User data processing method, device and system based on big data and electronic equipment

Abstract

The invention provides a user data processing method, device and system based on big data and electronic equipment, relates to the technical field of Internet of Vehicles big data application, and can comprehensively master basic information and potential demand characteristics of potential users by acquiring summarized data of the potential users in multiple aspects from multiple different data sources. Furthermore, the summarized data is converted into quantifiable and analyzable feature dimensions. According to the method, the service reference information corresponding to the potential users is determined by comprehensively evaluating and scoring the information of each dimension, so that the images and demands of the users can be identified and depicted more finely, the transition of the user portraits from'static description 'to'dynamic evaluation' is realized, the completeness of the user information and the accuracy of service matching are improved, and the user experience is improved. A data foundation is laid for providing more targeted service and support subsequently, meanwhile, the communication cost is reduced, and the service efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of big data application technology in the Internet of Vehicles (IoV), and in particular to a user data processing method, apparatus, system and electronic device based on big data. Background Technology

[0002] Current information processing methods for automotive customers are rather rudimentary, often relying on sales staff's subjective judgment or analysis based on limited customer contact information, lacking systematic integration and in-depth mining of customer behavior data. Due to the single data source and lagging information updates, staff struggle to comprehensively and accurately grasp customers' actual needs and potential intentions.

[0003] Furthermore, customer value assessment relies heavily on experience-based judgment, lacking standardized and quantifiable criteria. This leads to significant discrepancies in customer segmentation results, impacting the relevance and effectiveness of subsequent services. Inaccurate information processing makes it difficult for staff to provide tailored services during customer interactions, reducing communication efficiency and service quality. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a user data processing method, apparatus, system and electronic device based on big data, so as to provide more reliable service reference information and thereby improve service quality.

[0005] In a first aspect, embodiments of the present invention provide a user data processing method based on big data. The method includes: acquiring aggregated data of potential users from multiple different data sources; wherein the aggregated data of potential users includes at least one of the following: user identity description information, user's interest in vehicles, user's financial status description information, and user's driving-related historical information; subdividing the aggregated data of potential users into multiple dimensions according to a preset classification method to obtain classification features for each dimension of the potential user; wherein each dimension's classification feature includes multiple secondary indicator descriptions; wherein the secondary indicator descriptions are used to identify the specific category to which the potential user belongs in the classification features of that dimension; determining the comprehensive score of the potential user based on the secondary indicator descriptions in the classification features of each dimension of the potential user and a preset indicator quantification method; and determining service reference information for the potential user based on the comprehensive score of the potential user, wherein the service reference information characterizes the description information of the potential user's vehicle needs.

[0006] In conjunction with the first aspect, this embodiment of the invention also provides a first implementation method of the first aspect, wherein, according to a preset classification method, the aggregated data of potential users is subdivided into multiple dimensions to obtain the classification features of each dimension of the potential users, including: labeling each data feature in the aggregated data of potential users based on a preset feature label system, and determining the data label type corresponding to each data feature in the aggregated data of potential users; wherein, the feature labels include fact-type labels, model-type labels, and prediction-type labels; and classifying the aggregated data of potential users according to preset dimensions based on the data label type and the feature description corresponding to the data feature to obtain the classification features corresponding to each data dimension of the aggregated data of potential users.

[0007] In conjunction with the first aspect, this embodiment of the invention also provides a second implementation of the first aspect, wherein the secondary indicator description information includes the assigned score of the specific category to which the potential user belongs in the classification features of the dimension, and the method further includes: when the secondary indicator description information corresponds to a fact category label, determining the assigned score of the specific category to which the potential user belongs in the classification features of the dimension according to a preset segmented scoring rule; when the secondary indicator description information corresponds to a model category label and / or a prediction category label, determining the assigned score of the specific category to which the potential user belongs in the classification features of the dimension according to a preset prediction algorithm.

[0008] In conjunction with the first aspect, this embodiment of the invention also provides a third implementation of the first aspect, wherein determining the comprehensive score of a potential user based on the secondary indicator description information in the classification features of each dimension of the potential user and a preset indicator quantification method includes: performing a weighted fusion calculation on the assigned scores of the secondary indicator description information corresponding to the potential user according to the dimension weights corresponding to the classification features of each dimension, to obtain the comprehensive score of the potential user.

[0009] In conjunction with the first aspect, this invention also provides a fourth implementation of the first aspect, wherein the method further includes: acquiring historical data for a specified time period; wherein the historical data includes satisfaction feedback information determined based on service reference information of potential users; and adjusting dimension weights and / or specific category scores according to the satisfaction feedback information.

