Four-in-one automobile service data value mining and value-added operation method

Abstract

This invention relates to a four-in-one automotive service data value mining and value-added operation method, and to the field of automotive service data analysis technology. It includes constructing a three-dimensional dataset encompassing time, space, and business. The invention builds a four-in-one automotive service ecosystem comprising a mobile app, intelligent shared cloud cabinets, digital stores, and shared empowerment. The mobile app integrates AI and eight functional modules, providing users with a full-cycle intelligent service portal from car purchase and maintenance to financial insurance. The intelligent shared cloud cabinet integrates advertising, multi-terminal user interaction, and intelligent car key management, achieving centralized control and seamless service connection in offline scenarios. The digital stores, through full-process service visualization technology, allow users to remotely monitor repair status in real time, constructing a micro-repair network sharing empowerment model. This enables multi-dimensional sharing of automotive services, leasing, stores, products, tools, and equipment, achieving seamless user connection, precise scheduling of service resources, and dynamic optimization of operational strategies.

Description

Technical Field

[0001] This invention relates to the field of automotive service data analysis technology, and in particular to a four-in-one method for mining and value-added operation of automotive service data. Background Technology

[0002] With the continuous growth of car ownership and the increasing demands of consumers for service experience, the automotive aftermarket service industry is facing an urgent need to transform from traditional extensive operation to refined, intelligent, and personalized services. The data application in the automotive service field mainly adopts the following technical solutions: through preset business rules, maintenance reminders are pushed when the mileage reaches 5,000 kilometers, and replacement suggestions are pushed when tires are used for more than 3 years, triggering service recommendations; inventory management relies on safety stock thresholds for replenishment; workstations and technician resources are managed through manual scheduling and appointment registration; each store uses independent inventory management systems and customer relationship management systems, resulting in scattered data storage and a lack of cross-store and cross-regional data sharing and collaborative scheduling mechanisms.

[0003] The shortcomings of existing technology: In the current solution, the automotive aftermarket mainly relies on mobile apps as online access points. However, in offline scenarios such as parking lots and communities, users often want to access services directly and quickly without having to frequently take out their phones to operate. Existing smart terminal devices have limited functions and cannot provide an integrated interactive platform that covers diversified services such as repair, maintenance, leasing, finance, and insurance. In vehicle rental and vehicle relocation services, traditional key handover methods rely on manual transfer, which is inefficient, has high security risks, and is difficult to trace responsibility. There is a lack of intelligent management methods that can achieve secure storage and retrieval of vehicle keys and dual verification of user identity. The lack of a unified mechanism for collecting and integrating user behavior data, vehicle status data, and service execution data makes it impossible to form accurate insights into user needs and to achieve dynamic scheduling of service resources.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] This invention adopts the following technical solution: a four-in-one method for mining and value-added operation of automotive service data, comprising the following steps: Step 1: Through mobile internet APP, smart shared cloud cabinet, offline digital stores and micro-repair online store car service data, the mobile internet APP supports three roles for registration and login, the smart shared terminal device has dual identity recognition security verification, smart key management function, and connects with insurance companies, front-end customers and back-end service providers of operators, providing value-added service portals including buying and selling cars, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sale, advertising, as well as car rental and car moving service portals; Step 2: Map the 3D dataset to a dynamic spatiotemporal map with user vehicles, smart shared cloud cabinets, and offline stores as nodes, extract the spatiotemporal diffusion characteristics of service demand, obtain the demand probability field of the dynamic evolution law of demand, and automatically execute scheduling operations based on the demand probability field to push service recommendation information to users, issue work orders to offline stores, and reserve service workstations and technician resources. Step 3: After the user completes the dual identity verification on the smart shared cloud cabinet, they can directly interact with it, select the desired service from the mobile internet APP service, obtain the service authorization certificate, and record the user's interaction behavior and service selection data, which is then reported to the cloud server. The cloud server updates the service status and coordinates the corresponding service provider to execute the service. Step 4: After the service is completed, the offline store and service provider will record the real-time consumption data and service execution data generated by the vehicle, and update the user profile and vehicle maintenance cycle. The service execution data and user selection records will be automatically transmitted back to the data platform.

