Business recommendation method and device, equipment, storage medium and program product

Abstract

The invention provides a business recommendation method and device, equipment, a storage medium and a program product, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: acquiring the handling times of a plurality of alternative businesses; determining a plurality of candidate businesses from the plurality of candidate businesses according to the feedback information of the plurality of users on the candidate businesses and the handling times; and determining a target number of to-be-displayed target services from the plurality of candidate services based on the number of adjustment times of the candidate services, so as to display the content of the target number of target services in the service display interface. The service displayed on the interface is determined by combining the feedback information of multiple users on the service, such as scores, the handling times and the adjustment times of the service, so that the stability and the quality of the service displayed on the interface are improved, and the requirements of most users are better met; meanwhile, the problems that the difference of display services of different user interfaces is large and maintenance and management are inconvenient due to the fact that the display services are determined by focusing on user behaviors are solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a business recommendation method, device, equipment, storage medium and program product. Background Art

[0002] With the development of mobile technology and Internet technology, banking services are gradually transforming towards digitalization, and can provide online and mobile banking services. Since there are many banking services, such as liability services, asset services and intermediary services, only some services can be recommended to users on the business display interface.

[0003] At present, important or frequently used services are generally placed in a prominent position on the service display interface, relying on the experience of bank staff. Secondary functions are accessed through drop-down menus or other methods. Based on this method, it is difficult for users to find the functions they need, and the service processing efficiency is low, which may lead to poor user experience; or, according to the usage habits of different users, a personalized service display interface is customized. However, this method only considers the usage habits of a single user, is not universal, and is not convenient for system maintenance and management, and cannot ensure that users obtain a consistent user experience during use. Summary of the invention

[0004] The present application provides a service recommendation method, device, equipment, storage medium and program product, which determine the services displayed on the service display interface by combining a large number of user factors, improve the stability and hit rate of the services displayed on the interface, reduce the user's operations of searching and handling services, and improve the user's operation efficiency and experience.

[0005] In a first aspect, the present application provides a service recommendation method, comprising:

[0006] Get the number of times multiple alternative services have been processed;

[0007] Determine multiple candidate services from multiple candidate services according to feedback information and handling times of multiple users on the candidate services; wherein the feedback information includes scores;

[0008] Based on the adjustment times of the candidate services, a target number of target services to be displayed is determined from a plurality of candidate services, so as to display the contents of the target number of target services on the service display interface.

[0009] In a second aspect, the present application provides a service recommendation device, comprising:

[0010] A processing times acquisition module is used to obtain the processing times of multiple alternative services;

[0011] A candidate service determination module is used to determine multiple candidate services from multiple candidate services according to the feedback information and the number of times of handling of the candidate services by multiple users; wherein the feedback information includes a score;

[0012] The target business determination module is used to determine a target number of target businesses to be displayed from multiple candidate businesses based on the number of times the candidate businesses are adjusted, so as to display the contents of the target number of target businesses on the business display interface.

[0013] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0014] Memory stores computer-executable instructions;

[0015] The processor executes the computer-executable instructions stored in the memory to implement the method provided in the first aspect of the present application.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method provided in the first aspect of the present application.

[0017] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method provided in the first aspect of the present application when executed by a processor.

[0018] The service recommendation method, device, equipment, storage medium and program product provided by the present application realizes the determination of the service to be displayed by integrating the multi-dimensional factors of a large number of users. The specific process is to determine multiple candidate services suitable for most users from multiple candidate services based on the number of times multiple candidate services are handled and the feedback information of multiple users on the candidate services, taking into account the usage frequency and user preferences of the candidate services; then, based on the number of times the candidate services are adjusted, the candidate services with more adjustments, i.e., the more popular candidate services, are used as the services finally displayed on the service display interface. It realizes the determination of a universal service display interface based on the comprehensive usage experience of all users, improves the quality, stability and hit rate of the service displayed on the interface, greatly reduces the operations required for users to find the services they want to handle, improves the user's operating efficiency and experience, and at the same time, effectively avoids the problem of large differences in the service display interface caused by the use of a single user behavior to customize the service display interface, and reduces the complexity of system maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] Figure 1 A schematic diagram of an application scenario provided in an embodiment of the present application;

[0021] Figure 2 A flowchart of a service recommendation method provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of another service recommendation method provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of a business navigation bar is provided for an embodiment of the present application;

[0024] Figure 5 A schematic diagram of a menu bar provided in an embodiment of the present application;

[0025] Figure 6 A flowchart of another service recommendation method provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of the structure of a business recommendation device provided in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0030] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0032] It should be noted that the business recommendation method, device, equipment, storage medium and program product of the present application can be used in the field of financial technology or other related fields, and can also be used in any field other than the field of financial technology or other related fields. The application field of the business recommendation method, device, equipment, storage medium and program product of the present application is not limited.

[0033] In order to guide users to quickly find the services they need, the business display interface of the banking and financial system often requires selection of the displayed business content. At present, based on the experience of bank staff, core and commonly used services can be recommended to users on the business display interface; or, based on the user's history records and preferences, the business content displayed on the business display interface can be dynamically adjusted to generate a personalized business display interface.

