Factor adjustment method and device, equipment and storage medium

By determining the importance of the user and the initial success rate, selecting the target plan from the preset plan, and using multiple rounds of matching and group plan mechanisms to adjust the user's factor information, the problem of the factor adjustment method being affected by the subjective judgment of the operator is solved, and the problem of improving the problem of the factor adjustment method being affected by the operator's subjective judgment. The accuracy and effect of adjustment effects are achieved.

CN119088847APending Publication Date: 2024-12-06HANGZHOU HAILIANG DIGITAL TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410862715.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Existing factor adjustment methods are easily affected by the subjective judgment of the operator, resulting in poor adjustment results.

Method used

By determining the importance of the user and the initial success rate, select the target plan corresponding to the target user from the preset plan, and use multiple rounds of matching and group plan mechanisms to adjust the user's variable factor information to improve the success rate of target processing.

Benefits of technology

It improves the accuracy and effectiveness of factor adjustment methods, reduces the impact of operators' subjective judgments, and ensures that users get the most matching adjustment plan.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088847A_ABST
    Figure CN119088847A_ABST
Patent Text Reader

Abstract

The invention provides a factor adjustment method. The method comprises the following steps: determining at least one user; the importance degree of each user is obtained, the initial success rate of each user is obtained, the initial success rate is the success rate of target processing on the user under the influence of invariant factor information in at least one piece of factor information of the user, and the at least one piece of factor information of the user comprises factor information influencing target processing on the user; according to the importance degree and the initial success rate corresponding to the at least one user, determining a target scheme corresponding to the at least one target user from the at least one preset scheme, the target scheme being used for adjusting variable factor information in the at least one piece of factor information of the target user; and adjusting the variable factor information of the target user through the target scheme of the target user. The target scheme of the user is determined according to the initial success rate and the importance degree of the user, and the accuracy of the factor adjustment method is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent analysis technology, and in particular to a factor adjustment method, device, equipment and storage medium. Background Art

[0002] With the development of intelligent analysis technology, factor adjustment methods are widely used. Operators can adjust factor information through factor adjustment methods to improve the success rate of processing users. For example, teachers can adjust factors that affect students' learning through factor adjustment methods to improve students' academic performance.

[0003] In the prior art, the factor adjustment method usually relies on the operator to select a processing scheme suitable for the user based on his or her own experience, so as to adjust all or part of the factors of the user according to the processing scheme.

[0004] However, this method is easily affected by the subjective judgment of the operator, resulting in poor adjustment effect. Summary of the invention

[0005] The present application provides a factor adjustment method, device, equipment and storage medium, which solves the problem that the existing factor adjustment method is easily affected by the subjective judgment of the operator, resulting in poor adjustment effect.

[0006] In a first aspect, the present application provides a factor adjustment method, comprising: determining at least one user; obtaining the importance of each of the users, and obtaining the initial success rate of each of the users, the initial success rate being the success rate of target processing of the users under the influence of the immutable factor information in at least one factor information of the users, the at least one factor information of the users comprising: factor information affecting the target processing of the users; determining a target scheme corresponding to at least one target user from at least one preset scheme based on the importance and the initial success rate respectively corresponding to at least one user, the target scheme being used to adjust the variable factor information in at least one factor information of the target user; and adjusting the variable factor information of the target user through the target scheme of the target user.

[0007] In a possible design, determining a target solution corresponding to at least one target user from at least one preset solution according to the importance and the initial success rate respectively corresponding to at least one user includes: taking the initial success rate of each of the users as the current success rate of the user, and performing multiple rounds of matching until there is no group solution that successfully matches the user in a round of matching, and the group solution is a solution for multiple users in the at least one preset solution; wherein each round of matching includes: matching at least one user with at least one preset solution arranged in sequence according to the importance and the current success rate of each of the users and the activation conditions of each of the preset solutions, and determining the target solution for the target user according to the preset solution that successfully matches the target user; and predicting the success rate of the target user after adjustment corresponding to the target solution as the current success rate of the user in the next round of matching.

[0008] In a possible design, the preset plan also includes an individual plan, which is a plan for one user. Determining the target plan for the target user based on the preset plan that successfully matches the target user includes: when one of the target users successfully matches one of the individual plans, using the successfully matched individual plan as the target plan for the target user; when the target user successfully matches one of the group plans, recording the number of users who successfully match the group plan; when the number of users is greater than or equal to a threshold of the number of people starting the group plan, using the group plan as the target plan for the target user who successfully matches the group plan.

[0009] In one possible design, the enabling conditions of the preset scheme include: an importance range and a success rate range; accordingly, the user successfully matches the preset scheme includes: the importance of the user is within the importance range, and the success rate of the user is within the success rate range.

[0010] In a possible design, the ranking factor of the at least one preset solution includes at least one of the following: the adjustment cost of the preset solution, the minimum activation success rate of the preset solution, and the impact of the preset solution on the target processing.

[0011] In a possible design, obtaining the importance of each user includes: obtaining attribute information of the user; and adjusting the default importance of the user according to the attribute information to obtain the importance of the user.

[0012] In one possible design, the default importance of the user is adjusted according to the attribute information to obtain the importance of the user, including: determining an adjustment range of the importance according to the attribute information, different attribute information corresponding to different adjustment ranges; if the attribute information corresponds to a target value, adjusting the default importance of the user according to the adjustment range.

[0013] In a possible design, the initial success rate of the user and the success rate of the target user after adjustment corresponding to the target solution are both generated by a preset function model, and the generation process of the preset function model includes: obtaining at least one factor information of multiple historical users, and the actual success rate of performing the target processing on each of the historical users under the influence of the at least one factor information; performing function fitting to obtain an intermediate function model through the at least one factor information of the multiple historical users and the at least one actual success rate; inputting the at least one factor information of each of the historical users into the intermediate function model to obtain the predicted success rate of each of the historical users; normalizing the predicted success rate of each of the historical users to obtain a normalized success rate; performing function fitting to obtain a preset function model through the at least one factor information of the multiple historical users and the at least one normalized success rate.

