A method for real-time positioning of tire breakdown and matching with repair service

Abstract

A kind of method for tire fault real-time positioning and maintenance service matching, including information acquisition end, fault determination end, report generation end, service screening end, service matching end;The current accurate geographic position information of tire state parameter is collected in real time to vehicle, when it is monitored that tire parameter exceeds the normal threshold range of pre-set, it is determined that tire fault occurs, sends fault information together with positioning information to cloud server, starts fault degree evaluation model, generates evaluation report, establishes maintenance service resource database, cloud server automatically selects maintenance service provider according to tire fault positioning information, forms available maintenance service resource list, and maintenance service is matched using intelligent matching algorithm;The present application realizes fault extremely fast early warning, shortens response time, reduces on-site processing time, avoids resource waste, reduces fuel and labor cost, eliminates excessive repair or insufficient repair, makes service transparent and traceable.

Description

Technical Field

[0001] This invention belongs to the field of Internet of Things (IoT) technology, specifically a method for real-time tire fault location and repair service matching. Background Technology

[0002] In traditional technologies, tire problems rely primarily on driver judgment or periodic inspections, making it impossible to detect tire abnormalities in real time. This leads to delayed fault detection and can result in safety accidents such as tire blowouts and loss of vehicle control, especially at high speeds. Hidden faults, such as minor tire pressure abnormalities that remain unaddressed for extended periods, can accelerate tire wear and increase repair costs.

[0003] In traditional methods, drivers need to manually search for repair shops and rely on phone calls to confirm service areas, which is time-consuming and labor-intensive. Repair shops often lack information about the fault location and cannot prepare tools or parts in advance, potentially leading to multiple trips or service interruptions. The average response time can be several hours, causing vehicle delays and affecting logistics and travel efficiency. Drivers may also choose suboptimal repair shops due to insufficient information, resulting in inconsistent service quality.

[0004] Traditional tire repair resources are scattered across independent shops or individual service providers, lacking a unified database to manage their technical capabilities, equipment status, and real-time workload. Dispatch relies on manual experience, easily leading to contradictions such as nearby shops being unable to handle issues or distant shops having idle resources. Resource utilization is low; specialized tire repair shops may miss orders due to information asymmetry, while ordinary repair shops may take on faults beyond their capabilities. Repeated dispatching increases costs, and repair personnel may travel multiple times to the same area, ultimately passing the cost onto the customer.

[0005] Traditional fault assessment relies on on-site judgment by maintenance personnel, lacking quantitative standards and historical data on service quality, making it difficult to optimize processes or trace responsibility. Drivers may face situations of over-repair or incomplete repairs, and the lack of unified service standards across the industry leads to inconsistent user experiences. Summary of the Invention

[0006] In view of this, the present invention aims to propose a method for real-time tire fault location and repair service matching, including an information collection terminal, a fault determination terminal, a report generation terminal, a service filtering terminal, and a service matching terminal. By collecting real-time tire status parameters and current precise geographical location information, when tire parameters are detected to exceed a preset normal threshold range, a tire fault is determined. The fault information and location information are sent to a cloud server, a fault severity assessment model is activated, an assessment report is generated, and a repair service resource database is established. The cloud server automatically filters repair service providers based on the tire fault location information, forming a list of available repair service resources. A smart matching algorithm is used to match repair services. The platform sends the matched repair service provider list and related information to the user terminal. The user can select a provider according to their needs. If the user does not select one in time, the system will automatically select the provider with the highest matching degree, effectively solving the problems mentioned in the background technology.

[0007] The objective of this invention can be achieved through the following technical solution: A method for real-time tire fault location and repair service matching, comprising an information collection terminal, a fault determination terminal, a report generation terminal, a service filtering terminal, and a service matching terminal, specifically including the following steps:

[0008] S1. Real-time collection of vehicle tire status parameters and current precise geographical location information;

[0009] S2. When the tire parameters are detected to exceed the normal threshold range preset by the dynamic threshold model based on the tire model parameters, actual usage time and historical health data, it is determined that the tire has failed and the fault information and location information are sent to the cloud server together.

[0010] S3. After receiving tire fault information and location information, the cloud server starts the fault severity assessment model to calculate parameter deviation and impact factor correction values, and generates an assessment report by weighting the risk index.

[0011] S4. Establish a maintenance service resource database. The cloud server filters based on basic matching conditions according to tire fault location information, automatically selects maintenance service providers, and forms a list of available maintenance service resources.

[0012] S5. Based on the tire failure severity assessment results and the list of available repair service resources, the system uses an intelligent matching algorithm to dynamically calculate the matching score and perform repair service matching. At the same time, when a service provider accepts an order or its status changes, the system immediately recalculates the matching score of the remaining service providers and dynamically adjusts the list order.