[0034] However, the business display interface generated based on the experience of bank staff cannot meet the needs of different users, lacks flexibility, affects user experience, and in order to meet the needs of more users, it may try to display too much business content, resulting in information overload; and personalized business display interfaces often require complex algorithms and data processing capabilities to analyze user behavior and adjust content in real time, which increases the complexity of system maintenance and management, and is only for a single user and is not universal. At the same time, different businesses may be recommended to the same user when used, which is not conducive to enhancing user familiarity.

[0035] In response to the above problems, an embodiment of the present application provides a service recommendation method, which combines the usage and feedback information of multiple users on each service to determine the content of the target service displayed on the service display interface. Specifically, based on the number of times each candidate service is handled and the feedback information of multiple users on each candidate service, such as ratings, the more commonly used and high-quality candidate services are determined, and on the basis of considering the user's frequency of use and satisfaction with each service, the service that is finally displayed on the service display interface is determined from the candidate services in combination with the number of adjustments to the service. It is possible to determine the services displayed on the service display interface based on multi-dimensional factors of a large number of users, improve the quality, stability and hit rate of services displayed on the interface, greatly reduce the operations required for users to find services, improve user operation efficiency and experience, and at the same time, avoid the problem of large differences in the service display interface caused by customizing the service display interface based on a single user behavior, making it easier to develop and maintain the system.

[0036] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1 As shown, the business recommendation method provided by the present application can be applied to the banking and financial system. Since there are many banking businesses, such as liability business, asset business and intermediary business, developers can store the configuration information and historical records corresponding to each banking business in the system database; the business recommendation device communicates with the system database to obtain the configuration information and historical records of each banking business, and through the business recommendation method provided by the present application, determine the banking business to be displayed on the business display interface; the business display interface opened by the software of the banking and financial system installed on the user terminal displays the relevant content of the banking business determined to be displayed for the user to browse and operate, such as handling the displayed banking business. At the same time, the user's usage record can be transmitted to the system database to facilitate the guidance of the banking and financial system for improvement.

[0037] The user terminal is a device for users to interact with the banking and financial system, which can be a mobile phone, a bank terminal, a computer, etc. The business display interface is the software interface opened when the user interacts with the terminal.

[0038] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0039] Figure 2 The method provided in this embodiment can be executed by an electronic device with corresponding data processing capabilities, such as the aforementioned processor, such as Figure 2As shown, the service recommendation method includes the following steps:

[0040] Step S201, obtaining the processing times of multiple candidate services.

[0041] Multiple alternative businesses can be part or all of the multiple businesses provided in any system, such as a banking and financial system or a shopping system. Taking the financial system as an example, the alternative businesses are businesses carried out based on financial services, including liability businesses, asset businesses, and intermediary businesses. Each type of business also includes multiple sub-businesses. For example, liability businesses include deposit businesses, loan businesses, etc.; asset businesses include loan businesses, investment businesses, etc.; intermediary businesses include transfer and remittance businesses, credit card services, etc.

[0042] Exemplarily, the candidate service may be a relatively core service among the services carried out by the system, or a service with a large number of users.

[0043] The number of times a service is handled specifically refers to the number of times a service is handled within a unit time. The unit time can be one day, 12 hours, or other values, and is a configurable parameter.

[0044] The number of times each alternative service is processed can be counted in real time to obtain the corresponding relationship between the alternative service and the number of times processed, and the corresponding relationship is stored in the system database. When the number of times the alternative service is processed needs to be read, the current number of times the alternative service is processed is read from the system database using the service identifier of the alternative service as an index.

[0045] In some embodiments, each time an alternative service is handled, it can be recorded as a handling event, and the handling event can be obtained through the log recorded by the user terminal. Based on the handling time of the handling event and the corresponding alternative service, the number of handling events of the same alternative service per unit time is counted to obtain the handling times of the alternative service.

[0046] Step S202: Determine multiple candidate services from multiple candidate services according to the feedback information and the number of times of handling of the candidate services by multiple users.

[0047] The user feedback information on the alternative service refers to the feedback on the alternative service provided by the user who has used the alternative service within a certain period of time based on the user experience, including the rating.

[0048] In some embodiments, the feedback information may include other information in addition to the rating, such as user experience, product performance, improvement suggestions, etc.

[0049] The rating is a quantitative result of the user's evaluation of the service, for example, it can be a numerical score between 0 and 5.

[0050] The rating of an alternative service provided by a user may be one, i.e., a comprehensive rating of the alternative service as a whole by the user, or multiple, i.e., the rating includes multiple ratings of the alternative service by the user on multiple aspects, such as user experience, product performance, service interface, etc.

[0051] Specifically, the frequency of use of the alternative services can be determined according to the number of times the alternative services are handled; the evaluation score of the alternative services can be determined according to the scores of multiple users on the alternative services; and the candidate services can be determined from multiple alternative services based on the evaluation scores of the alternative services and the frequency of use of the alternative services. The candidate services are alternative services with high frequency of use and evaluation scores.

