Automotive repair shop matching optimization system and method for tire repair

Abstract

The application relates to the field of tire emergency repair, in particular to a car repair shop matching optimization system and method for tire emergency repair, which comprises a database module for receiving and integrating original tire damage data graphs from different scanning devices; a damage cause identification module for determining damage types by using a classification model, calculating damage indexes, and determining repair feasibility in combination with built-in rules; a repair scheme matching module for calling a repair knowledge base, screening and matching an adaptive feasible repair scheme; a maintenance resource scheduling module for displaying the matching scheme to maintenance technicians to guarantee repair quality standardization; and a user interaction module for supporting real-time viewing of maintenance progress by the user through information intercommunication between a user end and a maintenance end; the application integrates multi-source data, accurately identifies damage, intelligently matches a scheme, visually schedules maintenance resources, realizes two-way transparency of progress, and promotes intelligent, standardized and efficient development of tire emergency repair services.

Description

Technical Field

[0001] The present invention relates to the field of emergency tire repair, and more particularly to an automobile repair shop matching optimization system and method for emergency tire repair. Background Art

[0002] In the context of emergency tire repair services, with the continued growth of vehicle ownership and owners' increasing demands for repair efficiency and accuracy, traditional repair models are increasingly unable to meet actual needs, leaving many urgent challenges. Currently, tire repairs involve multiple scanning devices, and the raw tire damage data output by these devices varies in format and lacks effective integration. This requires maintenance personnel to manually sort through the data, which is not only inefficient but also prone to data omissions and mismatches, affecting subsequent repair decisions.

[0003] At the same time, multi-source data cannot be directly used for intelligent diagnosis and analysis due to inconsistent formats and scales, which restricts the intelligent upgrade of the maintenance process. In the damage identification process, manual experience is relied upon to judge the location, type, and repairability of the damage. This is highly subjective and accuracy is difficult to guarantee. It is prone to misjudgment, resulting in repairable tires being mistakenly replaced or unrepairable tires entering the maintenance process, causing waste of resources or safety hazards. When matching repair plans, manual screening from a vast amount of knowledge is required, which is time-consuming and prone to poor solution adaptability due to insufficient knowledge reserves, affecting maintenance quality and cost control. During the maintenance process, the communication of plans relies on manual communication, which is prone to misunderstandings and makes it difficult to ensure standardized repair quality. Car owners are also unable to know the progress of the repair in real time, and information opacity reduces service satisfaction.

[0004] Therefore, there is an urgent need for a system that can integrate multi-source data, unify format standards, accurately identify damage, intelligently match solutions, visually schedule maintenance resources, and achieve two-way transparency of progress. The present invention's raw data collection and integration, unified data format processing, accurate damage identification and judgment, intelligent matching of repair solutions, visual scheduling of repair solutions, and two-way interactive progress tracking steps can specifically solve the above-mentioned industry pain points and promote the intelligent, standardized, and efficient development of tire emergency repair services. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a car repair shop matching optimization system and method for emergency tire repair to solve the problems existing in the above-mentioned background technology.

[0006] The present invention provides the following technical solutions: The present invention provides an automobile repair shop matching optimization system and method for emergency tire repair, comprising: a database module including: an original database for receiving and integrating original tire damage data maps from different scanning devices;

[0007] Repair knowledge base, covering various tire repair contents and methods;

[0008] The damage cause identification module includes: a damage type determination unit for scanning the damage location in the original tire damage data map, determining the damage type using a classification model, and calculating a damage index;

[0009] Repairability assessment unit, which combines the damage index with built-in rules to provide a preliminary repairability judgment;

[0010] The repair solution matching module matches feasible repair solutions based on the precise damage information output by the damage cause identification module and the predefined repair knowledge base;

[0011] The maintenance resource scheduling module clearly displays the matching solutions to maintenance technicians to ensure standardized repair quality.

[0012] The user interaction module is divided into the user end and the maintenance end, which makes it easier for users to track the maintenance progress.