[0010] In conjunction with the first aspect, this embodiment of the invention also provides a fifth implementation of the first aspect, wherein determining the service reference information of a potential user based on the comprehensive rating of the potential user includes: determining the rating range corresponding to the comprehensive rating; determining the service reference information of the potential user according to the rating range; wherein the service reference information includes the service level of the potential user, and the service level corresponds to descriptive information regarding vehicle needs.

[0011] In conjunction with the first aspect, the present invention also provides a sixth implementation of the first aspect, wherein the method further includes: determining the service terminal corresponding to the potential user based on the aggregated data of the potential user; and pushing service reference information to the service terminal.

[0012] Secondly, embodiments of the present invention also provide a user data processing device based on big data. The device includes: a data acquisition module, used to acquire aggregated data of potential users from multiple different data sources; wherein the aggregated data of potential users includes at least one of the following: user identity description information, user's interest in vehicles, user's financial status description information, and user's driving-related historical information; a classification module, used to subdivide the aggregated data of potential users into multiple dimensions according to a preset classification method to obtain classification features for each dimension of the potential user; wherein the classification features for each dimension include multiple secondary indicator descriptions; wherein the secondary indicator descriptions are used to identify the specific category to which the potential user belongs in the classification features of that dimension; a data processing module, used to determine the comprehensive score of the potential user based on the secondary indicator descriptions in the classification features of each dimension of the potential user and a preset indicator quantification method; and an output module, used to determine service reference information of the potential user based on the comprehensive score of the potential user, wherein the service reference information characterizes the description information of the potential user's vehicle needs.

[0013] Thirdly, embodiments of the present invention also provide a user data processing system based on big data, the system comprising: a server and a service terminal, the server being used to execute the method of any of the above embodiments, and the service terminal being used to obtain and display service reference information of potential users from the server.

[0014] Fourthly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the methods of any of the above embodiments.

[0015] The embodiments of this invention bring the following beneficial effects: The user data processing method, apparatus, system, and electronic device provided by the embodiments of this invention, based on big data, can comprehensively grasp the basic information and potential needs of potential users by acquiring aggregated data from multiple different data sources. Furthermore, the aggregated data is transformed into quantifiable and analyzable feature dimensions. Through comprehensive evaluation and scoring of information in each dimension, service reference information corresponding to potential users is determined, enabling more refined identification and characterization of user profiles and needs. This achieves a leap from "static description" to "dynamic evaluation" of user profiles, helping to improve the completeness of user information and the accuracy of service matching, laying a data foundation for providing more targeted services and support, while reducing communication costs and improving service efficiency.

[0016] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a user data processing method based on big data, provided in an embodiment of the present invention;

[0020] Figure 2 A flowchart illustrating another user data processing method based on big data provided in an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the structure of a user data processing device based on big data provided in an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] In vehicle-related services, identifying potential customers and segmenting them by value typically relies on staff experience and personal judgment, as well as limited information obtained through face-to-face interactions. Due to varying levels of staff experience and competence, customer evaluation standards differ significantly, making it difficult to establish a unified and accurate customer evaluation system. Therefore, this invention provides a user data processing method, apparatus, system, and electronic device based on big data. It aims to provide staff with multi-dimensional profiles of potential users' vehicle needs through multi-dimensional data access, helping them accurately identify user preferences and requirements, thereby developing personalized service strategies. This solution helps optimize customer relationship management, improve service experience, reduce ineffective communication, and significantly improve service efficiency and quality.

[0025] To facilitate understanding of this embodiment, a user data processing method based on big data disclosed in this embodiment will first be described. Figure 1 A flowchart of a user data processing method based on big data provided by an embodiment of the present invention is shown, with reference to... Figure 1 The method includes the following steps:

[0026] Step S102: Obtain aggregated data of potential users from multiple different data sources.

[0027] The aggregated data of potential users includes at least one of the following: user identification information, user interest information in vehicles, user financial status description, and user driving-related historical information. This invention, by acquiring aggregated data of potential users from multiple different data sources, accurately grasps market and customer needs and dynamically monitors changes in the value of potential customers.

[0028] The aforementioned user identity description information may include user gender, education level, age, occupation, and geographic location information; user interest information regarding vehicles may include brand preference, model preference, price range, configuration requirements, and purchase intention time; user financial status description information may include user income level, assets, credit score, and debt; and user driving-related historical information may include years of driving experience, driving habits, accident records, and vehicle usage frequency.