[0006] Furthermore, user behavior data, vehicle status data, smart shared cloud cabinet data, and store service data are collected through mobile internet apps, smart shared cloud cabinets, and offline digital stores, respectively, and then the data is processed and aligned. The specific steps are as follows: The following data were collected from mobile internet apps, smart shared cloud cabinets, digital visual stores, and micro-repair online stores, and the data was preprocessed. APP data: User behavior, usage data of three roles and eight functional modules; Cloud cabinet data: interactive operation, identity verification, key storage and retrieval, service images, integration with insurance and front-end and back-end data; Store data: work order status, technician schedule, workstation occupancy, and full-process service visualization; Micro-repair online store data: shared resource usage records, work order acceptance, service execution and evaluation data.

[0007] By cross-referencing and fusing three-dimensional data, a three-dimensional dataset is formed.

[0008] Furthermore, the intelligent shared cloud lockers are deployed in large parking lots of residential communities, airports, train stations, commercial centers, and office buildings, and have the following functions: Dual identity verification security: Verify user identity through at least two of the following methods: facial recognition, fingerprint recognition, ID card verification, and mobile APP QR code verification; Smart Key Management System: Receives and stores vehicle smart keys, and automatically ejects and locks the corresponding vehicle key based on the service authorization certificate; Connect with insurance companies: Real-time vehicle insurance status inquiry, providing access to insurance purchase, renewal, and claims filing; Connect with front-end customers and back-end service providers of operators: display service information, receive user requests, and distribute requests to the corresponding service providers; Track and record vehicle service destination and on-site conditions: Real-time collection of vehicle location and service process images via cameras and GPS positioning modules for remote viewing by users; Connect to backend management and control: Receive control commands issued by the backend and perform device self-checks, service locks, and advertising push operations.

[0009] Furthermore, the mobile internet app supports independent registration and login for three different roles, as detailed below: Car User Role: Has full access to services, including buying and selling cars, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sales, advertising, car rental during off-peak hours, and car moving service; Mobile deliveryman role: Receive vehicle relocation tasks distributed by the platform, view task details and vehicle location, and upload vehicle relocation completion confirmation information and on-site photos; Renter role: Search for available vehicles nearby through the AiCarRent function, submit a rental application, and obtain temporary vehicle authorization after completing identity verification; The specific process of the AiCarRental service includes: Car users can post their vehicle's off-peak rental hours and rental price through the smart shared cloud cabinet. Renters can search for and book vehicles through a mobile internet app. Both parties sign an electronic rental agreement online. After the renter obtains a smart key through the smart shared cloud cabinet's dual identity verification, the renter returns the key to the cloud cabinet after the rental is completed. The platform automatically settles the rental fee and transfers it to the car user's account.

[0010] Furthermore, the aforementioned four-in-one automotive service data value mining and value-added operation method is characterized by mapping the three-dimensional dataset to a dynamic spatiotemporal graph with user vehicles, intelligent shared cloud cabinets, and offline stores as nodes, extracting the spatiotemporal diffusion characteristics of service demand, and obtaining the demand probability field of the dynamic evolution law of demand. The specific process is as follows: The user vehicle information, smart shared cloud cabinet information, and offline store information in the 3D dataset are used as nodes in a dynamic spatiotemporal graph. Edge connections are constructed based on the spatial distance and historical interaction relationships between users and service resources to form a dynamic spatiotemporal graph. A spatiotemporal graph convolutional network is used to process the dynamic spatiotemporal graph, and the demand features of neighboring nodes are aggregated through graph convolution. The extracted spatiotemporal features are input into a multilayer perceptron, which outputs the probability P of each node generating service demand within a future preset time window, generating a demand probability field covering the entire service area. When P>0.7, the high-value area in the probability field is marked as a hotspot area; when P<0.3, the low-value area is marked as a cold area; and when 0.7≥P≥0.3, the medium-value area is marked as a normal area.

