Recommendation method for vehicle repair shop based on big data and related device thereof

Abstract

This application discloses a vehicle repair shop recommendation method and related apparatus based on big data, relating to the field of vehicle data processing technology. In the vehicle repair recommendation system, the server obtains relevant information from a list of repair shops within a preset range, and simultaneously obtains fault information of the target vehicle through the user's terminal device. Then, it filters out repair shops capable of handling the fault from the list, forming a candidate list. Next, it extracts multi-dimensional data such as fault repair efficiency and customer return rate for each repair shop in the candidate list through a big data platform, calculates a recommendation score for each repair shop based on a preset weight formula, and then filters out the results that meet the score threshold, sorts them in descending order of score, generates a recommendation sequence, and sends it to the user's terminal device. This method evaluates repair shops through multi-dimensional big data analysis, improving the adaptability of vehicle repair shop recommendations, avoiding situations such as opaque pricing when users repair their vehicles, and enhancing the user experience.

Description

Technical Field

[0001] This application relates to the field of vehicle data processing technology, and in particular to a method for recommending vehicle repair shops based on big data and related apparatus. Background Technology

[0002] Currently, there are various types of repair shops on the market, such as 4S stores directly operated by OEMs, general repair shops, brand repair shops, or small roadside repair shops. These repair shops vary in their professional skills, facilities, prices, and services. When a user's vehicle breaks down and needs repair, they need someone who can provide repair advice to help them choose a repair shop. At present, users mainly consider the ratings on lifestyle service apps when choosing a repair shop. However, these apps' rating methods are partly based on user reviews, which are highly subjective, have relatively single rating dimensions, and lack a standardized and objective rating system. This can easily lead to opaque repair prices and poor repair results, resulting in a poor user experience.

[0003] Therefore, when a user's vehicle malfunctions and needs repair, how to effectively recommend repair shops and improve the user's experience throughout the repair process is an urgent issue that needs to be addressed. Summary of the Invention

[0004] This application provides a method and related device for recommending vehicle repair shops based on big data. It adopts a multi-dimensional evaluation system, which comprehensively calculates and ranks the scores based on factors such as repair technician suggestions, first-time repair rate, repair efficiency, number of repairs, customer return rate, and number of times advanced functions are used, and then recommends them to users. Users can then go to the recommended repair shops for repairs, thereby improving the user experience.

[0005] In a first aspect, embodiments of this application provide a method for recommending vehicle repair shops based on big data, applied to a server in a vehicle repair recommendation system. The vehicle repair recommendation system further includes a user terminal device and a big data platform. The server is communicatively connected to both the big data platform and the user terminal device. The method includes: Obtain a list of the first repair shops within a preset range, and obtain vehicle fault information of the target vehicle through the user terminal device; A second list of repair shops is obtained by filtering out repair shops that can handle the vehicle malfunction information from the first list of repair shops. The big data platform is used to obtain the fault repair efficiency, customer return rate, repair frequency, and number of deep diagnostic equipment operations for each repair shop in the second repair shop list, resulting in multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of deep diagnostic equipment operations. Based on a preset first weighting calculation formula, the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times are calculated to obtain multiple repair shop recommendation scores; From the multiple repair shop recommendation scores, repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold are selected to obtain multiple target repair shop recommendation scores; The multiple target repair shop recommendation scores are sorted in descending order to obtain a target repair shop recommendation score sequence, and the target repair shop recommendation score sequence is sent to the user terminal device so that the vehicle repair shop recommendation results can be displayed through the user terminal device.

[0006] Secondly, embodiments of this application provide a vehicle repair shop recommendation device based on big data, applied to a server in a vehicle repair recommendation system. The vehicle repair recommendation system further includes a user terminal device and a big data platform. The server is communicatively connected to both the big data platform and the user terminal device. The device includes: The acquisition unit is used to acquire a first list of repair shops within a preset range, and to acquire vehicle fault information of the target vehicle through the user terminal device; A determining unit is used to filter out repair shops that can handle the vehicle fault information from the first repair shop list to obtain a second repair shop list; The acquisition unit is also used to acquire the fault repair efficiency, customer return rate, repair frequency and number of deep operation times of diagnostic equipment for each repair shop in the second repair shop list through the big data platform, so as to obtain multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies and multiple number of deep operation times of diagnostic equipment; The calculation unit is used to calculate the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times based on a preset first weight calculation formula, and to obtain multiple repair shop recommendation scores. The control unit is configured to filter out repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold from the plurality of repair shop recommendation scores to obtain a plurality of target repair shop recommendation scores; sort the plurality of target repair shop recommendation scores in descending order to obtain a target repair shop recommendation score sequence; and send the target repair shop recommendation score sequence to the user terminal device so as to display the vehicle repair shop recommendation results through the user terminal device.

[0007] Thirdly, embodiments of this application provide a computing server, including: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing the steps in the first aspect of embodiments of this application.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform some or all of the steps described in the first aspect of embodiments of this application.

[0009] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of embodiments of this application. The computer program product may be a software installation package.

[0010] It can be seen that by implementing the embodiments of this application, the following beneficial effects are achieved: This application provides a method and related apparatus for recommending vehicle repair shops based on big data, applied to a server in a vehicle repair recommendation system. The system also includes a user terminal device and a big data platform, wherein the server communicates with both the big data platform and the user terminal device. The method includes: obtaining a first list of repair shops within a preset range; obtaining vehicle fault information of a target vehicle through the user terminal device; filtering repair shops capable of handling vehicle fault information from the first list to obtain a second list of repair shops; and obtaining fault repair efficiency, customer return rate, repair frequency, and number of deep diagnostic equipment operations for each repair shop in the second list through the big data platform. The system obtains multiple fault repair efficiencies, customer return rates, repair frequencies, and diagnostic equipment deep operation counts. Based on a preset first weighting calculation formula, it calculates multiple repair shop recommendation scores. Repair shop recommendation scores greater than or equal to a preset recommendation score threshold are selected to obtain multiple target repair shop recommendation scores. These target repair shop recommendation scores are then sorted in descending order to obtain a target repair shop recommendation score sequence, which is sent to the user's terminal device to display the vehicle repair shop recommendations. In this way, by evaluating repair shops through big data and multiple dimensions, the adaptability of vehicle repair shop recommendations is improved. When users choose repair shops based on the recommendations, they avoid situations such as opaque pricing when repairing their vehicles, thus improving the user experience. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0012] Figure 1 This is a flowchart illustrating a method for recommending vehicle repair shops based on big data, as provided in an embodiment of this application. Figure 2 This is an architecture diagram of a vehicle repair recommendation system provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating a recommended display of a user terminal device provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the details of a repair shop as provided in an embodiment of this application; Figure 5 This is a flowchart illustrating another method for recommending vehicle repair shops based on big data, provided in an embodiment of this application. Figure 6This is a functional module block diagram of a big data-based vehicle repair shop recommendation device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a computing server provided in an embodiment of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0014] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0015] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0016] The following describes the relevant content, concepts, meanings, technical issues, technical solutions, and beneficial effects involved in the embodiments of this application.

[0017] Please see Figure 1 , Figure 1 This is a flowchart illustrating a vehicle repair shop recommendation method based on big data, provided in an embodiment of this application. The method is applied to a server in a vehicle repair recommendation system, which also includes a user terminal device and a big data platform. The server is communicatively connected to both the big data platform and the user terminal device. The method includes, but is not limited to, the following steps: S101. Obtain a list of first repair shops within a preset range, and obtain vehicle fault information of the target vehicle through the user terminal device.

[0018] In this embodiment, the first repair shop list refers to a set of repair shops with vehicle repair qualifications selected within a preset geographical range based on the target user's current location information. For example, repair shops within the range can be obtained based on nearby kilometers, city, vehicle year, or brand. Vehicle fault information reflects the actual fault status of the target vehicle.