[0014] In a second aspect, the present application provides a factor adjustment device, comprising: a user determination module, used to determine at least one user; a data acquisition module, used to obtain the importance of each of the users, and to obtain the initial success rate of each of the users, the initial success rate being the success rate of target processing of the users under the influence of the immutable factor information in at least one factor information of the users, the at least one factor information of the users comprising: factor information affecting the target processing of the users; a scheme determination module, used to determine a target scheme corresponding to at least one target user from at least one preset scheme based on the importance and the initial success rate respectively corresponding to at least one user, the target scheme being used to adjust the variable factor information in at least one factor information of the target user; a factor adjustment module, used to adjust the variable factor information of the target user through the target scheme of the target user.

[0015] In a third aspect, the present application provides an electronic device comprising: at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect.

[0016] In a fourth aspect, the present application provides a computer storage medium, wherein the computer storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the method described in the first aspect is implemented.

[0017] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. 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 labor.

[0019] Figure 1 It is a schematic diagram of an application scenario of the factor adjustment method provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a factor adjustment method flow chart provided in one embodiment of the present application;

[0021] Figure 3 A schematic diagram of a factor adjustment method flow chart provided in another embodiment of the present application;

[0022] Figure 4 A schematic diagram of a factor adjustment method flow chart provided in another embodiment of the present application;

[0023] Figure 5 A schematic diagram of a factor adjustment method flow chart provided in another embodiment of the present application;

[0024] Figure 6 A schematic diagram of a factor adjustment method flow chart provided in another embodiment of the present application;

[0025] Figure 7 A schematic diagram of the structure of a factor adjustment device provided in one embodiment of the present application;

[0026] Figure 8 A schematic diagram of the hardware structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] The present disclosure is specifically used in a data optimization scenario to determine a target solution to optimize data. In existing data optimization solutions, the target solution is usually determined by the operator based on his or her own experience. However, this data optimization solution only relies on the operator's experience to determine the target solution, lacks objectivity, and may lead to errors in determining the target solution, thereby reducing the data optimization effect.

[0029] In order to solve the above technical problems, the embodiment of the present application proposes the following technical solution: based on the importance of the user and the initial success rate, a target solution corresponding to the target user is selected from the preset solutions through multiple rounds of matching, which is used to adjust the variable factor information of the target user to improve the success rate of target processing for the user. The method of determining the target solution corresponding to the user by the initial success rate and importance of the user can avoid the influence of the operator's subjective judgment on the factor adjustment method, obtain the target solution with the highest matching degree with the user, and thus improve the accuracy of the factor adjustment method.

[0030] Figure 1 Schematic diagram of the application scenario of the factor adjustment method provided in the embodiment of the present application. Figure 1 As shown, the electronic device 101 determines at least one user; the electronic device 101 obtains the importance of each user and the initial success rate of each user; the electronic device 101 determines a target plan corresponding to at least one target user from at least one preset plan according to the importance and the initial success rate corresponding to at least one user; the electronic device 101 adjusts the variable factor information of the target user through the target plan of the target user.

[0031] Figure 2 A schematic diagram of a factor adjustment method flow chart provided in an embodiment of the present application. The execution subject of this embodiment may be Figure 1 The electronic device in the embodiment shown is not particularly limited in this embodiment. Figure 2 As shown, the method includes:

[0032] S201: Determine at least one user.

[0033] The user may be any user. Specifically, the user may be determined by the age of the group. For example, students aged 6-12 are users who need to adjust the elementary school academic performance factor, and students aged 13-15 are users who need to adjust the junior high school academic performance factor.

[0034] Specifically, users may be determined according to the hobbies of the crowd. For example, the crowd that likes playing basketball is the user that needs to adjust the basketball training factor, and the crowd that likes playing football is the user that needs to adjust the football training factor.

[0035] S202: Obtain the importance of each user, and obtain the initial success rate of each user, where the initial success rate is the success rate of performing target processing on the user under the influence of the immutable factor information in at least one factor information of the user, and the at least one factor information of the user includes: factor information that affects the target processing on the user.

[0036] Among them, target processing refers to a specific action or operation performed on users in order to achieve a certain goal or meet a certain need. For example, target processing can be that the library improves the reading environment of readers to enhance their reading experience.

[0037] Among them, factor information refers to various factors that affect the success of target processing. For example, factor information can be factors that affect readers' reading experience, such as the number of books and the number of staff in the library.

[0038] In one way of generating importance, the importance of a user can be obtained based on historical data. For example, the importance of a user can be evaluated using a user value assessment model. There are three inputs in the user value assessment model: R, F, and M. R represents the time of the user's most recent purchase (the more recent the time, the higher the importance), F represents the user's purchase frequency (the higher the frequency, the higher the importance), and M represents the user's purchase amount (the higher the amount, the higher the importance). By inputting the user's data over a period of time into the user value assessment model, the user value assessment model can output the user's importance.

[0039] In another way to generate importance, the importance of users can be obtained based on a machine learning prediction model. Prepare a training data set containing user characteristics and historical performance, train a machine learning model, use the trained model to predict users, and output the importance of users. For example, you can use the past work performance characteristics of multiple employees to train a machine learning model, and then input the work performance characteristics of current employees into the model to obtain the current employees' importance.

[0040] Specifically, the initial success rate of users can be obtained based on historical data. First, determine the definition of initial success and count the behavior data of each user in the following period of time. For example, in an e-commerce platform, the behavior of a user completing the first purchase within 7 days after registration can be defined as initial success. Count the purchases of each user within 7 days after registration and calculate the initial success rate, such as: initial success rate = (number of users who completed the first purchase within 7 days / total number of registered users) * 100%.

