Service optimization method and device, equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of data analysis, is applied to a service recommendation optimization scene, and relates to a service optimization method, device and equipment and a storage medium thereof. Extracting multi-dimensional key feature data respectively corresponding to all historical users; calculating dynamic scores respectively corresponding to all historical users according to an estimation strategy; based on the dynamic score and a preset user group division strategy, performing user group division on all historical users; and performing service optimization on the target user by adopting different preset service optimization strategies according to different user groups to which the target user belongs. According to the method and the device, the service response data of all historical users are acquired, and the response conditions of different users to different right services can be known in time, so that the right response habits of the users and user groups are conveniently combined to carry out right service optimization and adjustment, and more scientific, reasonable and personalized right services are formulated.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and is applied to service recommendation optimization scenarios, and in particular to a service optimization method, device, equipment, and storage medium thereof. Background Art

[0002] The service industry is a highly competitive market. Various service companies have sprung up, and product homogeneity is becoming increasingly serious. In such a market environment, how to accurately locate potential customers and convert them into actual customers, as well as maintain existing mature customers, has become the focus of attention for all service companies.

[0003] At the same time, consumers' demand for services has also become more diversified and personalized. They are no longer satisfied with standardized products, but are pursuing customized services that better meet their needs. However, traditional strategy models can no longer meet this change in demand. How to formulate more scientific, reasonable and personalized rights and interests services based on users has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a service optimization method, device, equipment and storage medium thereof, so as to realize how the existing service industry can formulate more scientific, reasonable and personalized rights and interests services in combination with users.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a service optimization method, which adopts the following technical solutions:

[0006] A service optimization method comprises the following steps:

[0007] Get the service response data of all historical users;

[0008] Extracting multi-dimensional key feature data corresponding to all historical users from the service response data, wherein the multi-dimensional key feature data includes the number of times users have received various services in the past, the number of times they have used them, the time they have received them, the time they have used them, the channels through which they have received them, and the content of the services they have received them;

[0009] According to the valuation strategies corresponding to the multi-dimensional key feature data, a gradient boosting algorithm is used to calculate the dynamic scores corresponding to all the historical users;

[0010] Dividing all the historical users into user groups based on the dynamic scores and a preset user group division strategy;

[0011] According to the different user groups to which the target users belong, different preset service optimization strategies are adopted to optimize the services for the target users.

[0012] Furthermore, after executing the step of obtaining the service response data of all historical users, the method further includes:

[0013] Obtaining basic attribute data of all historical users, wherein the basic attribute data includes the user's age, gender, occupation, income level and educational background;

[0014] The static scores corresponding to all the historical users are calculated based on the basic attribute data and a preset score assignment strategy, wherein the preset score assignment strategy includes setting different scores according to the user's age, gender, occupation, income level and educational background.

[0015] Furthermore, after executing the step of extracting the multi-dimensional key feature data corresponding to all historical users from the service response data, the method further includes:

[0016] Determine the service item preferences corresponding to all the historical users according to the number of times they have received, the number of times they have used, and the service contents of various services corresponding to all the historical users;

[0017] Determine the service time preferences corresponding to all the historical users according to the receipt time and usage time of various services corresponding to all the historical users;

[0018] According to the historical receipt channels of various services respectively corresponding to all the historical users, the service channel preferences respectively corresponding to all the historical users are determined.

[0019] Furthermore, before executing the step of using the gradient boosting algorithm to calculate the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data, the method further includes:

[0020] Obtain the evaluation scores set in advance for different service items, service time, and service channels;

[0021] The step of using a gradient boosting algorithm to calculate the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data specifically includes:

[0022] Identify the service item preferences, service time preferences, and service channel preferences corresponding to all the historical users respectively;

[0023] According to the service item preferences, service time preferences and service channel preferences corresponding to all historical users, as well as the evaluation scores corresponding to different service items, service times and service channels, the XGBoost gradient boosting algorithm is used to accumulate the service item evaluation scores, service time evaluation scores and service channel evaluation scores corresponding to the same user;

[0024] The accumulated result is obtained as the dynamic score obtained by the corresponding user according to the service selection.