[0013] The technical effects and advantages of the present invention are as follows:

[0014] 1. This invention integrates multi-source tire damage data, including images, sensors, and historical case data, to construct information covering damage location, type, severity, and other dimensions. This provides a precise data foundation for the entire emergency tire repair process. Based on this multi-dimensional information, a multimodal feature fusion model is used to locate damage and determine its type. The damage index is then combined with a repair rule library to output a repairability conclusion. This effectively addresses the misjudgment problem caused by fragmented data and reliance on experience in traditional repair processes, reducing safety hazards and resource waste caused by damage identification errors.

[0015] 2. The repair solution matching module intelligently matches the precise damage information output by the damage cause identification module with the repair knowledge base. Using a pre-set screening algorithm and scoring mechanism, it selects feasible and suitable repair solutions from a vast pool of solutions, ensuring their scientificity and effectiveness. The repair resource scheduling module further visualizes the matching solutions for repair technicians and provides standardized operational instructions, effectively preventing discrepancies in repair quality caused by human misunderstanding and ensuring the standardization and stability of the repair process.

[0016] 3. This user interaction module breaks down information barriers by enabling information exchange between the user and repair departments. Users can view repair progress in real time, gaining insights into the entire repair process, from damage detection and solution matching to implementation. It also supports interactive features such as online communication and feedback. The repair department promptly responds and synchronizes results, creating a two-way, transparent service loop. This significantly enhances user engagement and trust in repair services, helping repair shops optimize service quality and strengthen their market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Fig. 1 is a schematic diagram of the overall structure of the present application.

[0018] Figure 2 Fig. 2 is a flowchart of the steps of the present application. DETAILED DESCRIPTION

[0019] The technical solutions of the present application will be described clearly and completely below in combination with the drawings of the present application. In addition, the forms of each structure described in the following embodiments are only examples, and the automobile repair shop matching optimization system and method for tire emergency repair involved in the present application are not limited to each structure described in the following embodiments. All other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present application.

[0020] Referring to Figure 1 , the present application provides an automobile repair shop matching optimization system for tire emergency repair, comprising:

[0021] The database module comprises: an original database for receiving and integrating original tire damage data graphs from different scanning devices;

[0022] A repair knowledge base for covering multiple types of tire repair content and methods;

[0023] The damage cause recognition module comprises: a damage type determination unit for scanning the position of damage in the original tire damage data graph, determining the damage type using a classification model, and calculating a damage index;

[0024] A repairability evaluation unit for giving a preliminary repairability judgment by combining the damage index with built-in rules;

[0025] A repair scheme matching module for matching a feasible repair scheme according to the accurate damage information output by the damage cause recognition module and combining a pre-defined repair knowledge base;

[0026] A maintenance resource scheduling module for clearly displaying the matched scheme to maintenance technicians to ensure standardized repair quality;

[0027] A user interaction module for being divided into a user end and a maintenance end to facilitate user tracking of maintenance progress.

[0028] Referring to Figure 2 , the specific implementation of the present application comprises the following steps:

[0029] S1: original data acquisition and integration: the database module receives original tire damage data graphs from different scanning devices;

[0030] Furthermore, the original tire damage data map includes image data, sensor data and historical data, wherein the image data specifically includes the tire surface texture, the shape and location of the damaged area, the sensor data specifically includes the tire pressure value, tire temperature changes and tire vibration frequency, and the historical data specifically includes the vehicle's past tire maintenance records and common failure cases of tires of the same model.

[0031] What needs to be specifically explained in this embodiment is that industrial-grade high-definition cameras are used to capture tire surface images. For example, a linear array camera equipped with a macro lens can clearly capture subtle damage such as cracks and nail holes on the tire surface; high-precision tire pressure sensors are used to collect tire pressure data in real time. A sudden drop in tire pressure can reflect tire leakage, and an abnormal increase in tire temperature may indicate internal structural damage; tire vibration frequency is monitored by an acceleration sensor, and abnormal vibration waveforms can assist in determining tire detachment or uneven wear problems; a deep neural network algorithm is used to retrieve the vehicle's past tire maintenance records from the database module to analyze the correlation between maintenance frequency and failures; at the same time, data crawler technology is used to obtain common failure cases of tires of the same model from the industry database to provide reference data for subsequent analysis.