[0052] The method for determining multiple candidate services can be based on the scores of multiple users on the candidate services and the number of times the candidate services are handled, and the candidate services with high handling times and high scores can be determined as candidate services. Specifically, the statistical values ​​of the scores in multiple feedback information can be calculated, such as the average value, median value, maximum value, minimum value, variance, and the proportion of scores below a certain score, etc. According to the statistical values ​​of the scores and the number of times they are handled, a comprehensive business evaluation index is calculated; through the business evaluation index, the candidate services are screened from multiple candidate services.

[0053] Multiple alternative businesses can be ranked according to the business evaluation index of the alternative business, and a preset number of alternative businesses ranked high can be selected as candidate businesses, wherein the preset number is greater than or equal to the number of businesses that can be displayed on the business display interface. Alternative businesses whose business evaluation index is greater than or equal to a preset value can also be selected as candidate businesses, wherein the preset value can be a fixed value determined based on experience, or a dynamic value determined based on the business evaluation index of multiple alternative businesses, such as the average value of the business evaluation index of multiple alternative businesses.

[0054] In some embodiments, the feedback information may include evaluation content in addition to the score. The evaluation content in the feedback information may also be judged for validity to eliminate feedback information with invalid evaluation content. Specifically, the keywords and semantic structures of the evaluation content may be identified and classified through natural language processing technology, and the evaluation content may be divided into appropriateness evaluation, meaningless evaluation, and malicious evaluation. For example, when evaluation content containing common spam words, links, or inappropriate language is identified, it is considered a malicious evaluation; when evaluation content that does not conform to normal grammar or logic is identified, it is considered a meaningless evaluation. Among them, meaningless evaluations and malicious evaluations often have no reference value, and only feedback information corresponding to appropriateness evaluations may be retained. The scores in the feedback information corresponding to the appropriateness evaluation are used to determine candidate businesses.

[0055] When the proportion of low scores in multiple feedback information of a candidate service is high, that is, the proportion of scores below a certain threshold is high, the candidate service that needs to be improved can be determined based on the evaluation content in the low-scoring feedback information. For example, if a candidate service is handled many times, but the user repeatedly describes the business process as cumbersome in the evaluation content of the feedback information of the candidate service, a process simplification prompt for the candidate service can be generated.

[0056] Optionally, based on the feedback information and the number of times of handling of the candidate services by multiple users, multiple candidate services are determined from the multiple candidate services, including:

[0057] Based on the scores of multiple users on the alternative services, an average score of the alternative services is determined; based on the average score and the number of times the alternative services are processed, multiple candidate services are determined from the multiple alternative services.

[0058] The multiple users may be all users who have rated the candidate services, or when the total number of users is greater than m, the multiple users may be m users who have recently rated the candidate services, where m is a positive integer, such as 100, 500 or other values.

[0059] Exemplarily, the candidate services may be screened based on the average score and the number of times of handling, for example, the candidate services with a lower average score or a smaller number of times of handling may be deleted, and the remaining candidate services may be used as candidate services.

[0060] Specifically, since the amount of feedback information on the candidate services from multiple users is large, the scores of the candidate services from multiple users can be averaged to obtain the average score of the candidate services, and the candidate services can be determined using the average score and the number of transactions. Using an average score can simplify the data processing process, and the average score can also represent the overall satisfaction of users with the candidate services, thereby improving the efficiency and accuracy of candidate service screening.

[0061] If the number of scores in the feedback information is 1, that is, a comprehensive score, then an average score of the alternative business can be calculated based on the scores of multiple users on the alternative business, and the candidate business can be determined from the multiple alternative businesses based on the average score and the number of times the alternative business is handled. If there are multiple scores in a piece of feedback information, that is, the score in the feedback information includes scores in multiple aspects, then the average score of each aspect can be calculated based on the scores of the alternative business in various aspects, and then the candidate business can be determined from the multiple alternative businesses based on the average or weighted average of the average scores of the alternative business in various aspects and the number of times the alternative business is handled.

[0062] Different weights are assigned to each aspect according to its relevance to the business recommendation. For example, assuming there are scores for user experience, product performance, and business interface, the user experience and product performance aspects are more relevant to the business recommendation, so they can be assigned a higher weight; the business interface aspect is less relevant to the business recommendation, so it can be assigned a lower weight.

[0063] Specifically, based on the average score and number of times the alternative businesses are handled, the business evaluation indicators of the alternative businesses are determined, and the candidate businesses are determined from the alternative businesses through the business evaluation indicators of the alternative businesses. The business evaluation indicators can be calculated by weighted sum of the average score and the number of times the business is handled, and the weight coefficients of the average score and the number of times the business is handled are adjusted according to specific needs. More factors can also be introduced, such as user weights, time factors, etc. Before calculating the business evaluation indicators, the average score and the number of times the business is handled can also be standardized, so as to determine the business evaluation indicators based on the standardized average score and the number of times the business is handled.

[0064] For example, assume that there are N candidate services, where N is a positive integer. The average score and number of times the i-th candidate service is handled are P i and C i , where i is a positive integer less than or equal to N. The service evaluation index Q of the i-th candidate service i It can be expressed as: , where λ 1 With λ 2 All are weight coefficients. Sort the candidate businesses in descending order of the business evaluation index, and select the top ranked candidate businesses as candidate businesses, such as the top 10 candidate businesses. You can also calculate the average value of the business evaluation index Q p , select the business evaluation index greater than the average value Q p The alternative businesses are candidate businesses.

