Data generation method and device based on big data analysis, equipment and storage medium

Abstract

The invention provides a data generation method and device based on big data analysis, computer equipment and a storage medium. The method comprises the following steps: acquiring user data of a user; calculating an index value of the user under a preset portrait dimension based on the user data; correspondingly converting the index value of the user under each portrait dimension into a target label of the user under each portrait dimension based on a preset label quantification rule; generating user portrait data of the user based on all the target tags; factors related to credit evaluation are screened out from the user portrait data; generating weights corresponding to the factors based on a preset weight generation strategy; performing calculation processing on each factor and the weight corresponding to each factor to obtain a target credit score of the user; and generating a target credit rating of the user based on the target credit score. According to the invention, the construction efficiency of the user credit evaluation system is effectively improved, and the fairness and accuracy of the generated user credit rating are ensured.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a data generation method, device, computer equipment and storage medium based on big data analysis. Background Art

[0002] In the rapidly developing Internet freight transportation industry, drivers play an important role as service providers, and their behavior and performance directly affect the service quality and user experience. Users, as service experiencers, their cooperation attitude, punctuality, communication efficiency and other behaviors and performances will also directly affect the driver's service quality. The two roles influence each other in the process of freight transportation.

[0003] At present, the evaluation of user behavior in the field of freight transportation mainly relies on manual review and analysis, that is, relevant personnel collect and organize a large amount of information related to user credit evaluation, and then make subjective judgments to build a user credit evaluation system. However, this way of building a credit evaluation system has significant technical limitations: 1. Inefficiency: With the surge in freight transportation, the amount of data that needs to be processed is growing exponentially. The manual review method is not only time-consuming and laborious, but also difficult to cope with the needs of large-scale data processing, resulting in a long credit score update cycle and failure to reflect the latest performance of users and drivers in a timely manner. 2. Accuracy is difficult to guarantee: The manual evaluation process will inevitably be affected by subjective factors such as the personal experience and emotional preferences of the evaluator, resulting in a lack of unified standards and objectivity in the evaluation results, affecting the fairness and accuracy of the evaluation. Summary of the invention

[0004] The main purpose of the present invention is to provide a data generation method, device, computer equipment and storage medium based on big data analysis, aiming to solve the technical problems of low efficiency and difficulty in ensuring accuracy in the construction method of the credit evaluation system adopted in the prior art.

[0005] To achieve the above object, the present invention provides a data generation method based on big data analysis, the method comprising:

[0006] Obtaining user data of the user; wherein the user data at least includes driver evaluation data, historical order data and personal information;

[0007] Calculating an index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple;

[0008] Based on a preset label quantization rule, the indicator value of the user in each of the portrait dimensions is converted into a target label of the user in each of the portrait dimensions;

[0009] Generate user portrait data of the user based on all the target tags;

[0010] Screening out factors related to credit evaluation from the user portrait data;

[0011] Generate weights corresponding to each of the factors based on a preset weight generation strategy;

[0012] Calculating and processing each of the factors and the weights corresponding to each of the factors to obtain a target credit score of the user;

[0013] A target credit rating for the user is generated based on the target credit score.

[0014] Optionally, generating user portrait data of the user based on all the target tags includes:

[0015] Get the preset data structure;

[0016] Integrate all the target tags into the data structure to obtain a corresponding target data structure;

[0017] The target data structure is used as user portrait data of the user.

[0018] Optionally, the generating weights corresponding to the factors respectively based on a preset weight generating strategy includes:

[0019] Call the preset weight generation model;

[0020] Inputting each of the factors into the weight generation model, and generating feature importance information corresponding to each of the factors through the weight generation model;

[0021] Based on the feature importance information of each of the factors, weights corresponding to each of the factors are generated.

[0022] Optionally, the calculating and processing each of the factors and the weights respectively corresponding to the factors to obtain the target credit score of the user includes:

[0023] Obtaining quantitative indicators corresponding to each of the factors;

[0024] Calling a preset credit scoring formula;

[0025] Based on the credit scoring formula, the quantitative index of each factor and the weight corresponding to each factor are calculated to obtain a corresponding calculation result;

[0026] The calculation result is used as the target credit score of the user.

[0027] Optionally, generating the target credit level of the user based on the target credit score includes:

[0028] Get the score range of each preset credit rating;

[0029] Filtering out a designated scoring interval corresponding to the target credit score from all the scoring intervals of the credit rating;

[0030] Obtaining a specified credit rating corresponding to the specified scoring interval;

[0031] The designated credit rating is used as the target credit rating.