[0029] In one implementation, data from online (such as social media, search engines, online car platforms, etc.) and offline (such as auto shows, test drive events, etc.) channels can be integrated to obtain multi-dimensional data, including user identity descriptions, vehicle interest information, financial status descriptions, and driving-related historical information, in order to build a more complete and accurate user profile.

[0030] Step S104: According to the preset classification method, the aggregated data of potential users is subdivided into multiple dimensions to obtain the classification features of each dimension of potential users.

[0031] The preset classification method can be a preset dimensional division method. For example, preset dimensions may include user basic attribute dimensions, user car purchase intention dimensions, vehicle preference dimensions, user behavior path dimensions, driving behavior and experience dimensions, and functional configuration requirements dimensions. These subdivided dimensions can be determined based on multiple aspects such as the strength of user car purchase intention, vehicle preference, purchasing power assessment, matching degree between usage scenarios and needs, and service acceptance and communication adaptability. In practical implementation, the included dimensions and their corresponding secondary indicators can be dynamically adjusted and expanded according to factors such as data sources, user group characteristics, and service goals to achieve a multi-faceted and multi-layered portrayal of user needs.

[0032] This invention also systematically and multidimensionally segments the aforementioned aggregated data, enabling a comprehensive understanding of potential customers and providing intuitive and quantifiable evaluation criteria. Each dimension's classification characteristics can include multiple secondary indicator descriptions; these secondary indicator descriptions identify the specific category a potential user belongs to within that dimension's classification characteristics. Through detailed secondary indicator descriptions, the aggregated data of potential users is systematically and multidimensionally segmented, constructing detailed classification characteristics for each potential customer. This allows for a comprehensive and in-depth understanding of potential customers' needs, preferences, and economic circumstances, providing strong support for developing personalized and precise service strategies.

[0033] In one implementation, multiple two-dimensional indicators are used to describe a user's basic personal information and lifestyle, respectively, to construct a basic user profile. For example: Gender: Male / Female; Age range: 0-18 years, 19-25 years, 26-35 years, etc.; Marital status: Single, married, divorced, or widowed; Family structure: Living alone, couple, family with children, or family with multiple children; Education level: High school or below, junior college, bachelor's degree, master's degree or above; Occupation: Corporate employee, civil servant, freelancer, student, retiree, or others; Income level: Low income, lower-middle income, middle income, upper-middle income, or high income (classified according to the family's total annual income range); City of residence: First-tier, new first-tier, second-tier, third- or fourth-tier cities and below. Regarding user interest in vehicles, secondary indicators describe the user's points of interest and focus, such as preferred car models, budget range, intended use, whether it's their first car purchase, vehicle preferences, purchase decision-making cycle, and preferred information sources, to understand their purchase intentions and preferences. For user financial status, multiple secondary indicators describe the user's economic capacity and creditworthiness, providing a basis for assessing their payment ability and potential value. Regarding user driving-related historical information, multiple secondary indicators describe the user's past driving behavior and car purchase history, such as historical purchase records, vehicle replacement information, driving frequency, driving habits, insurance claims records, and maintenance records, to understand their driving habits and purchasing patterns.

[0034] Step S106: Determine the comprehensive score of the potential user based on the description information of the secondary indicators in the classification features of each dimension of the potential user and the preset indicator quantification method.

[0035] The preset quantification methods for indicators can include weighted scoring, rule matching, machine learning model scoring, interval mapping, or multi-dimensional scoring output. The comprehensive score can be presented as a percentage score, a ten-point score, a multi-dimensional scoring system, a labeled scoring system, or a dynamic scoring system. The comprehensive score can be a total score reflecting the overall matching degree between user and vehicle needs; in other implementations, the comprehensive score can also be a summary of scores generated from multiple dimensions to support multi-faceted analysis of user needs. The form and calculation method of the comprehensive score can be dynamically adjusted according to business objectives, data characteristics, and service strategies to achieve accurate identification of user needs and personalized service matching.

[0036] Step S108: Based on the comprehensive rating of potential users, determine the service reference information for potential users.

[0037] Service reference information is generated based on the comprehensive ratings of potential users and serves as a reference for staff to provide personalized services to potential users. In one implementation, the service reference information is used to characterize key features of potential users regarding their vehicle needs, such as preferences, capabilities, intensity of intent, and service suitability, to assist staff in developing or recommending service content that meets user needs.