[0032] Furthermore, the database module also unifies the format of multi-source data in the original tire damage data map to ensure that the data meets the system processing standards. Format unification specifically refers to the use of the database module to clean, convert, and normalize the image data, sensor data, and historical data in the original tire damage data map, providing standard data for subsequent damage cause identification and repair plan matching.

[0033] It should be specifically noted that in this embodiment, data cleaning adopts differentiated strategies for different types of data: for image data, noise is removed by median filtering, and missing areas are filled using an image restoration algorithm. The specific formula is as follows: , where I is the original image pixel value from the S1 image data, up is the local area mean of the image, is the standard deviation of the local area of ​​the image, which is used to measure the complexity of the damage texture. α and β are empirical enhancement parameters used to improve the contrast of damage details. Their conventional values ​​are 1.2 and 0.5. The tire surface image obtained by S1 is denoised using a median filter, and the damaged area Ie is enhanced using the above formula for subsequent identification. Missing values ​​in the sensor data are filled using cubic spline interpolation, and outliers are filtered using the 3σ principle. In terms of format conversion, image data is uniformly converted to PNG format, and the resolution is adjusted to 1920×1080 pixels. Sensor data is standardized and stored in JSON format. Historical data is converted into a structured table that can be recognized by the system through data mapping.

[0034] Specifically, this embodiment employs a scale normalization method designed specifically for different data features: histogram equalization is used to enhance contrast in image data, and pixel values ​​are normalized to the [0, 1] range. Tire pressure and temperature sensor data are standardized using the Z-score method to eliminate dimensionality effects. Discrete historical data on maintenance frequency and fault level are digitized using one-hot encoding. Furthermore, for image features like tire surface texture and damaged area shape, feature vectors are extracted using the HOG algorithm and L2 norm normalization is performed. The sliding window technique is used to extract features from the sensor data on tire pressure change rate and temperature fluctuation trend, followed by Min-Max normalization to ensure that all data conforms to the system's unified processing standards.

[0035] S2: Accurate Damage Identification and Judgment: The damage cause identification module extracts damage parameters from the original tire damage data graph, uses a classification model to determine the damage type, calculates the damage index, and uses built-in rules to determine repair feasibility;

[0036] Furthermore, using the classification model to determine the damage type specifically includes the following steps:

[0037] A1: Receives pre-processed data and classifies and integrates image data, sensor data, and historical data;

[0038] Specifically, this embodiment classifies and integrates the preprocessed data. Specifically, image data is categorized into a visual feature set, sensor data is incorporated into a dynamic parameter set, and historical data is stored in an empirical data set. This classification and integration facilitates the application of correspondence analysis methods to different data types, laying the foundation for accurate damage identification.

[0039] A2: Locate the damaged area on the image data and use the target detection algorithm to determine the damage location;

[0040] Specifically, this example utilizes the YOLO and Faster R-CNN object detection algorithms to identify cracks, holes, and wear damage on the tire surface within image data. By analyzing the image pixel information, the algorithms can quickly and accurately identify the specific coordinates of the damage, providing a location reference for subsequent damage type determination.

[0041] A3: Combine image features and sensor data to determine the damage type;

[0042] Specifically, this embodiment extracts the texture, shape, and size visual features of the damaged area from the image data, and simultaneously analyzes the dynamic parameters of tire pressure changes, abnormal tire temperature, and vibration frequency changes in the sensor data. The specific model used is as follows: , image entropy is calculated by scipy.stats.entropy for the image enhanced by S2, tire pressure drop rate is calculated by , damage area ratio is calculated by , and vibration FFT main frequency is extracted by FFT transformation of S1 vibration frequency data, a11, a12, a21, a22 are default weights.

[0043] A4: According to the damage type and built-in rules, output the preliminary conclusion of damage repairability.