[0025] Furthermore, after executing the step of calculating the dynamic scores corresponding to all historical users respectively according to the valuation strategies respectively corresponding to the multi-dimensional key feature data using a gradient boosting algorithm, the method further includes:

[0026] The dynamic score and static score corresponding to the same user are accumulated to obtain the total score;

[0027] Determine whether the total score corresponding to the current user exceeds the preset score threshold;

[0028] If the total score corresponding to the current user exceeds the preset score threshold, a seat caller is assigned to the current user for service recommendation according to a preset seat allocation strategy.

[0029] Furthermore, the step of dividing all the historical users into user groups based on the dynamic scores and the preset user group division strategy specifically includes:

[0030] Identify pre-divided dynamic score intervals;

[0031] According to the pre-divided dynamic score intervals and the dynamic scores corresponding to all historical users, a mature user group, an adaptive user group and a novice user group are divided, wherein the minimum interval value of the dynamic score interval corresponding to the mature user group is greater than the maximum interval value of the dynamic score interval corresponding to the adaptive user group, and the minimum interval value of the dynamic score interval corresponding to the adaptive user group is greater than the maximum interval value of the dynamic score interval corresponding to the novice user group;

[0032] After executing the step of dividing all the historical users into user groups based on the dynamic scores and the preset user group division strategy, the method further includes:

[0033] Identify pre-defined static score intervals;

[0034] A high-value user group and a low-value user group are divided according to the pre-divided static score intervals and the static scores corresponding to all historical users, wherein the minimum value of the dynamic score interval corresponding to the high-value user group is greater than the maximum value of the dynamic score interval corresponding to the low-value user group.

[0035] Furthermore, before executing the step of optimizing the service for the target user by using different preset service optimization strategies according to the different user groups to which the target user belongs, the method further includes:

[0036] Obtain service response data of the target user;

[0037] Extracting multi-dimensional key feature data corresponding to the target user from the service response data;

[0038] According to the valuation strategies corresponding to the multi-dimensional key feature data, the dynamic score of the target user is calculated using the XGBoost gradient boosting algorithm;

[0039] Obtain basic attribute data of target users;

[0040] Calculating a static score of the target user according to the basic attribute data and the score assignment strategy;

[0041] Determining the user group to which the target user belongs according to the dynamic score of the target user and the static score of the target user;

[0042] The step of optimizing services for target users by using different preset service optimization strategies according to different user groups to which the target users belong specifically includes:

[0043] If the target user belongs to the mature user group, optimizing the service for the target user according to the target user's historical service item preference, service time preference and service channel preference;

[0044] If the target user belongs to the high-value user group, the service optimization for the target user is performed according to the service item preference, service time preference and service channel preference of all mature user groups in the high-value user group;

[0045] If the target user belongs to a low-value user group, service optimization is performed for the target user based on the service item preferences, service time preferences, and service channel preferences of all low-value user groups in the mature user group.

[0046] In order to solve the above technical problems, the embodiment of the present application also provides a service optimization device, which adopts the following technical solution:

[0047] A service optimization device, comprising:

[0048] The service response data acquisition module is used to obtain the service response data of all historical users;

[0049] A key feature data extraction module is used to extract multi-dimensional key feature data corresponding to all historical users from the service response data, wherein the multi-dimensional key feature data includes the number of times users have received various services in the past, the number of times they have used them, the time they have received them, the time they have been used, the channels they have been received, and the content of the services they have been provided;

[0050] A dynamic score calculation module, used to calculate the dynamic scores corresponding to all historical users respectively using a gradient boosting algorithm according to the valuation strategies corresponding to the multi-dimensional key feature data respectively;

[0051] A user group division module, used to divide all the historical users into user groups based on the dynamic scores and a preset user group division strategy;

[0052] The service optimization module is used to optimize the service for the target user by adopting different preset service optimization strategies according to the different user groups to which the target user belongs.

[0053] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0054] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned service optimization method when executing the computer-readable instructions.

[0055] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0056] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the service optimization method described above.