[0032] Optionally, the calculating the indicator value of the user under a preset portrait dimension based on the user data includes:

[0033] Obtain preset data cleaning strategies and data standardization strategies;

[0034] Cleaning the user data based on the data cleaning strategy to obtain corresponding first user data;

[0035] Performing standardization processing on the first user data based on the data standardization strategy to obtain corresponding second user data;

[0036] Based on the second user data, the index value of the user in each portrait dimension is calculated.

[0037] Optionally, after generating the target credit level of the user based on the target credit score, the method further includes:

[0038] Call the preset reward and punishment strategy library;

[0039] Determining a target reward and punishment strategy corresponding to the target credit rating from the reward and punishment strategy library;

[0040] Based on the target reward and punishment strategy, corresponding reward and punishment processing is performed on the user.

[0041] In addition, to achieve the above-mentioned purpose, the present invention further provides a data generation device based on big data analysis, the data generation device based on big data analysis comprising:

[0042] A first acquisition module is used to acquire user data of the user; wherein the user data at least includes driver evaluation data, historical order data and personal information;

[0043] A first calculation module, configured to calculate an index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple;

[0044] A conversion module, configured to convert the index value of the user in each of the portrait dimensions into a target label of the user in each of the portrait dimensions based on a preset label quantization rule;

[0045] A first generating module, used to generate user portrait data of the user based on all the target tags;

[0046] A screening module, used to screen out factors related to credit evaluation from the user portrait data;

[0047] A second generating module, used for generating weights corresponding to the factors respectively based on a preset weight generating strategy;

[0048] A second calculation module is used to calculate and process each of the factors and the weights corresponding to each of the factors to obtain a target credit score of the user;

[0049] The third generating module is used to generate the target credit level of the user based on the target credit score.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0051] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the data generation method based on big data analysis proposed in any one of the embodiments of the present application are implemented.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0053] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the data generation method based on big data analysis proposed in any one of the embodiments of the present application are implemented.

[0054] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0055] The present invention provides a data generation method, device, computer equipment and storage medium based on big data analysis, the method comprising: first obtaining user data of a user; wherein the user data at least includes driver evaluation data, historical order data and personal information; then calculating the index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple; then based on a preset label quantification rule, converting the index value of the user under each of the portrait dimensions into the target label of the user under each of the portrait dimensions; subsequently generating the user portrait data of the user based on all the target labels, and screening out factors related to credit evaluation from the user portrait data; further generating weights corresponding to each of the factors based on a preset weight generation strategy, and calculating and processing each of the factors and the weights corresponding to each of the factors to obtain the target credit score of the user; finally generating the target credit rating of the user based on the target credit score. The present application calculates the index value of the user under the preset portrait dimension based on the acquired user data, and converts the index value of the user under each of the portrait dimensions into the target label of the user under each of the portrait dimensions based on the label quantification rule, thereby automatically generating the user portrait data of the user based on all the target labels. Subsequently, factors related to credit evaluation are screened out from the user portrait data, and weights corresponding to each of the factors are generated based on a preset weight generation strategy. Then, each of the factors and the weights corresponding to each of the factors are calculated and processed to obtain the user's target credit score, and then the user's target credit rating is automatically and accurately generated based on the target credit score. This application can automatically and quickly establish a user portrait and user credit evaluation system based on multi-dimensional user data, effectively reducing the workload of manual review, improving the efficiency of building user portraits and user credit evaluation systems, and avoiding the influence of manual subjective evaluation, ensuring the fairness and accuracy of the generated user credit rating, and is conducive to providing more comprehensive and objective user credit evaluation and management methods for related enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0058] Figure 2is a flow chart of a data generation method based on big data analysis provided by an embodiment of the present invention;

[0059] Figure 3 is a structural schematic diagram of an embodiment of a data generation device based on big data analysis according to the present application;

[0060] Figure 4 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION

[0061] The data generation method based on big data analysis provided by the embodiment of the present invention is applied to the data generation device based on big data analysis. Unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned figures are used to distinguish different objects, not to describe a specific order.

[0062] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0064] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0065] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.

[0066] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0067] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0068] It should be noted that the data generation method based on big data analysis provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the data generation device based on big data analysis is generally arranged in the server / terminal device.

[0069] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0070] In the rapidly developing Internet freight transportation industry, drivers play an important role as service providers, and their behavior and performance directly affect the service quality and user experience. Users, as service experiencers, their cooperation attitude, punctuality, communication efficiency and other behaviors and performances will also directly affect the driver's service quality. The two roles influence each other in the process of freight transportation.

