Intelligent multi-terminal collaborative automobile after-market full-link service management system

Abstract

The application discloses a smart multi-terminal collaborative automobile after-market full-link service management system and relates to the technical field of service management.The system comprises a data receiving unit, a service updating unit, an identity recognition unit, a service confirming unit and an information output unit.Through multi-terminal data collection and fusion analysis, the application automatically matches the vehicle owner's reservation with the service capacity of the store, generates a precise time window and a recommended cloud cabinet, reduces the waiting and cabinet searching time of the vehicle owner, and enables the vehicle owner to complete the reservation, cabinet opening, key storage and retrieval and other operations without going to the store, thereby realizing a time-saving, labor-saving and worry-free service experience.Furthermore, the application adopts a dual identity authentication mechanism of face feature comparison and token verification to ensure that the cabinet opening operation is only performed by the owner himself, and simultaneously, the application monitors the cabinet door state and the key box in-place data in real time, automatically identifies irregular behaviors such as abnormal door opening or timeout without closing and generates an alarm, and effectively prevents the risk of asset loss.

Description

Technical Field

[0001] This invention relates to the field of service management technology, specifically to a smart multi-terminal collaborative full-chain service management system for the automotive aftermarket. Background Technology

[0002] With the continuous growth of car ownership, the demand for automotive aftermarket services is booming. However, the traditional automotive aftermarket service model has long suffered from the following technical bottlenecks: First, the service process relies on offline manual interaction, requiring car owners to personally visit the store to complete appointments, vehicle delivery, waiting, and vehicle pickup, resulting in high time and distance costs. Second, data is fragmented across multiple platforms, with a lack of a unified coordination mechanism between mobile apps, store systems, and smart devices, leading to low efficiency in matching service capabilities with user needs. Third, identity verification and operational supervision methods are limited, posing security risks during car key handover and resulting in insufficient asset traceability. Fourth, there is a lack of a complete data loop after service completion, preventing real-time communication between external institutions such as insurance and finance companies and the service platform, thus limiting the expansion of value-added services. In recent years, some companies have tried to introduce smart lockers to realize key storage and retrieval, but this only solves the single storage and retrieval link and fails to connect the entire process of appointment, service execution, evaluation feedback, and credit management. In the existing technology, there is a lack of a system solution that can integrate mobile Internet terminals, smart hardware devices and physical store systems in a multi-dimensional way. It is impossible to realize the data connection from online appointment to offline unmanned interaction and physical service closed loop. In addition, the existing system lacks intelligent analysis capabilities in supply and demand matching, credit assessment, dynamic deposit strategy and automatic update of technician performance, resulting in high operating costs for B-end and poor service experience for C-end. Therefore, there is an urgent need to develop a multi-terminal collaborative full-chain service management system for the automotive aftermarket. This system should address issues such as fragmented processes, low efficiency, insufficient security, and lack of value-added services in existing technologies through data collection, fusion analysis, aligned output, and closed-loop feedback. Summary of the Invention

[0003] The purpose of this invention is to provide a smart, multi-terminal collaborative, end-to-end service management system for the automotive aftermarket, in order to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a smart multi-terminal collaborative automotive aftermarket full-chain service management system, comprising: The data receiving unit collects different data from mobile internet apps, smart cloud cabinets, chain physical store ports and external institutions, and stores them in an ordered set. The service update unit calls the multi-terminal fusion engine to analyze the ordered set, and after obtaining the results, aligns the data in the ordered set to generate a confirmation appointment time window, a store task queue update instruction, a recommended recent cloud cabinet ID, a one-time cabinet opening token, a value-added service reminder mark, a deposit strategy code, and APP dynamic menu configuration parameters. The identity recognition unit collects interaction data after the vehicle owner arrives at the cloud cabinet, and obtains the identity verification result, face similarity score and operation compliance mark. Based on this, it generates the cabinet opening authorization instruction, identity confidence level, abnormal door opening alarm mark and interaction completion signal. The service confirmation unit collects execution records, key retrieval behavior, satisfaction evaluation and performance results after the service is completed. It calls the closed-loop analysis engine to obtain deviation rate, spatiotemporal consistency score and correlation influence coefficient. Based on this, it generates service completion confirmation certificate, key flow closed-loop mark, technician performance update record and value-added service trigger instruction. The information output unit pushes all data to the mobile APP, smart cloud cabinet and chain physical stores respectively, and completes the update of instructions and synchronization of status on each terminal.