[0065] By determining the average score of the candidate services, the user's satisfaction with the candidate services is evaluated intuitively and comprehensively, and the candidate services are determined based on the average score, thereby improving the efficiency and accuracy of determining the candidate services.

[0066] Step S203 : determining a target number of target businesses to be displayed from a plurality of candidate businesses based on the number of times the candidate businesses are adjusted, so as to display the contents of the target number of target businesses on the business display interface.

[0067] The number of adjustments specifically refers to the total number of times the display position of the candidate service is adjusted to the service display interface within a unit time, that is, the total number of times the candidate service is displayed on the service display interface within a unit time. The number of adjustments of the candidate service can be obtained through historical records.

[0068] The target number to be displayed specifically refers to the number of services displayed on the service display interface. The target number needs to be determined based on the space of the service display interface and the arrangement of elements to ensure that the content of the target number of target services can be displayed normally.

[0069] If a certain service is adjusted to the service display interface multiple times, it means that the service is a recent popular service and should be displayed first. Therefore, when determining the target number of target services to be displayed on the service display interface, the target number of target services to be displayed can be determined from multiple candidate services based on the number of times the candidate services have been adjusted. Specifically, multiple candidate services can be sorted or screened based on the number of times the candidate services have been adjusted and the aforementioned service evaluation indicators, and the target number of target services can be determined from multiple candidate services.

[0070] If the number of candidate services is less than or equal to the target number, each candidate service may be directly determined as a target service to be displayed.

[0071] Furthermore, the positions of the target number of target businesses on the business display interface can be determined based on the number of adjustments of the candidate businesses and the business evaluation indicators; more factors can also be introduced, such as the interaction information between the current user and the target business, to determine the positions of the target number of target businesses based on the interaction information, the number of adjustments and the business evaluation indicators.

[0072] A service recommendation method provided in the embodiment of the present application realizes the determination of services to be displayed by integrating multi-dimensional factors of a large number of users. The specific process is to determine multiple candidate services suitable for most users from multiple candidate services based on the number of times multiple candidate services are handled and the feedback information of multiple users on the candidate services, taking into account the usage frequency and user preferences of the candidate services; then, based on the number of times the candidate services are adjusted, the candidate services with more adjustments, i.e., the more popular candidate services, are used as the services finally displayed on the service display interface. It realizes the determination of a universal service display interface based on the comprehensive usage experience of all users, improves the quality, stability and hit rate of services displayed on the interface, greatly reduces the operations required for users to find the services they want to handle, improves the user's operating efficiency and experience, and at the same time, effectively avoids the problem of large differences in the service display interface caused by the use of a single user behavior to customize the service display interface, and reduces the complexity of system maintenance and management.

[0073] Figure 3 A flowchart of another service recommendation method provided in an embodiment of the present application. Figure 2 Further refinement of steps S202 and S203. Figure 3 As shown, the service recommendation method provided in this embodiment may specifically include the following steps:

[0074] Step S301, obtaining the processing times of multiple candidate services and feedback information of multiple users on the candidate services.

[0075] Step S302: for each piece of feedback information, determine the type of the feedback information based on the evaluation content of the feedback information.

[0076] In this embodiment, the feedback information includes evaluation content in addition to the score. The evaluation content refers to the comments provided by the user in natural language when giving the score, and the evaluation content may include the user's suggestions for the alternative services, experience sharing, etc.

[0077] The evaluation content can not only reflect the user's satisfaction with the alternative services, but also reflect the problems or deficiencies of the alternative services. Compared with a quantitative score, the evaluation content provides more information. Based on the evaluation content in the feedback information, the feedback information can be classified to facilitate targeted processing and analysis of different types of feedback information.

[0078] The types of feedback information can be classified according to the aspects of the candidate services that need to be improved as described by the user in the evaluation content, for example, feedback information on processing efficiency, feedback information on service convenience, feedback information on service interface, and feedback information on service. The types of feedback information are not limited and are only exemplary.

[0079] The keywords in the evaluation content can be extracted by natural language processing technology, and the type of feedback information can be determined based on the keywords. The correspondence between keywords and types of feedback information can be stored in advance, so that the extracted keywords can be input into the correspondence to determine the type of feedback information. The type of feedback information can also be predicted based on the evaluation content by using a large natural speech processing model or other classification models.

[0080] Step S303, determining multiple candidate services from multiple candidate services according to the number of times the candidate services are handled, the scores of multiple users on the candidate services, the types of feedback information, and the number of occurrences of the same type of feedback information.

[0081] In this embodiment, the lower the score of the feedback information of a certain type of candidate service, the worse the performance of the candidate service in the corresponding aspect of the type. Therefore, in terms of service recommendation, the feedback information of the type associated with the service recommendation can be analyzed and processed.

[0082] Exemplarily, the types related to service recommendation may include feedback information on service convenience, feedback information on user interface, and the like.