[0044] It needs to be specifically explained that the damage type is quantified by the damage index model to determine the damage severity, and the industry standard, historical maintenance experience and expert knowledge are combined to output the tire damage repairability conclusion; it needs to be explained that the damage index is calculated by DI value through multi-dimensional data, and then the DI associated repairability rule is used, the specific formula is: , b1, b2, b3 are weight coefficients, which are used to quantify the influence degree of different damage characteristics on damage severity, Ad is the damage area, which is calculated by converting the pixel ratio of the damage area by contour detection on the preprocessed tire surface image through image recognition algorithm, At is the total surface area of the tire, which is obtained by querying the tire specification parameters, dmax is the maximum depth of tire damage, tp is the thickness of the cord layer, which is known by querying the tire manufacturer's specification table, Pf is the position coefficient, which is an industry experience value, the conventional value of Pf is 1.5 when the sidewall is damaged, and the conventional value of Pf is 1.0 when the tread is damaged.

[0045] It needs to be further explained that the built-in rules associate the repairability conclusion with the DI value interval to achieve scientific determination. When DI≤1.2, it is determined to be repairable. From historical experience, this kind of damage is mostly conventional type of nail and small area wear, and the success rate of using standard repair process is more than 95%. The system can automatically match the pre-defined scheme, and the safety can be guaranteed after repair by basic detection; when 1.2≤DI≤2.0, expert review is required. The damage in this interval is in a critical state, and it is difficult to accurately identify the internal complex damage condition by conventional determination method. Professional personnel need to use ultrasonic detection means to review the damage details and confirm the feasibility of customized repair scheme; when DI>2.0, further evaluation of repair feasibility is required through data simulation model.

[0046] a1, collect historical repair case data of similar damage, build training data set containing damage area, depth, repair process and secondary failure probability;

[0047] a2, establish data simulation model, input current damage parameters, output safety risk prediction value R after repair;

[0048] a3. Preset safety risk threshold Rth. When R≤Rth, the tire is judged to be repairable and an enhanced repair plan is recommended. When R>Rth, the tire is judged to be unrepairable and tire replacement is recommended.

[0049] S3: Intelligent matching of repair solutions: The repair solution matching module calls the repair knowledge base based on the feasibility of the repair, and screens and matches the appropriate feasible repair solutions.

[0050] Furthermore, intelligent matching of repair solutions specifically includes the following steps:

[0051] B1: The repair solution matching module receives the damage type, location, and repairability conclusion output by the damage accurate identification and judgment step, and temporarily stores them in the solution matching buffer;

[0052] It should be specifically explained in this embodiment that the damage identification results include image feature analysis conclusions, sensor data anomaly records and historical data comparison results. This information is stored in a cache area in a structured format to facilitate subsequent rapid retrieval and provide an accurate basis for repair plan screening.

[0053] B2: Select a model that matches the loading repair scheme and optimize the model parameters based on the damage characteristics;

[0054] Specifically, the repair solution matching module incorporates multiple matching models, including a rule-based expert system model, a collaborative filtering recommendation model, and a deep learning ranking model. During operation, the module will select and load the appropriate model for the current scenario based on damage type, severity, and repairability. Solution selection follows the formula: SR is the historical success rate of the solution, which is calculated from historical maintenance records. c1 is the success rate weight, which focuses on reliability and is usually set to 0.6. represents the efficiency factor, the unit is minute, c2 is the timeliness weight, which focuses on efficiency, and the normal value is 0.4, I (Stocki>0) is the inventory indicator function, which is 1 when the inventory is sufficient, otherwise it is 0, It is the multiplication of the inventory indicator functions I of all n types of materials, where Stocki represents the current inventory quantity of the i-th repair material. For example, when faced with common nail damage, the rule-based expert system model is called first; when encountering complex explosion damage scenarios, the deep learning sorting model is activated. After the model is loaded, the parameters are fine-tuned using historical successful repair case data. By adjusting rule weights, transfer learning, or updating the user-item matrix, the model can better adapt to the current damage situation and improve the accuracy of solution matching.

[0055] B3: Input the cached damage data into the optimized matching model, perform solution reasoning and screening, and output feasible repair solutions.