[0011] Furthermore, based on the demand probability field, scheduling operations are automatically executed to push service recommendation information to users, issue work orders to offline stores, and reserve service positions and technician resources. The specific process is as follows: For user vehicle nodes corresponding to high-value areas in the probability field, customized service recommendations and value-added service options are pushed to users through mobile internet apps. The recommendations include predicted service items, recommended stores and discount information, and value-added service options include car buying and selling, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sales, advertising, car rental, and car moving service entry points. For smart shared cloud cabinet nodes around high-value areas in the probability field, service recommendation information and value-added service access are pushed to users simultaneously through the smart shared cloud cabinet. Users need to pass dual identity verification and then directly interact with the cloud cabinet to select the desired service. As an offline resource sensing node, the cloud cabinet reports the parking status of surrounding vehicles and user touch interaction data in real time and dynamically adjusts the scheduling strategy. For resource reservation scenarios, such as car rental during off-peak hours or car moving service reservations, a local service authorization certificate is generated through the cloud cabinet and linked to the smart key management system. The reservation time limit is set, and if it is not confirmed within the time limit, the reservation resource is automatically released. The smart shared cloud cabinet tracks and records the vehicle service destination and on-site status and connects to the back-end management and control. Users can choose not to use insurance or choose the option themselves. For offline store nodes around high-value areas, the system automatically generates work orders, reserves service workstations and technician resources, and sends the work orders to the store terminals. The scheduling operation results are updated in real time to the node attributes of the dynamic spatiotemporal map.

[0012] Furthermore, after the service is completed, the offline store and service provider will record the real-time consumption data and service execution data generated by the vehicle, and update the user profile and vehicle maintenance cycle. The service execution data and user selection records will be automatically transmitted back to the data platform. The specific process is as follows: Data on actual service items, parts consumption, technician working hours, and vehicle status changes are entered into the terminal and uploaded to the data platform in real time. The platform updates users' cumulative spending, service preferences, and service acceptance records, resets the remaining life counters for maintained items, and dynamically adjusts the recommended time for the next maintenance. The intelligent shared cloud cabinet tracks and records the vehicle service destination and on-site conditions, including service process images, vehicle location changes, service start and end times, and uploads them to the data platform for archiving and future reference. The platform integrates service execution data and user selection records to optimize subsequent service recommendation strategies, adjust store resource allocation, and prioritize mobile delivery personnel. Users can check the vehicle service location and on-site status in real time through the APP or smart shared cloud cabinet, and evaluate the service quality. The evaluation data is sent back to the platform as a basis for evaluating service providers.

[0013] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: This four-in-one approach to data value mining and value-added operation in the automotive service industry breaks down the bottleneck of disconnect between online booking and offline execution in traditional automotive services through the synergistic linkage of mobile internet apps, smart shared cloud cabinets, offline digital stores, and micro-stores. Users can remotely book services via the app, interact directly with the smart shared cloud cabinet in the parking lot to obtain service authorization, and then go to the store or service provider for on-site execution. Data is seamlessly integrated and status is synchronized throughout the process, achieving a truly closed-loop service experience. The intelligent interactive terminal integrates dual identity verification, smart key management, integration with insurance companies, front-end customers and back-end service providers, tracking and recording vehicle service destinations and on-site conditions, and back-end management and control. Users can seamlessly connect with the cloud cabinet in parking scenarios, obtaining convenient services with optimal time, distance, and cost. Through the micro-repair store sharing and empowerment model, it enhances the automotive service... By sharing and optimizing the configuration of leasing, stores, products, tools, and equipment, the system reduces the operating costs of service providers. It collects multi-source data to construct a three-dimensional dataset of time, space, and business, mapping it to a dynamic spatiotemporal graph. This extracts the spatiotemporal diffusion characteristics of demand to generate a demand probability field, automatically executing scheduling operations such as service recommendations, work order issuance, and resource reservation. Users can obtain service authorization through dual authentication via the app and cloud cabinet. The entire process tracks and records the service destination and on-site conditions. After service completion, data is transmitted back to the platform in real time to update user profiles and maintenance cycles, and used to optimize subsequent recommendation strategies and resource allocation. This four-in-one collaborative system, combining the three-dimensional dataset of time, space, and business with the dynamic spatiotemporal graph for demand prediction and scheduling, forms a complete closed loop from online booking, cloud cabinet interaction, store execution to resource sharing. This significantly reduces user waiting time, improves service transparency and resource utilization efficiency, and builds a shared service ecosystem covering the entire lifecycle of automobiles. Attached Figure Description