[0041] Specifically, the initial success rate of the user can be obtained based on the machine learning prediction model. For example, a machine learning model is trained based on user characteristics to predict the initial learning performance improvement success rate of the user. The characteristics may include the user's learning background, historical learning performance, etc. The training set may include the learning performance data of registered users. After model training, the initial learning performance improvement success rate of new users can be predicted.

[0042] S203: Determine a target solution corresponding to at least one target user from at least one preset solution according to the importance level and the initial success rate respectively corresponding to at least one user, where the target solution is used to adjust variable factor information in at least one factor information of the target user.

[0043] Specifically, you can define an importance threshold and a success rate threshold for a preset solution, match the user's importance and success rate with the importance threshold and success rate threshold of the preset solution, and get the target solution. For example, there are two preset solutions: Solution A and Solution B. If the user's importance is > 80 and the initial success rate is > 60%, use Solution A; if the user's importance is <= 80 or the initial success rate is <= 60%, use Solution B. The user's importance is 90 and the initial success rate is 70. The user's importance and initial success rate meet the threshold conditions of Solution A, so the target solution is Solution A.

[0044] Specifically, a target plan corresponding to at least one target user can be determined from at least one preset plan based on a machine learning model. For example, the library collects readers' reservation data over a period of time. Readers' characteristics are extracted from the collected data, such as readers' borrowing frequency (representing the importance), historical reservation success rate (initial success rate), etc. The library presets several seat reservation adjustment plans, and trains a machine learning model based on historical data and preset plans. This model can predict which preset plan is most suitable for the current user group based on the reader's characteristics and seat usage. When a new reader makes a reservation, the library can input the reader's characteristics and seat usage into the model to obtain the adjustment plan recommended by the model.

[0045] S204: Adjust the variable factor information of the target user through the target plan of the target user.

[0046] Specifically, the variable factor information of the target user can be adjusted directly by the operator according to the target plan. For example, if the variable factor is the training time of the athlete and the target plan is to increase the training time, the operator can increase the training time of the athlete according to the target plan.

[0047] Specifically, machine learning-based methods can be used to adjust the variable factor information of target users through target user's target program. For example, a model is trained using a machine learning algorithm, which can predict the best fitness plan and diet recommendations based on the user's fitness goals and historical data. When the user sets a new fitness goal or provides new data, the system uses the trained model to develop personalized fitness plans and diet recommendations for the user, and continuously adjusts and optimizes these recommendations based on the user's feedback and performance.

[0048] In summary, by confirming the plan for each user based on the importance and initial success rate of each user, each user can obtain the target plan that best matches his or her own importance and initial success rate, and then use the best matching target plan to adjust factors, thereby improving the accuracy of the factor adjustment method.

[0049] Figure 3 A flow chart of a factor adjustment method provided in another embodiment of the present application. Figure 2 Based on the embodiments provided, this embodiment focuses on describing a specific process of determining a target solution corresponding to at least one target user from at least one preset solution according to the importance and initial success rate respectively corresponding to at least one user, including:

[0050] S301: Taking each user's initial success rate as the user's current success rate, and performing multiple rounds of matching until there is no group solution that successfully matches the user in a round of matching, where the group solution is a solution for multiple users in at least one preset solution.

[0051] Specifically, when the current success rate of the user is within the success rate range of the group plan, the group plan is the target plan of the user, and multiple rounds of matching are performed to determine the multiple users corresponding to each group plan, and the corresponding group plan is used for the multiple users corresponding to each group plan to obtain the corresponding success rate after intervention for the multiple users corresponding to each group plan, and the group plan is matched again by the corresponding success rate after intervention for the multiple users corresponding to each group plan, and then the group plan is used again until there is no group plan that successfully matches the user. For example, a fitness center offers a variety of fitness courses, each of which is aimed at students of different levels and has an expected success rate range. Each student has an initial physical fitness test score when joining, which can be regarded as their initial success rate. According to the initial success rate of the students, the most suitable multi-person fitness course is assigned to them, and the success rate after intervention is calculated after using the multi-person fitness course, and the process of matching the multi-person fitness course and using the multi-person fitness course is repeated until there is no multi-person fitness course that successfully matches the student.

[0052] Specifically, the matching process in step S301 includes Sa~Sb:

[0053] Sa: According to the importance and current success rate of each user and the activation condition of each preset plan, at least one user is matched with at least one preset plan arranged in sequence, and a target plan for the target user is determined according to the preset plan that successfully matches the target user.

[0054] Among them, the activation conditions of the preset scheme include: importance range, success rate range; accordingly, the user successfully matches the preset scheme includes: the user's importance is within the importance range, and the user's success rate is within the success rate range. For example, the importance of user A is 6, and the success rate is 50%; the importance range of preset scheme 1 is >5, and the success rate range is >30%, the importance of user A is within the importance range of preset scheme 1, and the success rate of user A is within the success rate range of preset scheme 1, and user A successfully matches preset scheme 1.

[0055] Among them, the ranking factors of at least one preset solution include at least one of the following: the adjustment cost of the preset solution, the minimum activation success rate of the preset solution, and the degree of influence of the preset solution on the target processing. For example, in order to optimize reader satisfaction, the library has formulated several preset solutions to adjust the seating layout. These solutions need to be ranked according to different ranking factors. Preset solution A is to increase the number of single reading tables, with moderate adjustment costs, requiring the purchase of new reading tables and rearrangement of the library's internal space; the degree of influence on the target processing is significant, directly affecting the reader's reading experience in the library. Preset solution B is to set up more power sockets; the adjustment cost is low, mainly the installation and wiring of power equipment; the degree of influence on the target processing is moderate, and the convenience of readers using electronic devices is improved. The ranking is as follows: If the library's primary goal is to quickly improve reader satisfaction and the budget is sufficient, then solution A should be ranked before solution B; if the library hopes to quickly implement an improvement measure at a lower cost, then solution B should be ranked before solution A.