[0056] What needs to be specifically explained in this embodiment is that during the data input process, the damage data must be organized strictly in the format and order required by the model, and preprocessing of unified data dimensions and standardized numerical ranges must be completed to avoid matching deviations due to non-standard data; model reasoning and screening include two steps: one is feature mapping and weight calculation, mapping the damage data features to the model parameter space, and assigning weights to the importance of different features for solution selection; the other is solution sorting and output, in which the model sorts the solutions in the repair knowledge base based on the comprehensive score, and outputs the top N feasible solutions with the highest scores, along with detailed information on applicable scenarios, estimated costs, and repair duration, and performs consistency verification on the solutions to ensure consistency with the damage feature logic, providing a reliable reference for subsequent maintenance resource scheduling.

[0057] S5: Visual scheduling of maintenance plans: The maintenance resource scheduling module displays matching plans to maintenance technicians to ensure standardized repair quality;

[0058] Furthermore, the maintenance plan visualization scheduling specifically includes the following steps:

[0059] C1: Set visualization display rules, perform structured analysis on the feasible repair plans output by the repair plan intelligent matching module, and display them hierarchically by priority. At the same time, collect display effect feedback data corresponding to multiple historical repair cases, marked as 1, 2, ..., i, ..., n, and calculate the following indicators based on the feedback data of each case:

[0060] Average ease of use rating: ,

[0061] Average information comprehension score: ,

[0062] Average repair quality satisfaction rating: ,

[0063] Obtain the average operation convenience score Op, the average information comprehension score Up, and the average repair quality satisfaction score Qp;

[0064] It should be specifically explained in this embodiment that the operation convenience score represents the efficiency feedback of the maintenance technician in completing the plan review and preparation work, the information comprehension score represents the accuracy of the technician's understanding of the plan content, and the repair quality satisfaction score represents the customer satisfaction with the tire repair effect after the plan is executed.

[0065] C2: Based on the above average rating, calculate the following coefficients:

[0066] Program demonstration effectiveness coefficient εA: ,

[0067] Solution communication accuracy εP: ,

[0068] Program execution success rate εR: ,

[0069] F2 value: ;

[0070] It should be specifically explained in this embodiment that the solution display effectiveness coefficient reflects the degree to which the solution visualization display effectively promotes the overall maintenance process, the solution communication accuracy rate reflects the proportion of maintenance technicians who accurately obtain key solution information, the solution execution success rate indicates the proportion of repair technicians who achieve the expected repair effect after executing the displayed solution, and the F2 value reflects the comprehensive balance between solution communication and execution effects.

[0071] C3: Substitute the above coefficients into the formula to calculate the comprehensive visualization scheduling score:

[0072] ,

[0073] ω1, ω2, ω3, and ω4 represent the weight coefficients of the solution display effectiveness coefficient, solution communication accuracy, solution execution success rate, and F2 value, respectively, and their sum is 1.

[0074] Specifically, in this embodiment, the weighting coefficients are determined based on maintenance service requirements and quality objectives. If the maintenance service prioritizes rapid response, a higher weight should be assigned to operational convenience. If the emphasis is on stable repair quality, the weight for repair quality satisfaction can be increased accordingly. A cross-validation approach was used to experiment with different weight combinations. By comparing the performance of the maintenance process in real-world applications under different weights, the weight combination that optimizes the overall evaluation index was selected.

[0075] Furthermore, optimizing visual scheduling specifically includes setting a scoring standard threshold, comparing the comprehensive visual scheduling score with the scoring standard threshold, if the comprehensive visual scheduling score is greater than the scoring standard threshold, it means that the visual scheduling effect of the maintenance plan meets the standard and no adjustment is required; if the comprehensive visual scheduling score is less than the scoring standard threshold, it means that the visual scheduling effect of the maintenance plan does not meet the standard, and the visual scheduling method is dynamically optimized based on the specific plan display effectiveness coefficient, plan communication accuracy, plan execution success rate and F2 value.