[0014] Figure 1 A schematic diagram of the overall steps of the present invention is shown. Detailed Implementation

[0015] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below. Example 1:

[0016] like Figure 1 As shown, the four-in-one automotive service data value mining and value-added operation method includes the following steps: Step 1: Through mobile internet APP, smart shared cloud cabinet, offline digital stores and micro-repair online store car service data, the mobile internet APP supports three roles for registration and login, the smart shared terminal device has dual identity recognition security verification, smart key management function, and connects with insurance companies, front-end customers and back-end service providers of operators, providing value-added service portals including buying and selling cars, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sale, advertising, as well as car rental and car moving service portals; Step 2: Map the 3D dataset to a dynamic spatiotemporal map with user vehicles, smart shared cloud cabinets, and offline stores as nodes, extract the spatiotemporal diffusion characteristics of service demand, obtain the demand probability field of the dynamic evolution law of demand, and automatically execute scheduling operations based on the demand probability field to push service recommendation information to users, issue work orders to offline stores, and reserve service workstations and technician resources. Step 3: After the user completes the dual identity verification on the smart shared cloud cabinet, they can directly interact with it, select the desired service from the mobile internet APP service, obtain the service authorization certificate, and record the user's interaction behavior and service selection data, which is then reported to the cloud server. The cloud server updates the service status and coordinates the corresponding service provider to execute the service. Step 4: After the service is completed, the offline store and service provider will record the real-time consumption data and service execution data generated by the vehicle, and update the user profile and vehicle maintenance cycle. The service execution data and user selection records will be automatically transmitted back to the data platform.

[0017] User behavior data, vehicle status data, smart locker interaction data, and store service data are collected through mobile internet apps, smart shared lockers, and offline digital stores, respectively, and then the data is processed and aligned. The specific steps are as follows: The following data were collected from mobile internet apps, smart shared cloud cabinets, digital visual stores, and micro-repair online stores, and the data was preprocessed. APP data: User behavior, usage data of three roles and eight functional modules; Cloud cabinet data: interactive operation, identity verification, key storage and retrieval, service images, integration with insurance and front-end and back-end data; Store data: work order status, technician schedule, workstation occupancy, and full-process service visualization; Micro-repair online store data: shared resource usage records, work order acceptance, service execution and evaluation data.

[0018] By cross-referencing and fusing three-dimensional data, a three-dimensional dataset is formed.

[0019] The intelligent shared cloud lockers are deployed in large parking lots of residential communities, airports, train stations, commercial centers, and office buildings, and have the following functions: Dual identity verification security: Verify user identity through at least two of the following methods: facial recognition, fingerprint recognition, ID card verification, and mobile APP QR code verification; Smart Key Management System: Receives and stores vehicle smart keys, and automatically ejects and locks the corresponding vehicle key based on the service authorization certificate; Connect with insurance companies: Real-time vehicle insurance status inquiry, providing access to insurance purchase, renewal, and claims filing; Connect with front-end customers and back-end service providers of operators: display service information, receive user requests, and distribute requests to the corresponding service providers; Track and record vehicle service destination and on-site conditions: Real-time collection of vehicle location and service process images via cameras and GPS positioning modules for remote viewing by users; Connect to backend management and control: Receive control commands issued by the backend and perform device self-checks, service locks, and advertising push operations.