[0038] This invention transforms qualitative descriptive information (i.e., the aforementioned user identity description information, user's vehicle interest information, user financial status description information, and user driving-related historical information) into measurable and comparable structured numerical indicators (i.e., the classification features of each dimension), thereby forming a comprehensive assessment of the user's overall characteristics. In summary, this invention, based on a comprehensive analysis of user characteristics, can generate more accurate service reference information, thereby improving the personalization and execution efficiency of service strategies.

[0039] The user data processing method based on big data provided in this invention can comprehensively grasp the basic information and potential needs of potential users by acquiring aggregated data from multiple different data sources. Furthermore, the aggregated data is transformed into quantifiable and analyzable feature dimensions. Through comprehensive evaluation and scoring of information in each dimension, service reference information corresponding to potential users is determined. This enables a more refined identification and characterization of user profiles and needs, achieving a leap from "static description" to "dynamic evaluation." This helps improve the completeness of user information and the accuracy of service matching, laying a data foundation for providing more targeted services and support, while reducing communication costs and improving service efficiency.

[0040] Furthermore, based on the above embodiments, this invention also provides another user data processing method based on big data. Figure 2 A flowchart of another user data processing method based on big data provided by an embodiment of the present invention is shown, with reference to... Figure 2 The method includes the following steps:

[0041] Step S202: Obtain aggregated data of potential users from multiple different data sources.

[0042] Step S204: Based on the preset feature labeling system, label each data feature in the aggregated data of potential users and determine the data label type corresponding to each data feature in the aggregated data of potential users.

[0043] The feature labeling system is used to characterize a standardized label classification framework and rule system pre-built during user data processing. Its core function is to classify, collect, semantically name, and structurally represent user-related multi-source data features. Based on this feature labeling system, raw user data (i.e., the aggregated data of potential users mentioned above) can be mapped into structured label data with clear semantic definitions through rule matching or semantic parsing, thereby determining the data label type corresponding to each data feature. This enables standardized modeling of user behavior, attributes, preferences, and other information, allowing user data from different sources and in different formats to be identified and managed under a unified label dimension. This provides a consistent and measurable data foundation for subsequent user profile construction, comprehensive score calculation, and service reference information generation.

[0044] Step S206: Based on the data label type and the feature description corresponding to the data feature, the aggregated data of potential users is classified according to the preset dimensions to obtain the classification features corresponding to each data dimension of the aggregated data of potential users.

[0045] The feature descriptions corresponding to data features are used to clarify the semantic or business meaning of the feature. The classification features corresponding to each data dimension are used to characterize the structured feature set formed by classifying and integrating multiple data features with the same business meaning or semantic dimension. This invention, based on a preset feature labeling system and combined with the semantic descriptions of data features, performs semantically consistent dimensional division and feature integration of user data, thereby extracting classification features with clear business meaning and achieving structured modeling and accurate characterization of user profiles.

[0046] In one implementation, the feature tagging system includes, but is not limited to, the following three types of tags: factual tags, model tags, and prediction tags. Factual tags characterize a user's actual behavior or basic attribute information; model tags are generated through a rule engine or classification model and are used to summarize and classify user characteristics; prediction tags are based on machine learning models to predict future user behavior trends and are used to support the formulation of personalized service strategies. Through the collaborative construction of multiple tag types, a comprehensive characterization of user features can be achieved. Furthermore, the feature tagging system may also include time-series tags to reflect the timeliness or changing trends of user behavior. It may also include rule tags for quickly identifying specific user groups or behavioral characteristics. The category tags included in the feature tagging system can be flexibly determined according to actual business needs, data sources, user behavior characteristics, or service goals, and this embodiment of the invention does not impose limitations on them.

[0047] In one implementation, factual tags can be determined based on user behavior or objectively existing attributes, which can be directly extracted or summarized from data to determine the corresponding tags. Factual tags are characterized by being unchangeable or changing very little. In another implementation, factual tags can be determined based on data features extracted from consumer behavior logs (including consumer behavior and marketing campaign behavior), such as male, white-collar worker, first-time car buyer, rational consumer, etc.

[0048] Model-based tags are used to describe potential user characteristics, behavioral trends, or prediction results. These tags can be determined by analyzing, mining, and predicting user behavior data through algorithmic models. For example, user lifetime value tags, such as "high-value user," "medium-value user," and "low-value user," can be determined based on data characteristics such as historical spending amount, purchase frequency, average order value, activity cycle, and product preferences. Furthermore, user churn risk tags, such as "high churn risk," "medium churn risk," and "low churn risk," can be determined based on data characteristics such as the user's recent active time, changes in active frequency, declining spending trends, marketing campaign response rate, and login frequency. Finally, potential customer reactivation probability tags, such as "reactivatable user" and "unreactivatable user," can be determined based on data characteristics such as the user's activity level before dormancy, historical marketing response records, spending level, device usage status, and social behavior.