[0013] S6. The platform will send the list of matched repair service providers and related information to the user's terminal. The user can select a provider according to their own needs. If the user does not select one in time, the system will automatically select the provider with the highest matching degree.

[0014] The fault severity assessment model includes: comparing the deviation of real-time parameters with normal thresholds and calculating the parameter deviation.

[0015] Fault influencing factors include fault duration, vehicle driving status, environmental factors, vehicle model and tire type, and historical fault records. These influencing factors are standardized to obtain correction coefficients. Weights are assigned to each correction coefficient to derive the corrected value of the influencing factor, which can be expressed as:

[0016]

[0017] Where c is the impact factor correction value, u is the impact factor correction coefficient, and q is the weight of each impact factor correction coefficient;

[0018] The risk index is calculated based on the parameter deviation and the preset weights of each parameter, using the following expression:

[0019]

[0020] Where K is the risk index, t is the parameter deviation, w is the weight of each parameter, and c is the impact factor correction value; when the risk index is less than a, it is judged as a minor fault; when the risk index is greater than a and less than b, it is judged as a moderate fault; when the risk index is greater than b, it is judged as a severe fault; where a and b are preset thresholds, obtained by collecting a large number of fault cases of tires of the same model and in the same usage scenario.

[0021] The assessment report specifically includes: basic information such as vehicle information, time of failure, and location coordinates; failure details such as type, severity level, and parameter deviation; cause speculation such as possible causes based on model analysis; and recommended measures such as emergency handling plan, recommended repair items, and safety precautions.

[0022] The vehicle's tire condition parameters and current precise geographic location information include one or more of the following: tire pressure, tire temperature, tire wear, tire speed, tire vibration frequency, and tread depth; the current precise geographic location information includes latitude and longitude coordinates, altitude, road name, landmark information of the area, and location of nearby transportation hubs.

[0023] The preset normal threshold is specifically as follows: a dynamic threshold model is adopted, and the threshold is set based on tire model parameters including load index or speed rating, actual usage time and historical health data. A segmented threshold curve model is adopted, with the standard threshold used for the first x years of use, the safety threshold increasing by n% each year for the xy years of use, and the aging compensation algorithm being activated after y years.

[0024] The maintenance service resource database includes: basic information of maintenance service providers, including company name, contact information, service type, and qualification certification; geographic information, including the specific address of the service provider, service coverage radius, and location marked by a GIS geographic information system; service capability parameters, including equipment type, inventory tire models, number of technicians, and qualification level; and dynamic status data, including real-time busy / idle status, number of currently dispatchable maintenance vehicles, and estimated response time.

[0025] The automatic screening method for repair service providers is as follows: basic matching criteria are used for filtering, the service type must cover the fault type, the service provider's inventory must include the compatible tire model, and for emergency faults, service providers within the set time frame of ETA need to be screened.

[0026] The method for matching repair services is as follows: a dynamic weighting formula is designed, which integrates geographical distance and ETA, service response capability, qualifications and evaluation, and inventory matching degree. Weights are set for each factor, and a matching score is calculated. For severe and moderate faults, priority is given to matching service providers with the shortest ETA and the highest service capability, with weights tilted towards geographical distance and response capability. For minor faults, the matching range can be expanded by adding service evaluation and price factors.

[0027] Combining all the above technical solutions, the positive effects of this invention are as follows: 1. By collecting tire status parameters and threshold judgments in real time, rapid fault warnings are achieved. By detecting latent faults such as slow leaks and abnormal tread wear in advance, safety accidents such as tire blowouts and vehicle loss of control caused by delayed fault detection are avoided, especially suitable for high-speed driving or freight scenarios. 2. By synchronously uploading location information and fault information to the cloud, repair personnel can know the fault location in advance, quickly deploy rescue resources, and reduce subsequent risks of accidents.

[0028] 2. By integrating service provider capabilities, equipment, and location information through a maintenance service resource database, and using algorithms to match fault severity with service provider qualifications, response time is shortened. The cloud automatically filters the nearest qualified tire repair service provider, avoiding manual searching and repeated communication for drivers. Repair shops receive fault assessment reports in advance, allowing for precise preparation of tools and parts, reducing on-site processing time.

[0029] 3. The resource database is updated in real time with service provider workload and technical expertise. Algorithms optimize scheduling routes to avoid resource waste. Location-based filtering of nearby service providers reduces empty mileage for repair personnel, lowering fuel and labor costs. Service providers in remote areas can obtain nearby fault information via the cloud to avoid resource idleness; in densely populated urban areas, orders can be diverted to reduce waiting times.