[0020] The mobile internet app supports independent registration and login for three roles, as detailed below: Car User Role: Has full access to services, including buying and selling cars, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sales, advertising, car rental during off-peak hours, and car moving service; Mobile deliveryman role: Receive vehicle relocation tasks distributed by the platform, view task details and vehicle location, and upload vehicle relocation completion confirmation information and on-site photos; Renter role: Search for available vehicles nearby through the AiCarRent function, submit a rental application, and obtain temporary vehicle authorization after completing identity verification; The specific process of the AiCarRental service includes: Car users can post their vehicle's off-peak rental hours and rental price through the smart shared cloud cabinet. Renters can search for and book vehicles through a mobile internet app. Both parties sign an electronic rental agreement online. After the renter obtains a smart key through the smart shared cloud cabinet's dual identity verification, the renter returns the key to the cloud cabinet after the rental is completed. The platform automatically settles the rental fee and transfers it to the car user's account.

[0021] The three-dimensional dataset is mapped to a dynamic spatiotemporal graph with user vehicles, smart shared cloud lockers, and offline stores as nodes. The spatiotemporal diffusion features of service demand are extracted to obtain the demand probability field of the dynamic evolution law of demand. The specific process is as follows: The user vehicle information, smart shared cloud cabinet information, and offline store information in the 3D dataset are used as nodes in a dynamic spatiotemporal graph. Edge connections are constructed based on the spatial distance and historical interaction relationships between users and service resources to form a dynamic spatiotemporal graph. A spatiotemporal graph convolutional network is used to process the dynamic spatiotemporal graph, and the demand features of neighboring nodes are aggregated through graph convolution. The extracted spatiotemporal features are input into a multilayer perceptron, which outputs the probability P of each node generating service demand within a future preset time window, generating a demand probability field covering the entire service area. When P>0.7, the high-value area in the probability field is marked as a hotspot area; when P<0.3, the low-value area is marked as a cold area; and when 0.7≥P≥0.3, the medium-value area is marked as a normal area. Node demand probability calculation Features of each node extracted from the spatiotemporal graph neural network Given a three-layer multilayer perceptron, output the probability of demand for this node within a preset future time window. calculate: in, These are the weighting coefficients. For bias terms; For any spatial location Demand probability It is obtained by the probability-weighted average of the surrounding nodes: in, , d is the bandwidth parameter, and d is the distance parameter; in, The predicted probability after smoothing the time dimension of the current window. The smoothing probability of the previous window. This represents the original probability of the current window.

[0022] Based on the demand probability field, the system automatically executes scheduling operations, pushes service recommendation information to users, issues work orders to offline stores, and reserves service positions and technician resources. The specific process is as follows: For user vehicle nodes corresponding to high-value areas in the probability field, customized service recommendations and value-added service options are pushed to users through mobile internet apps. The recommendations include predicted service items, recommended stores and discount information, and value-added service options include car buying and selling, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sales, advertising, car rental, and car moving service entry points. For smart shared cloud cabinet nodes around high-value areas in the probability field, service recommendation information and value-added service access are pushed to users simultaneously through the smart shared cloud cabinet. Users need to pass dual identity verification and then directly interact with the cloud cabinet to select the desired service. As an offline resource sensing node, the cloud cabinet reports the parking status of surrounding vehicles and user touch interaction data in real time and dynamically adjusts the scheduling strategy. For resource reservation scenarios, such as car rental during off-peak hours or car moving service reservations, a local service authorization certificate is generated through the cloud cabinet and linked to the smart key management system. The reservation time limit is set, and if it is not confirmed within the time limit, the reservation resource is automatically released. The smart shared cloud cabinet tracks and records the vehicle service destination and on-site status and connects to the back-end management and control. Users can choose not to use insurance or choose the option themselves. For offline store nodes around high-value areas, the system automatically generates work orders, reserves service workstations and technician resources, and sends the work orders to the store terminals. The scheduling operation results are updated in real time to the node attributes of the dynamic spatiotemporal map.