[0049] Furthermore, if current user behavior data can be used to predict future behaviors or needs through modeling or rules, the corresponding data features can be classified as predictive tags. Specifically, user social attribute tags can be determined based on data features such as geographic location, device type, consumer product category preferences, active time periods, search keywords, and social media information, such as white-collar worker, student, married, or car owner. Marketing activity sensitivity tags can be determined based on data features such as user activity click-through rate, coupon usage rate, activity participation frequency, conversion rate, and marketing response time, such as highly sensitive user, moderately sensitive user, or low-sensitive user. Further, future car purchase intention tags can be determined based on data features such as user car model search history, car model page browsing frequency, test drive appointment behavior, car loan / insurance inquiry history, and spending power assessment, such as high purchase intention or low purchase intention. Furthermore, based on data characteristics such as the price range of car models viewed, search keywords, financial product inquiry records, spending power assessment, and brand preferences, corresponding car purchase budget range tags can be determined, such as "Budget 100,000-200,000 yuan," "Budget 200,000-300,000 yuan," and "Budget over 300,000 yuan." Based on data characteristics such as the type of car models viewed, car models saved, video viewing history, search keywords, and social media interaction content, corresponding intended car model tags can be determined, such as "Intended SUV," "Intended Sedan," and "Intended New Energy Vehicle."

[0050] Furthermore, user data can be divided into multiple data dimensions based on relevant tags. For example, four data dimensions: basic attributes, car purchase behavior characteristics, needs and preferences, and value and risk.

[0051] Based on the steps above, the classification features for each data dimension of the aggregated data for potential users are shown in the table below:

[0052]

[0053]

[0054]

[0055] Step S208: Based on the dimension weights corresponding to the classification features of each dimension, the scores of the secondary indicator description information corresponding to the potential user are weighted and fused to obtain the comprehensive score of the potential user.

[0056] The description information of each secondary indicator for the classification features of each dimension mentioned above includes the assigned score for the specific category to which the potential user belongs within that dimension's classification features. Combining the above steps, different scoring rules can be determined based on the type of tag. For example, factual tags are determined based on known and unchanging factual information (such as age, gender, etc.). Therefore, when the secondary indicator description information corresponds to a factual tag, a simple and direct scoring rule can be determined for that category, such as a preset fixed standard or segmented scoring rule.

[0057] Model-based tags typically require the analysis of large amounts of behavioral data through algorithmic models to reveal potential behavioral patterns or trends. Their scoring rules can rely on specific model outputs, determining corresponding scores according to pre-defined prediction algorithms to reflect the complexity and dynamic changes in user behavior. Predictive tags focus on predicting users' future needs or behavioral tendencies (such as various vehicle-related service scenarios, including but not limited to: vehicle accessory customization, car cover design and replacement, vehicle parts replacement and upgrades, after-sales service appointments and feedback, vehicle usage behavior analysis, intelligent driving function preference identification, collection of user feedback on vehicle design improvements, personalized vehicle configuration recommendations, and user content preference analysis on vehicle information service platforms). Corresponding predictive algorithms can be used as scoring rules, emphasizing forward-looking perspectives to obtain corresponding scores, providing a reliable data foundation for advance planning of marketing activities or product recommendations.

[0058] Based on the above steps, taking car purchase-related services as an example, the corresponding scores are calculated using a segmented scoring method and a logistic regression model. Taking the user basic attribute dimension data from the above summary data as an example, the scoring results can be represented by Table 1 below:

[0059] Table 1: Basic Attribute Dimensions

[0060]

[0061] Taking the car purchase behavior feature data corresponding to user attention information about vehicles as an example, the scoring results can be represented by Table 2 below:

[0062] Table 2: Dimensions of Car Purchase Behavior Characteristics

[0063]

[0064] Taking the user's attention to vehicle information and the corresponding demand and preference dimensions as an example, the scoring results can be represented by Table 3 below:

[0065] Table 3: Demand and Preference Dimensions

[0066]

[0067] Taking the value and risk dimensions data broken down by dimension in the aggregated data as an example, the scoring results can be represented by Table 4 below:

[0068] Table 4: Value and Risk Dimensions

[0069]

[0070] For the scores assigned to each dimension of the aggregated data, the scores of each data feature can be weighted and integrated according to the respective dimension weights to determine the corresponding comprehensive score. Each data dimension has a corresponding weight percentage. Under the premise of the above data dimensions, the basic attribute dimension is used to help judge the rationality of the demand (such as the matching degree between family structure, income and budget), and its weight can be 10%; the car purchase behavior characteristic dimension directly reflects the urgency of car purchase (such as the number of test drives, the frequency of inquiries), and its weight can be 40%; the demand and preference dimension matches product supply and avoids resource mismatch (such as the fit between user preferences and the models on sale), and its weight can be 30%; the value and risk dimension is used to balance short-term conversion and long-term benefits (such as users with high lifetime value (LTV) are worth cultivating in the long term), and its weight can be 20%.