[0071] At present, the evaluation of user behavior in the field of freight transportation mainly relies on manual review and analysis, that is, relevant personnel collect and organize a large amount of information related to user credit evaluation, and then make subjective judgments to build a user credit evaluation system. However, this way of building a credit evaluation system has significant technical limitations: 1. Inefficiency: With the surge in freight transportation, the amount of data that needs to be processed is growing exponentially. The manual review method is not only time-consuming and laborious, but also difficult to cope with the needs of large-scale data processing, resulting in a long credit score update cycle and failure to reflect the latest performance of users and drivers in a timely manner. 2. Accuracy is difficult to guarantee: The manual evaluation process will inevitably be affected by subjective factors such as the personal experience and emotional preferences of the evaluator, resulting in a lack of unified standards and objectivity in the evaluation results, affecting the fairness and accuracy of the evaluation.

[0072] Continue to refer Figure 2 , shows a flow chart of an embodiment of a data generation method based on big data analysis proposed in this application. The embodiment of this application can acquire and process relevant data based on artificial intelligence technology.

[0073] The data generation method based on big data analysis provided by the embodiment of the present invention comprises the following steps:

[0074] S210, obtaining user data of the user; wherein the user data at least includes driver evaluation data, historical order data and personal information.

[0075] In this step, the present invention can be applied to the scenario of building user portraits for transportation service experiencers (users) and establishing a user credit evaluation system in the field of Internet freight transportation. Specifically, relevant data, that is, user data of users, can be collected from the driver evaluation system, order management system and user registration system, and the security and privacy protection of the data can be ensured, and relevant laws and regulations must be complied with. Among them, the above-mentioned driver evaluation data includes the driver's evaluation of the user after each cargo transportation order (such as ratings, text evaluations, complaint records, etc.), reflecting the user's car use behavior and attitude. The above-mentioned historical order data includes order frequency, order amount, payment status, cancellation records, complaint records, etc., reflecting the user's consumption capacity and stability. The above-mentioned personal information may include registration information such as name, gender, age, occupation, contact information and other information.

[0076] S220, calculating the index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple.

[0077] In this step, the above-mentioned portrait dimensions at least include driver evaluation dimension, consumption habit dimension and personal information dimension. Among them, the driver evaluation dimension is based on driver evaluation data to evaluate the user's car use behavior and attitude. The consumption habit dimension is based on historical order data to analyze the user's consumption ability, consumption preference and order stability. The personal information dimension is based on registration information to understand the user's basic attributes and social background. In addition, the specific implementation process of calculating the indicator value of the user under the preset portrait dimension based on the user data will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0078] S230, based on a preset label quantization rule, convert the indicator value of the user in each of the portrait dimensions into a target label of the user in each of the portrait dimensions.

[0079] In this step, specific labels and quantitative standards can be designed for each portrait dimension in advance according to the actual portrait construction requirements to obtain the above-mentioned label quantification rules. Among them, the portrait dimensions and labels can be defined based on the label quantification rules. Specifically, 1) For the driver evaluation dimension, the label definition is: "high-rated users" (average rating ≥ 4.5 stars), "low complaint rate users" (number of complaints / number of orders <0.01), "positive feedback users" (positive evaluation ratio > 80%), etc. Quantification standard: calculated based on data such as ratings, number of complaints and evaluation content. 2) For the consumption habit dimension, the label definition is: "high-frequency consumption users" (monthly orders ≥ 10 times), "large-amount consumption users" (average order amount > X yuan, X is the threshold set according to the business), "stable consumption users" (order records for N consecutive months, N is the set value), etc. Quantification standard: calculated based on data such as order quantity, order amount and order time interval. 3) For the personal information dimension, the label definition is directly generated based on the registration information, such as "young users" (age range 18-30 years old), "business people" (the occupation field contains keywords such as "business" and "management"), etc. Quantitative criteria: Match or classify directly based on the value of the registration information field. In addition, statistical methods or machine learning algorithms can be used to score or classify users to quantify their performance in various portrait dimensions. In addition, after calculating the index value of the user in the preset portrait dimension based on the user data, the user can be assigned a corresponding label according to the label and quantitative criteria defined in the above label quantification rules, thereby obtaining the user's target label in each of the portrait dimensions.

[0080] S240: Generate user portrait data of the user based on all the target tags.