[0056] Specifically, the importance and current success rate of the first user can be matched with the activation conditions of the first preset solution. If the first user and the first preset solution are matched successfully, the first preset solution is the target solution of the first user; if the first user and the first preset solution are matched unsuccessfully, the first user and the second preset solution are matched continuously until all users are matched successfully. For example, there are 2 users and 2 preset solutions: User A: importance is 4, current success rate is 70%; User B: importance is 2, current success rate is 85%. The activation conditions of preset solution 1 are importance ≥ 4, success rate ≥ 70%; the activation conditions of preset solution 2 are importance ≥ 2, success rate ≥ 60%. The importance and current success rate of user A are matched with the enabling conditions of preset plan 1, user A is successfully matched with the first preset plan, and preset plan 1 is the target plan for user A; the importance and current success rate of user B are matched with the enabling conditions of preset plan 1, user B fails to match with the first preset plan, the importance and current success rate of user B are matched with the enabling conditions of preset plan 2, user B is successfully matched with preset plan 2, and preset plan 2 is the target plan for user B.

[0057] Specifically, the importance and current success rate of the first user can be matched with the activation conditions of each preset solution to obtain multiple successfully matched preset solutions, and any one of them can be selected as the target solution for the first target user. For example, still using the above example, user C: importance is 8, current success rate is 80%, user C successfully matches both preset solution 1 and preset solution 2, and one of preset solution 1 and preset solution 2 can be selected as the target solution for user C.

[0058] Sb: Predict the success rate of the target user after adjustment of the corresponding target solution, which will be used as the current success rate of the user in the next round of matching.

[0059] Specifically, the corresponding target plan can be implemented for the target user, and the new success rate of the target user can be calculated. For example, the target user is an employee with a work efficiency of 75%, and the target plan is to recommend a series of work methods that can improve work efficiency. The platform recommends work methods to the employee, and the employee's new work efficiency after using the target work method is 85%. 85% can be used as the current success rate of the employee in the next round of matching.

[0060] Specifically, you can collect data on changes in success rates after previous users applied similar solutions. Use machine learning models to analyze historical data and establish a model between changes in success rates and solution implementation. Apply the corresponding target solution to the target user, and use the established model to predict the new success rate. For example, an e-commerce website wants to improve the user's purchase conversion rate (i.e., success rate), and the website collects the purchase conversion rates of users after applying different marketing solutions in the past few months. Use a machine learning algorithm to build a model that can predict the purchase conversion rate based on the marketing solution and user characteristics. When the website decides to implement a marketing solution for the target user, use the established model to predict the new purchase conversion rate of the target user after applying the solution. This predicted value can be used as the current success rate of the target user in the next round of matching.

[0061] In summary, by introducing the concept of multi-round matching mechanism and group scheme, the factor adjustment process is optimized. Through the multi-round matching process, it is possible to ensure that the most suitable adjustment scheme is found for the user. Each round of matching is performed based on the importance of the user, the current success rate and the activation conditions of the preset scheme, which improves the accuracy of the matching results.

[0062] Figure 4 A flow chart of a factor adjustment method provided in another embodiment of the present application. Figure 3 Based on the provided embodiment, the preset solution also includes an individual solution, which is a solution for one user. Accordingly, the target solution of the target user is determined according to the preset solution that successfully matches the target user, including:

[0063] S401: When one of the target users is successfully matched with one of the individual plans, the successfully matched individual plan is used as the target plan of the target user.

[0064] Specifically, when the importance of the target user is within the importance range of an individual solution, and the success rate of the target user is within the success rate range of an individual solution, the individual solution can be used as the target solution for the target user. For example, the importance of user A is 5, the success rate is 50%, and the importance range of individual solution 1 is importance>4, and the success rate range is>45%. When the importance of user A is within the importance range of individual solution 1, and the success rate of user A is within the success rate range of individual solution 1, individual solution 1 is the target solution for user A.

[0065] Specifically, a machine learning algorithm can be used to match target users with individual solutions. Collect historical user data, individual solution data, and the matching results between users and solutions as training data. Use a machine learning algorithm to train a regression model that can predict the matching degree between users and individual solutions. For new target users and individual solutions, use the trained model to make predictions, and set the solution with the highest matching degree as the target solution. For example, an advertising recommendation system based on machine learning has trained a prediction model using historical data. When a new user A enters the system, the system collects the features of user A. The system has two advertising solutions to be recommended (Solution 1 and Solution 2). Use the trained model to predict the matching degree between user A and Solution 1 and Solution 2. The model predicts that the matching degree between user A and Solution 1 is 0.8, and the matching degree between user A and Solution 2 is 0.6, and Solution 1 is used as the target solution for user A.

[0066] S402: When the target user is successfully matched with one of the group plans, the number of users successfully matched with the group plan is recorded.

[0067] Specifically, the direct counting method can be used to record the number of users who successfully match the group scheme. Initialize a counter for each group scheme to record the number of users who successfully match the group scheme. Traverse all target users and match each user with all group schemes. When a user successfully matches a group scheme, add one to the counter corresponding to the group scheme. After completing the matching of all users, record the counter value corresponding to each group scheme, which is the number of users who successfully match the group scheme. For example, there are three preset schemes (Scheme A, Scheme B, Scheme C) and three target users (User 1, User 2, User 3). Initialize counters: Scheme A counter = 0, Scheme B counter = 0, Scheme C counter = 0. Perform matching: User 1 successfully matches Scheme A. User 2 successfully matches Scheme B. User 3 successfully matches Scheme A. Update counters: Scheme A counter = 2 (User 1 and User 3 successfully match), Scheme B counter = 1 (User 2 successfully matches), Scheme C counter = 0 (No user successfully matches). Record results: Plan A has 2 matching users, Plan B has 1 matching user, and Plan C has 0 matching users.