[0019] In a specific embodiment, the server first obtains the target user's location information through the user terminal device, and based on the location information and a preset service radius parameter, retrieves repair shop records within the preset range from the repair shop database to generate a first repair shop list. The preset range can be a radius of 10 km or 5 km, and is not limited here. The repair shop database pre-stores basic information, service type information, and historical repair data index information of the repair shops. Simultaneously, the user terminal device obtains the target vehicle's fault information through an in-vehicle terminal or manual input, and uploads the vehicle fault information to the server. The vehicle fault information includes at least vehicle identification information to uniquely identify the vehicle and fault code information to characterize the vehicle fault type.

[0020] It is evident that by obtaining the first list of repair shops and the vehicle fault information of the target vehicle, the repair shop recommendation process has clear constraints in terms of spatial scope and repair needs. This provides a reliable data foundation for subsequent repair shop screening, capability assessment, and recommendation score calculation based on big data, effectively avoiding the uncertainty brought about by relying solely on subjective scores or single-dimensional information for repair shop recommendations.

[0021] For a clearer explanation, please refer to [link / reference]. Figure 2 , Figure 2 This is an architecture diagram of a vehicle repair recommendation system provided in an embodiment of this application. The vehicle repair recommendation system 200 includes: a user terminal device 110, a server 120, and a big data platform 130.

[0022] The user terminal device 110 serves as the front-end interface between the vehicle repair recommendation system 200 and the user, handling both request initiation and result reception. On one hand, it features a visual interactive interface, allowing users to input fault information about the target vehicle, preferred repair locations, and other relevant details, forming a structured user request query. On the other hand, it receives repair shop recommendation results from the server 120 and displays them intuitively in the form of a rating list and priority sorting, providing information support for user repair selection. This device must possess stable communication capabilities to ensure real-time and reliable transmission of requests and results. The server 120 establishes a bidirectional communication connection with the user terminal device 110, receiving user request queries from the user terminal device 110. Simultaneously, it interacts with the big data platform 130, acquiring multi-dimensional evaluation data of repair shops as needed (including fault repair efficiency, customer return rate, diagnostic equipment operation records, etc.). Based on preset filtering rules, it first filters out repair shops with corresponding fault handling capabilities, then combines the evaluation data with a weighted algorithm to calculate and rank recommendation scores, ultimately generating repair shop recommendation results and feeding them back to the user terminal device 110. The big data platform 130 stores comprehensive service data from repair shops within a certain area (e.g., a district in a city), including historical repair records, fault repair efficiency statistics, customer return rate data, and the number of times diagnostic equipment has been deeply operated. This data comes from actual service scenarios in the automotive aftermarket. After standardized cleaning and structured storage, it can output the corresponding evaluation data of the repair shops according to the request instructions of server 120, providing objective and comprehensive information basis for server 120's screening and scoring.

[0023] In one possible embodiment, a user submits fault information about the target vehicle's "engine malfunction light illuminated" and a geographical preference for "within 3 kilometers of urban area" through a user terminal device 110. This user request is transmitted to the server 120 via a communication link. The server 120 initiates a data request to the big data platform 130 to obtain basic information about repair shops within the geographical range and evaluation data related to engine fault handling. Then, the server 120 filters out repair shops with engine fault handling capabilities and performs weighted scoring based on data such as fault repair efficiency and customer return rate provided by the big data platform 130. The recommended sequence is generated by sorting the scores in descending order. Finally, the server 120 uses this recommended sequence as the repair shop recommendation result and feeds it back to the user terminal device 110, completing a complete recommendation process.

[0024] visible, Figure 2 The vehicle repair recommendation system 200 shown in the diagram ensures the efficiency, objectivity, and accuracy of the vehicle repair recommendation process through the collaborative interaction of user terminal device 110, server 120, and big data platform 130.

[0025] S102. Select repair shops that can handle the vehicle fault information from the first repair shop list to obtain a second repair shop list.

[0026] In this embodiment of the application, the second repair shop list refers to the set of repair shops obtained by further matching and filtering the actual repair capabilities of the repair shops based on the first repair shop list and combining the vehicle fault information of the target vehicle.

[0027] In a specific embodiment, the server first parses the vehicle identifier and fault code information from the vehicle fault information to determine the vehicle brand, model category, and fault type or fault system corresponding to the fault code for the target vehicle. Then, the server reads the pre-stored repair capability description information of each repair shop from the first repair shop list. This description includes the range of vehicle brands supported by the repair shop, the types of fault systems it can handle, and the corresponding historical repair record index. Based on the vehicle brand information, the server performs a preliminary screening of the repair shops in the first repair shop list to obtain a set of candidate repair shops capable of supporting repairs of the target vehicle brand. Further, combining the fault type corresponding to the fault code, the server performs matching analysis on the historical repair data of the candidate repair shops to filter out repair shops with experience in repairing the aforementioned fault type in their historical repair records, thereby generating a second repair shop list.

[0028] It is evident that by performing capability matching and screening on the first list of repair shops based on vehicle fault information, the scope of repair shops participating in the recommendation calculation is effectively narrowed down. This ensures that subsequent repair shop evaluations based on multi-dimensional indicators are grounded in real and feasible repair capabilities, thereby improving the accuracy and reliability of repair shop recommendation results and avoiding problems such as low repair efficiency or poor user experience caused by mismatched repair capabilities.

[0029] Optionally, the vehicle fault information includes fault type and vehicle identification. The above step of filtering repair shops that can handle the vehicle fault information from the first repair shop list to obtain a second repair shop list specifically includes the following steps: A201. Determine the vehicle brand in the vehicle identification; A202. Select repair shop information that meets the requirements for repairing the vehicle brand from the multiple first repair shop lists to obtain multiple candidate repair shops; A203. Obtain historical repair data from the multiple candidate repair shops for the fault type; A204. Statistically analyze the repair frequency and number of successful repairs for the fault types mentioned in the historical maintenance data; A205. Based on the multiple repair frequencies and the multiple repair success counts, determine whether the multiple candidate repair shops meet the preset first repair condition; A206. If so, then determine the multiple repair shops that meet the first repair conditions among the multiple candidate repair shops as the second repair shop list; A207. If not, then remove the target candidate repair shop and execute the step of determining whether the multiple candidate repair shops meet the preset first repair conditions based on the multiple repair frequencies and the multiple repair success counts; the target candidate repair shop is any one of the multiple candidate repair shops.

[0030] In this embodiment of the application, the vehicle fault information includes at least the fault type and the vehicle identifier. The vehicle identifier is used to characterize the brand, model and system configuration characteristics of the target vehicle, while the fault type is used to reflect the specific fault category or fault system currently existing in the target vehicle.

[0031] In the implementation process, the server first parses the vehicle identifier to determine the vehicle brand of the target vehicle. Since different vehicle brands differ in overall vehicle architecture, control unit configuration, and diagnostic protocols, whether a repair shop possesses the corresponding brand's repair qualifications and technical capabilities directly affects the feasibility of the repair and the reliability of the repair results. Based on the vehicle brand information, the server filters from the initial repair shop list those that declare support for or have actually participated in the repair of vehicles of that brand in their historical repair records, forming multiple candidate repair shop sets, thus completing the initial screening of the repair shop's brand compatibility. On this basis, to further evaluate the actual handling capabilities of the candidate repair shops for specific fault types, the server obtains historical repair data for each candidate repair shop from the big data platform, generated during their historical operations for the aforementioned fault types. This historical repair data comes from the repair shops' long-term accumulated diagnostic reports and repair records, which can truly reflect the repair shops' repair experience and handling effects on specific fault types. By analyzing the historical repair data, the server calculates the repair frequency and number of successful repairs for each candidate repair shop under the corresponding fault type. Repair frequency reflects the repair shop's coverage of this type of fault, while the number of successful repairs reflects the actual repair effectiveness during the handling of this type of fault. After obtaining the repair frequency and the number of successful repairs, the server determines whether the candidate repair shops meet the preset first repair condition based on the statistical relationship between the two. The first repair condition describes the minimum technical capability required of the repair shop for a specific fault type. It is set based on experience or the repair qualifications of each repair shop, and is not limited here. When a candidate repair shop meets the first repair condition, the server determines that it is a repair shop capable of handling the target vehicle's fault and includes it in the second repair shop list; when a candidate repair shop does not meet the first repair condition, it is removed from the candidate set, and the same judgment process is continued for the remaining candidate repair shops until the capability screening of all candidate repair shops is completed.