[0057] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0058] The service optimization method described in the embodiment of the present application obtains the service response data of all historical users; extracts the multi-dimensional key feature data corresponding to all historical users from the service response data; calculates the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data; divides all historical users into user groups based on the dynamic scores and the preset user group division strategy; and optimizes the service for the target user using different preset service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, the present application can timely understand the response of different users to different rights and interests services, thereby facilitating the optimization and adjustment of rights and interests services in combination with the user's rights and interests response habits and user groups, and formulating more scientific, reasonable and personalized rights and interests services. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0061] Figure 2 is a flow chart of an embodiment of a service optimization method according to the present application;

[0062] Figure 3 It is a flowchart of a specific embodiment of the static score acquisition step in the service optimization method described in this application;

[0063] Figure 4 It is a flowchart of a specific embodiment of analyzing user service response preferences in the service optimization method described in this application;

[0064] Figure 5 yes Figure 2 A flowchart of a specific embodiment of step 203 is shown;

[0065] Figure 6 It is a flowchart of a specific embodiment of verifying seat allocation in the service optimization method described in this application;

[0066] Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 204 is shown;

[0067] Figure 8It is a flowchart of a specific embodiment of performing secondary group division on all historical users in the service optimization method described in this application;

[0068] Fig. 9 It is a flowchart of a specific embodiment of determining the user group to which the target user belongs in the service optimization method described in the present application;

[0069] Fig.10 yes Figure 2 A flowchart of a specific embodiment of step 205 is shown;

[0070] Fig.11 is a structural diagram of an embodiment of a service optimization device according to the present application;

[0071] Fig.12 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0072] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0073] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0074] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0075] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0076] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0077] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0078] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0079] It should be noted that the service optimization method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the service optimization device is generally arranged in the terminal device.

[0080] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0081] Continue to refer Figure 2 , shows a flow chart of an embodiment of a service optimization method according to the present application. The service optimization method comprises the following steps:

[0082] Step 201, obtaining service response data of all historical users;

[0083] Specifically, the service response data can be understood as the behavioral data of the user's operations on the user side after the server side pushes or publishes the rights and interests service information to the user side. For example, in the financial field, when the target financial institution or banking institution issues vouchers or discount cards to the user, the user's selection, receipt, and use of the vouchers or discount cards, etc.

[0084] By obtaining the service response data of all historical users, we can timely understand the response enthusiasm of different users to different rights and interests services, so as to facilitate optimization and adjustment based on the user's rights and interests collection habits and formulate more personalized rights and interests services.

[0085] Step 202, extracting multi-dimensional key feature data corresponding to all historical users from the service response data, wherein the multi-dimensional key feature data includes the number of times the user has received various services in the past, the number of times used, the time of receiving, the time of use, the channel of receiving, and the content of the service;

[0086] By extracting multi-dimensional key feature data corresponding to all historical users from the service response data, it is possible to reasonably identify the users' corresponding service content preferences, service time preferences and service collection channel preferences through the users' historical collection times, usage times, collection time, usage time, collection channel and service content of various services, so as to make optimization adjustments based on the users' preferences and formulate more personalized rights and interests services.

[0087] Step 203, according to the valuation strategies corresponding to the multi-dimensional key feature data, a gradient boosting algorithm is used to calculate the dynamic scores corresponding to all the historical users;

[0088] Specifically, the use of the gradient boosting algorithm to calculate the dynamic scores corresponding to all historical users is, in fact, to first obtain the evaluation scores corresponding to different key feature dimensions of the same user, and then perform multi-dimensional accumulation to calculate the total evaluation score corresponding to the multi-dimensional key features.

[0089] In this embodiment, the valuation strategies corresponding to the multi-dimensional key feature data respectively use a gradient boosting algorithm to calculate the dynamic scores corresponding to all historical users respectively, that is, the valuation strategies corresponding to different key feature dimensions may also be different, and there is no limitation here. The valuation strategies can be freely set according to the specific data values ​​of the key feature data, which is more scientific and flexible.

[0090] Step 204, dividing all the historical users into user groups based on the dynamic scores and a preset user group division strategy;

[0091] By dividing all the historical users into user groups, it is convenient to optimize the rights and interests service recommendations for users in combination with their user groups, so as to provide users with better services.

[0092] Step 205 , optimizing services for the target users by using different preset service optimization strategies according to the different user groups to which the target users belong.

[0093] Specifically, different service optimization strategies correspond to different user groups, so as to formulate more scientific and reasonable services for users.

[0094] In this embodiment, the service response data of all historical users is obtained; the multi-dimensional key feature data corresponding to all historical users are extracted from the service response data; the dynamic scores corresponding to all historical users are calculated according to the valuation strategies corresponding to the multi-dimensional key feature data; all historical users are divided into user groups based on the dynamic scores and the preset user group division strategy; and the service of the target user is optimized by using the preset different service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, the present application can timely understand the response of different users to different rights and interests services, so as to facilitate the optimization and adjustment of rights and interests services in combination with the rights and interests response habits of users and user groups, and formulate more scientific, reasonable and personalized rights and interests services.

