured to acquire identity information and operation behavior data of all users when the users use the financial tool application to search.

[0096] In one embodiment, the processing device for the hot search list of the financial tool application can further include a forming unit configured to form a hot word library according to the plurality of hot search keywords.

[0097] The classification unit is specifically configured to determine the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword in the hot word library.

[0098] In one embodiment, as shown in Figure 5 The processing device for the hot search list of the financial tool application can further include an adjusting unit 06 configured to adjust the hot search keyword and / or the weight value of the hot search keyword according to actual needs of operation of the financial tool application, to obtain an adjusted hot search keyword and / or weight value of the hot search keyword.

[0099] The hot search list generating unit is specifically configured to generate a recommendation strategy of the hot search list according to the adjusted hot search keyword and / or weight value of the hot search keyword, and generate different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list.

[0100] In one embodiment, as shown in Figure 6 The processing device for the hot search list of the financial tool application can further include a display unit 10 configured to display different exclusive hot search lists for users of different operation behavior types.

[0101] In one embodiment, the identity information can include a financial institution signed by the user and geographical location information, and the operation behavior data can include a search keyword input by the user, a search frequency and a click frequency.

[0102] In one embodiment, the number of labels of each user can be a plurality, and the number of labels of each hot search keyword can be a plurality.

[0103] In the technical solution of the present application, the acquisition, storage, use, processing and the like of data all comply with relevant provisions of national laws and regulations.

[0104] The embodiment of the present application further provides a computer device including a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements the processing method for the hot search list of the financial tool application when executing the computer program.

[0105] The embodiment of the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the processing method of the hot search list of the financial tool application.

[0106] The embodiment of the present application also provides a computer program product, the computer program product comprises a computer program, and the computer program is executed by a processor to realize the processing method of the hot search list of the financial tool application.

[0107] Compared with the prior art, the processing method of the hot search list of the financial tool application has the beneficial technical effects that:

[0108] Firstly, according to the identity information and operation behavior data of all users using the application to search, a plurality of hot search keywords, a label of each user and a label of each hot search keyword are determined, and according to the label of each user and the label of each hot search keyword, the operation behavior type and the hot search keyword type are determined, and the label technology is used to determine the operation behavior type and the hot search keyword type, which lays a foundation for subsequent improvement of the update frequency and the use rate of the hot search list.

[0109] Secondly, since it is the processing method of the hot search list of the financial tool application, the weight value of each hot search keyword is determined based on the investment risk operation behavior type and the product class hot search keyword type, which also lays a foundation for subsequent improvement of the update frequency and the use rate of the hot search list.

[0110] Thirdly, a recommendation strategy of the hot search list is generated according to the weight value of each hot search keyword, different exclusive hot search lists are generated for users of different operation behavior types according to the recommendation strategy of the hot search list, and after a preset period of time, the number of clicks of the exclusive hot search list is detected, the recommendation strategy of the hot search list is adjusted again when the number of clicks is less than a preset value, different exclusive hot search lists are generated for users of different operation behavior types according to the recommendation strategy of the hot search list, which realizes that different exclusive hot search lists are generated for users of different operation behavior types based on the recommendation strategy, avoids the case that the list content seen by all users is the same, and simultaneously, the hot search list is updated in real time based on the effect of the detection recommendation strategy, so that the hot search list of the user can be quickly affected, and therefore the update frequency and the use rate of the hot search list are improved.

[0111] To sum up, the processing method of the hot search list of the financial tool application improves the update frequency and the use rate of the hot search list of the financial tool application, and further improves the user experience.