[0068] Specifically, a paper record sheet can be used to record the number of users who successfully match the group plan. Make a paper record sheet, the columns of which can include user ID, user information, matching plan, etc. Whenever a user successfully matches a group plan, fill in the user ID, user information, and matching plan on the corresponding row of the table. By looking at the different group plans under the plan column in the table, count the number of users corresponding to each group plan. For example, a travel company is providing different travel packages for users with different preferences. The travel company prepares a paper record sheet with columns such as user name, user preference, and matching package. When user A expresses interest in the history and culture package and successfully matches the package, the employee adds a row to the table and fills in the user name (Zhang San), user preference (history and culture), and matching package (history and culture package). At the end of the day, the employee looks at the different group packages under the package column in the table and counts the number of users corresponding to each group package.

[0069] S403: When the number of users is greater than or equal to the threshold of the number of people starting the preset plan, the group plan is used as the target plan for the target users who successfully match the group plan.

[0070] Specifically, a counter can be set for each group plan to record the number of users who successfully match the plan. Whenever a target user successfully matches a group plan, the counter of the corresponding plan is increased. The counter value of each plan is checked regularly to see if it has reached the preset start-up number threshold. When the counter value of a group plan reaches or exceeds the number threshold, the group plan is determined as the target plan for the successfully matched target user. For example, a community wants to organize several different activities, each of which has a start-up number threshold. Community members can sign up to participate in these activities. At the beginning of the activity, the counter of each activity is 0. As time goes by, if someone signs up for a basketball game, the counter of the basketball game will increase by 1; if someone signs up for a reading club, the counter of the reading club will also increase by 1, and so on. The community organizer regularly checks the counter value of each activity, such as once every weekend. If it is found that the number of people who have signed up for the basketball game has reached the start-up number threshold, the community organizer will announce that the basketball game has officially started and use the basketball game as the target plan for the registered participants.

[0071] Specifically, a visual chart (such as a progress bar, a bar chart, etc.) can be set for each group plan. Whenever a target user successfully matches a group plan, the corresponding mark is moved or the chart is updated. By observing the changes in the mark or chart, it is determined whether the number of matched users of a group plan has reached the preset start-up number threshold. When the mark or chart of a plan reaches or exceeds the threshold mark, the plan is determined as the target plan for the successfully matched target user. For example, a company wants to open interest classes for employees with different interests and hobbies. The company sets a start-up number threshold and draws a progress bar for each interest class on the bulletin board, which is initially empty. Employees can post their names on the progress bar of the corresponding interest class when signing up. As more and more employees sign up, the progress bars of each interest class are gradually filled. When the progress bar of an interest class reaches or exceeds the number threshold, the company announces that the interest class is officially opened and uses the interest class as the target plan for the registered employees.

[0072] In summary, by introducing individual plans, the process of factor adjustment is further refined, and different user needs can be responded to more flexibly. Individual plans can be precisely adjusted to the special needs of specific users, while group plans can be batch processed for a group of users with similar characteristics or needs, improving the efficiency of factor adjustment.

[0073] Figure 5 A flow chart of a factor adjustment method provided in another embodiment of the present application. Figure 2 Based on the provided embodiment, this embodiment focuses on describing the specific process of obtaining the importance of each user, including:

[0074] S501: Obtaining user attribute information.

[0075] Specifically, the attribute information of the user can be obtained through the communication between the operator and the user. For example, the operator can obtain attribute information such as the employee's work completion status and teamwork status through communication with the employee.

[0076] Specifically, the user's attribute information can be obtained through the Internet. For example, the user's age, hobbies, and place of origin can be obtained by searching the user's name on the Internet.

[0077] S502: Adjust the default importance of the user according to the attribute information to obtain the importance of the user.

[0078] Specifically, the default importance of the user can be adjusted according to whether the user's attribute information meets the preset conditions to obtain the user's importance. For example, the default importance of the user is 1. When the user is a group consultation, the default importance of the user is increased by 1. When the user is an old customer, the default importance of the user is increased by 1. When the user is a well-known person, the default importance of the user is increased by 2, and the user's importance is 5.

[0079] Specifically, the default importance of the user is adjusted according to the attribute information to obtain the importance of the user, which is described in detail as follows: Sc~Sd:

[0080] Sc: Determine the adjustment range of importance based on the attribute information. Different attribute information corresponds to different adjustment ranges.

[0081] Specifically, the adjustment range of the importance can be determined according to whether the user's attribute information is personal attribute information or non-personal attribute information. For example, when the user's attribute information is personal attribute information such as the student's test ranking, the student's hobbies and interests, and the student's age, the adjustment range is 1; when the user's attribute information is non-personal attribute information such as the student's school ranking and school location, the adjustment range is 2.

[0082] Specifically, the adjustment range of the importance can be determined according to whether the user's attribute information is subjective attribute information or objective attribute information. For example, when the user's attribute information is subjective attribute information of students such as the student's study time and the teacher-student communication time, the adjustment range is 2; when the user's attribute information is objective attribute information of students such as the student's family economic conditions and the school's tuition exemption policy, the adjustment range is 1.

[0083] Sd: If the attribute information corresponds to the target value, the user's default importance is adjusted according to the adjustment range.