[0023] The vehicle status data is input into a pre-trained generative adversarial network model to generate a list of potential additional services, using vehicle status and maintenance history as inputs. The specific process is as follows: The system automatically acquires the vehicle's current status data through the store terminal, including mileage, fluid life, tire pressure, and battery health. It also retrieves the vehicle's historical maintenance records from the data platform, including service items, replaced parts, repair time, and technician notes. The data is then integrated into a structured feature vector, which serves as the input condition for the generative adversarial network model. The pre-trained generative adversarial network model is invoked, which consists of a generator and a discriminator; The generator takes the vehicle state structured feature vector as input and combines it with random noise vector to generate multiple sets of potential additional service lists in the demand space. Each additional service includes service type, estimated working hours, parts requirements and reference price. The discriminator takes the generated list of additional services and the historical list of actual additional services as input, outputs a reasonableness score for the list, and generates a reasonable list of value-added services through service conflict checks and accessory compatibility checks.

[0024] Based on user consumption habits, price sensitivity, and historical acceptance rates, the probability of user acceptance for each additional service is predicted. Preferred additional services are then pushed to the user for confirmation before execution. The specific process is as follows: Based on user profile features This includes consumption habits: historical average order value, purchase frequency, preferred service types, price sensitivity: discount acceptance rate, and each additional item in the value-added service list. Calculate the probability of user acceptance: Candidate additions are sorted from highest to lowest based on acceptance probability, and weighted according to the expected profit or user value of the additions, with priority given to pushing additions with high acceptance probability and high value to users' mobile internet apps. The platform will push the sorted list of preferred add-ons to users via a mobile internet app. Each push includes the add-on name, a description of its necessity, an estimated cost, an expected duration of the add-on, and an accept / reject option button. After the user clicks to confirm, the app will send the confirmation instruction back to the data platform.

[0025] This system enables in-depth mining of user intent, generating structured data for direct consumption by advanced models such as adversarial networks. It predicts the spatial diffusion patterns of user demand, pre-locks nearby service resources, and reserves store workstations, ensuring availability upon user arrival. This proactive pre-positioning of service resources significantly reduces user waiting time. Based on user consumption habits, price sensitivity, and historical acceptance rates, it constructs an acceptance probability prediction model to personalize and prioritize candidate add-ons, pushing high-acceptance-probability and high-value add-ons for personalized and precise service delivery. Users obtain service authorization credentials directly through interaction on the intelligent shared cloud cabinet and proceed directly to the store for service, eliminating the need for queuing. Service status is automatically updated and synchronized with the platform after user interaction, allowing stores to know user arrival time and service needs in advance, achieving precise matching of service resources. After each service, data such as the actual service items performed, accessory consumption, and user acceptance / rejection behavior are automatically transmitted back to the platform, serving as positive and negative samples for the spatiotemporal graph neural network and generative adversarial network models. This improves prediction accuracy and the rationality of add-ons, ensuring that operational strategies dynamically adapt to market and user changes.

[0026] After the service is completed, the offline store and service provider will record the real-time consumption data and service execution data generated by the vehicle, and update the user profile and vehicle maintenance cycle. The service execution data and user selection records will be automatically transmitted back to the data platform. The specific process is as follows: Data on actual service items, parts consumption, technician working hours, and vehicle status changes are entered into the terminal and uploaded to the data platform in real time. The platform updates users' cumulative spending, service preferences, and service acceptance records, resets the remaining life counters for maintained items, and dynamically adjusts the recommended time for the next maintenance. The intelligent shared cloud cabinet tracks and records the vehicle service destination and on-site conditions, including service process images, vehicle location changes, service start and end times, and uploads them to the data platform for archiving and future reference. The platform integrates service execution data and user selection records to optimize subsequent service recommendation strategies, adjust store resource allocation, and prioritize mobile delivery personnel. Users can check the vehicle service location and on-site status in real time through the APP or smart shared cloud cabinet, and evaluate the service quality. The evaluation data is sent back to the platform as a basis for evaluating service providers.