[0005] Preferably, the service update unit includes a work order number calculation module, a matching degree calculation module, and a credit coefficient calculation module; The work order calculation module calculates the number of work orders from an ordered set. Extract appointment request data Expected service time within Service capability data Number of vacant workstations in stores and technician scheduling status ,in , Indicates the first The on-duty status of each technician Indicates the total number of technicians, according to and Calculate the time Maximum number of service orders that can be processed in an inner store ,in , Indicates time The number of available workstations in the store. Indicates the first Master technicians in time On-duty status Indicates the serial number; The matching degree calculation module utilizes Calculate the matching degree between the current user and the store. ,in , , Represents the natural constant. Represents the time sensitivity coefficient. Indicates the appointment time. This represents the difference between the expected time and the nearest available time. This represents the theoretical maximum parallel service capacity of a store. If it is a high match, the appointment can be confirmed directly. If the match is medium, the user is advised to adjust the time. If the match is not found, it is considered a low match, and it is recommended to change stores. The credit rating calculation module from Extract policy binding data Number of claims Credit assessment data Car owner credit score and lease history default records ,use and Calculate the overall credit score ,in , This represents the maximum credit score. This represents the minimum credit score. Represents the attenuation coefficient, according to Identify the corresponding deposit reduction eligibility tags.

[0006] Preferably, the service update unit further includes a preference weight calculation module, an analysis result generation module, and an analysis result alignment module; The preference weight calculation module calculates from ordered sets Extract appointment request data Historical service type selection records Interaction preference data Click hotspot matrix within Average page dwell time vector The frequency of canceled appointments in the past 30 days Then, the preference weights of car owners for four service types—maintenance, car rental, minor repairs, and detailing—are calculated, and the service type with the highest preference weight is selected as the default recommended service type. The analysis result generation module combines the current user's matching degree with the store, the deposit reduction qualification tag, and the preference weights of the four service types to obtain a set of analysis results; The analysis result alignment module aligns the ordered set according to the analysis result set. Alignment is performed to obtain a new set. ,in , Indicates the appointment time window. This indicates a command to update the store's task queue. This indicates a recent recommendation for a cloud storage ID. This indicates a one-time unlocking token. This indicates a reminder about value-added services. This indicates the deposit strategy code. This indicates the configuration parameters for the app's dynamic menu.

[0007] Preferably, the identity recognition unit includes an interactive data acquisition module, a token comparison module, and a similarity calculation module; After the vehicle owner arrives at the cloud cabinet, the interactive data collection module collects the interactive data at the cloud cabinet, forming an interactive set. ,in , This indicates a token for opening the cabinet. This represents the facial feature vector of the car owner. This represents the cabinet door status data collected by the cloud cabinet's mechanical sensors. This indicates the location data of the key box collected jointly by the cloud cabinet's gravity sensor and RFID reader; The token comparison module for To conduct analysis, In The tokens are compared one by one with the list of valid tokens cached locally in the cloud cabinet. If the token exists in the list and has not expired, the authentication result is successful. If the token does not exist or has expired, the result is unsuccessful. The similarity calculation module will In The similarity between the registered facial feature templates bound to the reservation is calculated to obtain the similarity score between the two feature vectors, which is used as the facial similarity score.

[0008] Preferably, the identity recognition unit further includes an opening instruction analysis module, a result output module, and a signal generation module; The cabinet opening instruction analysis module will In The opening timestamp is compared with the time of the opening instruction. If the opening time is later than the instruction issuance time and the interval between the two is within the preset threshold, the operation is compliant. If the opening time is earlier than the instruction issuance time, it is marked as opening the door before the instruction. If no closing signal is detected after the preset time has elapsed, it is marked as not closing after timeout. The result output module summarizes the identity verification result, face similarity score, and operation compliance mark to obtain the judgment result; The signal generation module will apply the determination result to the interaction set. Alignment is performed to obtain a new set. .in , This indicates an authorization to open the cabinet. Indicates the level of confidence in the identity. This indicates an abnormal door opening alarm sign. This indicates that the interaction is complete.

[0009] Preferably, the service confirmation unit includes a service data acquisition module and a deviation rate calculation module; After the service data collection module completes its service execution, the store and external organizations collect closed-loop data to form a set. ,in , This indicates the service execution record. This represents the data related to the key retrieval behavior. This represents the satisfaction rating data. This represents the data indicating the performance results. The deviation rate calculation module utilizes a closed-loop analysis engine to... To conduct analysis, from of Extract the actual start and end times of the service from the ordered set to calculate the actual service duration. Reservation request data Extract the expected service duration at the time of booking, and analyze the deviation rate based on the absolute value of the difference between the actual service duration and the expected service duration and the expected service duration.