[0095] Continue to refer Figure 3 In some optional implementations, a static score acquisition step is also included before executing step 201. Figure 3 It is a flowchart of a specific embodiment of the static score acquisition step in the service optimization method described in this application, comprising the following steps:

[0096] Step 301, obtaining basic attribute data of all historical users, wherein the basic attribute data includes the user's age, gender, occupation, income level and educational background;

[0097] Step 302, based on the basic attribute data and a preset score assignment strategy, calculate the static scores corresponding to all the historical users, wherein the preset score assignment strategy includes setting different scores according to the user's age, gender, occupation, income level and educational background.

[0098] Specifically, the step of calculating the static scores corresponding to all the historical users respectively according to the basic attribute data and the preset score assignment strategy specifically includes: using the accumulation method to obtain the static scores corresponding to all the historical users respectively according to the basic attribute data of all the historical users, and the scores corresponding to the users' age, gender, occupation, income level and educational background.

[0099] In this embodiment, the static score is actually obtained by accumulating the user's basic attribute data through scoring. It can be understood that the user's basic attribute data will not change much compared to the user's service response data, while the user's service response data will show a large fluctuation depending on the user's interests or the increase in the number of rights and interests service issuances. Therefore, the static score is calculated based on the user's basic attribute data, and the dynamic score is subsequently calculated based on the user's service response data, thereby realizing a comprehensive evaluation of the user from multiple angles, which is more helpful in formulating more scientific, reasonable and personalized rights and interests services in combination with the user.

[0100] Continue to refer Figure 4 In some optional implementations, before executing step 202, a step of analyzing the user service response preference is also included. Figure 4 This is a flowchart of a specific embodiment of analyzing user service response preferences in the service optimization method described in this application, comprising the following steps:

[0101] Step 401, determining the service item preferences corresponding to all the historical users according to the number of receipts, usages and service contents of various services corresponding to all the historical users;

[0102] Step 402, determining the service time preferences corresponding to all the historical users according to the historical receipt time and usage time of various services corresponding to all the historical users;

[0103] Step 403 , determining the service channel preferences corresponding to all the historical users according to the historical receiving channels of various services corresponding to all the historical users.

[0104] By analyzing user service response preferences, we can formulate more scientific, reasonable and personalized rights services based on user preferences.

[0105] In this embodiment, before executing the step of using the gradient boosting algorithm to calculate the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data, the method further includes: obtaining evaluation scores set in advance for different service items, service times, and service channels;

[0106] Specifically, different evaluation scores may be set for different service items, service times, and service channels.

[0107] Continue to refer Figure 5 , in some optional implementations, Figure 5 yes Figure 2 The flowchart of a specific embodiment of step 203 shown includes the following steps:

[0108] Step 501, identifying the service item preferences, service time preferences and service channel preferences corresponding to all historical users respectively;

[0109] Step 502, according to the service item preferences, service time preferences and service channel preferences respectively corresponding to all the historical users, and the evaluation scores respectively corresponding to different service items, service times and service channels, the XGBoost gradient boosting algorithm is used to accumulate the service item evaluation scores, service time evaluation scores and service channel evaluation scores corresponding to the same user;

[0110] Step 503: Obtain the accumulated result as the dynamic score obtained by the corresponding user according to the service selection.

[0111] The dynamic score means that the score will gradually change as the user's corresponding service item preference, service time preference and service channel preference change.

[0112] By calculating dynamic scores based on users' service response data, we can conduct comprehensive evaluations of users from multiple angles, which is more helpful in formulating more scientific, reasonable and personalized rights and interests services based on users' service response data.

[0113] Continue to refer Figure 6 In some optional implementations, after executing step 203, a step of verifying the seat allocation is also included. Figure 6 This is a flowchart of a specific embodiment of verifying seat allocation in the service optimization method described in this application, including the following steps:

[0114] Step 601, the dynamic score and the static score corresponding to the same user are accumulated to obtain a total score;

[0115] Step 602, determining whether the total score corresponding to the current user exceeds a preset score threshold;

[0116] Step 603: If the total score corresponding to the current user exceeds the preset score threshold, a seat caller is assigned to the current user for service recommendation according to a preset seat assignment strategy.