[0071] In one implementation, historical data for a specified period can be acquired to determine satisfaction feedback information based on service reference information from potential users. Based on this satisfaction feedback, dimensional weights and / or specific category scores can be adjusted to improve the accuracy, predictive ability, and precision of the tagging system and personalized services, ultimately achieving collaborative optimization and a closed-loop strategy between the platform and stores.

[0072] Step S210: Determine the scoring range corresponding to the comprehensive score.

[0073] In this embodiment, the scoring interval can be a two-segment interval to fundamentally classify potential users' matching degree or purchase intention. For example, users scoring above the interval threshold are classified as high-intent users, and those scoring below the interval threshold are classified as low-intent users. Alternatively, potential users can be classified and managed in a more detailed manner, with multi-segment scoring intervals such as three-segment or five-segment intervals designed. Furthermore, the scoring interval boundaries can be automatically defined and the scoring interval dynamically determined based on the distribution ratio of potential users' comprehensive scores within the entire user group.

[0074] Step S212: Based on the rating range, determine the service reference information for potential users. This service reference information includes the service level of the potential user, and each service level corresponds to a descriptive information regarding their vehicle needs.

[0075] Based on the determined comprehensive score, the results can be divided into corresponding score intervals according to preset interval division rules, enabling value segmentation management of potential users and identifying their value level in vehicle-related services. By using service levels and their associated vehicle demand descriptions, the demand characteristics of potential users can be structurally identified, and targeted service reference information can be generated accordingly. This allows for precise service matching and optimized resource allocation for potential users.

[0076] Taking the classification of potential customers into five levels—1-star, 2-star, 3-star, 4-star, and 5-star—based on their overall rating as an example, the service reference information for different aggregated data can be represented by the following table:

[0077]

[0078] It should be noted that the information in the feature descriptions in the table above can be determined based on the corresponding summary data, and the content in the table does not limit the specific descriptions.

[0079] Furthermore, aggregated data from different potential users can be used to identify their corresponding intended cities (or districts) to determine the target locations for the required services. Based on this, the method also includes: determining the service terminal devices associated with users based on the aggregated data, and pushing relevant service reference information to those terminals to achieve matching and integration between user information and terminal devices.

[0080] Based on the above embodiments, this invention also provides a user data processing device based on big data, referring to... Figure 3 The device includes: a data acquisition module 100, used to acquire aggregated data of potential users from multiple different data sources; wherein the aggregated data of potential users includes at least one of the following: user identity description information, user's interest in vehicles, user's financial status description information, and user's driving-related historical information; a classification module 200, used to subdivide the aggregated data of potential users into multiple dimensions according to a preset classification method to obtain classification features for each dimension of potential users; wherein each dimension's classification feature includes multiple secondary indicator description information; wherein the secondary indicator description information is used to identify the specific category to which the potential user belongs in the classification feature of that dimension; a data processing module 300, used to determine the comprehensive score of potential users based on the secondary indicator description information in the classification features of each dimension of potential users and a preset indicator quantification method; and an output module 400, used to determine the service reference information of potential users based on the comprehensive score of potential users, wherein the service reference information represents the description information of potential users' vehicle needs.

[0081] This invention also provides a user data processing device based on big data. Its implementation principle and the resulting technical effects are the same as those in the aforementioned method embodiments. For the sake of brevity, any parts not mentioned in the device embodiments can be referred to the corresponding content in the aforementioned method embodiments.

[0082] Furthermore, the aforementioned classification module 200 is also used to label each data feature in the aggregated data of the potential users based on a preset feature label system, and determine the data label type corresponding to each data feature in the aggregated data of the potential users; wherein, the feature labels include fact-type labels, model-type labels and prediction-type labels; based on the data label type and the feature description corresponding to the data feature, the aggregated data of the potential users is classified according to preset dimensions to obtain the classification features corresponding to each data dimension of the aggregated data of the potential users.

