Welfare distribution method and device based on user portrait and electronic equipment

Abstract

The invention belongs to the technical field of job big data analysis, and particularly discloses a welfare allocation method and device based on a user portrait and electronic equipment, and the method comprises the steps: obtaining the basic information of a user, and extracting the user features in the basic information; distributing weights for different user features according to the user feature types; generating a user portrait based on the user features and the weights corresponding to the different user features; and based on the user portraits corresponding to different users, allocating corresponding welfare to the users. According to the method, welfare distribution can be accurately matched with member contributions and demands, and the fairness and flexibility of welfare distribution are improved.

Description

Technical Field

[0001] This application belongs to the field of trade union big data analysis technology, and more specifically, relates to a welfare distribution method, device and electronic device based on user profiles. Background Technology

[0002] Currently, union welfare distribution is generally carried out indiscriminately, meaning that all members enjoy the same benefits regardless of factors such as length of service or job rank. This approach does not take into account individual differences and contributions among members, resulting in a lack of incentive and fairness in welfare distribution. Alternatively, it may be based on a single factor, determining welfare solely based on factors such as job rank or length of service, which fails to fully reflect members' contributions and needs and is prone to causing unreasonable welfare distribution.

[0003] The above-mentioned welfare distribution method does not take into account the individual differences of members and the factors considered in the distribution are too simplistic, which results in the welfare distribution not being able to accurately match the members' contributions and needs, and thus failing to achieve fair, flexible and personalized distribution. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the purpose of this application is to provide a welfare distribution method, device, and electronic device based on user profiles, aiming to solve the problem that existing welfare distribution methods do not consider individual differences among members and have only one factor in consideration, resulting in the welfare distribution not being able to accurately match members' contributions and needs.

[0005] To achieve the above objectives, firstly, this application provides a welfare allocation method based on user profiles, including: Obtain the user's basic information and extract the user features from the basic information; Assign weights to different user characteristics based on user characteristic types; User profiles are generated based on the user features and the weights corresponding to different user features; Based on the user profiles of different users, corresponding benefits are allocated to users.

[0006] This application extracts features from users' basic information, considers multiple factors, and generates user profiles by assigning weights to each factor. It then provides targeted welfare allocations for members with different user profiles, enabling welfare allocation to accurately match members' contributions and needs, thereby improving the fairness and flexibility of welfare allocation.

[0007] According to the user profile-based welfare allocation method provided in this application, after obtaining the user's basic information and extracting user features from the basic information, the method further includes: The user characteristics are cleaned and standardized.

[0008] This application cleanses and standardizes user characteristics to facilitate subsequent calculations.

[0009] According to the welfare allocation method based on user profiles provided in this application, the step of assigning weights to different user characteristics based on user characteristic types includes: Assign initial weights to different user features based on user feature type; The user features are weighted and summed based on the initial weights to obtain a first weighted value; Based on the first weighted value and the preset target value, a loss function is set; Gradient calculation is performed based on the loss function, and the initial weights are updated until the loss function converges to near the minimum value, thereby obtaining the optimized weights corresponding to different user features.

[0010] This application uses loss functions and gradient algorithms to dynamically learn and adjust the weights of various factors affecting welfare distribution. It can automatically optimize based on actual data to find the weight combination that makes the welfare distribution scheme closest to the ideal. This data-driven weight adjustment method can fully consider the impact of multiple factors on welfare distribution, and dynamically adjust the weights in real time as the data is continuously updated and the algorithm continues to learn.

[0011] According to the welfare allocation method based on user profiles provided in this application, the step of generating user profiles based on the user characteristics and the weights corresponding to different user characteristics includes: The user features are weighted and summed based on the weights corresponding to the different user features to obtain a second weighted value; Based on the second weighted value and the preset threshold, user profiles corresponding to different users are generated.

[0012] Secondly, this application provides a welfare allocation device based on user profiles, comprising: The acquisition module is used to acquire the user's basic information and extract user features from the basic information; The first allocation module is used to assign weights to different user features based on the user feature type. The generation module is used to generate user profiles based on the user features and the weights corresponding to different user features; The second allocation module is used to allocate corresponding benefits to users based on their respective user profiles.

[0013] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the user profile-based welfare allocation method described in the first aspect or any possible implementation thereof.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to perform the user profile-based welfare allocation method described in the first aspect or any possible implementation of the first aspect.

[0015] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to execute the user profile-based welfare allocation method described in the first aspect or any possible implementation of the first aspect.

[0016] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0017] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art: (1) This application extracts features from the user’s basic information, takes into account a variety of factors, and generates a user profile by assigning weights to each factor. It then provides targeted welfare allocation for members with different user profiles, so that the welfare allocation can accurately match the member’s contribution and needs, thereby improving the fairness and flexibility of the welfare allocation.