[0084] Specifically, a set of rules can be defined to clarify the correspondence between the target values ​​and adjustment ranges of different attribute information. Obtain the user's attribute information and the corresponding target values. According to the defined rules, determine the adjustment range corresponding to the target value. According to the calculated adjustment range, add or subtract adjustments to the user's default importance. For example, there is a user system in which users have two attributes: "activity" and "spending power". The rules are defined as follows: For activity values ​​above 80, the importance increases by 10%, and for spending power values ​​above 1000, the importance increases by 5%. Now there is a user whose activity is 90 and spending power is 1500. According to the rules, the user's importance will increase by 10% and 5%, for a total increase of 15%.

[0085] Specifically, a large amount of user data can be collected and a model can be trained using machine learning. The model can predict the adjustment range of importance based on the user's attribute information and target value. Obtain user attributes and target values. Input the user's attributes and target values ​​into the model to predict the adjustment range of importance. Dynamically adjust the user's default importance based on the adjustment range predicted by the model. For example, there is an e-commerce website where the user's attributes include "purchase frequency" and "average unit price", and the target value is the amount of consumption that the user may generate in the future. A random forest-based model is trained using historical data, which can predict the adjustment range of importance based on the user's attributes and historical consumption data. Now there is a user whose purchase frequency is 2 times a week and the average unit price is 200 yuan. Input these data into the model, and the model predicts that the user may generate a higher consumption amount in the next month, and recommends increasing his importance by 8%. Therefore, the importance of the user can be adjusted based on this prediction result.

[0086] In summary, by obtaining the importance of each user, a target solution can be determined for the user according to the importance of the user in the subsequent solution determination process, thereby improving the accuracy of solution determination.

[0087] Figure 6 A flow chart of a factor adjustment method provided in another embodiment of the present application. Figure 2 Based on the provided embodiment, the initial success rate of the user and the success rate of the target user after adjustment of the corresponding target solution are both generated by a preset function model. The generation process of the preset function model includes:

[0088] S601: Acquire at least one factor information of a plurality of historical users, and the actual success rate of performing target processing on each historical user under the influence of the at least one factor information.

[0089] Specifically, at least one factor information of multiple historical users can be obtained through a database query method, as well as the actual success rate of target processing for each historical user under the influence of the at least one factor information. For example, an e-commerce platform wants to analyze the actual success rate of users of different age groups when purchasing products. The user's age information and purchase records can be extracted from the database, and then the purchase success rate of users of each age group can be calculated.

[0090] Specifically, at least one factor information of multiple historical users can be obtained through direct communication between operators and historical users, as well as the actual success rate of target processing for each historical user under the influence of at least one factor information. For example, a library administrator communicates with a reader to obtain factor information such as the reader's borrowing history and browsing history. The library administrator adjusts the borrowing system based on the reader's factor information and communicates with the reader again to obtain the reader's borrowing success rate.

[0091] S602: Perform function fitting based on at least one factor information and at least one real success rate of multiple historical users to obtain an intermediate function model.

[0092] Specifically, a linear regression model can be used to fit the function to obtain an intermediate function model. Organize historical user data, including factor information of each user and the corresponding real success rate. Use a linear regression algorithm to fit the data to obtain an intermediate function model. This model can be a linear equation that represents the relationship between factor information and real success rate. For example, an e-commerce platform wants to predict the real success rate (dependent variable) of a user's purchase of a product based on the user's age (factor information). Historical data can be collected, which contains the age and purchase success rate of historical users. Then, a linear regression model can be used to fit this data to obtain a linear equation that represents the relationship between age and purchase success rate.

[0093] Specifically, a feedforward neural network can be used to fit the function to obtain an intermediate function model. Use historical user data to train the neural network model. Take the factor information as input and the success rate as output. Update the weights and bias terms of the neural network through the back propagation algorithm to minimize the error between the predicted value and the true value, and obtain a trained feedforward neural network model. For example, there is a data set of houses, including factor information such as the area, region, number of rooms, and the success rate of sales. The factor information of the house can be used as input and the success rate of sales as output to train a feedforward neural network model to predict the success rate of sales of other houses.

[0094] S603: Input at least one factor information of each historical user into the intermediate function model to obtain the prediction success rate of each historical user.

[0095] Specifically, you can load a trained linear regression model. Organize the factor information of historical users into feature vectors in the same format as the training data. Input the feature vector of each user into the linear regression model to obtain the predicted success rate of each historical user. For example, there is a linear regression model that predicts the success rate of purchasing a product based on the user's age. Now, there is a batch of user age data. These age data are organized into feature vectors in the same format as the training data, and the feature vectors are input into the linear regression model to obtain the success rate of purchasing products for this batch of users.

[0096] Specifically, multiple factor information of each historical user can be input into the intermediate function model to obtain multiple success rates of each historical user, and the average of the multiple success rates is taken as the predicted success rate. For example, the student's study time is input into the test pass prediction model, and the test pass prediction value is 70%. The number of times the student reviews is input into the test pass prediction model, and the test pass prediction value is 60%. The average value is calculated to obtain the student's test pass prediction value of 65%.

[0097] S604: normalize the prediction success rate of each historical user to obtain a normalized success rate.

[0098] Specifically, the prediction success rate of each historical user can be normalized directly using division. Select a benchmark value, divide all prediction success rates by this benchmark value, and get the normalized success rate. For example, the prediction success rates of 5 historical users are: 0.9, 0.7, 0.85, 0.6, 0.5. Use the maximum value of all prediction success rates as the benchmark value, that is, 0.9. Divide the prediction success rate of each historical user by the benchmark value, and the normalized success rate calculation process is: the normalized success rate of the first user is 0.9 / 0.9=1, the normalized success rate of the second user is 0.7 / 0.9≈0.78, the normalized success rate of the third user is 0.85 / 0.9≈0.94, the normalized success rate of the fourth user is 0.6 / 0.9≈0.67, and the normalized success rate of the fifth user is 0.5 / 0.9≈0.56. The normalized success rates are 1, 0.78, 0.94, 0.67, and 0.56 respectively.