[0032] It is evident that by introducing a tiered screening mechanism based on vehicle brand and fault type, and combining historical repair frequency and number of successful repairs to assess the repair shop's capabilities, the repair shops entering the recommendation process are highly matched with the target vehicle's repair needs in terms of technical capabilities. This effectively avoids repair failures or repeated repairs due to insufficient repair capabilities, improves the accuracy and credibility of repair shop recommendations, and ultimately enhances the user's overall repair experience.

[0033] Optionally, the above step of determining multiple repair shops that meet the first repair conditions from among the multiple candidate repair shops as the second repair shop list specifically includes the following steps: B201. Determine the ratio between the number of successful repairs and the repair frequency to obtain multiple ratios; each of the multiple ratios corresponds one-to-one with each of the first repair shops in the multiple first repair shop lists; B202. Determine whether the repair frequency is greater than or equal to the preset minimum sample threshold; B203. If so, then determine the repair shop that is greater than or equal to the preset fault repair success rate threshold among the multiple ratios as the repair shop that meets the first repair condition, obtain multiple repair shops, and determine the multiple repair shops as the second repair shop list. B204. If not, then eliminate the repair shops whose ratios are lower than the fault repair success rate.

[0034] In this embodiment of the application, to further improve the reliability and statistical rationality of the repair shop capability screening results, a ratio calculation and threshold judgment mechanism based on historical repair data is introduced when determining the repair shops that meet the first repair condition among multiple candidate repair shops. The preset minimum sample threshold is set based on experience, generally greater than or equal to 10. The fault repair success rate threshold is set to 80%.

[0035] In a specific embodiment, the server first calculates the ratio between the number of successful repairs and the repair frequency for each candidate repair shop based on its historical repair data for the target fault type. This ratio characterizes the success rate of the repair shop in handling this type of fault, and can intuitively reflect the stability of the repair shop in effectively repairing faults through multiple repair practices. After calculating the ratio, the server further judges the repair frequency to confirm whether the historical data used for capability assessment has statistical significance. The minimum sample threshold is used to limit the minimum repair frequency requirement for participating in capability assessment. Its purpose is to exclude repair shops with too few repair samples and avoid large deviations in capability assessment results due to individual repair records. When the repair frequency of a candidate repair shop for the target fault type is greater than or equal to the minimum sample threshold, it indicates that the repair shop's repair behavior for this type of fault has a certain degree of continuity and representativeness, and its corresponding repair success ratio can be used as a valid basis for subsequent capability assessment. Under the premise of meeting the repair frequency condition, the server compares the repair success ratio with a preset fault repair success rate threshold. When the repair success rate of a candidate repair shop is greater than or equal to the fault repair success rate threshold, it indicates that the repair shop has a high probability of successfully repairing the target fault type, meeting the first repair condition. Therefore, it is identified as a repair shop capable of handling the target vehicle fault and included in the second repair shop list. This method allows for the selection of repair shops that demonstrate stable and reliable performance in actual repairs. If the repair frequency of a candidate repair shop does not reach the minimum sample threshold, or its repair success rate is lower than the fault repair success rate threshold, the server determines that it does not temporarily meet the first repair condition and removes it from the candidate repair shop set.

[0036] It is evident that by using a combined judgment method based on the repair success ratio and sample threshold, the screening of repair shop capabilities no longer relies on single repair results or subjective evaluations, but is based on the analysis of statistically significant historical repair data, thereby enhancing the objectivity and credibility of repair shop capability assessment at the data level.

[0037] S103. Obtain the fault repair efficiency, customer return rate, repair frequency, and number of deep operation times of diagnostic equipment for each repair shop in the second repair shop list through the big data platform, and obtain multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple number of deep operation times of diagnostic equipment.

[0038] In this embodiment, fault repair efficiency, customer return rate, repair frequency, and number of in-depth diagnostic equipment operations are multi-dimensional evaluation indicators used to characterize the comprehensive repair capabilities and service levels of a repair shop. These indicators are all derived from objective historical data generated by the repair shop during its long-term actual operation.

[0039] In a specific embodiment, the server retrieves historical repair data and diagnostic operation data for each repair shop in the second repair shop list through the big data platform. Historical repair data includes repair records, repair completion times, repair result status, and user subsequent repair behavior records for each repair shop for different vehicles and fault codes. Based on the historical repair data, the server counts the number of times the same fault code is successfully repaired at the same repair shop within a preset time window, along with the corresponding total number of repairs, and calculates the repair shop's fault repair efficiency based on the relationship between the two. Simultaneously, the server calculates the repair shop's customer return rate based on the number of times the same vehicle returns to the same repair shop after repair, combined with the corresponding total number of repairs. Specifically, the definitions of each indicator are as follows: Customer return rate = (Number of vehicles repaired again within 2 years after 90 days / Total number of repaired vehicles (after all vehicles diagnosed by the repair shop)) * 100%; Fault repair efficiency: Sum of repair time intervals within 7 days for the same vehicle repaired at the repair shop / Total number of repaired vehicles; Number of deep diagnostic equipment operations = Number of hidden code refreshes + Number of programming codes + Number of ADAS calibration reports.

[0040] Furthermore, within a preset statistical period, the server summarizes and analyzes the repair records of each repair shop in the second repair shop list to count the number of repairs performed by each repair shop within the statistical period, thereby obtaining the corresponding repair frequency to reflect the business activity level and service capacity of the repair shops. In addition, the server extracts the deep operation records performed by each repair shop through the diagnostic equipment within the statistical period from the diagnostic equipment log data, counting the number of times operations such as control unit programming, parameter coding, system calibration, or vehicle function parameter configuration are executed, thereby obtaining the number of deep operations performed by the diagnostic equipment, which characterizes the technical capability level of the repair shops in complex fault handling and deep diagnosis.

[0041] It is evident that by using a big data platform to uniformly acquire and quantify the multidimensional historical data of each repair shop in the second repair shop list, the subsequent repair shop recommendation process no longer relies on a single subjective evaluation or simple statistical indicators, but is based on objective and traceable repair behavior data, thereby effectively improving the accuracy and credibility of the comprehensive capability assessment of repair shops.

[0042] Optionally, the above steps include: obtaining the fault repair efficiency, customer return rate, repair frequency, and number of in-depth diagnostic equipment operations for each repair shop in the second repair shop list, to obtain multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of in-depth diagnostic equipment operations. Specifically, this includes the following steps: C301. Obtain the historical repair report corresponding to each of the second repair shops in the second repair shop list through the big data platform; C302. Based on the historical maintenance reports, determine the maintenance records for the fault codes to obtain multiple maintenance records; C303. Within a preset first time window, count the number of times the fault code appears and the number of repairs from the multiple repair records to obtain multiple fault counts and multiple repair counts; C304. Determine the repair efficiency of the multiple faults based on the multiple fault counts and the multiple repair counts; C305. Within a preset second time window, count the number of times the target vehicle was repaired again at all second repair shops in the second repair shop list from the multiple repair records to obtain multiple repair counts; C306. Determine the customer retention rate based on the multiple repair counts; C307. Determine the multiple maintenance frequencies based on the multiple maintenance records within a preset period; C308. The number of deep operations performed by each repair shop through diagnostic equipment within the cycle is counted from the multiple repair records to obtain the number of deep operations of the multiple diagnostic equipment; the number of deep operations includes at least one of the following: programming and coding times, ADAS calibration times, and vehicle function parameter configuration times.