[0081] In this step, the specific implementation process of generating the user portrait data of the user based on all the target tags will be described in further detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0082] S250, screening out factors related to credit evaluation from the user portrait data.

[0083] In this step, data analysis can be performed on the user portrait data to screen out factors directly related to credit evaluation. Specifically, in the driver evaluation dimension, the average score and complaint rate may more directly reflect the user's credit status, and the average score and complaint rate are used as factors related to credit evaluation; in the consumption habit dimension, order stability (such as cancellation rate) and payment records (such as overdue payment) are important credit indicators, and the cancellation rate and overdue payment are used as factors related to credit evaluation. In the personal information dimension, the direct correlation between personal information and credit may not be as good as the first two, but it can be used as an auxiliary factor, such as using one or more of age, occupation, income level, etc. as factors related to credit evaluation.

[0084] S260: Generate weights corresponding to the factors based on a preset weight generation strategy.

[0085] In this step, the specific implementation process of generating weights corresponding to each of the factors based on the preset weight generation strategy will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0086] S270, calculating and processing each of the factors and the weights corresponding to each of the factors to obtain a target credit score of the user.

[0087] In this step, the specific implementation process of calculating and processing each of the factors and the weights corresponding to each of the factors to obtain the target credit score of the user will be further described in detail in the subsequent specific embodiments of the present application, and will not be elaborated on here.

[0088] S280: Generate a target credit rating for the user based on the target credit score.

[0089] In this step, the specific implementation process of generating the target credit level of the user based on the target credit score will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0090] In an embodiment of the present invention, firstly, the user data of the user is obtained; wherein the user data at least includes driver evaluation data, historical order data and personal information; then, the index value of the user under the preset portrait dimension is calculated based on the user data; wherein the number of the portrait dimensions includes multiple; then, based on the preset label quantification rule, the index value of the user under each of the portrait dimensions is converted into the target label of the user under each of the portrait dimensions; subsequently, the user portrait data of the user is generated based on all the target labels, and factors related to credit evaluation are screened out from the user portrait data; further, the weights corresponding to each of the factors are generated based on the preset weight generation strategy, and each of the factors and the weights corresponding to each of the factors are calculated and processed to obtain the target credit score of the user; finally, the target credit level of the user is generated based on the target credit score. This application calculates the index value of the user under the preset portrait dimension based on the acquired user data, and converts the index value of the user under each of the portrait dimensions into the target label of the user under each of the portrait dimensions based on the label quantification rule, thereby automatically generating the user portrait data of the user based on all the target labels. Subsequently, factors related to credit evaluation are screened out from the user portrait data, and weights corresponding to each of the factors are generated based on a preset weight generation strategy. Then, each of the factors and the weights corresponding to each of the factors are calculated and processed to obtain the user's target credit score, and then the user's target credit rating is automatically and accurately generated based on the target credit score. This application can automatically and quickly establish a user portrait and user credit evaluation system based on multi-dimensional user data, effectively reducing the workload of manual review, improving the efficiency of building user portraits and user credit evaluation systems, and avoiding the influence of manual subjective evaluation, ensuring the fairness and accuracy of the generated user credit rating, and is conducive to providing more comprehensive and objective user credit evaluation and management methods for related enterprises.

[0091] Optionally, generating user portrait data of the user based on all the target tags includes:

[0092] Get the preset data structure.

[0093] In this step, the above data structure is a pre-constructed structure for forming a portrait.

[0094] All the target tags are integrated into the data structure to obtain a corresponding target data structure.

[0095] In this step, all the target tags are integrated into a unified data structure to form comprehensive user portrait data.

[0096] The target data structure is used as user portrait data of the user.

[0097] In this step, after generating the user's user portrait data, you can further use visualization tools (such as Tableau, Power BI, Python's Matplotlib / Seaborn, etc.) to display the user's user portrait data in the form of charts, dashboards, etc. to ensure that the visualization results are intuitive and easy to understand, and can clearly show the user's characteristics and performance, which is conducive to providing enterprises with deeper user insights and decision support.

[0098] In this embodiment, a preset data structure is obtained; then all the target tags are integrated into the data structure to obtain a corresponding target data structure; and the target data structure is subsequently used as the user portrait data of the user. This application integrates all the target tags into a preset data structure, thereby enabling the user portrait data of the user to be constructed quickly and intelligently, thereby improving the efficiency of constructing the user portrait data and the intelligence of generating the user portrait data.

[0099] Optionally, the generating weights corresponding to the factors respectively based on a preset weight generating strategy includes:

[0100] Call the preset weight generation model.