[0099] Specifically, the prediction success rate of each historical user can be normalized using the maximum and minimum normalization to obtain the normalized success rate. For example, there is a data set containing the following four data points: 1, 3, 5, 7. The minimum value is 1 and the maximum value is 7. The first data point is normalized to (1-1) / (7-1)=0; the second data point is normalized to (3-1) / (7-1)≈0.33, the third data point is normalized to (5-1) / (7-1)≈0.67, and the fourth data point is normalized to (7-1) / (7-1)=1, resulting in the normalized data set: 0, 0.33, 0.67, 1.

[0100] S605: Perform function fitting based on at least one factor information and at least one normalized success rate of multiple historical users to obtain a preset function model.

[0101] Specifically, a linear regression model can be used to fit the function to obtain a preset function model. For example, there are two factors: user activity X1 and user age X2, and the corresponding normalized success rate Y. There are the following historical data: User 1: X1=5, X2=30, Y=0.8, User 2: X1=3, X2=25, Y=0.6, User 3: X1=7, X2=35, Y=0.9. A linear regression model can be used to fit these data. The linear regression model assumes that Y is a linear combination of X1 and X2, that is: Y=β0+β1*X1+β2*X2, where β0 is the intercept, β1 and β2 are coefficients, which can be calculated by the least squares method: β0=0.1, β1=0.15, β2=0.01. Therefore, the function model is: Y=0.1+0.15*X1+0.01*X2.

[0102] Specifically, a decision tree regression model can be used to perform function fitting to obtain a preset function model. For example, the above-mentioned data of user activity X1, user age X2 and normalized success rate Y are used. The decision tree regression model predicts the target variable by constructing a tree. Each node in the tree is split based on a factor information such as the value of X1 or X2, and the leaf nodes of the tree contain the predicted value of the target variable Y. The decision tree may divide users into different groups based on different ranges of user activity and user age, and assign an average normalized success rate to each group as the predicted value. By traversing the entire tree structure, the predicted value of each data point can be obtained, that is, the estimated value of the normalized success rate. In this way, a preset function model based on decision tree regression is obtained.

[0103] Specifically, the preset function model may be:

[0104] Y1=K0+K1X1+K2X2+K3X3+…+K n X n

[0105] Among them, Y1 is the normalized success rate, X1, X2, X3, X n is the factor information, K1, K2, K3, K4, K n is the coefficient of factor information.

[0106] In summary, based on the factor information and real success rate of historical users, the intermediate function model and the preset function model are obtained through function fitting. This preset function model can accurately reflect the relationship between factor information and success rate, and improve the accuracy of subsequent success rate calculation.

[0107] Figure 7 This is a schematic diagram of the structure of a factor adjustment device provided by an embodiment of the present application. Figure 7 As shown, the factor adjustment device includes: a user determination module 701 , a data acquisition module 702 , a solution determination module 703 and a factor adjustment module 704 .

[0108] The user determination module 701 is used to determine at least one user.

[0109] The data acquisition module 702 is used to obtain the importance of each user and the initial success rate of each user. The initial success rate is the success rate of target processing of the user under the influence of the immutable factor information in at least one factor information of the user. The at least one factor information of the user includes: factor information that affects the target processing of the user.

[0110] The solution determination module 703 is used to determine a target solution corresponding to at least one target user from at least one preset solution according to the importance and initial success rate respectively corresponding to at least one user, and the target solution is used to adjust variable factor information in at least one factor information of the target user.

[0111] The factor adjustment module 704 is used to adjust the variable factor information of the target user through the target solution of the target user.

[0112] In one embodiment, the solution determination module 703 includes: a matching unit, which is used to use the initial success rate of each user as the current success rate of the user, and perform multiple rounds of matching until there is no group solution that successfully matches the user in a round of matching, and the group solution is a solution for multiple users in at least one preset solution. The matching unit includes: a matching component, which is used to match at least one user with at least one preset solution arranged in sequence according to the importance and current success rate of each user and the activation conditions of each preset solution, and determine the target solution of the target user according to the preset solution that successfully matches the target user; an adjustment component, which is used to predict the success rate of the target user after adjustment of the corresponding target solution, so as to serve as the current success rate of the user in the next round of matching.

[0113] In one embodiment, the preset plan also includes an individual plan, which is a plan for one user. The matching component includes: a target plan calculation part, which is used to use the successfully matched individual plan as the target plan for the target user when one of the target users is successfully matched with one of the individual plans; a recording part, which is used to record the number of users who are successfully matched with the group plan when the target user is successfully matched with one of the group plans; and a target plan determination part, which is used to use the group plan as the target plan for the target user who is successfully matched with the group plan when the number of users is greater than or equal to the activation number threshold of the group plan.

[0114] In one embodiment, the data acquisition module 702 includes: an attribute information acquisition unit, used to acquire the attribute information of the user; and an adjustment unit, used to adjust the default importance of the user according to the attribute information to obtain the importance of the user.

[0115] In one embodiment, the adjustment unit includes: an adjustment amplitude determination component, which is used to determine the adjustment amplitude of the importance according to the attribute information, and different attribute information corresponds to different adjustment amplitudes; an adjustment component, which is used to adjust the user's default importance according to the adjustment amplitude if the attribute information corresponds to the target value.