[0010] Preferably, the service confirmation unit further includes a consistency analysis module, an impact coefficient calculation module, and a record update module; The consistency analysis module from the set Key retrieval behavior data Extract the timestamp of the car owner retrieving the keys from the set. Interaction completion signal Extract the timestamp of the key stored by the car owner. Service execution records Extract the start and end times of service execution, check the logical order of the four time points. The key deposit time must be earlier than the service start time, and the service end time must be earlier than the key retrieval time. If the order is correct and the adjacent time intervals are all within the preset threshold, the spatiotemporal consistency score is set to 1. If the order is correct but there are intervals that exceed the threshold, the score is set to 0.5. If the order is incorrect, the score is set to 0. The influence coefficient calculation module is based on satisfaction evaluation data. and performance data Calculate the correlation impact coefficient; The record update module aggregates the deviation rate, spatiotemporal consistency score, and correlation influence coefficient, and then bases the aggregation results on the set. The system identifies service completion confirmation credentials, key transfer loop markers, technician performance update records, and value-added service trigger instructions.

[0011] Preferably, the information output unit includes an information feedback module and an information display module; The information feedback module will integrate , The service completion confirmation certificate, key circulation closed loop mark, technician performance update record and value-added service trigger instruction are respectively fed back to the mobile APP, smart cloud cabinet and chain physical stores and back-end management platform. The information display module on the mobile APP displays the confirmation time window, deposit policy and service completion certificate. The smart cloud cabinet executes the cabinet opening instruction, reports abnormal alarms and records the key transfer loop. The chain physical stores and the back-end management platform update the task queue, technician performance and value-added service instructions.

[0012] Compared with the prior art, the beneficial effects of the present invention are: This invention automatically matches car owner appointments with store service capabilities through multi-terminal data collection and fusion analysis, generating precise time windows and recommended cloud lockers, reducing car owners' waiting and locker search time. Car owners can complete appointments, locker opening, and key storage / retrieval without visiting the store, achieving a time-saving, hassle-free, and worry-free service experience. In terms of technical architecture, this invention constructs a "four-in-one" service system: First, the mobile app and AI-powered modules rely on artificial intelligence algorithms to predict user behavior, make intelligent recommendations, and dynamically schedule tasks, supporting online operations throughout the entire process, including appointments, payments, service tracking, and credit assessments. Second, the intelligent cloud cabinet system integrates advertising playback, user operation interaction and intelligent car key management functions, supports multi-terminal data collaboration, and realizes efficient information flow between car owners and stores; Third, digital and visual stores enable visualized monitoring of the entire automotive service process. Car owners and managers can view service progress, equipment status, and personnel dynamics in real time, improving service transparency and management efficiency. Fourth, the micro-repair network sharing empowerment system covers the sharing capabilities of multiple parties, including car services, leasing, stores, products, tools and equipment, to improve resource utilization and service coverage. This invention employs a dual authentication mechanism combining facial recognition and token verification to ensure that opening the cabinet is performed only by the account holder. Simultaneously, it monitors the cabinet door status and key box availability in real time, automatically identifying unauthorized openings or failure to close the door within a specified time and generating alarms to effectively prevent asset loss. This invention dynamically generates deposit strategies based on credit assessment data, incentivizing good credit behavior and lowering the barrier to car rental. Technician performance updates and value-added service trigger instructions provide data support for store management, driving continuous growth in service traffic and profitability. From booking to service completion and feedback, data at each stage is seamlessly integrated with insurance and financial institutions, supporting automatic claims triggering and dynamic credit score updates. This provides car owners with more comprehensive value-added services and also provides decision-making basis for platform supply chain optimization and cost control. Attached Figure Description

[0013] Figure 1 A schematic diagram of the overall system flow is provided for embodiments of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and 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.