[0101] In this step, there is no specific limitation on the selection of the weight generation model, which can be determined according to actual business needs. For example, any one of decision tree, random forest, gradient boosting tree, etc. can be used as the weight generation model.

[0102] Each of the factors is input into the weight generation model, and feature importance information corresponding to each of the factors is generated through the weight generation model.

[0103] In this step, the feature importance of each of the input factors is evaluated by using a weight generation model, and feature importance information corresponding to each of the factors is output.

[0104] Based on the feature importance information of each of the factors, weights corresponding to each of the factors are generated.

[0105] In this step, the feature importance information of each factor is normalized to obtain the corresponding normalized target feature importance, and then the target feature importance of each factor is used as the weight corresponding to each factor. The maximum and minimum normalization or Z-score normalization method can be used for normalization to ensure the consistency of the weight.

[0106] In this embodiment, a preset weight generation model is called; each of the factors is then input into the weight generation model, and feature importance information corresponding to each of the factors is generated by the weight generation model; and weights corresponding to each of the factors are subsequently generated based on the feature importance information of each of the factors. This application selects factors related to credit evaluation from the user portrait data, and processes each of the factors using the feature importance evaluation function of the weight generation model to quickly and accurately determine the weights corresponding to each of the factors, thereby improving the efficiency of determining the weights of the factors and ensuring the data accuracy of the weights of the factors.

[0107] Optionally, the calculating and processing each of the factors and the weights respectively corresponding to the factors to obtain the target credit score of the user includes:

[0108] Obtain quantitative indicators corresponding to each of the factors.

[0109] In this step, for each factor, specific quantitative indicators are designed according to the actual processing requirements. For example, the service evaluation dimension can be quantified using indicators such as average score and complaint rate; the consumption habit dimension can be quantified using indicators such as order frequency and order amount; the personal information dimension may involve indicators such as age and career stability for quantification.

[0110] Call the preset credit scoring formula.

[0111] In this step, the above credit scoring formula may specifically include: Where s represents the credit score, n is the total number of factors, and L i represents the quantitative index of factor i, w i Represents the weight corresponding to factor i.

[0112] Based on the credit scoring formula, the quantitative index of each factor and the weight corresponding to each factor are calculated and processed to obtain the corresponding calculation result.

[0113] In this step, the quantitative index of each factor and the weight corresponding to each factor can be substituted into the corresponding position in the above credit score formula and calculated, so as to obtain the corresponding calculation result, that is, the target credit score of the user.

[0114] The calculation result is used as the target credit score of the user.

[0115] In this embodiment, by obtaining the quantitative indicators corresponding to each of the factors, the preset credit scoring formula is called, and then the quantitative indicators of each of the factors and the weights corresponding to each of the factors are calculated based on the credit scoring formula to obtain the corresponding calculation results, and the calculation results are subsequently used as the target credit score of the user. After obtaining the quantitative indicators corresponding to each of the factors, the application uses the preset credit scoring formula to calculate the quantitative indicators of each of the factors and the weights corresponding to each of the factors, thereby achieving the rapid and accurate generation of the target credit score of the user that can accurately reflect the credit status of the user, ensuring the transparency and fairness of the credit score calculation process, improving the efficiency of generating the generated target credit score, and ensuring the data accuracy of the obtained target credit score.

[0116] Optionally, generating the target credit level of the user based on the target credit score includes:

[0117] Get the score ranges for each preset credit rating.

[0118] In this step, multiple credit levels can be pre-set according to actual business needs and historical data distribution, and reasonable scoring intervals can be set for each credit level. So that the scoring intervals of different credit levels can distinguish users with different credit levels. Exemplarily, the credit level can be divided into four levels: A level, B level, C level, and D level, and each credit level corresponds to four scoring intervals: [90,100] is A level, [80,89] is B level, [60,79] is C level, and [0,59] is D level.

[0119] A designated scoring interval corresponding to the target credit score is selected from the scoring intervals of all the credit grades.

[0120] In this step, the target credit score can be matched with the score intervals of each preset credit grade to select a designated score interval that matches the score value of the target credit score from all the score intervals of the credit grade. For example, if the target credit score is 96 points, the designated score interval corresponding to the target credit score is the score interval [90,100] corresponding to the credit grade A.

[0121] A specified credit rating corresponding to the specified scoring interval is obtained.