[0027] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0028] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. In the two embodiments provided in this application, it should be understood that the disclosed methods can be implemented in other ways; for example, the device embodiments described above are merely illustrative, and the division of modules is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or modules may be electrical, mechanical or other forms. The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A four-in-one method for data value mining and value-added operation in the automotive service industry, characterized by: Includes the following steps: Step 1: Through mobile internet APP, smart shared cloud cabinet, offline digital stores and micro-repair online store car service data, the mobile internet APP supports three roles for registration and login, the smart shared terminal device has dual identity recognition security verification, smart key management function, and connects with insurance companies, front-end customers and back-end service providers of operators, providing value-added service portals including buying and selling cars, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sale, advertising, as well as car rental and car moving service portals; Step 2: Map the 3D dataset to a dynamic spatiotemporal map with user vehicles, smart shared cloud cabinets, and offline stores as nodes, extract the spatiotemporal diffusion characteristics of service demand, obtain the demand probability field of the dynamic evolution law of demand, and automatically execute scheduling operations based on the demand probability field to push service recommendation information to users, issue work orders to offline stores, and reserve service workstations and technician resources. Step 3: After the user completes the dual identity verification on the smart shared cloud cabinet, they can directly interact with it, select the desired service from the mobile internet APP service, obtain the service authorization certificate, and record the user's interaction behavior and service selection data, which is then reported to the cloud server. The cloud server updates the service status and coordinates the corresponding service provider to execute the service. Step 4: After the service is completed, the offline store and service provider will record the real-time consumption data and service execution data generated by the vehicle, and update the user profile and vehicle maintenance cycle. The service execution data and user selection records will be automatically transmitted back to the data platform.

2. The four-in-one automotive service data value mining and value-added operation method according to claim 1, characterized in that, User behavior data, vehicle status data, smart locker interaction data, and store service data are collected through mobile internet apps, smart shared lockers, and offline digital stores, respectively, and then the data is processed and aligned. The specific steps are as follows: The following data were collected from mobile internet apps, smart shared cloud cabinets, digital visual stores, and micro-repair online stores, and the data was preprocessed. APP data: User behavior, usage data of three roles and eight functional modules; Cloud cabinet data: interactive operation, identity verification, key storage and retrieval, service images, integration with insurance and front-end and back-end data; Store data: work order status, technician schedule, workstation occupancy, and full-process service visualization; Micro-repair online store data: shared resource usage records, work order acceptance, service execution and evaluation data.

3. Cross-reference and merge the three-dimensional data to form a three-dimensional dataset.

4. The four-in-one automotive service data value mining and value-added operation method according to claim 1, characterized in that, The intelligent shared cloud lockers are deployed in large parking lots of residential communities, airports, train stations, commercial centers, and office buildings, and have the following functions: Dual identity verification security: Verify user identity through at least two of the following methods: facial recognition, fingerprint recognition, ID card verification, and mobile APP QR code verification; Smart Key Management System: Receives and stores vehicle smart keys, and automatically ejects and locks the corresponding vehicle key based on the service authorization certificate; Connect with insurance companies: Real-time vehicle insurance status inquiry, providing access to insurance purchase, renewal, and claims filing; Connect with front-end customers and back-end service providers of operators: display service information, receive user requests, and distribute requests to the corresponding service providers; Track and record vehicle service destination and on-site conditions: Real-time collection of vehicle location and service process images via cameras and GPS positioning modules for remote viewing by users; Connect to backend management and control: Receive control commands issued by the backend and perform device self-checks, service locks, and advertising push operations.

5. The four-in-one automotive service data value mining and value-added operation method according to claim 1, characterized in that, The mobile internet app supports independent registration and login for three roles, as detailed below: Car User Role: Has full access to services, including buying and selling cars, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sales, advertising, car rental during off-peak hours, and car moving service; Mobile deliveryman role: Receive vehicle relocation tasks distributed by the platform, view task details and vehicle location, and upload vehicle relocation completion confirmation information and on-site photos; Renter role: Search for available vehicles nearby through the AiCarRent function, submit a rental application, and obtain temporary vehicle authorization after completing identity verification; The specific process of the AiCarRental service includes: Car users can post their vehicle's off-peak rental hours and rental price through the smart shared cloud cabinet. Renters can search for and book vehicles through a mobile internet app. Both parties sign an electronic rental agreement online. After the renter obtains a smart key through the smart shared cloud cabinet's dual identity verification, the renter returns the key to the cloud cabinet after the rental is completed. The platform automatically settles the rental fee and transfers it to the car user's account.