[0076] What needs to be specifically explained in this embodiment is that the specific optimization methods include adjusting the layout of the display interface, optimizing the solution information presentation logic, improving the operation guidance prompts, and integrating multiple visualization technologies. Among them, adjusting the display interface layout means adjusting the functional partitions and button positions of the solution display interface according to the operational convenience problem reflected by the scoring results. For example, when the operational convenience score is low, the key operation buttons can be placed in a more conspicuous area to reduce the technician's operation steps; optimizing the solution information presentation logic means re-arranging the display order of the solution content and giving priority to the display of key information such as maintenance steps and safety precautions; improving the operation guidance prompts means that if the scoring results show that the technician has difficulty understanding part of the solution content, graphic annotations and animation demonstrations can be added to assist in the explanation; integrating multiple visualization technologies means considering combining different display methods such as flow charts and three-dimensional simulation demonstrations according to the scoring situation to enhance the solution visualization effect.

[0077] S5: Two-way interactive progress tracking: The user interaction module supports users to view the maintenance progress in real time through information exchange between the user end and the maintenance end.

[0078] Specifically, the user interaction module, through information exchange between the user-side app and the maintenance-side system, allows users to view repair progress in real time in an intuitive, visual manner. Data presentation utilizes a timeline, progress bar, and Gantt chart visualization to clearly display the progress of tire removal, damage cause detection, repair solution matching, repair implementation, and quality inspection and repair. For example, a progress bar displays the completion percentage of the current repair phase in real time, while the timeline indicates the actual operation time and planned time for each key node, allowing users to intuitively compare progress.

[0079] It should be explained that users can interact with the system through the user-side APP. During the maintenance process, users can send messages at any time to inquire about maintenance details, request a replacement maintenance plan, or add special maintenance requirements. After receiving the user's instructions, the maintenance-side system will respond and update the maintenance plan in a timely manner, and simultaneously feedback the processing results to the user side. The system also has an evaluation and feedback function. After the maintenance is completed, the user can evaluate the maintenance service through star ratings and text comments. This feedback information will be synchronized to the maintenance side to help maintenance personnel improve their services and provide data support for the subsequent optimization of user interaction functions.

[0080] It needs further explanation that in order to further quantify the quality of maintenance services, a comprehensive maintenance quality scoring mechanism is introduced. The specific formula is: , where d1, d2, and d3 are the weight coefficients of maintenance time, cost control, and user satisfaction, d1+d2+d3=1. This score comprehensively evaluates the maintenance quality from the dimensions of time, cost, and user experience. If the score is lower than the threshold, the optimization of the time overrun and cost out-of-control links can be located. When the value is low, the solution matching or resource scheduling process is optimized, so that the two-way interactive progress tracking not only focuses on progress presentation and operation, but also continuously improves services through quality scoring.

[0081] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict.

[0082] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A matching optimization system for automobile repair shops for emergency tire repair, characterized in that: include: The database module includes: a raw database for receiving and integrating raw tire damage data from different scanning devices, including image data, sensor data, and historical data; the image data specifically includes tire surface texture, damaged area shape and location; the sensor data specifically includes tire pressure values, tire temperature changes, and tire vibration frequency; and the historical data specifically includes past tire maintenance records and common failure cases of the same model tire; A repair knowledge base covers various tire repair content and methods. The database module also unifies the format of multi-source data in the original tire damage data: for image data, median filtering is used to remove noise, and image inpainting algorithms are used to fill in missing areas. The damage cause identification module includes a damage type determination unit, which is used to scan the damage location in the original tire damage data, use the YOLO and FasterR-CNN target detection algorithms to locate the damaged area, extract the tire surface texture feature vector using the HOG algorithm and perform L2 norm normalization, and then determine the damage type based on the classification model. The classification model formula is: , DataMatrix is ​​the result of the final matrix multiplication. Image entropy is used to measure the texture complexity of the tire damage area. The tire pressure drop rate is The damage area ratio is calculated by Calculation: The vibration FFT main frequency refers to the main frequency extracted after the FFT transformation of the tire vibration frequency data. a11, a12, a21, and a22 are the default weights. At the same time, the damage index DI is calculated: the formula is: , DI is the damage index, b1, b2, and b3 are weight coefficients, Ad is the area of ​​the damaged area, which is calculated by converting the pixel ratio of the damaged area through the image recognition algorithm, At is the total surface area of ​​the tire, which is obtained by querying the tire specification parameters, dmax is the maximum depth of tire damage, which is obtained by querying the tire manufacturer's specification table, tp is the cord thickness, and Pf is the position coefficient; The repairability assessment unit combines the damage index with built-in rules to provide a preliminary repairability assessment: when DI ≤ 1.2, the tire is judged repairable; when 1.2 ≤ DI ≤ 2.0, expert review is required, as the damage in this range is critical; when DI > 2.0, further assessment of repair feasibility is required using a data simulation model. The data simulation model includes: collecting historical repair case data of similar damage to construct a training data set, establishing a data simulation model, inputting current damage parameters to output a post-repair safety risk prediction value R, and presetting a safety risk threshold Rth. When R ≤ Rth, the tire is judged repairable and an enhanced repair plan is recommended; when R > Rth, the tire is judged unrepairable and a tire replacement is recommended. The repair solution matching module matches feasible repair solutions based on the precise damage information output by the damage cause identification module and the predefined repair knowledge base. The solution screening of the matching model follows the formula: SR is the historical success rate of the solution, c1 is the success rate weight, represents the efficiency factor, c2 is the timeliness weight, The stock indicator function I of all n materials is multiplied together, and Stocki represents the current stock quantity of the i-th maintenance material; The maintenance resource scheduling module clearly displays the matching solutions to maintenance technicians to ensure standardized repair quality. The user interaction module includes a user end and a maintenance end. The user end facilitates users to track the maintenance progress.