[0015] Please see Figure 1 This invention provides a technical solution: a smart multi-terminal collaborative automotive aftermarket full-chain service management system, comprising: The data receiving unit collects different data from mobile internet apps, smart cloud cabinets, chain physical store terminals and external institutions, and stores them into an ordered set. The service update unit calls the multi-terminal fusion engine to analyze the ordered set. After obtaining the results, it aligns the data in the ordered set and generates confirmation appointment time windows, store task queue update instructions, recommended recent cloud cabinet IDs, one-time cabinet opening tokens, value-added service reminder tags, deposit policy codes, and APP dynamic menu configuration parameters. The identity recognition unit collects interaction data after the vehicle owner arrives at the cloud cabinet, and obtains the identity verification result, face similarity score and operation compliance mark. Based on this, it generates the cabinet opening authorization command, identity confidence level, abnormal door opening alarm mark and interaction completion signal. The service confirmation unit collects execution records, key retrieval behavior, satisfaction evaluation and performance results after the service is completed. It calls the closed-loop analysis engine to obtain deviation rate, spatiotemporal consistency score and correlation impact coefficient. Based on this, it generates service completion confirmation certificate, key flow closed-loop mark, technician performance update record and value-added service trigger instruction. The information output unit pushes all data to the mobile APP, smart cloud cabinet and chain physical stores respectively, and completes the update of instructions and synchronization of status on each terminal.

[0016] The car owner opens the mobile internet app, selects the service type, sets the desired service time, and authorizes the app to access the vehicle's current location and historical service type selection records. The app encapsulates these four pieces of information into JSON format and uploads them to the system's cloud server via HTTPS protocol. After receiving the data, the server generates a unique reservation number for this appointment and uses the reservation number and related information as the reservation request data submitted by the car owner through the mobile app. Store in the temporary order pool.

[0017] Merchants enter the remaining available working hours, technician shift status, and number of currently available workstations daily through the backend management platform. All data is automatically refreshed every 15 minutes, and the platform's scheduled tasks extract service capacity data from the store's database. Store it in the service capability cache table.

[0018] When a car owner registers on the app, the camera captures the user's face, and an embedded AI model extracts a 128-dimensional facial feature vector. When the car owner initiates a reservation, the app obtains the current Unix timestamp, concatenates the facial feature vector and timestamp into a string, performs a SHA-256 hash operation, and generates a 256-bit hash value as a one-time identity credential. It is transmitted to the cloud server.

[0019] By using a pre-established data interface with the insurance company, and with the vehicle owner's authorization, a query request is sent to the insurance company. The request parameters include the vehicle owner's ID number and the vehicle's VIN code. The insurance company's API returns options for purchasing extended warranty services and the number of past claims, which are then used as policy-linked data. Link and bind it to the current vehicle owner's account.