[0117] Specifically, the preset agent allocation strategy, for example: based on the current user's geographical location, the current user is preferentially assigned to the agent responsible for the area; allocation is based on the agent's professional skills, experience or specific industry knowledge to ensure that each agent handles the service they are best at; allocation is based on the current user's answering preferences, such as similarity with past interactions or communication styles with specific agents; allocation is based on the agent's historical performance and conversion rate, the current user is assigned to the best performing agent.

[0118] Correspondingly, if the total score corresponding to the current user does not exceed the preset score threshold, step 204 is continued.

[0119] By judging whether the cumulative score of the dynamic score and static score corresponding to the current user exceeds the preset score threshold, when the user's static score is high enough, that is, when the user participates in enough rights and interests service activities, a manual seat can be provided to provide special services to the current user, which is more humane and reasonable, and ensures the stickiness of mature users.

[0120] Continue to refer Figure 7 , in some optional implementations, Figure 7 yes Figure 2 The flowchart of a specific embodiment of step 204 shown includes the following steps:

[0121] Step 701, identifying a pre-divided dynamic score interval;

[0122] Specifically, the pre-divided dynamic score intervals, for example: a dynamic score of 0 to 30 is an interval, a dynamic score exceeding 30 and not exceeding 70 is an interval, and a dynamic score exceeding 70 is an interval.

[0123] Step 702: According to the pre-divided dynamic score intervals and the dynamic scores corresponding to all the historical users, a mature user group, an adaptive user group and a novice user group are divided, wherein the minimum value of the dynamic score interval corresponding to the mature user group is greater than the maximum value of the dynamic score interval corresponding to the adaptive user group, and the minimum value of the dynamic score interval corresponding to the adaptive user group is greater than the maximum value of the dynamic score interval corresponding to the novice user group.

[0124] Through the scoring range method, we divide the user groups into mature user groups, adaptive user groups and novice user groups, so as to facilitate the subsequent service optimization for new and old users of rights and interests services, which is more scientific and realizes customized service optimization according to different users.

[0125] Continue to refer Figure 8 In some optional implementations, after executing step 204, a step of dividing all historical users into secondary groups is also included. Figure 8 This is a flowchart of a specific embodiment of performing secondary group division on all historical users in the service optimization method described in this application, comprising the following steps:

[0126] Step 801, identifying a pre-divided static score interval;

[0127] Step 802, dividing a high-value user group and a low-value user group according to the pre-divided static score intervals and the static scores corresponding to all historical users, wherein the minimum value of the dynamic score interval corresponding to the high-value user group is greater than the maximum value of the dynamic score interval corresponding to the low-value user group.

[0128] By combining the pre-divided static score intervals, all historical users are divided into groups for the second time, ensuring that when the service for users is optimized later, the results of the two group divisions can be combined successively to jointly optimize the service, thereby improving the rationality of the service optimization.

[0129] Continue to refer Fig. 9 In some optional implementations, before executing step 205, a step of determining the user group to which the target user belongs is also included. Fig. 9 This is a flowchart of a specific embodiment of determining the user group to which the target user belongs in the service optimization method described in the present application, comprising the following steps:

[0130] Step 901, obtaining service response data of the target user;

[0131] Step 902: extracting multi-dimensional key feature data corresponding to the target user from the service response data;

[0132] Step 903, using the XGBoost gradient boosting algorithm to calculate the dynamic score of the target user according to the valuation strategies corresponding to the multi-dimensional key feature data;

[0133] Step 904, obtaining basic attribute data of the target user;

[0134] Step 905, calculating the static score of the target user according to the basic attribute data and the score assignment strategy;

[0135] Step 906: Determine the user group to which the target user belongs according to the dynamic score of the target user and the static score of the target user.

[0136] Through the dynamic score of the target user and the static score of the target user, the user group to which the target user belongs is determined, so that different service optimization strategies can be selected to optimize the service for the target user in the future, thereby achieving more scientific, reasonable and personalized rights and interests services based on the user.