[0116] In one embodiment, the initial success rate of the user and the success rate of the target user after adjustment of the corresponding target plan are both generated by a preset function model. The generation module of the preset function model includes: an acquisition unit, which is used to acquire at least one factor information of multiple historical users, and the actual success rate of target processing for each historical user under the influence of the at least one factor information; a first fitting unit, which is used to perform function fitting to obtain an intermediate function model through at least one factor information of multiple historical users and at least one actual success rate; a predicted success rate calculation unit, which is used to input at least one factor information of each historical user into the intermediate function model to obtain a predicted success rate of each historical user; a normalization unit, which is used to normalize the predicted success rate of each historical user to obtain a normalized success rate; and a second fitting unit, which is used to perform function fitting to obtain a preset function model through at least one factor information of multiple historical users and at least one normalized success rate.

[0117] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0118] Figure 8 The hardware structure diagram of an electronic device provided in one embodiment of the present application is shown in FIG. Figure 8 As shown, the electronic device of this embodiment includes: at least one processor 801 and a memory 802; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the above factor adjustment method.

[0119] Optionally, the memory 802 may be independent or integrated with the processor 801 .

[0120] When the memory 802 is independently provided, the service device further includes a bus 803 for connecting the memory 802 and the processor 801 .

[0121] The embodiment of the present application also provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the above factor adjustment method is implemented.

[0122] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above factor adjustment method when executed by a processor.

[0123] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0124] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0125] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0126] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0127] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0128] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0129] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0130] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0131] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0132] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A factor adjustment method, characterized in that: include: identifying at least one user; Obtaining the importance of each user and obtaining the initial success rate of each user, wherein the initial success rate is the success rate of performing target processing on the user under the influence of the immutable factor information in at least one factor information of the user, wherein the at least one factor information of the user includes: factor information that affects performing the target processing on the user; Determining a target solution corresponding to at least one target user from at least one preset solution according to the importance level and the initial success rate respectively corresponding to at least one user, wherein the target solution is used to adjust variable factor information in at least one factor information of the target user; The variable factor information of the target user is adjusted through the target plan of the target user.

2. The method according to claim 1, characterized in that: The determining, according to the importance level and the initial success rate respectively corresponding to at least one user, a target solution corresponding to at least one target user from at least one preset solution comprises: The initial success rate of each user is used as the current success rate of the user, and multiple rounds of matching are performed until there is no group solution that successfully matches the user in a round of matching, and the group solution is a solution for multiple users in the at least one preset solution; Each round of matching process includes: According to the importance and the current success rate of each user and the activation condition of each preset solution, at least one user is matched with at least one preset solution arranged in sequence, and a target solution for the target user is determined according to the preset solution that successfully matches the target user; The success rate of the target user after adjustment corresponding to the target solution is predicted as the current success rate of the user in the next round of matching.

3. The method according to claim 2, characterized in that The preset solution also includes an individual solution, which is a solution for one user. Determining the target solution for the target user according to the preset solution that successfully matches the target user includes: When one of the target users is successfully matched with one of the individual plans, the successfully matched individual plan is used as the target plan of the target user; When the target user successfully matches one of the group plans, the number of users successfully matching the group plan is recorded; When the number of users is greater than or equal to the activation number threshold of the group plan, the group plan is used as the target plan for the target users who successfully match the group plan.

4. The method according to claim 2, characterized in that: The activation conditions of the preset scheme include: importance range, success rate range; Correspondingly, the user successfully matches the preset solution including: the importance of the user is within the importance range, and the success rate of the user is within the success rate range.

5. The method according to claim 2, characterized in that: The ranking factor of the at least one preset solution includes at least one of the following: an adjustment cost of the preset solution, a minimum activation success rate of the preset solution, and a degree of influence of the preset solution on the target processing.

6. The method according to any one of claims 1 to 5, characterized in that The obtaining of the importance of each user includes: Obtaining attribute information of the user; The default importance of the user is adjusted according to the attribute information to obtain the importance of the user.

7. The method according to claim 6, characterized in that The adjusting the default importance of the user according to the attribute information to obtain the importance of the user includes: Determining an adjustment range of the importance according to the attribute information, where different attribute information corresponds to different adjustment ranges; If the attribute information corresponds to the target value, the default importance of the user is adjusted according to the adjustment range.

8. The method according to any one of claims 2 to 5, characterized in that The initial success rate of the user and the success rate of the target user after adjustment corresponding to the target solution are both generated by a preset function model. The generation process of the preset function model includes: Acquire at least one factor information of a plurality of historical users, and the actual success rate of performing the target processing on each of the historical users under the influence of the at least one factor information; Performing function fitting based on the at least one factor information of the multiple historical users and the at least one real success rate to obtain an intermediate function model; Inputting the at least one factor information of each of the historical users into the intermediate function model to obtain the prediction success rate of each of the historical users; Normalizing the prediction success rate of each of the historical users to obtain a normalized success rate; A preset function model is obtained by performing function fitting based on the at least one factor information and the at least one normalized success rate of the multiple historical users.

9. A factor adjustment device, characterized in that: include: A user determination module, used to determine at least one user; A data acquisition module, used to acquire the importance of each user and the initial success rate of each user, wherein the initial success rate is the success rate of performing target processing on the user under the influence of the immutable factor information in at least one factor information of the user, wherein the at least one factor information of the user includes: factor information that affects performing the target processing on the user; a scheme determination module, configured to determine a target scheme corresponding to at least one target user from at least one preset scheme according to the importance level and the initial success rate respectively corresponding to at least one user, wherein the target scheme is used to adjust variable factor information in at least one factor information of the target user; A factor adjustment module is used to adjust the variable factor information of the target user through the target solution of the target user.

10. An electronic device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method according to any one of claims 1 to 8.

11. A computer storage medium, characterized in that: The computer storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1 to 8 is implemented.

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

Citation Information

Cited By

  • Photovoltaic power generation power prediction method and device, electronic equipment and storage medium

    CN119809043A

  • Methods, devices, electronic equipment, and storage media for predicting photovoltaic power generation.

    CN119809043B