[0020] By using a pre-established data interface with financial institutions, and with the vehicle owner's authorization, a credit inquiry request is sent to a legitimate credit reporting agency or partner financial institution. The request parameters include the vehicle owner's name, ID number, and mobile phone number. The financial institution's API returns the vehicle owner's credit score and lease history default records, which are then used as credit assessment data. Stored in the vehicle owner's credit file; The car owner's app has a built-in front-end tracking SDK that automatically records user behavior data during normal app use. This behavior data includes click hotspots, page dwell time, and appointment cancellation frequency. Every 5 minutes, the SDK packages and compresses this data and sends it to the data collection gateway via an asynchronous reporting channel. After receiving and cleaning the data, the gateway generates interaction preference data. ; Data was collected from mobile internet apps, smart vending machines, chain store portals, and external organizations. Then, store it in an ordered set. ; The service update unit includes a work order number calculation module, a matching degree calculation module, and a credit coefficient calculation module; The work order count calculation module starts from ordered sets. Extract appointment request data Expected service time within Service capability data Number of vacant workstations in stores and technician scheduling status ,in , Indicates the first The on-duty status of each technician Indicates the total number of technicians, according to and Calculate the time Maximum number of service orders that can be processed in an inner store ,in , Indicates time The number of available workstations in the store. Indicates the first Master technicians in time On-duty status Indicates the serial number; The matching degree calculation module utilizes Calculate the matching degree between the current user and the store. ,in , , Represents the natural constant. Represents the time sensitivity coefficient. Indicates the appointment time. This represents the difference between the expected time and the nearest available time. This represents the theoretical maximum parallel service capacity of a store. If it is a high match, the appointment can be confirmed directly. If the match is medium, the user is advised to adjust the time. If the match is not found, it is considered a low match, and it is recommended to change stores. Credit coefficient calculation module from Extract policy binding data Number of claims Credit assessment data Car owner credit score and lease history default records ,use and Calculate the overall credit score ,in , This represents the maximum credit score. This represents the minimum credit score. Represents the attenuation coefficient, according to Identify the corresponding deposit reduction eligibility tags; The service update unit also includes a preference weight calculation module, an analysis result generation module, and an analysis result alignment module; The preference weight calculation module starts from ordered sets. Extract appointment request data Historical service type selection records Interaction preference data Click hotspot matrix within Average page dwell time vector The frequency of canceled appointments in the past 30 days Then, the preference weights of car owners for four service types—maintenance, car rental, minor repairs, and detailing—are calculated, and the service type with the highest preference weight is selected as the default recommended service type. For each service type The specific preference weights are as follows: in, Indicates service type Preference weights, This indicates the type of service the car owner selected in the past 90 days. frequency, This indicates that the clicked hotspot is related to the service type. Total number of clicks for the corresponding interface area. This indicates the total number of appointments made by the car owner in the past 90 days. Indicates the weighting coefficient. Indicates all service types Total number of page clicks; The analysis results generation module combines the current user's matching degree with the store, the deposit reduction qualification tag, and the preference weights of the four service types to obtain a set of analysis results; The analysis result alignment module aligns the analysis result set with the ordered set. Alignment is performed to obtain a new set. ,in , Indicates the appointment time window. This indicates a command to update the store's task queue. This indicates a recent recommendation for a cloud storage ID. This indicates a one-time unlocking token. This indicates a reminder about value-added services. This indicates the deposit strategy code. This indicates the configuration parameters for the app's dynamic menu; The identity recognition unit includes an interactive data acquisition module, a token comparison module, and a similarity calculation module; After the car owner arrives at the cloud cabinet, the cloud cabinet collects the interaction data to form an interaction set. ,in , This indicates a token for opening the cabinet. This represents the facial feature vector of the car owner. This represents the cabinet door status data collected by the cloud cabinet's mechanical sensors. This indicates the location data of the key box collected jointly by the cloud cabinet's gravity sensor and RFID reader; Token comparison module To conduct analysis, In The tokens are compared one by one with the list of valid tokens cached locally in the cloud cabinet. If the token exists in the list and has not expired, the authentication result is successful. If the token does not exist or has expired, the result is unsuccessful. The similarity calculation module will In The similarity between the registered facial feature templates bound to the reservation is calculated to obtain the similarity score between the two feature vectors, which is used as the facial similarity score. The identification unit also includes an opening instruction analysis module, a result output module, and a signal generation module; The cabinet opening instruction analysis module will In The opening timestamp is compared with the time of the opening instruction. If the opening time is later than the instruction issuance time and the interval between the two is within the preset threshold, the operation is compliant. If the opening time is earlier than the instruction issuance time, it is marked as opening the door before the instruction. If no closing signal is detected after the preset time has elapsed, it is marked as not closing after timeout. The results output module summarizes the identity verification results, face similarity score, and operation compliance flag to obtain the judgment result; The signal generation module will evaluate the results to the interaction set. Alignment is performed to obtain a new set. .in , This indicates an authorization to open the cabinet. Indicates the level of confidence in the identity. This indicates an abnormal door opening alarm sign. This indicates that the interaction is complete. The service verification unit includes a service data acquisition module and a deviation rate calculation module; After the service data collection module completes its service execution, the store and external organizations collect closed-loop data to form a collection. ,in , This indicates the service execution record. This represents the data related to the key retrieval behavior. This represents the satisfaction rating data. This represents the data indicating the performance results. The deviation rate calculation module utilizes a closed-loop analysis engine to... To conduct analysis, from of Extract the actual start and end times of the service from the ordered set to calculate the actual service duration. Reservation request data Extract the expected service duration at the time of booking, and analyze the deviation rate based on the absolute value of the difference between the actual service duration and the expected service duration and the expected service duration. The service verification unit also includes a consistency analysis module, an impact coefficient calculation module, and a record update module; The consistency analysis module starts from the set Key retrieval behavior data Extract the timestamp of the car owner retrieving the keys from the set. Interaction completion signal Extract the timestamp of the key stored by the car owner. Service execution records Extract the start and end times of service execution, check the logical order of the four time points. The key deposit time must be earlier than the service start time, and the service end time must be earlier than the key retrieval time. If the order is correct and the adjacent time intervals are all within the preset threshold, the spatiotemporal consistency score is set to 1. If the order is correct but there are intervals that exceed the threshold, the score is set to 0.5. If the order is incorrect, the score is set to 0. The impact coefficient calculation module is based on satisfaction evaluation data. and performance data Calculate the correlation impact coefficient; The record update module aggregates the deviation rate, spatiotemporal consistency score, and correlation influence coefficient, and then updates the data based on the aggregation results and the set. Identify service completion confirmation credentials, key transfer closure markers, technician performance update records, and value-added service trigger instructions; The information output unit includes an information feedback module and an information display module; The information feedback module will integrate , The service completion confirmation certificate, key circulation closed loop mark, technician performance update record and value-added service trigger instruction are respectively fed back to the mobile APP, smart cloud cabinet and chain physical stores and back-end management platform. The information display module on the mobile APP shows the confirmation time window, deposit policy and service completion certificate. The smart cloud cabinet executes the cabinet opening instruction, reports abnormal alarms and records the key circulation loop. The chain physical stores and the back-end management platform update the task queue, technician performance and value-added service instructions.