[0122] In this step, the designated credit grade corresponding to the designated scoring interval can be determined from all credit grades according to the mapping relationship between the scoring interval and the credit grade. Continuing with the above example, if the designated scoring interval is [90, 100], the designated credit grade corresponding to the designated scoring interval is grade A.

[0123] The designated credit rating is used as the target credit rating.

[0124] In this embodiment, by obtaining the scoring intervals of each preset credit grade; then screening out the designated scoring interval corresponding to the target credit score from all the scoring intervals of the credit grades; then obtaining the designated credit grade corresponding to the designated scoring interval; and subsequently using the designated credit grade as the target credit grade. This application uses the scoring intervals of each preset credit grade to match the target credit score of the user, thereby achieving rapid and accurate generation of the target credit grade corresponding to the target credit score of the user, improving the efficiency of generating the target credit grade, and ensuring the accuracy of the obtained target credit grade.

[0125] Optionally, the calculating the indicator value of the user under a preset portrait dimension based on the user data includes:

[0126] Get the preset data cleaning strategy and data normalization strategy.

[0127] In this step, the policy content of the above data cleaning strategy may specifically include: removing duplicate data, invalid data and outliers. Correcting or filling missing values ​​to ensure data integrity. The policy content of the above data standardization strategy may specifically include: uniformly processing data from different sources and formats, such as converting timestamps to a unified date format. And normalizing or standardizing numerical data for subsequent analysis.

[0128] The user data is cleansed based on the data cleaning strategy to obtain corresponding first user data.

[0129] In this step, the user data may be cleansed according to the policy content of the above data cleansing policy, thereby obtaining corresponding first user data.

[0130] The first user data is standardized based on the data standardization strategy to obtain corresponding second user data.

[0131] In this step, the first user data may be standardized according to the policy content of the above data standardization policy, so as to obtain corresponding second user data.

[0132] Based on the second user data, the index value of the user in each portrait dimension is calculated.

[0133] In this step, the above-mentioned portrait dimensions may at least include driver evaluation dimensions, consumption habits dimensions, and personal information dimensions. For users, the specific index values ​​of the user in the service evaluation dimension, consumption habits dimension, and personal information dimension may be calculated respectively according to the above-mentioned second user data to obtain the index values ​​of the user in each of the portrait dimensions. Among them, the index values ​​corresponding to the driver evaluation dimension may include the average score, the number of complaints, and the proportion of evaluation content. Exemplarily, if the average score corresponds to 4.5 stars, the corresponding index value under the service evaluation dimension is 4.5. The index values ​​corresponding to the consumption habit dimension may include the number of orders, the average order amount, the order time interval, etc. Exemplarily, if the number of orders is 10 times, the corresponding index value under the consumption habit dimension is 10. The index value corresponding to the personal information dimension may include the value of the registration information field. Exemplarily, if the user is 24 years old, the corresponding index value under the personal information dimension is 24.

[0134] In this embodiment, by obtaining a preset data cleaning strategy and a data standardization strategy; then the user data is cleaned based on the data cleaning strategy to obtain the corresponding first user data; then the first user data is standardized based on the data standardization strategy to obtain the corresponding second user data; and subsequently the index value of the user under each of the portrait dimensions is calculated based on the second user data. Before executing the process of calculating the index value of the user under the preset portrait dimension based on the user data, the present application will also intelligently clean and standardize the user data through the data cleaning strategy and the data standardization strategy to ensure the integrity, accuracy and standardization of the generated second user data, so that the subsequent calculation of the index value of the user under each of the portrait dimensions based on the second user data can effectively ensure the numerical accuracy of the index value of the generated user under each of the portrait dimensions.

[0135] Optionally, after generating the target credit level of the user based on the target credit score, the method further includes:

[0136] Call the preset reward and punishment strategy library.

[0137] In this step, corresponding reward and punishment strategies are pre-formulated according to the performance of users with different credit levels and stored in a pre-constructed reward and punishment strategy library. Among them, the above-mentioned reward and punishment strategy library stores the reward and punishment strategies corresponding to each credit level. In addition, the formulated reward and punishment strategies are incentive and restrictive, and can guide users to improve their behavior. For example, for users with a credit rating of A, incentives such as priority order acceptance and preferential discounts can be provided as reward strategies; for users with a credit rating of D, restrictive measures such as limiting order acceptance and increasing deposits can be adopted as punishment strategies, and so on.

[0138] A target reward and punishment strategy corresponding to the target credit rating is determined from the reward and punishment strategy library.