[0043] In this embodiment of the application, in order to conduct a more comprehensive and objective capability assessment of each repair shop in the second repair shop list, a big data platform is used to perform multi-dimensional statistical analysis on the historical repair behavior of the repair shops, thereby obtaining key evaluation indicators such as fault repair efficiency, customer return rate, repair frequency, and number of deep operations on diagnostic equipment.

[0044] In the implementation process, the server first obtains historical repair reports for each repair shop in the second list of repair shops through a big data platform. These historical repair reports are generated and uploaded by the repair shops during actual repairs and include vehicle identification information, fault code information, diagnostic process records, repair operation details, and repair completion status. After parsing the historical repair reports, the server filters out the repair records corresponding to the target vehicle's fault codes, thus forming a set of multiple repair records to reflect the actual repair situation of each repair shop for this type of fault. Based on this, the server performs statistical analysis on the multiple repair records within a preset first time window (set to 90 days), respectively counting the number of times the fault code appears in the repair records and the corresponding number of repairs. The number of fault code occurrences reflects the recurrence of the target fault after repair, while the number of repairs reflects the total number of repair actions performed for that fault. Furthermore, to assess the service quality and customer loyalty of repair shops, the server statistically analyzes the repeat repair activities of the target vehicle at each repair shop in the second repair shop list within a preset second time window (set to 6 months), obtaining the corresponding number of repairs. Based on the relationship between the number of repeat repairs and related repair activities, the customer return rate of each repair shop can be calculated, reflecting the degree of customer satisfaction with the repair shop's service quality after a repair is completed. In addition, the server also summarizes and analyzes multiple repair records within a preset statistical period (set to 120 days) to statistically analyze the repair frequency of each repair shop within the period. Repair frequency is used to characterize the business activity and service capacity of a repair shop within a certain time range, serving as an important reference indicator for assessing the overall operational capabilities of the repair shop. Simultaneously, the server further extracts the operation log information of diagnostic equipment from the repair records, statistically analyzing the number of deep operations performed by each repair shop through diagnostic equipment within the period, including but not limited to programming and coding, ADAS calibration, and vehicle function parameter configuration. Deep operations typically correspond to repair behaviors with higher technical complexity, and their statistical results can be used to reflect the technical capabilities of repair shops in handling complex faults and in-depth diagnostics.

[0045] It is evident that by conducting statistical analysis on historical repair reports from repair shops across multiple time scales and technical dimensions, a comprehensive set of multi-dimensional evaluation indicators reflecting repair effectiveness, service quality, business activity, and technical capabilities can be obtained. This provides real and reliable data support for the subsequent calculation of repair shop recommendation scores, significantly improving the accuracy and credibility of repair shop recommendation results.

[0046] Optionally, the above steps, including determining the customer return rate based on the multiple repair counts, specifically include the following steps: D301. Within the second time window, determine the records of multiple vehicle models that have been repaired based on the multiple repair records, and obtain the repair record set of the vehicle models; D302. Count the number of times the target vehicle model appears in the maintenance record set at least twice, and obtain the number of times the vehicle was revisited; the target vehicle model is any one of the multiple vehicle models. D303. Determine the number of repair records in the repair record set to obtain the total number of repairs for the target vehicle model; D304. Determine the ratio of the number of vehicles visited to the total number of repairs to obtain the target customer return rate.

[0047] In this embodiment, multiple repair records refer to all vehicle repair business records generated by the repair shop within the second time window, covering core business information such as vehicle model, repair time, and repair items. This serves as the foundational data source for customer return rate statistics. The vehicle model repair record set is a dataset formed by classifying and integrating multiple repair records according to the vehicle model field. Each subset corresponds to all repair records for a specific vehicle model. The number of vehicle visits refers to the frequency of at least two repair records for the target vehicle model within the second time window, i.e., the number of times the same vehicle is repaired again within the statistical period. This is an indicator directly reflecting customer repeat repair behavior. The total number of repairs refers to the total number of repair records for the target vehicle model within the second time window, representing the total demand for repair shop services for this model within the statistical period. The target customer return rate is the ratio of the number of vehicle visits to the total number of repairs, a key quantitative indicator for quantifying customer satisfaction and loyalty to the repair shop's services.

[0048] In a specific embodiment, firstly, based on a preset second time window (e.g., January 1, 2024 to June 31, 2024), all repair records within this time period are extracted from the repair shop's business database. Then, based on the vehicle model field in the records, these records are categorized and organized by model to form repair record sets corresponding to different vehicle models. Taking "a certain brand of B-class sedan" in this set as the target vehicle model, the corresponding repair record set is statistically analyzed. First, repair record entries that appear at least twice within the second time window for this model are selected, and the number of these entries is counted to obtain the number of times the model has been revisited. Simultaneously, the total number of records in the repair record set for this model is counted to obtain the total number of repairs for this model. Then, the ratio of the two is calculated. For example, if the number of revisited vehicles for this model is 5 and the total number of repairs is 15, the corresponding target customer return rate is 33%.

[0049] It is evident that by employing standardized statistical processes and precise indicator definitions, the problems of data confusion and ambiguous judgment in customer return rate statistics are effectively avoided. The results can truly reflect the impact of repair shop service quality on customer "stickiness," providing a reliable quantitative basis for the repair shop recommendation rating system and helping to improve the rationality and accuracy of vehicle repair shop recommendations.

[0050] S104. Based on the preset first weight calculation formula, calculate the multiple fault repair efficiency, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times to obtain multiple repair shop recommendation scores.

[0051] In this embodiment, the repair shop recommendation score is a quantitative result used to comprehensively characterize the overall performance of the repair shop across multiple dimensions, including fault handling capabilities, service quality, business stability, and technical level. The first weighting calculation formula is: Repair Shop Overall Score (calculated according to the year selected by the user) = (First-time repair rate score × 0.35) + (Repair efficiency score × 0.2) + (Number of repairs score × 0.1) + (Customer return rate score × 0.25) + (Number of deep equipment operations score × 0.1).

[0052] In a specific embodiment, the server first preprocesses the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times, including normalization or standardization, to eliminate the impact of differences in numerical units and value ranges of different indicators on the calculation results. Subsequently, the server calculates a weighted average of the processed indicators and their corresponding first weight parameters according to the first weight calculation formula to obtain a repair shop recommendation score for each repair shop.

[0053] Optionally, the above steps, which calculate the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times based on a preset first weighting formula, to obtain multiple repair shop recommendation scores, specifically include the following steps: E401. Based on preset recommendation scoring rules, determine recommended scores for the target fault repair rate, target customer return rate, target maintenance frequency, and target diagnostic equipment operation depth, obtaining the target fault repair rate score, target customer return rate score, target maintenance frequency score, and target diagnostic equipment operation depth score; wherein the target fault repair rate, the target customer return rate, the target maintenance frequency, and the target diagnostic equipment operation depth are each any one of the plurality of fault repair rates, the plurality of customer return rates, the plurality of maintenance frequencies, and the plurality of diagnostic equipment deep operation times; E402. Determine multiple first weight parameters corresponding to the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score; E403. Based on the multiple first weight parameters, the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score, the target repair shop recommendation score is determined.

[0054] In this embodiment, the preset recommendation scoring rule is a quantitative mapping criterion built based on user demands for vehicle repair services and industry quality standards. It transforms evaluation indicators of different dimensions, such as fault repair efficiency and customer return rate, into standardized scores within a unified range. For example, fault repair efficiency is based on "average repair time per fault," with shorter times corresponding to higher scores. Repair frequency is determined by setting a reasonable score peak within a given range, taking into account the repair shop's service capacity, to avoid overloading repairs and impacting service quality. The target fault repair rate score, target customer return rate score, etc., are standardized scores for each evaluation indicator corresponding to a single repair shop after transformation by this rule, serving as the basic unit for comprehensive evaluation of multi-dimensional indicators. The first weight parameter is a percentage coefficient set based on the priority of each indicator's impact on repair service quality. Its allocation must match user concerns in the vehicle repair scenario (e.g., the reliability of fault repair has a higher priority than repair frequency), reflecting the relative importance of each indicator in the comprehensive score. The target repair shop recommendation score is the weighted sum of each standardized score and its corresponding weight parameter for a single repair shop, and is the core quantitative indicator for measuring the repair shop's comprehensive service capabilities.