[0021] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0022] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart, multi-terminal collaborative, end-to-end automotive aftermarket service management system, characterized in that: include: The data receiving unit collects different data from mobile internet apps, smart cloud cabinets, chain physical store ports and external institutions, and stores them in an ordered set. The service update unit calls the multi-terminal fusion engine to analyze the ordered set, and after obtaining the results, aligns the data in the ordered set to generate a confirmation appointment time window, a store task queue update instruction, a recommended recent cloud cabinet ID, a one-time cabinet opening token, a value-added service reminder mark, a deposit strategy code, and APP dynamic menu configuration parameters. The identity recognition unit collects interaction data after the vehicle owner arrives at the cloud cabinet, and obtains the identity verification result, face similarity score and operation compliance mark. Based on this, it generates the cabinet opening authorization instruction, identity confidence level, abnormal door opening alarm mark and interaction completion signal. The service confirmation unit collects execution records, key retrieval behavior, satisfaction evaluation and performance results after the service is completed. It calls the closed-loop analysis engine to obtain deviation rate, spatiotemporal consistency score and correlation influence coefficient. Based on this, it generates service completion confirmation certificate, key flow closed-loop mark, technician performance update record and value-added service trigger instruction. The information output unit pushes all data to the mobile APP, smart cloud cabinet and chain physical stores respectively, and completes the update of instructions and synchronization of status on each terminal.

2. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 1, characterized in that, The service update unit includes a work order number calculation module, a matching degree calculation module, and a credit coefficient calculation module; The work order calculation module calculates the number of work orders from an ordered set. Extract appointment request data Expected service time within Service capability data Number of vacant workstations in stores and technician scheduling status ,in , Indicates the first The on-duty status of each technician Indicates the total number of technicians, according to and Calculate the time Maximum number of service orders that can be processed in an inner store ,in , Indicates time The number of available workstations in the store. Indicates the first Master technicians in time On-duty status Indicates the serial number; The matching degree calculation module utilizes Calculate the matching degree between the current user and the store. ,in , , Represents the natural constant. Represents the time sensitivity coefficient. Indicates the appointment time. This represents the difference between the expected time and the nearest available time. This represents the theoretical maximum parallel service capacity of a store. If it is a high match, the appointment can be confirmed directly. If the match is medium, the user is advised to adjust the time. If the match is not found, it is considered a low match, and it is recommended to change stores. The credit rating calculation module from Extract policy binding data Number of claims Credit assessment data Car owner credit score and lease history default records ,use and Calculate the overall credit score ,in , This represents the maximum credit score. This represents the minimum credit score. Represents the attenuation coefficient, according to Identify the corresponding deposit reduction eligibility tags.

3. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 2, characterized in that, The service update unit also includes a preference weight calculation module, an analysis result generation module, and an analysis result alignment module; The preference weight calculation module calculates from ordered sets Extract appointment request data Historical service type selection records Interaction preference data Click hotspot matrix within Average page dwell time vector The frequency of canceled appointments in the past 30 days Then, the preference weights of car owners for four service types—maintenance, car rental, minor repairs, and detailing—are calculated, and the service type with the highest preference weight is selected as the default recommended service type. The analysis result generation module combines the current user's matching degree with the store, the deposit reduction qualification tag, and the preference weights of the four service types to obtain a set of analysis results; The analysis result alignment module aligns the ordered set according to the analysis result set. Alignment is performed to obtain a new set. ,in , Indicates the appointment time window. This indicates a command to update the store's task queue. This indicates a recent recommendation for a cloud storage ID. This indicates a one-time unlocking token. This indicates a reminder about value-added services. This indicates the deposit strategy code. This indicates the configuration parameters for the app's dynamic menu.

4. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 1, characterized in that, The identity recognition unit includes an interactive data acquisition module, a token comparison module, and a similarity calculation module; After the vehicle owner arrives at the cloud cabinet, the interactive data collection module collects the interactive data at the cloud cabinet, forming an interactive set. ,in , This indicates a token for opening the cabinet. This represents the facial feature vector of the car owner. This represents the cabinet door status data collected by the cloud cabinet's mechanical sensors. This indicates the location data of the key box collected jointly by the cloud cabinet's gravity sensor and RFID reader; The token comparison module for To conduct analysis, In The tokens are compared one by one with the list of valid tokens cached locally in the cloud cabinet. If the token exists in the list and has not expired, the authentication result is successful. If the token does not exist or has expired, the result is unsuccessful. The similarity calculation module will In The similarity between the registered facial feature templates bound to the reservation is calculated to obtain the similarity score between the two feature vectors, which is used as the facial similarity score.

5. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 4, characterized in that, The identity recognition unit also includes an opening instruction analysis module, a result output module, and a signal generation module; The cabinet opening instruction analysis module will In The opening timestamp is compared with the time of the opening instruction. If the opening time is later than the instruction issuance time and the interval between the two is within the preset threshold, the operation is compliant. If the opening time is earlier than the instruction issuance time, it is marked as opening the door before the instruction. If no closing signal is detected after the preset time has elapsed, it is marked as not closing after timeout. The result output module summarizes the identity verification result, face similarity score, and operation compliance mark to obtain the judgment result; The signal generation module will apply the determination result to the interaction set. Alignment is performed to obtain a new set. .in , This indicates an authorization to open the cabinet. Indicates the level of confidence in the identity. This indicates an abnormal door opening alarm sign. This indicates that the interaction is complete.

6. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 1, characterized in that, The service confirmation unit includes a service data acquisition module and a deviation rate calculation module; After the service data collection module completes its service execution, the store and external organizations collect closed-loop data to form a set. ,in , This indicates the service execution record. This represents the data related to the key retrieval behavior. This represents the satisfaction rating data. This represents the data indicating the performance results. The deviation rate calculation module utilizes a closed-loop analysis engine to... To conduct analysis, from of Extract the actual start and end times of the service from the ordered set to calculate the actual service duration. Reservation request data Extract the expected service duration at the time of booking, and analyze the deviation rate based on the absolute value of the difference between the actual service duration and the expected service duration and the expected service duration.

7. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 6, characterized in that, The service confirmation unit also includes a consistency analysis module, an impact coefficient calculation module, and a record update module; The consistency analysis module from the set Key retrieval behavior data Extract the timestamp of the car owner retrieving the keys from the set. Interaction completion signal Extract the timestamp of the key stored by the car owner. Service execution records Extract the start and end times of service execution, check the logical order of the four time points. The key deposit time must be earlier than the service start time, and the service end time must be earlier than the key retrieval time. If the order is correct and the adjacent time intervals are all within the preset threshold, the spatiotemporal consistency score is set to 1. If the order is correct but there are intervals that exceed the threshold, the score is set to 0.

5. If the order is incorrect, the score is set to 0. The influence coefficient calculation module is based on satisfaction evaluation data. and performance data Calculate the correlation impact coefficient; The record update module aggregates the deviation rate, spatiotemporal consistency score, and correlation influence coefficient, and then bases the aggregation results on the set. The system identifies service completion confirmation credentials, key transfer loop markers, technician performance update records, and value-added service trigger instructions.

8. The intelligent multi-terminal collaborative automotive aftermarket full-chain service management system according to claim 1, characterized in that, The information output unit includes an information feedback module and an information display module; The information feedback module will integrate , The service completion confirmation certificate, key circulation closed loop mark, technician performance update record and value-added service trigger instruction are respectively fed back to the mobile APP, smart cloud cabinet and chain physical stores and back-end management platform. The information display module on the mobile APP displays the confirmation time window, deposit policy and service completion certificate. The smart cloud cabinet executes the cabinet opening instruction, reports abnormal alarms and records the key transfer loop. The chain physical stores and the back-end management platform update the task queue, technician performance and value-added service instructions.

Images