[0030] 4. The fault severity assessment model generates reports based on quantitative parameters and provides a transparent supplier list, which can prevent over-repair or under-repair, making the service transparent and traceable. Users can view service provider ratings, historical cases and matching degree algorithm logic, and choose independently or rely on the system to automatically assign the supplier with the highest matching degree, reducing decision-making costs. Attached Figure Description

[0031] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0032] Figure 1 This is a flowchart illustrating the implementation steps of the method of the present invention.

[0033] Figure 2 This is a flowchart illustrating the implementation of the fault severity assessment model. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] See Figure 1 As shown, this invention proposes a method for real-time tire fault location and repair service matching, including an information collection terminal, a fault determination terminal, a report generation terminal, a service filtering terminal, and a service matching terminal.

[0036] In a more specific application of this invention, vehicle tire condition parameters can be collected in the following ways:

[0037] Tire pressure and temperature can be monitored by installing pressure and temperature sensors inside the tire, transmitting data wirelessly to an onboard receiver in real time. Tire wear and tread depth can be measured by installing LiDAR or line-scan cameras near the chassis or wheel hubs to scan the tread pattern and calculate wear depth using image recognition algorithms. Tire speed and vibration frequency can be measured by wheel speed sensors installed near the wheel bearings, which generate pulse signals by cutting a magnetic field through the wheel tooth ring to calculate speed; a triaxial accelerometer fixed to the wheel hub or suspension system can monitor the vibration acceleration spectrum in real time and identify abnormal frequencies.

[0038] The precise geographic location information is collected as follows: latitude and longitude coordinates and altitude are obtained by receiving signals through a vehicle-mounted GNSS antenna, combined with real-time dynamic technology for positioning. Road names and landmark information are obtained by sending GNSS coordinates to a map service platform, using reverse geocoding to retrieve road names and district / county information, and then using a POI search interface to find nearby landmarks. The locations of nearby transportation hubs are retrieved based on the location coordinates using the map service interface within a 5-kilometer radius.

[0039] When tire parameters are detected to exceed the preset normal threshold range, the preset threshold adopts a dynamic threshold model. The threshold setting is based on tire model parameters including load index or speed rating, actual usage time and historical health data. A segmented threshold curve model is adopted. The standard threshold is used for the first x years of use, and the safety threshold is increased by n% each year for the xy years of use. After y years, the aging compensation algorithm is activated.

[0040] Because tire pressure tolerance, heat resistance, and structural strength significantly decline with age after a tire has been used for more than a year, the aging compensation algorithm adaptively adjusts the original threshold. The algorithm adjusts the threshold in three steps: First, it quantifies the degree of aging by combining "actual aging duration" and "historical health data" to transform the abstract concept of "aging" into a calculable "aging level" of 1-5, with level 5 representing extremely severe aging. Second, it correlates performance degradation patterns by using a preset "aging level-performance degradation curve" based on tire model parameters. This curve is generated from long-term aging test data of the same tire model. Finally, it corrects the threshold by using "original standard threshold × (1 - performance degradation ratio)" to obtain the new threshold after aging. For example, if the original normal tire pressure threshold for a tire is 2.5-2.8 bar, and level 3 aging corresponds to a 15% degradation, then the new threshold is adjusted to 2.125-2.38 bar, ensuring that the threshold closely matches the actual safety performance boundary of the aging tire.

[0041] Statistical regression algorithms can be used to analyze historical health data of a large number of tires of the same model and usage duration to establish a regression model between "aging duration / aging level" and "threshold correction amount". For example, linear regression can be used to fit the linear relationship between "aging duration - tire pressure threshold correction value" to directly calculate the threshold correction amount for any aging duration. When tire aging performance degradation is not linear, the algorithm will divide the aging stage into multiple intervals, such as y+1-y+3 years, y+3-y+5 years, and determine the threshold correction benchmark value for each interval based on experimental data. Then, the threshold for any aging duration within the interval is calculated by interpolation. Considering individual tire differences, key indicators in the "historical health data", such as tire temperature fluctuation frequency and number of failures, are assigned weights. The final threshold correction magnitude is calculated by weighting to ensure that the correction result is adapted to the actual aging state of each tire.

[0042] The system uses various sensors distributed inside the tire or on the rim to collect various tire parameters in real time and transmit the data to the vehicle's central processing unit (CPU). The CPU, based on the tire's age and current operating conditions, calls upon the appropriate dynamic threshold model to analyze and judge the collected data. If the tire parameters exceed the dynamically adjusted threshold range, the system immediately determines that a tire malfunction has occurred and packages the malfunction information along with the vehicle's location information, sending it to the cloud server via wireless network. Simultaneously, the system continuously optimizes the parameters of the dynamic threshold model based on real-time monitoring data, making it more closely reflect the actual performance changes of the tire.