[0083] The secondary indicator description information includes the score value of the specific category to which the potential user belongs in the classification features of this dimension. The classification module 200 is further used to determine the score value of the specific category to which the potential user belongs in the classification features of this dimension according to a preset segmented scoring rule when the secondary indicator description information corresponds to a fact label; and to determine the score value of the specific category to which the potential user belongs in the classification features of this dimension according to a preset prediction algorithm when the secondary indicator description information corresponds to a model label and / or a prediction label.

[0084] The aforementioned data processing module 300 is further configured to: perform weighted fusion calculation on the assigned scores of the secondary indicator description information corresponding to the potential user based on the dimension weights corresponding to the classification features of each dimension, thereby obtaining the comprehensive score of the potential user.

[0085] The aforementioned data processing module 300 is further configured to: acquire historical data for a specified time period; wherein the historical data includes satisfaction feedback information determined based on service reference information of potential users; and adjust the dimension weights and / or the scores of the specific categories according to the satisfaction feedback information.

[0086] The output module 400 is further configured to: determine the scoring range corresponding to the comprehensive score; determine the service reference information of the potential user based on the scoring range; wherein the service reference information includes the service level of the potential user, and the service level corresponds to descriptive information regarding vehicle needs.

[0087] The output module 400 is further configured to: determine the service terminal corresponding to the potential user based on the aggregated data of the potential user; and push the service reference information to the service terminal.

[0088] Based on the above embodiments, this invention also provides a user data processing system based on big data. The system includes: a server and a service terminal. The server is used to execute the method of any of the above embodiments, and the service terminal is used to obtain and display service reference information of potential users from the server.

[0089] In one implementation, the server can be a cloud service platform, such as Amazon Web Services (AWS), Microsoft Azure, or Google Cloud Platform (GCP), which provides elastic computing resources, big data processing services (such as AWS EMR and Azure HDInsight), and machine learning services. Enterprise-grade server hardware, such as high-performance servers provided by Dell EMC, HPE, and IBM, is used for locally deployed big data analytics and processing tasks. Dedicated database servers, such as relational database management systems like Oracle Database, MySQL, and PostgreSQL, or NoSQL databases like MongoDB and Cassandra, are used to store and query large-scale user data.

[0090] Service terminals are used to retrieve and display service reference information for potential users from a server. They can be devices or software applications. In one implementation, they may include: desktop computers or laptops: office equipment used by staff to access information on the server via a browser or dedicated application; mobile devices: such as smartphones and tablets running iOS or Android systems, with customized applications installed to receive the latest user data and service recommendations; digital dashboards or displays: located in 4S stores or other sales points, displaying information such as popular car models and promotions to visiting customers; and CRM systems: integrated into the enterprise's existing customer relationship management system, such as Salesforce or Zoho CRM, directly pushing server data to the sales team. Smart wearable devices: for situations requiring rapid response, such as smartwatches worn by on-site staff, enabling them to receive key notifications instantly.

[0091] Furthermore, this embodiment of the invention also provides a user data processing system based on big data. Its implementation principle and the resulting technical effects are the same as those in the aforementioned method embodiments. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiments.

[0092] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described... Figures 1 to 2The steps of any of the methods shown. Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the above-described steps. Figures 1 to 2 The steps of any of the methods shown.

[0093] This invention also provides a schematic diagram of the structure of an electronic device, such as... Figure 4 The diagram shows the structure of the electronic device, which includes a processor 41 and a memory 40. The memory 40 stores computer-executable instructions that can be executed by the processor 41. The processor 41 executes the computer-executable instructions to implement the above-mentioned... Figures 1 to 2 Any of the methods shown.

[0094] exist Figure 4 In the illustrated embodiment, the electronic device further includes a bus 42 and a communication interface 43, wherein the processor 41, the communication interface 43, and the memory 40 are connected via the bus 42. The memory 40 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk drive. Communication between this system network element and at least one other network element is achieved through at least one communication interface 43 (which can be wired or wireless), using the Internet, wide area network, local area network, metropolitan area network, etc. Bus 42 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, or an AMBA (Advanced Microcontroller Bus Architecture) bus. AMBA defines three types of buses: APB (Advanced Peripheral Bus), AHB (Advanced High-performance Bus), and AXI (Advanced deXtensible Interface). Bus 42 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0095] Processor 41 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 41 or by instructions in software form. Processor 41 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in the memory. The processor 41 reads the information in the memory and, in conjunction with its hardware, completes the aforementioned task. Figures 1 to 2 Any of the methods shown.