[0137] Continue to refer Fig.10 , in some optional implementations, Fig.10 yes Figure 2 The flowchart of a specific embodiment of step 205 shown includes the following steps:

[0138] Determining whether the target user belongs to a mature user group;

[0139] Step 10a, if the target user belongs to a mature user group, optimizing services for the target user according to the target user's historical service item preferences, service time preferences, and service channel preferences;

[0140] If the target user does not belong to the mature user group, determining whether the target user belongs to the high-value user group;

[0141] Step 10b: if the target user belongs to the high-value user group, optimizing the service for the target user according to the service item preference, service time preference and service channel preference of all mature user groups in the high-value user group;

[0142] If the target user does not belong to the high-value user group, then the target user belongs to the low-value user group;

[0143] Step 10c: if the target user belongs to the low-value user group, the service optimization for the target user is performed according to the service item preference, service time preference and service channel preference of all low-value user groups in the mature user group.

[0144] Specifically, step 10a, step 10b and step 10c are a specific service optimization order, that is, the judgment priority of the mature user group is higher than that of the high-value user group, and the judgment priority of the high-value user group is higher than that of the low-value user group. By successively judging the target users as mature user groups, high-value user groups and low-value user groups, different service optimization strategies can be selected to optimize the services for the target users.

[0145] This application obtains the service response data of all historical users; extracts the multi-dimensional key feature data corresponding to all historical users from the service response data; calculates the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data; divides all historical users into user groups based on the dynamic scores and the preset user group division strategy; optimizes the service for the target user using different preset service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, this application can timely understand the responses of different users to different rights and interests services, so as to optimize and adjust the rights and interests services in combination with the user's rights and interests response habits and user groups, and formulate more scientific, reasonable and personalized rights and interests services.

[0146] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0147] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0148] In the embodiment of the present application, the service response data of all historical users is obtained; the multi-dimensional key feature data corresponding to all historical users are extracted from the service response data; the dynamic scores corresponding to all historical users are calculated according to the valuation strategies corresponding to the multi-dimensional key feature data; all historical users are divided into user groups based on the dynamic scores and the preset user group division strategy; and the service of the target user is optimized by using different preset service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, the present application can timely understand the response of different users to different rights and interests services, so as to facilitate the optimization and adjustment of rights and interests services in combination with the rights and interests response habits of users and user groups, and formulate more scientific, reasonable and personalized rights and interests services.

[0149] Further references Fig.11 , as a response to the above Figure 2 The present application provides an embodiment of a service optimization device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0150] like Fig.11 As shown, the service optimization device 11 described in this embodiment includes: a service response data acquisition module 11a, a key feature data extraction module 11b, a dynamic score calculation module 11c, a user group classification module 11d and a service optimization module 11e. Among them:

[0151] A service response data acquisition module 11a is used to acquire the service response data of all historical users;

[0152] The key feature data extraction module 11b is used to extract the multi-dimensional key feature data corresponding to all the historical users from the service response data, wherein the multi-dimensional key feature data includes the number of times the user has received various services in the past, the number of times used, the time of receiving, the time of use, the channel of receiving, and the content of the service;

[0153] A dynamic score calculation module 11c is used to calculate the dynamic scores corresponding to all historical users respectively using a gradient boosting algorithm according to the valuation strategies corresponding to the multi-dimensional key feature data respectively;

[0154] A user group division module 11d, configured to divide all the historical users into user groups based on the dynamic scores and a preset user group division strategy;

[0155] The service optimization module 11e is used to optimize the service for the target user by using different preset service optimization strategies according to the different user groups to which the target user belongs.

[0156] This application obtains the service response data of all historical users; extracts the multi-dimensional key feature data corresponding to all historical users from the service response data; calculates the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data; divides all historical users into user groups based on the dynamic scores and the preset user group division strategy; optimizes the service for the target user using different preset service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, this application can timely understand the responses of different users to different rights and interests services, so as to optimize and adjust the rights and interests services in combination with the user's rights and interests response habits and user groups, and formulate more scientific, reasonable and personalized rights and interests services.

[0157] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0158] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings 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 their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0159] To solve the above technical problems, the present application also provides a computer device. Fig.12 , Fig.12 This is a basic structural block diagram of the computer device in this embodiment.