[0139] In this step, the designated credit rating that matches the target credit rating can be found from the above-mentioned reward and punishment strategy library, and then the designated reward and punishment strategy that has a corresponding relationship with the designated credit rating can be obtained from the reward and punishment strategy library, and the designated reward and punishment strategy can be used as the above-mentioned target reward and punishment strategy corresponding to the target credit rating.

[0140] Based on the target reward and punishment strategy, corresponding reward and punishment processing is performed on the user.

[0141] In this step, the corresponding reward and punishment processing can be performed on the user according to the policy content of the above-mentioned target reward and punishment policy. For example, if the target credit rating of the user is A, the user can be provided with incentives such as priority order acceptance and preferential discounts according to the target reward and punishment policy corresponding to A, so as to complete the reward and punishment processing for the user.

[0142] In this embodiment, by calling a preset reward and punishment strategy library; then determining the target reward and punishment strategy corresponding to the target credit level from the reward and punishment strategy library; and subsequently executing corresponding reward and punishment processing on the user based on the target reward and punishment strategy. After generating the target credit level of the user based on the target credit score, the present application will also intelligently determine the target reward and punishment strategy corresponding to the target credit level from the preset reward and punishment strategy library, and then execute corresponding reward and punishment processing on the user based on the target reward and punishment strategy, thereby helping to improve the car-using experience of users with high credit levels, improve the car-using habits of users with low credit levels, and guide the improvement of car-using behaviors, thereby helping to improve the driver response rate, driver service quality, and cargo transportation efficiency.

[0143] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a data generation device 300 based on big data analysis, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0144] An embodiment of the present invention provides a data generation device 300 based on big data analysis. The data generation device 300 based on big data analysis includes:

[0145] The first acquisition module 310 is used to acquire user data of the user; wherein the user data at least includes driver evaluation data, historical order data and personal information;

[0146] A first calculation module 320 is used to calculate the index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple;

[0147] The conversion module 330 is used to convert the indicator value of the user in each of the portrait dimensions into the target label of the user in each of the portrait dimensions based on a preset label quantization rule;

[0148] A first generating module 340, configured to generate user portrait data of the user based on all the target tags;

[0149] A screening module 350, for screening out factors related to credit evaluation from the user portrait data;

[0150] A second generating module 360, configured to generate weights corresponding to the factors based on a preset weight generating strategy;

[0151] A second calculation module 370 is used to calculate each of the factors and the weights corresponding to each of the factors to obtain a target credit score of the user;

[0152] The third generating module 380 is configured to generate a target credit level for the user based on the target credit score.

[0153] Optionally, the first generating module 340 includes:

[0154] A first acquisition submodule is used to acquire a preset data structure;

[0155] An integration submodule, used to integrate all the target tags into the data structure to obtain a corresponding target data structure;

[0156] The first determination submodule is used to use the target data structure as user portrait data of the user.

[0157] Optionally, the second generating module 360 ​​includes:

[0158] The first calling submodule is used to call a preset weight generation model;

[0159] A first generating submodule is used to input each of the factors into the weight generating model, and generate feature importance information corresponding to each of the factors through the weight generating model;

[0160] The second generating submodule is used to generate weights corresponding to each of the factors based on the feature importance information of each of the factors.

[0161] Optionally, the second calculation module 370 includes:

[0162] The second acquisition submodule is used to acquire the quantitative indicators corresponding to each of the factors;

[0163] The second calling submodule is used to call a preset credit scoring formula;

[0164] A first calculation submodule, configured to calculate the quantitative index of each factor and the weight corresponding to each factor based on the credit scoring formula to obtain a corresponding calculation result;

[0165] The second determination submodule is used to use the calculation result as the target credit score of the user.

[0166] Optionally, the third generating module 380 includes:

[0167] The third acquisition submodule is used to obtain the score interval of each preset credit level;

[0168] A screening submodule, configured to screen out a designated score interval corresponding to the target credit score from among all the score intervals of the credit grade;

[0169] A fourth acquisition submodule is used to acquire a specified credit rating corresponding to the specified scoring interval;

[0170] The third determination submodule is configured to use the designated credit rating as the target credit rating.

[0171] Optionally, the first calculation module 320 includes:

[0172] The fifth acquisition submodule is used to acquire the preset data cleaning strategy and data standardization strategy;

[0173] A cleaning submodule, configured to clean the user data based on the data cleaning strategy to obtain corresponding first user data;

[0174] A standardization submodule, configured to perform standardization processing on the first user data based on the data standardization strategy to obtain corresponding second user data;

[0175] The second calculation submodule is used to calculate the indicator value of the user in each portrait dimension based on the second user data.