[0018] (2) This application uses loss function and gradient algorithm to dynamically learn and adjust the weights of each factor affecting welfare distribution. It can automatically find the weight combination that makes the welfare distribution scheme closest to the ideal by using actual data. This data-driven weight adjustment method can fully consider the influence of multiple factors on welfare distribution, and adjust the weights in real time as the data is continuously updated and the algorithm continues to learn. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1This is a flowchart illustrating the welfare allocation method based on user profiles provided in an embodiment of this application; Figure 2 This is a schematic diagram of the weight adjustment process provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of the welfare distribution device based on user profiles provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0023] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0024] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple processing units means two or more processing units, multiple elements means two or more elements, etc.

[0025] Next, combined Figures 1-2 The welfare allocation method based on user profiles provided in the embodiments of this application is introduced.

[0026] Figure 1 This is a flowchart illustrating the user profile-based welfare allocation method provided in this application embodiment, as shown below. Figure 1 As shown, the method includes the following steps: Step 100: Obtain the user's basic information and extract user features from the basic information; Optionally, the user's basic information may include, but is not limited to, the user's personal information, such as age and gender, and the user's work information, such as length of service and job title.

[0027] Alternatively, user characteristics can be factors in personal information that are considered to influence welfare allocation.

[0028] In one embodiment of this application, data such as length of service, job rank, amount of contributions, number of years of contributions, frequency and activity of participation in union activities (such as attendance records, number of times speaking, and creative solutions contributed in union activities), work performance rating (which can be obtained by connecting to the enterprise management system or by the union regularly collecting department head evaluations), and honors received are extracted as user characteristics.

[0029] Step 110: Assign weights to different user features based on user feature type; Optionally, the allocation principle can be based on the degree of influence of user characteristic type on welfare allocation, with greater influence assigned a larger weight and less influence assigned a smaller weight.

[0030] Step 120: Generate user profiles based on user features and the weights corresponding to different user features; Step 130: Based on the user profiles of different users, allocate corresponding benefits to the users.

[0031] Optionally, user profiles can be used to differentiate user levels, allowing for a more equitable distribution of benefits towards higher-level users.

[0032] For example, if user profile levels are A, B, C, and D from high to low, high-end holiday gifts and premium health check-up packages can be assigned to users of category A, ordinary holiday gifts and basic health check-up packages can be assigned to users of category B, simple holiday gifts and basic health check-up services can be assigned to users of category C, and basic gifts and routine health check-up services can be assigned to users of category D.

[0033] The user profile-based welfare allocation method provided in this application extracts features from users' basic information, considers multiple factors, and generates a weighted user profile by assigning weights to each factor. This allows for targeted welfare allocation to members with different user profiles, enabling welfare allocation to accurately match members' contributions and needs, and improving the fairness and flexibility of welfare allocation.

[0034] In some embodiments, after step 100, the method further includes: User characteristics are cleaned and standardized.

[0035] The collected user feature data across various dimensions is cleaned and standardized. This includes imputing missing values ​​(using the mean, median, or interpolation based on similar members), correcting outliers (setting upper and lower thresholds based on historical data distribution, and taking values ​​exceeding the threshold), and normalizing data from different dimensions (such as amount, frequency, rating, etc.) to ensure they fall within the same numerical range (e.g., 0-1). Assuming the system has m dimensions, the multidimensional data of an employee i can be represented as (v... i1 ,v i2 ,...,v im ), where v ij Let i be the value of employee i after data normalization in the j-th dimension.

[0036] In some embodiments, step 110 specifically includes: Step 1101: Assign initial weights to different user features based on user feature type; Step 1102: Perform a weighted summation of the user features based on the initial weights to obtain the first weighted value; Step 1103: Set the loss function based on the first weighted value and the preset target value; Step 1104: Calculate the gradient based on the loss function and update the initial weights until the loss function converges to near the minimum value, thereby obtaining the optimized weights corresponding to different user features.

[0037] Figure 2 This is a schematic diagram of the weight adjustment process provided in the embodiments of this application, such as... Figure 2 As shown, the weights corresponding to different user characteristics are adjusted through the following steps: First, initial weights are assigned to different user features based on the user feature type.

[0038] Optionally, based on the union's past experience in welfare distribution and a preliminary assessment of the importance of each factor, an initial weight can be assigned to each user characteristic that affects welfare distribution.

[0039] For example, the initial weights are set as follows: length of service 0.2, job rank 0.3, years of contribution 0.15, honors received 0.25, and participation in activities 0.1. These initial weights will serve as the starting point for the gradient descent algorithm. The weights for each dimension can be denoted as (w1, w2, ..., w...). m ).

[0040] Then, a weighted calculation is performed based on user characteristic data from different dimensions, such as the member's length of service, job level, years of contribution, honors received, and enthusiasm for participating in union activities, to obtain the member's comprehensive score. The calculation method is as follows: For employee i, calculate the first weighted value of its m-dimensional user feature data:

[0041] The loss function is used to measure the difference between the current user's first weighted value and the preset target value.

[0042] Optionally, the preset target value can be determined based on reasonable scoring cases approved by the trade union in historical data, or it can be obtained by deep learning algorithms or other methods. This application does not limit this.