[0160] The computer device 12 includes a memory 12a, a processor 12b, and a network interface 12c which are interconnected through a system bus. It should be noted that: Fig.12 Only a computer device 12 having a component memory 12a, a processor 12b, and a network interface 12c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0161] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0162] The memory 12a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 12a can be an internal storage unit of the computer device 12, such as a hard disk or memory of the computer device 12. In other embodiments, the memory 12a can also be an external storage device of the computer device 12, such as a plug-in hard disk equipped on the computer device 12, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 12a can also include both the internal storage unit of the computer device 12 and its external storage device. In this embodiment, the memory 12a is generally used to store an operating system and various application software installed on the computer device 12, such as a computer-readable instruction of a service optimization method. In addition, the memory 12a can also be used to temporarily store various data that have been output or will be output.

[0163] The processor 12b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 12b is generally used to control the overall operation of the computer device 12. In this embodiment, the processor 12b is used to run the computer-readable instructions or process data stored in the memory 12a, such as the computer-readable instructions for running the service optimization method.

[0164] The network interface 12c may include a wireless network interface or a wired network interface. The network interface 12c is generally used to establish a communication connection between the computer device 12 and other electronic devices.

[0165] The computer device proposed in this embodiment belongs to the field of data analysis technology and is applied to service recommendation optimization scenarios. This application obtains the service response data of all historical users; extracts the multi-dimensional key feature data corresponding to all historical users from the service response data; calculates the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data; divides all historical users into user groups based on the dynamic scores and the preset user group division strategies; optimizes the service for the target user using different preset service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, this application can timely understand the responses of different users to different rights and interests services, thereby facilitating the optimization and adjustment of rights and interests services in combination with the user's rights and interests response habits and user groups, and formulating more scientific, reasonable and personalized rights and interests services.

[0166] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the service optimization method as described above.

[0167] The computer-readable storage medium proposed in this embodiment belongs to the field of data analysis technology and is applied to service recommendation optimization scenarios. This application obtains the service response data of all historical users; extracts the multi-dimensional key feature data corresponding to all historical users from the service response data; calculates the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data; divides all historical users into user groups based on the dynamic scores and the preset user group division strategies; optimizes the service for the target user using different preset service optimization strategies according to the different user groups to which the target user belongs. By obtaining the service response data of all historical users, this application can timely understand the responses of different users to different rights and interests services, thereby facilitating the optimization and adjustment of rights and interests services in combination with the user's rights and interests response habits and user groups, and formulating more scientific, reasonable and personalized rights and interests services.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0169] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A service optimization method, characterized in that: The steps include: Get the service response data of all historical users; Extracting multi-dimensional key feature data corresponding to all historical users from the service response data, wherein the multi-dimensional key feature data includes the number of times users have received various services in the past, the number of times they have used them, the time they have received them, the time they have used them, the channels through which they have received them, and the content of the services they have received them; According to the valuation strategies corresponding to the multi-dimensional key feature data, a gradient boosting algorithm is used to calculate the dynamic scores corresponding to all the historical users; Dividing all the historical users into user groups based on the dynamic scores and a preset user group division strategy; According to the different user groups to which the target users belong, different preset service optimization strategies are adopted to optimize the services for the target users.

2. The service optimization method according to claim 1, characterized in that: After executing the step of acquiring the service response data of all historical users, the method further includes: Obtaining basic attribute data of all historical users, wherein the basic attribute data includes the user's age, gender, occupation, income level and educational background; The static scores corresponding to all the historical users are calculated based on the basic attribute data and a preset score assignment strategy, wherein the preset score assignment strategy includes setting different scores according to the user's age, gender, occupation, income level and educational background.

3. The service optimization method according to claim 2, characterized in that: After executing the step of extracting the multi-dimensional key feature data corresponding to all historical users respectively from the service response data, the method further includes: Determine the service item preferences corresponding to all the historical users according to the number of times they have received, the number of times they have used, and the service contents of various services corresponding to all the historical users; Determine the service time preferences corresponding to all the historical users according to the receipt time and usage time of various services corresponding to all the historical users; According to the historical receipt channels of various services respectively corresponding to all the historical users, the service channel preferences respectively corresponding to all the historical users are determined.