[0055] In a specific embodiment, the operation is carried out using repair shop B in a certain city as the target object. First, the preset recommended scoring rules are invoked. The quantitative standards for fault repair efficiency in these rules are: "10 points for repair time ≤ 2 hours, 8 points for 2-4 hours, and 5 points for > 4 hours"; the standards for customer return rate are: "10 points for ≥ 80%, 7 points for 60%-80%, and 4 points for < 60%"; the standards for repair frequency are: "8 points for monthly average repair volume of 30-60 times, 5 points for < 30 times, and 6 points for > 60 times"; and the standards for the number of in-depth diagnostic operations on equipment are: "9 points for monthly average of ≥ 20 times, 7 points for 10-20 times, and 4 points for < 10 times". According to the data statistics, repair shop B's fault repair efficiency is 1.8 hours, corresponding to a score of 10 points; the customer return rate is 82%, corresponding to a score of 10 points; the monthly average repair volume is 42 times, corresponding to a score of 8 points; and the monthly average in-depth diagnostic operations on equipment is 23 times, corresponding to a score of 9 points. Then, the primary weighting parameters for each indicator are determined: fault repair efficiency 0.3, customer return rate 0.3, repair frequency 0.2, and number of in-depth diagnostic equipment operations 0.2. Finally, the recommended score for the target repair shop is calculated through weighted average: 10×0.3+10×0.3+8×0.2+9×0.2=9.4 points. This process needs to be performed on all repair shops to be evaluated one by one to obtain the final recommended score for each repair shop.

[0056] It is evident that by standardizing indicators and differentiating weight allocation, a scientific comprehensive rating system for repair shops has been constructed, effectively improving the objectivity and rationality of the recommendation rating, providing a reliable quantitative basis for accurate recommendations of vehicle repair shops, and helping users quickly match high-quality repair resources.

[0057] Optionally, the above steps, including determining multiple first weight parameters corresponding to the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score, specifically include the following steps: F401. Obtain historical repair evaluation data for the second repair list; F402. Based on the historical maintenance evaluation data, determine the weight coefficients corresponding to the target fault repair score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score, and obtain multiple second weight parameters; F403. Normalize the plurality of second weight parameters to obtain the plurality of first weight parameters.

[0058] In this embodiment, historical repair evaluation data is a collection of user feedback, repair effect tracking, and service quality records accumulated by repair shops in the second repair list within a preset service period. This includes post-fault repair satisfaction scores, repeat purchase records, and repair resource load feedback, serving as the objective basis for determining the weighting coefficients. The second weighting parameter is a preliminary influence coefficient obtained based on historical repair evaluation data through correlation analysis between indicators and core user satisfaction. Its value reflects the actual correlation between the corresponding indicator and repair service quality. Normalization is a method of converting second weighting parameters with different numerical ranges into a set of coefficients summing to 1. This is to eliminate dimensional differences between parameters and ensure the rationality of the weighting percentages of each indicator and the mathematical consistency of the weighted calculation. The first weighting parameter is the final weighting coefficient after normalization, serving as the weighting basis for the scores of each indicator in the subsequent comprehensive scoring calculation, directly determining the contribution percentage of each indicator in the recommended score.

[0059] In a specific embodiment, 25 repair shops with transmission fault handling capabilities selected within a certain region (i.e., the second repair list) are used as the target. First, historical repair evaluation data for these repair shops over the past 18 months is obtained, including user satisfaction ratings on a 5-point scale for fault repair effectiveness, repeat purchase records within the past 3 months, user waiting time feedback corresponding to the average monthly repair volume, and fault resolution rate after using advanced diagnostic equipment functions. Pearson correlation analysis is used to calculate the correlation between each indicator and overall user satisfaction: the correlation coefficient for fault repair score is 0.42, the correlation coefficient for customer return rate score is 0.36, the correlation coefficient for repair frequency score is 0.12, and the correlation coefficient for diagnostic equipment operation depth score is 0.10. These values ​​are the multiple second weight parameters. Subsequently, the second weight parameters are normalized to obtain first weight parameters of 0.42, 0.36, 0.12, and 0.10, thus ensuring that the proportion of each parameter meets the requirements of weighted calculation.

[0060] It is evident that determining weights based on historical service data and optimizing parameter formats through normalization improves the objectivity and scientific rigor of weight allocation, providing a reliable basis for accurate calculation of repair shop recommendation scores and effectively enhancing the fit between recommendation results and actual user needs.

[0061] S105. Select repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold from the multiple repair shop recommendation scores to obtain multiple target repair shop recommendation scores.

[0062] In this embodiment, the recommendation scoring threshold is a reference parameter used to distinguish whether a repair shop meets the expected recommendation criteria, thus limiting the range of repair shops that can be included in the final recommendation results. By setting a recommendation scoring threshold, repair shops with low overall capability ratings or insufficient matching with current repair needs can be effectively eliminated, thereby ensuring that the repair shops recommended to users meet the expected level in terms of overall repair capability and service quality.

[0063] In a specific embodiment, after obtaining multiple repair shop recommendation ratings, the server compares each rating with a preset recommendation rating threshold. The recommendation rating threshold can be preset based on historical recommendation results, user satisfaction statistics, or system operating experience, or it can be dynamically adjusted based on the current vehicle fault type, repair complexity, or user preference parameters. When a repair shop's recommendation rating is greater than or equal to the recommendation rating threshold, the server determines that repair shop's rating as the target repair shop recommendation rating; when the recommendation rating is lower than the recommendation rating threshold, the corresponding repair shop is not included in the subsequent recommendation scope.

[0064] It is evident that by applying a threshold to the repair shop recommendation scores, the range of repair shops participating in the final recommendation ranking is effectively narrowed down. This ensures that the subsequent recommendation results are concentrated on repair shops with superior overall capabilities and a high degree of matching with the target vehicle's repair needs, thereby improving the reliability and practicality of the repair shop recommendation results.

[0065] S106. Sort the multiple target repair shop recommendation scores in descending order to obtain a target repair shop recommendation score sequence, and send the target repair shop recommendation score sequence to the user terminal device so as to display the vehicle repair shop recommendation results through the user terminal device.

[0066] In this embodiment, the target repair shop recommendation rating sequence refers to the result set formed by orderly arranging repair shops that meet the recommendation criteria according to the magnitude of their recommendation ratings. This sequence is used to intuitively reflect the relative merits of different repair shops under a comprehensive evaluation dimension. By sorting the target repair shop recommendation ratings and forming a recommendation rating sequence, a clear decision-making reference can be provided to users, avoiding disordered comparisons between multiple repair shops.

[0067] In a specific embodiment, after obtaining multiple target repair shop recommendation ratings, the server sorts the corresponding repair shops according to the recommendation ratings from highest to lowest, generating a target repair shop recommendation rating sequence. Then, the server sends the target repair shop recommendation rating sequence to the user terminal device via a communication connection. Upon receiving the recommendation rating sequence, the user terminal device can present the repair shop information according to preset display rules, such as displaying the name, location, recommendation rating, and related repair capabilities of each repair shop in the form of a list, card, or sorting results. This allows the user to intuitively understand the comprehensive recommendation results of each repair shop; no specific limitations are imposed here.

[0068] It is evident that by sorting the target repair shop recommendation ratings and sending them to the user's terminal device for display, the recommendation results calculated based on big data and multi-dimensional indicators are presented to the user in an intuitive and orderly manner, effectively reducing the user's decision-making cost in choosing a repair shop and improving the usability of the repair shop recommendation results and the user experience.