[0083] Specifically, according to the types of feedback information of multiple users on the alternative services, the number of occurrences of the same type of feedback information of the alternative services is counted. According to the average or sum of the scores in the feedback information of a certain type of the alternative services and the number of occurrences of the feedback information of this type, the score of the alternative services under this type is determined, and according to the scores of the alternative services in each type, the average score of the alternative services is determined. Based on the average feedback score and the number of times the alternative services are handled, the business evaluation index of the alternative services is determined, and according to the business evaluation index of the alternative services, multiple candidate services are determined from multiple alternative services.

[0084] The service evaluation index Q of the i-th candidate service i It can be expressed as:

[0085]

[0086] Among them, C i is the number of times the i-th alternative business is handled; P i is the average feedback score of the i-th alternative business; C is the sum of the handling times of N alternative businesses; N is the total number of alternative businesses, i is a positive integer less than or equal to N; λ is the proportionality coefficient.

[0087] Exemplarily, a candidate service whose service evaluation index is greater than an average value of service evaluation indexes of a plurality of candidate services may be determined as a candidate service.

[0088] Optionally, based on the evaluation content of the feedback information, the type of the feedback information is determined, including:

[0089] For feedback information in which the score of the candidate business is lower than the preset score, the low-score type of the feedback information is determined based on the evaluation content of the feedback information.

[0090] Accordingly, according to the number of times the candidate services are handled, the scores of the candidate services by multiple users, the types of feedback information, and the number of occurrences of the same type of feedback information, multiple candidate services are determined from the multiple candidate services, including:

[0091] Based on the number of feedbacks for each type of low score, the weights of the scores corresponding to each type of low score are determined; based on the scores and weights of the feedback information of the alternative businesses from multiple users, the weighted scores of the alternative businesses are determined; wherein the weights of the scores in the feedback information other than the feedback information of the low score types are preset weights; based on the weighted scores and the number of times handled, multiple candidate businesses are determined from multiple alternative businesses.

[0092] When the score in the feedback information of the candidate service is higher than the preset score, it means that the user is relatively satisfied with the candidate service. For feedback information with a score lower than the preset score, the low score type of the feedback information is determined based on the evaluation content of the feedback information. The method for determining the low score type can refer to the method for determining the type of feedback information. Here, since the feedback information is low-scoring, the type is recorded as a low score type.

[0093] The preset score can be determined based on statistical results of scores in a large amount of feedback information, or can be determined based on experience. For example, the preset score is 4, and there is no limitation on the value and determination method of the preset score.

[0094] According to the feedback information of each low-scoring type related to the service recommendation, the number of feedbacks is obtained, that is, the number of feedback information of the low-scoring type within a certain period of time. If the number of feedbacks of the feedback information of the low-scoring type is large, it can be indicated that a large number of users are dissatisfied with this aspect of the alternative service. According to the number of feedbacks of the feedback information of each low-scoring type of the alternative service, different weights can be assigned to the scores corresponding to each low-scoring type, so as to weight the scores of the feedback information of the alternative service.

[0095] Feedback information other than low-scoring feedback information may be regarded as feedback information with higher user satisfaction, and its weight may be determined to be higher than the weight of low-scoring feedback information, such as a preset weight.

[0096] Based on the corresponding weights, the scores of each type of low-scoring feedback information of the same candidate service and the scores of feedback information other than the low-scoring feedback information are weighted to obtain the average score of the candidate service. Thus, based on the average score and the number of times the candidate service is handled, a candidate service is screened from multiple candidate services.

[0097] By classifying feedback information with low scores and assigning matching weights to the scores of different types of low-scoring feedback information, the score calculation of alternative businesses is realized through score weighting, which improves the accuracy of score calculation. At the same time, the score calculation takes into account the feedback information of a large number of users, avoiding malicious scoring by a single user that leads to a low overall score.

[0098] Step S304: for each candidate service, obtain the interaction information of the current user for the candidate service.

[0099] The interaction information includes interaction duration, interaction times, and interaction content.

[0100] The current user is the user who needs to make a service recommendation, that is, the target service to be displayed needs to be determined for the service display interface opened by the current user. After determining multiple candidate services, the interaction information of the current user for each candidate service can be obtained through the historical usage record of the current user to indicate the usage of the candidate service by the current user.

[0101] Step S305 : determining a target number of target services to be displayed from a plurality of candidate services based on the interaction information and the number of adjustments, so as to display the contents of the target number of target services on the service display interface currently opened by the user.

[0102] Based on the interaction duration and number of interactions of each candidate service, the interaction value of the current user for each candidate service can be determined; based on the number of adjustments of each candidate service, the display value of each candidate service can be determined. According to the interaction value of each candidate service for the current user and the display value of each candidate service for multiple users, a target number of target services to be displayed can be determined from multiple candidate services, so that the determined target services combine the usage experience of multiple users and the current user.

[0103] Interaction value H i It can be expressed as:

[0104]

[0105] Display value Z i It can be expressed as:

[0106]

[0107] Among them, F i is the interaction time between the current user and the i-th candidate service; K i is the number of interactions between the current user and the i-th candidate service; θ is the proportionality coefficient; Q i is the business evaluation index of the i-th candidate business; T i is the adjustment times of the ith candidate service; V i is the interactive response speed of the i-th candidate service; λ is the preset proportional coefficient; n is the total number of candidate services, and i is a positive integer less than or equal to n.