[0112] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0113] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0114] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0116] The above-described specific embodiments are merely intended to further describe and explain the present application, and should not be used to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A method for processing a hot search list, characterized in that, The processing method of the hot search list is a processing method of a hot search list of a financial tool application, and the method comprises the following steps of: determining a plurality of hot search keywords, a label of each user and a label of each hot search keyword according to pre-authorized identity information and operation behavior data of all users when searching by using the financial tool application; the identity information comprises a financial institution and geographical position information signed by the user; determining an operation behavior type and a hot search keyword type according to the label of each user and the label of each hot search keyword; the hot search keyword type comprises an activity type hot search keyword type and a product type hot search keyword type; determining a weight value of each hot search keyword according to the operation behavior type and the hot search keyword type; generating a recommendation strategy of the hot search list according to the weight value of each hot search keyword; and generating different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list. It further comprises the following steps of:

2. The method of claim 1, wherein the processing of the hot search list comprises: adjusting the hot search keyword and / or the weight value of the hot search keyword according to actual needs of application operation to obtain an adjusted hot search keyword and / or weight value of the hot search keyword; generating a recommendation strategy of the hot search list according to the weight value of each hot search keyword; generating different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list, which comprises the following step of generating a recommendation strategy of the hot search list according to the adjusted hot search keyword and / or weight value of the hot search keyword; generating different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list. The operation behavior data comprises search keyword content input by the user, search times and click times. 3.The method of claim 1, wherein, It further comprises the following step of:

4. The method of claim 1, wherein the processing of the hot search list comprises: displaying different exclusive hot search lists for users of different operation behavior types. It further comprises the following steps of:

5. The method of claim 1, wherein the processing of the hot search list comprises: forming a popular keyword library according to the plurality of hot search keywords; determining the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword, which comprises the following step of determining the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword in the popular keyword library. The number of labels of each user is a plurality, and the number of labels of each hot search keyword is a plurality.

6. The method of claim 1, wherein the processing of the hot search list comprises: The processing method of the hot search list is a processing device of a hot search list of a financial tool application, and the device comprises the following units:

7. A processing device of a hot search list, characterized in that, an analysis unit configured to determine a plurality of hot search keywords, a label of each user and a label of each hot search keyword according to pre-authorized identity information and operation behavior data of all users when searching by using the financial tool application; the identity information comprises a financial institution and geographical position information signed by the user; a classification unit configured to determine an operation behavior type and a hot search keyword type according to the label of each user and the label of each hot search keyword; the hot search keyword type comprises an activity type hot search keyword type and a product type hot search keyword type; ​ The weight determination unit is configured to determine a weight value of each hot search keyword according to the investment risk operation behavior type and the hot search keyword type. The strategy and hot search list generation unit is configured to generate a recommendation strategy of a hot search list according to the weight value of each hot search keyword, and generate different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list. The real-time updating unit is configured to detect a click number of the exclusive hot search list after a preset time period, readjust the recommendation strategy of the hot search list when the click number is less than a preset value, and generate different exclusive hot search lists for users of different operation behavior types according to the readjusted recommendation strategy of the hot search list.

8. The hot search list processing apparatus of claim 7, wherein, Further comprising: The adjustment unit is configured to adjust the hot search keyword and / or the weight value of the hot search keyword according to actual needs of application operation, and obtain an adjusted hot search keyword and / or weight value of the hot search keyword. The strategy and hot search list generation unit is configured to generate a recommendation strategy of a hot search list according to the adjusted hot search keyword and / or weight value of the hot search keyword, and generate different exclusive hot search lists for users of different operation behavior types according to the recommendation strategy of the hot search list.

9. The hot search list processing apparatus of claim 7, wherein, Further comprising: The display unit is configured to display different exclusive hot search lists for users of different operation behavior types.

10. The hot search list processing apparatus of claim 7, wherein, Further comprising: The forming unit is configured to form a popular keyword library according to the plurality of hot search keywords. The classification unit is configured to determine the operation behavior type and the hot search keyword type according to the label of each user and the label of each hot search keyword in the popular keyword library.

11. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method in any one of claims 1 to 6.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1 to 6.

13. A computer program product, characterised in that, The computer program product includes a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1 to 6.

Images