4. The service optimization method according to claim 3, characterized in that: Before executing the step of calculating the dynamic scores corresponding to all historical users respectively using a gradient boosting algorithm according to the valuation strategies respectively corresponding to the multi-dimensional key feature data, the method further includes: Obtain the evaluation scores set in advance for different service items, service time, and service channels; The step of using a gradient boosting algorithm to calculate the dynamic scores corresponding to all historical users according to the valuation strategies corresponding to the multi-dimensional key feature data specifically includes: Identify the service item preferences, service time preferences, and service channel preferences corresponding to all the historical users respectively; According to the service item preferences, service time preferences and service channel preferences corresponding to all historical users, as well as the evaluation scores corresponding to different service items, service times and service channels, the XGBoost gradient boosting algorithm is used to accumulate the service item evaluation scores, service time evaluation scores and service channel evaluation scores corresponding to the same user; The accumulated result is obtained as the dynamic score obtained by the corresponding user according to the service selection.

5. The service optimization method according to claim 2 or 4, characterized in that: After executing the valuation strategies respectively corresponding to the multi-dimensional key feature data and using a gradient boosting algorithm to calculate the dynamic scores respectively corresponding to all historical users, the method further includes: The dynamic score and static score corresponding to the same user are accumulated to obtain the total score; Determine whether the total score corresponding to the current user exceeds the preset score threshold; If the total score corresponding to the current user exceeds the preset score threshold, a seat caller is assigned to the current user for service recommendation according to a preset seat allocation strategy.

6. The service optimization method according to claim 2 or 4, characterized in that: The step of dividing all the historical users into user groups based on the dynamic scores and the preset user group division strategy specifically includes: Identify pre-divided dynamic score intervals; According to the pre-divided dynamic score intervals and the dynamic scores corresponding to all historical users, a mature user group, an adaptive user group and a novice user group are divided, wherein the minimum interval value of the dynamic score interval corresponding to the mature user group is greater than the maximum interval value of the dynamic score interval corresponding to the adaptive user group, and the minimum interval value of the dynamic score interval corresponding to the adaptive user group is greater than the maximum interval value of the dynamic score interval corresponding to the novice user group; After executing the step of dividing all the historical users into user groups based on the dynamic scores and the preset user group division strategy, the method further includes: Identify pre-defined static score intervals; A high-value user group and a low-value user group are divided according to the pre-divided static score intervals and the static scores corresponding to all historical users, wherein the minimum value of the dynamic score interval corresponding to the high-value user group is greater than the maximum value of the dynamic score interval corresponding to the low-value user group.

7. The service optimization method according to claim 6, characterized in that: Before executing the step of optimizing services for the target users by using different preset service optimization strategies according to the different user groups to which the target users belong, the method further includes: Obtain service response data of the target user; Extracting multi-dimensional key feature data corresponding to the target user from the service response data; According to the valuation strategies corresponding to the multi-dimensional key feature data, the dynamic score of the target user is calculated using the XGBoost gradient boosting algorithm; Obtain basic attribute data of target users; Calculating a static score of the target user according to the basic attribute data and the score assignment strategy; Determining the user group to which the target user belongs according to the dynamic score of the target user and the static score of the target user; The step of optimizing services for target users by using different preset service optimization strategies according to different user groups to which the target users belong specifically includes: If the target user belongs to the mature user group, optimizing the service for the target user according to the target user's historical service item preference, service time preference and service channel preference; If the target user belongs to the high-value user group, the service optimization for the target user is performed according to the service item preference, service time preference and service channel preference of all mature user groups in the high-value user group; If the target user belongs to a low-value user group, service optimization is performed for the target user based on the service item preferences, service time preferences and service channel preferences of all low-value user groups in the mature user group.

8. A service optimization device, characterized in that: include: The service response data acquisition module is used to obtain the service response data of all historical users; A key feature data extraction module is used to extract multi-dimensional key feature data corresponding to all historical users from the service response data, wherein the multi-dimensional key feature data includes the number of times users have received various services in the past, the number of times they have used them, the time they have received them, the time they have used them, the channels they have received them, and the content of the services they have received them; A dynamic score calculation module, used to calculate the dynamic scores corresponding to all historical users respectively using a gradient boosting algorithm according to the valuation strategies corresponding to the multi-dimensional key feature data respectively; A user group division module, used to divide all the historical users into user groups based on the dynamic scores and a preset user group division strategy; The service optimization module is used to optimize the service for the target user by adopting different preset service optimization strategies according to the different user groups to which the target user belongs.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the service optimization method as claimed in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the service optimization method according to any one of claims 1 to 7 are implemented.

Images