[0069] For easier understanding, please refer to Figure 3 , Figure 3This is a schematic diagram illustrating the recommended display of a user terminal device according to an embodiment of this application. As can be seen, the interface displays repair shop recommendations in a structured list format, providing intuitive and accurate information support for users to quickly locate suitable repair resources. Specifically, the interface features a repair shop recommendation title at the top, and a search box with a "Please enter" prompt below the title, allowing users to accurately retrieve recommendation results using keywords (such as repair shop name or specific vehicle model), improving the targeting and efficiency of information acquisition. The main body presents candidate repair shop information in a modular format. Each module contains key information across multiple dimensions: First, the "Repair Shop Name" serves as a unique identifier for the repair shop, providing a basis for users to distinguish between different candidates; second, the location dimension is quantified with distance values ​​of 2.5km and 2.7km, intuitively reflecting the spatial relationship between the repair shop and the user or the faulty vehicle, providing direct data reference for users to assess travel costs (time consumption, transportation convenience); third, the "Mainly Repaired Vehicle Models" section contains two types of information: one is a professional ranking description such as "Ranked first in repair of XX vehicle model in XX district" or "Ranked second in repair of XX vehicle model in XX district," reflecting the industry recognition and service advantages of the corresponding repair shop in the specific vehicle model repair field; the other is a coverage description of "Number of Vehicle Models Repaired Proficiently XX," reflecting the range of vehicle models the repair shop can handle, helping users match professional repair resources suitable for their target vehicle model. Taking the two repair shop modules in the interface as an example: the first module's "2.5km" location distance corresponds to high spatial accessibility, "ranked first in repair of XX model in XX district" indicates that its service quality in the repair of this model is at a leading level, and "XX models of repair expertise" reflects its wide coverage of vehicle repair capabilities; the second module's "2.7km" location distance is slightly higher than the former, "ranked second in repair of XX model in XX district" reflects its second-best service capability in the repair of similar vehicle models, and "XX models of repair expertise" reflects its wide coverage of vehicle repair capabilities. The two modules form differentiated recommendation options to meet users' different decision priorities (such as prioritizing repair shops that are closer or prioritizing service providers with higher professional rankings).

[0070] As can be seen, this interface integrates core information such as repair shop name, spatial distance, vehicle compatibility, and professional ranking to construct a well-structured recommendation result display framework. It comprehensively covers the key decision dimensions for users to choose repair services and presents information in a concise and intuitive form, effectively reducing the information filtering cost for users, improving the efficiency and accuracy of repair resource matching, and thus enhancing the user experience.

[0071] For easier understanding, please refer to Figure 4 , Figure 4This is a schematic diagram of the details of a repair shop provided in an embodiment of this application. As can be seen, the diagram displays the core service information of a single repair shop in an integrated form of images and structured text, which helps users to fully understand the actual attributes and service reputation of the target repair shop.

[0072] Specifically, Figure 4 The top of the page uses "XX Repair Shop" as the title, clearly identifying the main information and helping users quickly locate the repair shop they are looking for. Below the title, on the left, is a picture of the repair shop's physical location, showing its signage, facilities, and parked vehicles, providing users with an intuitive understanding and making it easier to find the shop. To the right of the picture, key details are presented in a structured text format: "Repair Shop Name: XXX Auto Service Center" is the official identifier, ensuring users get accurate service information; "Location: No. XX, XX Road, XX District" provides the accurate geographical address, offering spatial guidance for users to plan their route and confirm accessibility; "Main Vehicle Types Repaired: BYD, Volkswagen" clarifies the types of vehicles the shop specializes in, helping users quickly match compatibility with their target vehicle; and "Review: Good service attitude, high repair efficiency" reflects user feedback after their actual experience, directly reflecting the repair shop's service quality and user satisfaction, and is an important basis for users to evaluate its service level. As can be seen, the detailed information display of this repair shop, through the integration of visual elements and structured text, comprehensively covers the core dimensions of the repair shop, such as its logo, location, serviced vehicle models, and user reviews. This makes up for the limitations of the recommended list information, improves the transparency and richness of the repair shop information, helps users make repair choices that better suit their needs, and further improves the information service of the vehicle repair recommendation system.

[0073] For easier understanding, please refer to Figure 5 , Figure 5This is a flowchart illustrating another big data-based vehicle repair shop recommendation method provided in this application embodiment. As can be seen, the process mainly includes four steps: Step S501 is the candidate range screening stage, which involves "obtaining repair shops within the range based on distance to nearby repair shops, brand, and vehicle year." This step defines an initial set of repair shops that meet the user's basic needs based on spatial accessibility (distance to nearby shops) and vehicle model compatibility (brand, vehicle year), limiting effective candidate objects for subsequent accurate evaluation and avoiding redundant intervention of irrelevant repair resources; Step S502 is the comprehensive capability evaluation stage, which involves "calculating the comprehensive score of the repair shop based on the first-time repair rate, repair efficiency, number of repairs, customer return rate, and number of times advanced functions are used." This step integrates the technical capabilities of the repair shop (first-time repair rate, number of times advanced functions are used). Service efficiency (repair efficiency), user reputation (customer return rate), and business scale (number of repairs) are quantitatively calculated to transform multi-dimensional information into a comparable comprehensive score, enabling an objective assessment of repair shop service quality. Step S503 is the sorting and reason matching stage, which involves "sorting the comprehensive scores to form a recommended list of repair shops and matching the recommendation reasons for each repair shop in the list." This step prioritizes candidate repair shops based on their comprehensive scores and associates the recommendation criteria corresponding to the score advantages of each repair shop. Step S504 is the personalized output stage, which involves "personalized service recommendations to users." This step combines the user's potential preferences (such as the priority of repair efficiency) to transform the sorted recommendation list into service suggestions that fit the individual needs of the user, completing the terminal implementation of the recommendation process.

[0074] It is evident that this process not only ensures the comprehensiveness and objectivity of repair shop assessments through multi-dimensional indicators, but also enhances the practicality and relevance of recommendation results through ranking matching and personalized output, effectively improving the scientific nature of vehicle repair shop recommendations and the user experience during the repair process.

[0075] In summary, by implementing the vehicle repair shop recommendation method based on big data provided in this application, relevant information from a list of repair shops within a preset range is obtained, and the fault information of the target vehicle is simultaneously obtained through the user's terminal device. Then, repair shops capable of handling the fault are selected from the list to form a candidate list. Next, multi-dimensional data such as fault repair efficiency and customer return rate of each repair shop in the candidate list are extracted through a big data platform. A recommendation score for each repair shop is calculated based on a preset weight formula. Finally, the results that meet the score threshold are selected, sorted in descending order of score, and a recommendation sequence is generated and sent to the user's terminal device. This method improves the adaptability of vehicle repair shop recommendations by evaluating repair shops from multiple dimensions using big data, avoiding situations such as opaque pricing when users repair their vehicles, and enhancing the user experience.

[0076] Please see Figure 6 , Figure 6 This application provides a functional module block diagram of a vehicle repair shop recommendation device based on big data, applied to a server in a vehicle repair system. The vehicle repair system also includes a user terminal device and a big data platform. The server is communicatively connected to both the big data platform and the user terminal device. Specifically, the big data-based vehicle repair shop recommendation device 600 includes: The acquisition unit 601 is used to acquire a first list of repair shops within a preset range, and to acquire vehicle fault information of the target vehicle through the user terminal device. The determining unit 602 is used to filter out repair shops that can handle the vehicle fault information from the first repair shop list to obtain a second repair shop list; The acquisition unit 601 is also used to acquire the fault repair efficiency, customer return rate, repair frequency and number of deep operation times of diagnostic equipment for each repair shop in the second repair shop list through the big data platform, so as to obtain multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies and multiple number of deep operation times of diagnostic equipment; The calculation unit 603 is used to calculate the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times based on a preset first weight calculation formula, and to obtain multiple repair shop recommendation scores. The control unit 604 is used to filter out repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold from the plurality of repair shop recommendation scores to obtain a plurality of target repair shop recommendation scores; sort the plurality of target repair shop recommendation scores in descending order to obtain a target repair shop recommendation score sequence, and send the target repair shop recommendation score sequence to the user terminal device so as to display the vehicle repair shop recommendation results through the user terminal device.