[0108] First, the target number of target services to be displayed can be determined according to the display value of each candidate service. Then, the target number of target services to be displayed can be sorted according to the interaction value of each candidate service, and the contents of the target number of target services can be displayed in a certain order on the service display interface currently opened by the user. The contents of the target services are images or texts used to concisely and clearly represent the service functions, and can be service icons or service names, etc.

[0109] It is also possible to determine a target score for each candidate service based on the interaction value and display value of each candidate service, and determine a target number of target services to be displayed based on the target score.

[0110] Optionally, based on the interaction information and the number of adjustments, a target number of target services to be displayed is determined from multiple candidate services, including:

[0111] Based on the interaction information and the number of adjustments, a target score for each candidate service is determined; multiple candidate services are sorted in descending order of the target scores; based on the sorting result, a target number of target services to be displayed is determined.

[0112] The target score is used to evaluate the usage of each candidate service for multiple users and the current user, and can be determined based on the interaction value and display value of each candidate service.

[0113] For example, the target score can be determined as the sum of the interaction value and the display value of each candidate service. The candidate services are sorted from high to low according to the target score; and the target services with the highest target quantity are displayed first in the service display interface.

[0114] By combining the interaction information of the current user with the number of times multiple users have adjusted the target service, a more comprehensive and flexible service display interface can be provided to the user. While meeting the usage needs of a single user, the determined target service is also applicable to most users.

[0115] In this embodiment, by introducing the type of feedback information, feedback information with a higher relevance to the business recommendation can be obtained, and by analyzing the feedback information, the situation of each target business can be accurately evaluated, which helps to accurately determine the candidate business; and by obtaining the current user's interaction information on each candidate business, the determined target business not only combines the usage experience of multiple users, but also combines the usage experience of the current user. On the basis of the universality of the determined target business, dynamic adjustments are made according to the current user, which can enable the current user to find the business he needs more quickly, thereby improving user operation efficiency and user experience.

[0116] Optionally, after determining the target number of target services to be displayed, the service recommendation method may further include:

[0117] Obtain display content of each target business; generate a business navigation bar based on the display content of each target business, so as to display the business navigation bar on the business display interface.

[0118] After determining the target number of target services to be displayed, the target services need to be displayed. The display content of the target services can enable the user to quickly locate the location of the target services, and the display content may include service icons, services, and the like.

[0119] A business navigation bar is generated according to the display content of each target business and the space of the business display interface, and the display content is arranged in the business navigation bar to be displayed to the user.

[0120] For example, Figure 4 A schematic diagram of a business navigation bar is provided for an embodiment of the present application. Figure 4 As shown, in order to enable users to quickly locate the interface of the service they want to operate, the service navigation bar is generally located in a more prominent position on the service display interface, such as the upper part of the service display interface. The display content of the target number of target services to be displayed is generated to the relevant position of the service navigation bar, and by clicking on the position, the user is provided with the access path to the service.

[0121] The displayed content can be arranged according to the order of each target business, that is, the target business with a higher order is placed in front of the business navigation bar. According to the user's usage habits, it can be arranged from left to right or from top to bottom.

[0122] During the arrangement process, related target businesses can also be arranged together so that users can quickly find the information they need. For example, sub-businesses related to liability businesses can be arranged together so that users can quickly locate them when using them.

[0123] Through the displayed content of the business, users can quickly locate the interface of the business and understand some attribute information of the target business, such as the name, so that users can decide whether to operate the business. At the same time, by generating a business navigation bar, users can quickly find the business they need to operate, providing users with a clear and convenient access path and improving the user experience.

[0124] Optionally, the business navigation bar also includes more buttons, and the method also includes: determining a preset number of alternative businesses from the alternative businesses excluding the target number of target businesses; generating a menu bar corresponding to more buttons based on the display content of the preset number of alternative businesses, so as to display the menu bar corresponding to more buttons when the more buttons are triggered.

[0125] The target number of target businesses to be displayed is determined to be only commonly used businesses. In order to provide comprehensive services, businesses other than the target number of target businesses need to be displayed on the business display interface. You can use the drop-down menu to hide other businesses.

[0126] Specifically, more buttons can be generated in the business navigation bar, each button corresponds to a menu bar, and each menu bar can contain a preset number of alternative businesses. Among the alternative businesses excluding the target number of target businesses, a preset number of alternative businesses are determined, and the display contents of the preset number of alternative businesses are displayed in the menu bar.

[0127] For example, Figure 5 A schematic diagram of a menu bar provided in an embodiment of the present application. Figure 5 As shown, the More button in the business navigation bar corresponds to the More button. When you click the More button, the following Figure 5 A button may correspond to multiple menu bars, each menu may contain a preset number k of display contents of alternative services, and each display content corresponds to an access path of the alternative service. Figure 5 This is only for illustrative purposes, and the number of further buttons and the number of menu bars are not limited herein.

[0128] Related alternative businesses can be placed in the same menu bar according to their relevance; the arrangement of the alternative businesses in the same menu bar is similar to the arrangement of the target number of target businesses to be displayed, which will not be described in detail here.