2. The matching optimization system for automobile repair shops for emergency tire repair according to claim 1, characterized in that: The repair solution matching specifically includes the following steps: B1: The repair solution matching module receives the damage type, location, and repairability conclusion, and temporarily stores them in the solution matching buffer; B2: Select a model that matches the loading repair scheme and optimize the model parameters based on the damage characteristics; B3: Input the cached damage data into the optimized matching model, perform solution reasoning and screening, and output feasible repair solutions.

3. A matching optimization method for automobile repair shops for emergency tire repair, characterized in that: The method is applicable to the automobile repair shop matching optimization system for emergency tire repair according to claim 1, and specifically comprises the following steps: S1: Raw data collection and integration: The database module receives raw tire damage data from different scanning devices; S2: Accurate Damage Identification and Judgment: The damage cause identification module extracts damage parameters from the original tire damage data, uses a classification model to determine the damage type, calculates the damage index, and uses built-in rules to determine the feasibility of repair; S3: Intelligent matching of repair solutions: The repair solution matching module calls the repair knowledge base based on the feasibility of the repair, and screens and matches the appropriate feasible repair solutions. S4: Visual scheduling of maintenance plans: The maintenance resource scheduling module displays matching plans to maintenance technicians to ensure standardized repair quality; S5: Two-way interactive progress tracking: The user interaction module supports users to view the maintenance progress in real time through information exchange between the user end and the maintenance end.

4. The method for optimizing matching of automobile repair shops for emergency tire repair according to claim 3, characterized in that: The maintenance plan visual scheduling specifically includes the following steps: C1: Set visual display rules, perform structured analysis on the feasible repair plans output by the repair plan intelligent matching module, and display them in a hierarchical manner according to priority. At the same time, collect display effect feedback data corresponding to multiple historical maintenance cases. ， Marked as 1, 2, ..., i, ..., n, the following indicators are calculated based on the feedback data of each case: Average ease of use rating: , Average information comprehension score: , Average repair quality satisfaction rating: , Obtain the average operation convenience score Op, the average information comprehension score Up, and the average repair quality satisfaction score Qp; C2: Based on the above average rating, calculate the following coefficients: Program demonstration effectiveness coefficient εA: , Solution communication accuracy εP: , Program execution success rate εR: , F2 value: ; C3: Substitute the above coefficients into the formula to calculate the comprehensive visualization scheduling score: ， ω1, ω2, ω3, and ω4 represent the weight coefficients of the solution display effectiveness coefficient, solution communication accuracy, solution execution success rate, and F2 value, respectively, and their sum is 1.

Images