[0043] Optionally, the loss function can be the mean squared error function, which is the average of the squares of the differences between the first weighted value of each member calculated based on the current weights and the preset target value. The formula is as follows:

[0044] in, It is the first weighted value calculated based on the current weights of each dimension. is the preset target value, and n is the number of members.

[0045] The gradient is the partial derivative of the loss function with respect to each weight; it indicates the direction and rate of change of the loss function in the weight space. For each weight w... j Calculate its gradient:

[0046] The weights are updated according to the principle of gradient descent. The update formula is:

[0047] Among them, w j Let j be the weight of the j-th dimension. The learning rate (controls the adjustment range for each iteration, which can be set between 0.01 and 0.1). For the loss function on w j The partial derivatives of .

[0048] Repeat the update process until the loss function converges to near its minimum value, at which point the optimized weights for each data dimension are obtained.

[0049] In some embodiments, step 120 specifically includes: Step 1201: The user features are weighted and summed based on the weights corresponding to different user features to obtain the second weighted value; Step 1202: Based on the second weighted value and the preset threshold, generate user profiles corresponding to different users.

[0050] Once the weights reach their optimal state, the weights are calculated by combining the specific data of each member on each user characteristic with the final determined weights to obtain the second weighted value for each member. Then, a user profile corresponding to each member can be generated based on the second weighted value and the preset threshold.

[0051] Optionally, the preset threshold can be several specific weighted values, forming several weighted value intervals, each interval corresponding to a different user profile. Alternatively, it can be set as a percentage based on the number of users. For example, users can be sorted from largest to smallest according to the second weighted value, with the top 10% of users being type A, 10%-30% being type B, 30%-60% being type C, and 60%-100% being type D.

[0052] Optionally, the preset threshold can be set according to actual needs, and this application does not limit it.

[0053] Figure 3 This is a schematic diagram of a welfare distribution device based on user profiles provided in an embodiment of this application, as shown below. Figure 3 As shown, the system includes an acquisition module 310, a first allocation module 320, a generation module 330, and a second allocation module 330, wherein: The acquisition module 310 is used to acquire the user's basic information and extract user features from the basic information; The first allocation module 320 is used to allocate weights to different user features according to the user feature type; The generation module 330 is used to generate user profiles based on user features and the weights corresponding to different user features. The second allocation module 340 is used to allocate corresponding benefits to users based on their respective user profiles.

[0054] Based on the methods in the above embodiments, Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown in the illustration, this application provides an electronic device that may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440. The processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions stored in the memory 430 to execute the user profile-based welfare allocation method described in the above embodiment.

[0055] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the user profile-based welfare allocation method described in the various embodiments of this application.

[0056] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the user profile-based welfare allocation method in the above embodiments.

[0057] Based on the methods in the above embodiments, this application provides a computer program product that, when running on a processor, causes the processor to execute the user profile-based welfare allocation method in the above embodiments.

[0058] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0059] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from 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 reside in an ASIC.

[0060] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0061] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0062] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A welfare allocation method based on user profiles, characterized in that, include: Obtain the user's basic information and extract the user features from the basic information; Assign weights to different user characteristics based on user characteristic types; User profiles are generated based on the user features and the weights corresponding to different user features; Based on the user profiles of different users, corresponding benefits are allocated to users.

2. The welfare allocation method based on user profiles according to claim 1, characterized in that, After obtaining the user's basic information and extracting user features from the basic information, the method further includes: The user characteristics are cleaned and standardized.

3. The welfare allocation method based on user profiles according to claim 1 or 2, characterized in that, The process of assigning weights to different user features based on user feature type includes: Assign initial weights to different user features based on user feature type; The user features are weighted and summed based on the initial weights to obtain a first weighted value; Based on the first weighted value and the preset target value, a loss function is set; Gradient calculation is performed based on the loss function, and the initial weights are updated until the loss function converges to near the minimum value, thereby obtaining the optimized weights corresponding to different user features.

4. The welfare allocation method based on user profiles according to claim 1, characterized in that, The process of generating a user profile based on the user features and the weights corresponding to different user features includes: The user features are weighted and summed based on the weights corresponding to the different user features to obtain a second weighted value; Based on the second weighted value and the preset threshold, user profiles corresponding to different users are generated.

5. A welfare allocation device based on user profiles, characterized in that, include: The acquisition module is used to acquire the user's basic information and extract user features from the basic information; The first allocation module is used to assign weights to different user features based on the user feature type. The generation module is used to generate user profiles based on the user features and the weights corresponding to different user features; The second allocation module is used to allocate corresponding benefits to users based on their respective user profiles.

6. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the user profile-based welfare allocation method as described in any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, the processor performs the user profile-based welfare allocation method as described in any one of claims 1-4.

8. A computer program product, characterized in that, When the computer program product is run on a processor, the processor performs the user profile-based welfare allocation method as described in any one of claims 1-4.

Images