6. The four-in-one automotive service data value mining and value-added operation method according to claim 1, characterized in that, The three-dimensional dataset is mapped to a dynamic spatiotemporal graph with user vehicles, smart shared cloud lockers, and offline stores as nodes. The spatiotemporal diffusion features of service demand are extracted to obtain the demand probability field of the dynamic evolution law of demand. The specific process is as follows: The user vehicle information, smart shared cloud cabinet information, and offline store information in the 3D dataset are used as nodes in a dynamic spatiotemporal graph. Edge connections are constructed based on the spatial distance and historical interaction relationships between users and service resources to form a dynamic spatiotemporal graph. A spatiotemporal graph convolutional network is used to process the dynamic spatiotemporal graph, and the demand features of neighboring nodes are aggregated through graph convolution. The extracted spatiotemporal features are input into a multilayer perceptron, which outputs the probability P of each node generating service demand within a future preset time window, generating a demand probability field covering the entire service area. When P>0.7, the high-value area in the probability field is marked as a hotspot area; when P<0.3, the low-value area is marked as a cold area; and when 0.7≥P≥0.3, the medium-value area is marked as a normal area.

7. The four-in-one automotive service data value mining and value-added operation method according to claim 1, characterized in that, Based on the demand probability field, the system automatically executes scheduling operations, pushes service recommendation information to users, issues work orders to offline stores, and reserves service positions and technician resources. The specific process is as follows: For user vehicle nodes corresponding to high-value areas in the probability field, customized service recommendations and value-added service options are pushed to users through mobile internet apps. The recommendations include predicted service items, recommended stores and discount information, and value-added service options include car buying and selling, car repair and maintenance, car insurance, parts mall, auto finance, car owner health care, one-yuan flash sales, advertising, car rental, and car moving service entry points. For smart shared cloud cabinet nodes around high-value areas in the probability field, service recommendation information and value-added service access are pushed to users simultaneously through the smart shared cloud cabinet. Users need to pass dual identity verification and then directly interact with the cloud cabinet to select the desired service. As an offline resource sensing node, the cloud cabinet reports the parking status of surrounding vehicles and user touch interaction data in real time and dynamically adjusts the scheduling strategy. For resource reservation scenarios, such as car rental during off-peak hours or car moving service reservations, a local service authorization certificate is generated through the cloud cabinet and linked to the smart key management system. The reservation time limit is set, and if it is not confirmed within the time limit, the reservation resource is automatically released. The smart shared cloud cabinet tracks and records the vehicle service destination and on-site status and connects to the back-end management and control. Users can choose not to use insurance or choose the option themselves. For offline store nodes around high-value areas, the system automatically generates work orders, reserves service workstations and technician resources, and sends the work orders to the store terminals. The scheduling operation results are updated in real time to the node attributes of the dynamic spatiotemporal map.

8. The four-in-one automotive service data value mining and value-added operation method according to claim 1, characterized in that, After the service is completed, the offline store and service provider will record the real-time consumption data and service execution data generated by the vehicle, and update the user profile and vehicle maintenance cycle. The service execution data and user selection records will be automatically transmitted back to the data platform. The specific process is as follows: Data on actual service items, parts consumption, technician working hours, and vehicle status changes are entered into the terminal and uploaded to the data platform in real time. The platform updates users' cumulative spending, service preferences, and service acceptance records, resets the remaining life counters for maintained items, and dynamically adjusts the recommended time for the next maintenance. The intelligent shared cloud cabinet tracks and records the vehicle service destination and on-site conditions, including service process images, vehicle location changes, service start and end times, and uploads them to the data platform for archiving and future reference. The platform integrates service execution data and user selection records to optimize subsequent service recommendation strategies, adjust store resource allocation, and prioritize mobile delivery personnel. Users can check the vehicle service location and on-site status in real time through the APP or smart shared cloud cabinet, and evaluate the service quality. The evaluation data is sent back to the platform as a basis for evaluating service providers.

Images