[0077] Optionally, the determining unit 602, in the context of the vehicle fault information including fault type and vehicle identifier, and the step of filtering repair shops capable of handling the vehicle fault information from the first repair shop list to obtain a second repair shop list, is specifically used for: Determine the vehicle brand in the vehicle identification; From the multiple first repair shop lists, information on repair shops that meet the requirements for repairing the vehicle brand is filtered out to obtain multiple candidate repair shops; Obtain historical repair data from the multiple candidate repair shops for the aforementioned fault type; Statistically analyze the repair frequency and number of successful repairs for the aforementioned fault types in the historical repair data; Based on the multiple repair frequencies and the multiple repair success counts, determine whether the multiple candidate repair shops meet the preset first repair condition; If so, then the multiple repair shops that meet the first repair conditions among the multiple candidate repair shops are determined as the second repair shop list; If not, the target candidate repair shop is eliminated, and the step of determining whether the multiple candidate repair shops meet the preset first repair condition based on the multiple repair frequencies and the multiple repair success counts is executed; the target candidate repair shop is any one of the multiple candidate repair shops.

[0078] Optionally, the determining unit 602, in determining that the plurality of repair shops meeting the first repair conditions among the plurality of candidate repair shops are part of the second repair shop list, is specifically used for: Determine the ratio between the number of successful repairs and the repair frequency to obtain multiple ratios; each of the multiple ratios corresponds one-to-one with each of the multiple first repair shops in the list of first repair shops. Determine whether the repair frequency is greater than or equal to a preset minimum sample threshold; If so, then the repair shops that are greater than or equal to the preset fault repair success rate threshold among the multiple ratios are identified as those that meet the first repair conditions, resulting in multiple repair shops, and the multiple repair shops are identified as the second repair shop list; If not, then eliminate the repair shops whose ratios are lower than the fault repair success rate.

[0079] Optionally, the acquisition unit 601, in acquiring the fault repair efficiency, customer return rate, repair frequency, and number of deep diagnostic equipment operations for each repair shop in the second repair shop list, specifically uses the following to obtain multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of deep diagnostic equipment operations: The historical repair reports for each of the second repair shops in the second repair shop list are obtained through the big data platform. Based on the historical maintenance reports, maintenance records for the fault codes are determined, resulting in multiple maintenance records; Within a preset first time window, the number of times the fault code appears and the number of repairs are counted from the multiple repair records to obtain multiple fault counts and multiple repair counts; The repair efficiency of the multiple faults is determined based on the multiple number of faults and the multiple number of repairs. Within a preset second time window, the number of times the target vehicle was repaired again at all second repair shops in the second repair shop list is counted from the multiple repair records to obtain multiple repair counts; The customer retention rate is determined based on the number of repairs performed. The multiple repair frequencies are determined based on the multiple repair records within a preset period; The number of deep operations performed by each repair shop using diagnostic equipment within the cycle is calculated from the multiple repair records to obtain the number of deep operations of the multiple diagnostic equipment; the number of deep operations includes at least one of the following: programming and coding times, ADAS calibration times, and vehicle function parameter configuration times.

[0080] Optionally, the acquisition unit 601, in determining the multiple customer return rates based on the multiple repair counts, is specifically used for: Within the second time window, based on the multiple repair records, determine the records of multiple vehicle models that have been repaired, and obtain the repair record set of the vehicle models; The number of times the target vehicle model appears in at least two maintenance records in the maintenance record set is counted to obtain the number of vehicles visited; the target vehicle model is any one of the multiple vehicle models. The number of repair records in the repair record set is determined to obtain the total number of repairs for the target vehicle model; The target customer return rate is obtained by determining the ratio of the number of vehicles visited to the total number of repairs.

[0081] Optionally, the calculation unit 603, in calculating the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times based on a preset first weighting calculation formula to obtain multiple repair shop recommendation scores, is specifically used for: Based on preset recommendation scoring rules, recommended scores are determined for the target fault repair rate, target customer return rate, target repair frequency, and target diagnostic equipment operation depth, resulting in target fault repair rate score, target customer return rate score, target repair frequency score, and target diagnostic equipment operation depth score; the target fault repair rate, target customer return rate, target repair frequency, and target diagnostic equipment operation depth are each any one of the plurality of fault repair rates, plurality of customer return rates, plurality of repair frequencies, and plurality of diagnostic equipment operation depths. Determine multiple first weight parameters corresponding to the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score; The target repair shop recommendation score is determined based on the multiple first weight parameters, the target fault repair rate score, the target customer return rate score, the target repair frequency score, and the target diagnostic equipment operation depth score.

[0082] Optionally, the calculation unit 603 is specifically used for determining the multiple first weight parameters corresponding to the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score, in the following ways: Obtain historical repair evaluation data from the second repair list; Based on the historical maintenance evaluation data, the weight coefficients corresponding to the target fault repair score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score are determined, resulting in multiple second weight parameters; The plurality of second weight parameters are normalized to obtain the plurality of first weight parameters.

[0083] As can be seen, the vehicle repair shop recommendation device 600 described in this application, based on big data, obtains a first list of repair shops within a preset range, and obtains vehicle fault information of the target vehicle through a user terminal device. It then filters repair shops capable of handling vehicle fault information from the first list to obtain a second list of repair shops. Through a big data platform, it obtains the fault repair efficiency, customer return rate, repair frequency, and number of deep diagnostic equipment operations for each repair shop in the second list, resulting in multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of deep diagnostic equipment operations. Based on a preset first weighting calculation formula, it calculates multiple repair shop recommendation scores, selects repair shops with recommendation scores greater than or equal to a preset recommendation score threshold, obtains multiple target repair shop recommendation scores, sorts the multiple target repair shop recommendation scores in descending order, obtains a target repair shop recommendation score sequence, and sends the target repair shop recommendation score sequence to the user terminal device to display the vehicle repair shop recommendation results. In this way, by using big data to evaluate repair shops from multiple dimensions, the suitability of vehicle repair shop recommendations is improved. When users go for repairs based on the recommendations, they can avoid situations such as opaque pricing, thus improving the user experience.

[0084] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a computing server provided in an embodiment of this application. The computing server 700 may include a processor 710, a memory 720, a communication interface 730, and one or more programs 721. The processor 710, the memory 720, and the communication interface 730 can be interconnected via a bus. The one or more programs 721 are stored in the memory 720 and configured to be executed by the processor 710. In this embodiment, the programs include instructions for performing the following steps: Obtain a list of the first repair shops within a preset range, and obtain vehicle fault information of the target vehicle through the user terminal device; A second list of repair shops is obtained by filtering out repair shops that can handle the vehicle malfunction information from the first list of repair shops. By using a big data platform, we can obtain the fault repair efficiency, customer return rate, repair frequency, and number of deep diagnostic equipment operations for each repair shop in the second list of repair shops, thus obtaining multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of deep diagnostic equipment operations. Based on a preset first weighting calculation formula, the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times are calculated to obtain multiple repair shop recommendation scores; From the multiple repair shop recommendation scores, repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold are selected to obtain multiple target repair shop recommendation scores; The multiple target repair shop recommendation scores are sorted in descending order to obtain a target repair shop recommendation score sequence, and the target repair shop recommendation score sequence is sent to the user terminal device so that the vehicle repair shop recommendation results can be displayed through the user terminal device.

[0085] The one or more programs 721 are stored in the memory 720 and configured to be executed by the processor 710. The one or more programs 721 include instructions for performing any step in the above method embodiments.

[0086] The processor 710 can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit can be a memory.