[0043] To ensure the accuracy and effectiveness of the dynamic threshold model, it needs to be optimized and updated regularly. On one hand, more tire usage data should be collected, including performance data from different brands, models, and usage environments, to enrich the historical health database and provide more data support for model optimization. On the other hand, the dynamic threshold model should be adjusted and improved in light of the development of new materials and processes, as well as updates to industry standards. For example, with the emergence of new rubber materials, the wear resistance and high-temperature resistance of tires have improved, and the corresponding dynamic threshold model needs to be adjusted to adapt to the performance characteristics of tires made of new materials. Through continuous model optimization and updates, the accuracy and reliability of tire fault monitoring can be continuously improved.

[0044] Reference Figure 2 As shown, after receiving tire fault information and location information, the cloud server starts the fault severity assessment model, which specifically compares the deviation of real-time parameters with normal thresholds and calculates the parameter deviation.

[0045] Fault influencing factors include fault duration, vehicle driving status, environmental factors, vehicle model and tire type, and historical fault records. These influencing factors are standardized to obtain correction coefficients. Weights are assigned to each correction coefficient to derive the corrected value of the influencing factor, which can be expressed as:

[0046]

[0047] Where c is the impact factor correction value, u is the impact factor correction coefficient, and q is the weight of each impact factor correction coefficient;

[0048] The risk index is calculated based on the parameter deviation and the preset weights of each parameter, using the following expression:

[0049]

[0050] Where K is the risk index, t is the parameter deviation, w is the weight of each parameter, and c is the adjustment value of the influencing factor. The risk index is determined as follows: a risk index less than 'a' is classified as a minor fault; a risk index greater than 'a' but less than 'b' is classified as a moderate fault; and a risk index greater than 'b' is classified as a severe fault. 'a' and 'b' are preset thresholds obtained by collecting numerous fault cases of tires of the same model and usage scenario. For example, if statistics show that 95% of minor faults have a K value less than 0.3 and 95% of severe faults have a K value greater than 0.7, then 'a' can be initially set to 0.3 and 'b' to 0.7. Simultaneously, the rationality of the thresholds is verified by combining laboratory aging test and fault simulation test data.

[0051] Based on the fault information, location information, and the results of the fault severity model, an assessment report is automatically generated. The assessment report includes: basic information such as vehicle information, fault occurrence time, and location coordinates; fault details such as type, severity level, and parameter deviation; cause speculation such as possible causes based on model analysis; and recommended measures such as emergency handling plan, recommended repair items, and safety precautions.

[0052] By operating the fault severity assessment model, we can achieve a shift from post-event alarms to pre-event predictions, from single fault identification to full lifecycle management, and from isolated data to supply chain data collaboration, thereby reducing safety risks related to tire faults.

[0053] Establish a maintenance service resource database, including: basic information of maintenance service providers, such as company name, contact information, service type, and qualification certification; geographic information, such as the specific address of the service provider, service coverage radius, and location marked by a GIS geographic information system; service capability parameters, such as equipment type, inventory tire models, number of technicians, and qualification level; and dynamic status data, such as real-time busy / idle status, number of currently dispatchable maintenance vehicles, and estimated response time.

[0054] The cloud server automatically filters repair service providers based on tire fault location information. The process involves: filtering based on basic matching criteria, ensuring the service type covers the fault type; and ensuring the service provider inventory includes compatible tire models. For emergency faults, providers with an ETA (Estimated Time of Arrival) within 30 minutes of their current location (based on real-time traffic data and geographical distance) are selected. The filtered results form a list of available repair service resources. This rigorous rule-based approach quickly narrows down the candidate set, providing high-quality input data for the subsequent intelligent matching algorithm. This ensures that recommended repair providers fully meet the fault requirements in terms of geographical scope, service capabilities, and inventory, laying the foundation for accurate service delivery.

[0055] Based on the tire fault severity assessment results and the list of available repair service resources, an intelligent matching algorithm is used to match repair services. The method is as follows: a dynamic weight formula is designed to map the fault severity assessment results to an urgency coefficient; the estimated arrival time is calculated by combining geographical distance and ETA with real-time traffic data and converted into a standardized score; the service response capability is calculated by the cosine similarity between the fault service demand and the repairer's service vector; qualifications and evaluations are standardized into scores based on the repairer's historical ratings; inventory matching degree is based on the quantity of suitable tires in stock or the quantity required, with 0 points for no stock and 1 point for sufficient stock; weights are assigned to each factor, and the matching score is calculated.