[0129] By generating menu bars corresponding to more buttons, other alternative services can be hidden in the main interface of the service display interface, which can keep the service navigation bar simple while providing more choices.

[0130] Figure 6 A flowchart of another service recommendation method provided in an embodiment of the present application is shown as follows: Figure 6 As shown, in order to more clearly understand the service recommendation method provided by this embodiment, this embodiment specifically describes the method.

[0131] Step S601, obtaining the processing times of multiple candidate services.

[0132] Step S602: Determine multiple candidate services from multiple candidate services according to the feedback information and the number of times of handling of the candidate services by multiple users.

[0133] The business evaluation index is calculated based on the scores of multiple users' feedback information on the candidate business and the number of times the business is handled. The candidate business whose business evaluation index is greater than or equal to the average value of the business evaluation index is determined as the candidate business.

[0134] Step S603 : determining a target number of target businesses to be displayed from a plurality of candidate businesses based on the number of times the candidate businesses are adjusted, so as to display the contents of the target number of target businesses on the business display interface.

[0135] According to the interaction information and adjustment times of the current user, a target score of each candidate service is determined, and according to the target score, a target number of target services to be displayed are determined from multiple candidate services, and the determined target services are sorted.

[0136] Step S604: Obtain display content of each target service.

[0137] The display content of the target business included in the banking and financial system is obtained to guide user operations on the business display interface.

[0138] Step S605: Generate a business navigation bar based on the display content of each target business.

[0139] A business navigation bar is generated based on the included target businesses and the displayed contents of the target businesses to help users quickly find the target businesses they need.

[0140] Step S606: Display the target quantity of target services on the service display interface.

[0141] The display contents of the target number of target services determined in the above step S603 are displayed in a certain order in the service navigation bar.

[0142] Step S607: determining a preset number of candidate services from the candidate services excluding the target number of target services; and generating menu bars corresponding to more buttons based on the displayed contents of the preset number of candidate services.

[0143] A corresponding menu bar is generated under the multiple buttons of the business navigation bar, for displaying the display contents of target businesses other than the target number of target businesses in step S606 after clicking the button.

[0144] The technical effect of the service recommendation method provided in the embodiment of the present application is similar to that of the method provided in any of the above embodiments of the present application, and this embodiment will not be repeated here.

[0145] Figure 7 A schematic diagram of the structure of a business recommendation device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the service recommendation device provided in this embodiment includes: a processing times acquisition module 701, a candidate service determination module 702 and a target service determination module 703.

[0146] The processing times acquisition module 701 is used to obtain the processing times of multiple alternative services; the candidate service determination module 702 is used to determine multiple candidate services from multiple alternative services based on the feedback information and processing times of multiple users on the alternative services, wherein the feedback information includes scores; the target service determination module 703 is used to determine the target number of target services to be displayed from multiple candidate services based on the adjustment times of the candidate services, so as to display the contents of the target number of target services on the service display interface.

[0147] Optionally, the candidate service determination module 702 is specifically configured to:

[0148] Based on the scores of multiple users on the alternative services, an average score of the alternative services is determined; based on the average score and the number of times the alternative services are processed, multiple candidate services are determined from the multiple alternative services.

[0149] Optionally, the candidate service determination module 702 is specifically configured to:

[0150] The feedback information also includes evaluation content. For each alternative business, feedback information on the alternative business from multiple users is obtained; for each piece of feedback information, the type of feedback information is determined based on the evaluation content of the feedback information; and multiple candidate businesses are determined from multiple alternative businesses based on the number of times the alternative business is handled, the scores of the alternative business by multiple users, the type of feedback information, and the number of times the same type of feedback information appears.

[0151] Optionally, the candidate service determination module 702 is specifically configured to:

[0152] For feedback information in which the score of alternative services is lower than the preset score, the low-score type of the feedback information is determined based on the evaluation content of the feedback information; the weight of the score corresponding to each low-score type is determined based on the number of feedbacks for each low-score type; the weighted score of the alternative services is determined based on the scores of multiple users' feedback information on the alternative services and their weights; wherein the weight of the score in the feedback information excluding the feedback information of the low-score type is the preset weight; and multiple candidate services are determined from multiple alternative services based on the weighted scores and the number of times of handling.

[0153] Optionally, the target service determination module 703 includes an interaction information acquisition unit and a target service determination unit, wherein:

[0154] The interaction information acquisition unit is used to obtain the interaction information of the current user for each candidate service; the target service determination unit is used to determine the target number of target services to be displayed from multiple candidate services based on the interaction information and the number of adjustments, so as to display the contents of the target number of target services on the service display interface opened by the current user.

[0155] Optionally, the target service determination unit is specifically used to:

[0156] Based on the interaction information and the number of adjustments, a target score for each candidate service is determined; multiple candidate services are sorted in descending order of the target scores; based on the sorting result, a target number of target services to be displayed is determined.

[0157] Optionally, the business recommendation device further includes:

[0158] A business navigation bar generation module is used to obtain the display content of each target business, and generate a business navigation bar based on the display content of each target business, so as to display the business navigation bar on the business display interface; a menu bar generation module is used to determine a preset number of target businesses from target businesses other than a target number of target businesses, and the business navigation bar includes more buttons. Based on the display content of the preset number of target businesses, menu bars corresponding to more buttons are generated, so that menu bars corresponding to more buttons are displayed when more buttons are triggered.