[0087] The memory 720 can be volatile memory or non-volatile memory, or it can include both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0088] It is understood that the computing server 700 may include more or fewer structural components than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the computing server 700 may be equipped with... Figure 2 The architecture of the vehicle repair recommendation system.

[0089] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include a computing server.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0091] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. Alternatively, the processor and storage medium can exist as discrete components in a terminal device or management device.

[0092] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A method for recommending vehicle repair shops based on big data, characterized in that, A server is used in a vehicle repair recommendation system, the vehicle repair recommendation system also including user terminal equipment and a big data platform, the server being communicatively connected to the big data platform and the user terminal equipment respectively, the method comprising: Obtain a list of the first repair shops within a preset range, and obtain vehicle fault information of the target vehicle through the user terminal device; A second list of repair shops is obtained by filtering out repair shops that can handle the vehicle malfunction information from the first list of repair shops. The big data platform is used to obtain the fault repair efficiency, customer return rate, repair frequency, and number of deep diagnostic equipment operations for each repair shop in the second repair shop list, resulting in multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of deep diagnostic equipment operations. Based on a preset first weighting calculation formula, the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times are calculated to obtain multiple repair shop recommendation scores; From the multiple repair shop recommendation scores, repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold are selected to obtain multiple target repair shop recommendation scores; The multiple target repair shop recommendation scores are sorted in descending order to obtain a target repair shop recommendation score sequence, and the target repair shop recommendation score sequence is sent to the user terminal device so that the vehicle repair shop recommendation results can be displayed through the user terminal device.

2. The method as described in claim 1, characterized in that, The vehicle fault information includes the fault type and vehicle identifier. The process of filtering repair shops capable of handling the vehicle fault information from the first repair shop list to obtain a second repair shop list includes: Determine the vehicle brand in the vehicle identification; From the multiple first repair shop lists, information on repair shops that meet the requirements for repairing the vehicle brand is filtered out to obtain multiple candidate repair shops; Obtain historical repair data from the multiple candidate repair shops for the aforementioned fault type; Statistically analyze the repair frequency and number of successful repairs for the aforementioned fault types in the historical repair data; Based on the multiple repair frequencies and the multiple repair success counts, determine whether the multiple candidate repair shops meet the preset first repair condition; If so, then the multiple repair shops that meet the first repair conditions among the multiple candidate repair shops are determined as the second repair shop list; If not, the target candidate repair shop is eliminated, and the step of determining whether the multiple candidate repair shops meet the preset first repair condition based on the multiple repair frequencies and the multiple repair success counts is executed; the target candidate repair shop is any one of the multiple candidate repair shops.

3. The method as described in claim 2, characterized in that, The step of determining the multiple candidate repair shops that meet the first repair conditions as the second repair shop list includes: Determine the ratio between the number of successful repairs and the repair frequency to obtain multiple ratios; each of the multiple ratios corresponds one-to-one with each of the multiple first repair shops in the list of first repair shops. Determine whether the repair frequency is greater than or equal to a preset minimum sample threshold; If so, then the repair shops that are greater than or equal to the preset fault repair success rate threshold among the multiple ratios are identified as those that meet the first repair conditions, resulting in multiple repair shops, and the multiple repair shops are identified as the second repair shop list; If not, then eliminate the repair shops whose ratios are lower than the fault repair success rate.

4. The method according to any one of claims 1-3, characterized in that, The step of obtaining the fault repair efficiency, customer return rate, repair frequency, and number of in-depth diagnostic equipment operations for each repair shop in the second repair shop list yields multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple numbers of in-depth diagnostic equipment operations, including: The historical repair reports for each of the second repair shops in the second repair shop list are obtained through the big data platform. Based on the historical maintenance reports, maintenance records for the fault codes are determined, resulting in multiple maintenance records; Within a preset first time window, the number of times the fault code appears and the number of repairs are counted from the multiple repair records to obtain multiple fault counts and multiple repair counts; The repair efficiency of the multiple faults is determined based on the multiple number of faults and the multiple number of repairs. Within a preset second time window, the number of times the target vehicle was repaired again at all second repair shops in the second repair shop list is counted from the multiple repair records to obtain multiple repair counts; The customer retention rate is determined based on the number of repairs performed. The multiple repair frequencies are determined based on the multiple repair records within a preset period; The number of deep operations performed by each repair shop using diagnostic equipment within the cycle is calculated from the multiple repair records to obtain the number of deep operations of the multiple diagnostic equipment; the number of deep operations includes at least one of the following: programming and coding times, ADAS calibration times, and vehicle function parameter configuration times.

5. The method as described in claim 4, characterized in that, The determination of the multiple customer return rates based on the multiple repair counts includes: Within the second time window, based on the multiple repair records, determine the records of multiple vehicle models that have been repaired, and obtain the repair record set of the vehicle models; The number of times the target vehicle model appears in at least two maintenance records in the maintenance record set is counted to obtain the number of vehicles visited; the target vehicle model is any one of the multiple vehicle models. The number of repair records in the repair record set is determined to obtain the total number of repairs for the target vehicle model; The target customer return rate is obtained by determining the ratio of the number of vehicles visited to the total number of repairs.

6. The method according to any one of claims 1-3, characterized in that, The calculation is based on a preset first weighting formula to calculate the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple deep operation times of diagnostic equipment, resulting in multiple repair shop recommendation scores, including: Based on preset recommendation scoring rules, recommended scores are determined for the target fault repair rate, target customer return rate, target repair frequency, and target diagnostic equipment operation depth, resulting in target fault repair rate score, target customer return rate score, target repair frequency score, and target diagnostic equipment operation depth score; the target fault repair rate, target customer return rate, target repair frequency, and target diagnostic equipment operation depth are each any one of the plurality of fault repair rates, plurality of customer return rates, plurality of repair frequencies, and plurality of diagnostic equipment operation depths. Determine multiple first weight parameters corresponding to the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score; The target repair shop recommendation score is determined based on the multiple first weight parameters, the target fault repair rate score, the target customer return rate score, the target repair frequency score, and the target diagnostic equipment operation depth score.

7. The method as described in claim 6, characterized in that, The determination of the target fault repair rate score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score, along with several first weighted parameters, includes: Obtain historical repair evaluation data from the second repair list; Based on the historical maintenance evaluation data, the weight coefficients corresponding to the target fault repair score, the target customer return rate score, the target maintenance frequency score, and the target diagnostic equipment operation depth score are determined, resulting in multiple second weight parameters; The plurality of second weight parameters are normalized to obtain the plurality of first weight parameters.

8. A vehicle repair shop recommendation device based on big data, characterized in that, A server is used in a vehicle repair recommendation system, which also includes user terminal equipment and a big data platform. The server is communicatively connected to the big data platform and the user terminal equipment, respectively. The device includes: The acquisition unit is used to acquire a first list of repair shops within a preset range, and to acquire vehicle fault information of the target vehicle through the user terminal device; A determining unit is used to filter out repair shops that can handle the vehicle fault information from the first repair shop list to obtain a second repair shop list; The acquisition unit is also used to acquire the fault repair efficiency, customer return rate, repair frequency and number of deep operation times of diagnostic equipment for each repair shop in the second repair shop list through the big data platform, so as to obtain multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies and multiple number of deep operation times of diagnostic equipment; The calculation unit is used to calculate the multiple fault repair efficiencies, multiple customer return rates, multiple repair frequencies, and multiple diagnostic equipment deep operation times based on a preset first weight calculation formula, and to obtain multiple repair shop recommendation scores. The control unit is configured to filter out repair shop recommendation scores that are greater than or equal to a preset recommendation score threshold from the plurality of repair shop recommendation scores to obtain a plurality of target repair shop recommendation scores; sort the plurality of target repair shop recommendation scores in descending order to obtain a target repair shop recommendation score sequence; and send the target repair shop recommendation score sequence to the user terminal device so as to display the vehicle repair shop recommendation results through the user terminal device.

9. A computing server, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images