[0096] The present invention provides a computer program product for a user data processing method, apparatus, system, and electronic device based on big data, comprising a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. Specific implementations can be found in the method embodiments and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0097] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part 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, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0098] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0099] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A user data processing method based on big data, characterized in that, The method includes: Aggregated data of potential users is obtained from multiple different data sources; wherein, the aggregated data of potential users includes at least one of the following: user identity description information, user interest information on vehicles, user financial status description information, and user driving-related historical information; According to a preset classification method, the aggregated data of potential users is subdivided into multiple dimensions to obtain the classification features of each dimension of the potential users; wherein, the classification features of each dimension include multiple secondary indicator descriptions; wherein, the secondary indicator descriptions are used to identify the specific category to which the potential user belongs in the classification features of that dimension; Based on the secondary indicator description information in the classification features of each dimension of the potential user and the preset indicator quantification method, the comprehensive score of the potential user is determined; Based on the comprehensive rating of the potential users, service reference information for the potential users is determined, and the service reference information represents the description information of the potential users' vehicle needs.

2. The method according to claim 1, characterized in that, Based on a preset classification method, the aggregated data of potential users is subdivided into multiple dimensions to obtain the classification features of each dimension of the potential users, including: Based on a preset feature labeling system, each data feature in the aggregated data of the potential users is labeled to determine the data label type corresponding to each data feature in the aggregated data of the potential users; wherein, the feature labels include factual labels, model labels and prediction labels; Based on the data label type and the feature description corresponding to the data feature, the aggregated data of the potential users is classified according to preset dimensions to obtain the classification features corresponding to each data dimension of the aggregated data of the potential users.

3. The method according to claim 2, characterized in that, The secondary indicator description information includes the score assigned to the specific category to which the potential user belongs in the classification features of this dimension, and the method further includes: When the secondary indicator description information corresponds to a fact category label, the score of the specific category to which the potential user belongs in the classification feature of this dimension is determined according to the preset segmented scoring rules. When the secondary indicator description information corresponds to the model class label and / or the prediction class label, the score of the specific category to which the potential user belongs in the classification features of this dimension is determined according to the preset prediction algorithm.

4. The method according to claim 3, characterized in that, Based on the secondary indicator description information in the classification features of each dimension of the potential user and the preset indicator quantification method, the comprehensive score of the potential user is determined, including: Based on the dimensional weights corresponding to the classification features of each dimension, the scores of the secondary indicator description information corresponding to the potential user are weighted and fused to obtain the comprehensive score of the potential user.

5. The method according to claim 4, characterized in that, The method further includes: Acquire historical data for a specified time period; wherein, the historical data includes satisfaction feedback information determined based on service reference information of potential users; Based on the satisfaction feedback information, adjust the dimension weights and / or the scores for the specific categories.

6. The method according to claim 1, characterized in that, Based on the comprehensive ratings of the potential users, the service reference information for the potential users is determined to include: Determine the score range corresponding to the comprehensive score; Based on the rating range, service reference information for the potential user is determined; wherein, the service reference information includes the service level of the potential user, and the service level corresponds to descriptive information regarding vehicle needs.

7. The method according to claim 1, characterized in that, The method further includes: Based on the aggregated data of the potential users, the service terminal corresponding to the potential user is determined; The service reference information is pushed to the service terminal.

8. A user data processing device based on big data, characterized in that, The device includes: The data acquisition module is used to acquire aggregated data of potential users from multiple different data sources; wherein, the aggregated data of potential users includes at least one of the following information: user identity description information, user interest information on vehicles, user financial status description information, and user driving-related historical information. The classification module is used to subdivide the aggregated data of potential users into multiple dimensions according to a preset classification method, so as to obtain the classification features of each dimension of the potential users; wherein, the classification features of each dimension include multiple secondary indicator description information; wherein, the secondary indicator description information is used to identify the specific category to which the potential user belongs in the classification features of that dimension; The data processing module is used to determine the comprehensive score of the potential user based on the secondary indicator description information in the classification features of each dimension of the potential user and the preset indicator quantification method. The output module is used to determine the service reference information of the potential user based on the comprehensive rating of the potential user. The service reference information represents the description information of the potential user's vehicle needs.

9. A user data processing system based on big data, characterized in that, The system includes: a server and a service terminal, wherein the server is configured to perform the method according to any one of claims 1 to 7, and the service terminal is configured to obtain and display service reference information of the potential user from the server.

10. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the method of any one of claims 1 to 7.

Images