[0159] The service recommendation device provided in the embodiment of the present application can be used to execute the technical solution of the service recommendation method provided in any of the above embodiments of the present application. The implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0160] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device of this embodiment may include: at least one processor 801; and a memory 802 communicatively connected to the at least one processor; wherein the memory 802 stores instructions executable by the at least one processor 801, and the instructions are executed by the at least one processor 801 so that the electronic device executes a method as in any of the above embodiments.

[0161] Optionally, the memory 802 may be independent or integrated with the processor 801 .

[0162] When the memory 802 is independently provided, the device further includes a bus for connecting the memory 802 and the processor 801 .

[0163] The implementation principle and technical effects of the electronic device provided in this embodiment can be found in the aforementioned embodiments and will not be described in detail here.

[0164] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the method provided in any of the aforementioned embodiments can be implemented.

[0165] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method provided in any of the above embodiments when executed by a processor.

[0166] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0167] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0168] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0169] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0170] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc.

[0171] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0172] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0173] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0174] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A business recommendation method, characterized in that: include: Get the number of times multiple alternative services have been processed; Determine a plurality of candidate services from the plurality of candidate services according to the feedback information of the plurality of users on the candidate services and the number of times of handling; wherein the feedback information includes a score; Based on the number of times the candidate services are adjusted, a target number of target services to be displayed is determined from the multiple candidate services, so as to display the contents of the target number of target services on the service display interface.

2. The method according to claim 1, characterized in that Determining a plurality of candidate services from the plurality of candidate services according to the feedback information of the plurality of users on the candidate services and the number of times of handling the candidate services includes: Determining an average score of the candidate services based on scores of the candidate services by multiple users; Based on the average score and the number of times of handling, the multiple candidate services are determined from the multiple candidate services.

3. The method according to claim 1, characterized in that The feedback information also includes evaluation content. According to the feedback information of multiple users on the candidate services and the number of times of handling, multiple candidate services are determined from the multiple candidate services, including: For each of the candidate services, obtaining feedback information of multiple users on the candidate services; For each piece of feedback information, determining the type of the feedback information based on the evaluation content of the feedback information; The multiple candidate services are determined from the multiple candidate services according to the number of times the candidate services are handled, scores of the candidate services by multiple users, the types of the feedback information, and the number of times the same type of feedback information appears.

4. The method according to claim 3, characterized in that Determining the type of the feedback information based on the evaluation content of the feedback information includes: For feedback information in which the score of the candidate service is lower than a preset score, determining the low-score type of the feedback information based on the evaluation content of the feedback information; Determining the plurality of candidate services from the plurality of candidate services according to the number of times the candidate services are handled, scores of the candidate services by a plurality of users, the type of the feedback information, and the number of times the same type of feedback information appears, includes: Based on the number of feedbacks for each type of low score, determine the weight of the score corresponding to each type of low score; Determine a weighted score of the candidate service based on scores and weights of feedback information of the candidate service from multiple users; wherein the weight of the scores in the feedback information excluding the feedback information of the low-scoring type is a preset weight; Based on the weighted scores and the number of times of handling, the multiple candidate services are determined from the multiple candidate services.

5. The method according to claim 1, characterized in that Based on the number of times the candidate services are adjusted, determining a target number of target services to be displayed from the multiple candidate services, so as to display the contents of the target number of target services on the service display interface, including: For each of the candidate services, obtaining interaction information of the current user for the candidate service; Based on the interaction information and the adjustment times, a target number of target services to be displayed is determined from the multiple candidate services, so as to display the contents of the target number of target services on the service display interface opened by the current user.

6. The method according to claim 5, characterized in that Determining a target number of target services to be displayed from the multiple candidate services based on the interaction information and the number of adjustments includes: Determining a target score for each of the candidate services based on the interaction information and the number of adjustments; Sorting the multiple candidate services in descending order of the target scores; Based on the sorting result, a target number of target services to be displayed is determined.

7. The method according to any one of claims 1 to 6, characterized in that: After determining the target number of target services to be displayed, the method further includes: Obtaining display content of each of the target services; Based on the display content of each of the target services, a service navigation bar is generated to display the service navigation bar on the service display interface.

8. The method according to claim 7, characterized in that The business navigation bar includes more buttons, and the method further includes: Determining a preset number of candidate businesses from the candidate businesses excluding the target number of target businesses; Based on the display contents of the preset number of candidate services, a menu bar corresponding to the more buttons is generated, so that the menu bar corresponding to the more buttons is displayed when the more buttons are triggered.

9. A business recommendation device, comprising: A processing times acquisition module is used to obtain the processing times of multiple alternative services; A candidate service determination module, configured to determine a plurality of candidate services from the plurality of candidate services according to feedback information of a plurality of users on the candidate services and the number of times the services are handled; wherein the feedback information includes a score; The target business determination module is used to determine a target number of target businesses to be displayed from the multiple candidate businesses based on the number of adjustment times of the candidate businesses, so as to display the contents of the target number of target businesses on the business display interface.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images