[0176] Optionally, the data generation device 300 based on big data analysis further includes:

[0177] The calling module is used to call the preset reward and punishment strategy library;

[0178] A determination module, used to determine a target reward and punishment strategy corresponding to the target credit rating from the reward and punishment strategy library;

[0179] An execution module is used to execute corresponding reward and punishment processing on the user based on the target reward and punishment strategy.

[0180] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0181] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0182] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0183] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the program code of the data generation method based on big data analysis, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0184] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the data generation method based on big data analysis.

[0185] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0186] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores the application crash processing program, and the application crash processing program can be executed by at least one processor to enable the at least one processor to perform the steps of the data generation method based on big data analysis as described above.

[0187] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware online platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0188] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0189] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data generation method based on big data analysis, characterized in that: include: Obtaining user data of the user; wherein the user data at least includes driver evaluation data, historical order data and personal information; Calculating an index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple; Based on a preset label quantization rule, the indicator value of the user in each of the portrait dimensions is converted into a target label of the user in each of the portrait dimensions; Generate user portrait data of the user based on all the target tags; Screening out factors related to credit evaluation from the user portrait data; Generate weights corresponding to each of the factors based on a preset weight generation strategy; Calculating and processing each of the factors and the weights corresponding to each of the factors to obtain a target credit score of the user; A target credit rating for the user is generated based on the target credit score.

2. The method according to claim 1, characterized in that The generating user portrait data of the user based on all the target tags includes: Get the preset data structure; Integrate all the target tags into the data structure to obtain a corresponding target data structure; The target data structure is used as user portrait data of the user.

3. The method according to claim 1, characterized in that The generating of weights corresponding to the factors based on a preset weight generating strategy includes: Call the preset weight generation model; Inputting each of the factors into the weight generation model, and generating feature importance information corresponding to each of the factors through the weight generation model; Based on the feature importance information of each of the factors, weights corresponding to each of the factors are generated.

4. The method according to claim 1, characterized in that: The calculating and processing of each of the factors and the weights respectively corresponding to the factors to obtain the target credit score of the user includes: Obtaining quantitative indicators corresponding to each of the factors; Calling a preset credit scoring formula; Based on the credit scoring formula, the quantitative index of each factor and the weight corresponding to each factor are calculated to obtain a corresponding calculation result; The calculation result is used as the target credit score of the user.

5. The method according to claim 1, characterized in that: Generating the target credit level of the user based on the target credit score includes: Get the score range of each preset credit rating; Filtering out a designated scoring interval corresponding to the target credit score from all the scoring intervals of the credit rating; Obtaining a specified credit rating corresponding to the specified scoring interval; The designated credit rating is used as the target credit rating.

6. The method according to claim 1, characterized in that The calculating the index value of the user under a preset portrait dimension based on the user data includes: Obtain preset data cleaning strategies and data standardization strategies; Cleaning the user data based on the data cleaning strategy to obtain corresponding first user data; Performing standardization processing on the first user data based on the data standardization strategy to obtain corresponding second user data; Based on the second user data, the index value of the user in each portrait dimension is calculated.

7. The method according to claim 1, characterized in that After generating the target credit rating of the user based on the target credit score, the method further includes: Call the preset reward and punishment strategy library; Determining a target reward and punishment strategy corresponding to the target credit rating from the reward and punishment strategy library; Based on the target reward and punishment strategy, corresponding reward and punishment processing is performed on the user.

8. A data generation device based on big data analysis, characterized in that: include: A first acquisition module is used to acquire user data of the user; wherein the user data at least includes driver evaluation data, historical order data and personal information; A first calculation module, configured to calculate an index value of the user under a preset portrait dimension based on the user data; wherein the number of the portrait dimensions includes multiple; A conversion module, configured to convert the index value of the user in each of the portrait dimensions into a target label of the user in each of the portrait dimensions based on a preset label quantization rule; A first generating module, used to generate user portrait data of the user based on all the target tags; A screening module, used to screen out factors related to credit evaluation from the user portrait data; A second generating module, used for generating weights corresponding to the factors respectively based on a preset weight generating strategy; A second calculation module is used to calculate and process each of the factors and the weights corresponding to each of the factors to obtain a target credit score of the user; The third generating module is used to generate the target credit level of the user based on the target credit score.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the data generation method based on big data analysis as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the data generation method based on big data analysis as described in any one of claims 1 to 7.

Images