[0056] For severe and moderate failures, the system prioritizes matching service providers with the shortest ETA and the highest service capacity, with weighting shifted towards geographical distance and responsiveness. For minor failures, the matching range can be expanded, and service evaluation and price factors can be added. When a service provider accepts an order or its status changes, the system immediately recalculates the matching score of the remaining service providers and dynamically adjusts the list order.

[0057] The platform pushes a list of matched repair service providers to users through multiple channels, including app pop-ups, SMS notifications, and in-vehicle infotainment screen prompts. The user terminal interface displays repair service provider information in a card-style layout. Each card includes the provider's name, actual driving time from the fault location, service rating, key service advantages tags, and buttons for "Select Now" and "View Details." Clicking "View Details" allows users to further view detailed information such as a service item list, past user reviews, and estimated repair cost range.

[0058] Users can select filter criteria at the top of the list page, such as reordering suppliers by distance, highest rating, or lowest price; they can also customize service selections, such as displaying only suppliers that support tire balancing, to narrow down the selection. The filter results refresh in real time, allowing users to quickly locate suppliers that meet their needs. After clicking the "Select Now" button, a confirmation pop-up appears, displaying the selected supplier's name, estimated arrival time, and estimated service cost. After user confirmation, the system sends a service request to the supplier and generates a service order. Simultaneously, users can view the supplier's order acceptance status and the real-time location of the rescue vehicle on the order details page, achieving full visibility into the service progress.

[0059] In severe fault scenarios, if the user's inaction exceeds the system's default response time limit, an automatic selection process is triggered. The system prioritizes the supplier with the highest matching score to perform the service. If multiple suppliers have the same matching score, the selection is based on priority: the supplier closest to the fault location; the supplier with the higher service score; and the supplier with the fastest historical response time. After selection, the system automatically sends a service request to the supplier and informs the user of the automatically selected supplier information and the estimated service start time via the app and SMS, preventing delays in repairs due to user non-action. If the automatically selected supplier is unable to accept the order due to being busy or lacking available rescue vehicles, the system immediately switches to the next supplier according to the matching score order, simultaneously notifying the user of the reason for the switch and the new supplier information. If three consecutive suppliers are unable to accept the order, the system expands the search scope to the surrounding area and re-matches and selects suppliers to ensure smooth service delivery.

[0060] In one specific embodiment, a heavy commercial vehicle was traveling on a certain road when a pressure sensor installed on the right rear wheel detected a sudden drop in tire pressure to 1.8 bar, while the standard tire pressure range is 2.5-2.8 bar. Simultaneously, a temperature sensor reported that the tire temperature had risen to 85°C, exceeding the normal threshold of ≤70°C. A LiDAR scan of the chassis revealed that the tire tread depth was only 1.5 mm, below the legal minimum standard of 1.6 mm. A three-axis accelerometer detected abnormal vibration frequencies. The onboard GNSS antenna used real-time positioning of the vehicle's latitude, longitude, and altitude. Through reverse geocoding on a map service platform, the vehicle's specific location was determined, with a nearby landmark being a service area. The vehicle's central processing unit integrated the sensor data and found that the tire pressure, tire temperature, and wear level all exceeded dynamic threshold ranges. The tire had been used for 4 years, placing it in the xy-year stage, and the current upper limit of the tire pressure threshold was 2.8 × (1 + 5%). 2 =3.09 bar, immediately diagnosed as tire failure.

[0061] The central processing unit packages the fault information (tire pressure 1.8 bar, tire temperature 85℃, wear depth 1.5 mm) with the location information and sends it to the cloud server via a 5G network. The cloud server then activates the fault severity assessment model and calculates the parameter deviations: tire pressure deviation is 0.36, tire temperature deviation is 0.21, and wear deviation is 0.06.

[0062] The following impact factor correction values ​​were determined: Fault duration standardized value 0.2; vehicle driving status 0.6; comprehensive environmental factor standardized value 0.3; vehicle model and tire type coding value 0.8; historical fault record standardized value 0.9. Preset weights were 0.2, 0.3, 0.1, 0.2, and 0.2, respectively, resulting in an impact factor correction value c of 0.59. The risk index was calculated: tire pressure, tire temperature, and wear weights were preset to 0.5, 0.3, and 0.2, respectively, resulting in a risk index K of 0.78. A b value of 0.7 was set, classifying the fault as severe.

[0063] After the system automatically generates an evaluation report, the cloud server filters the repair service resource database based on location information: after filtering according to basic matching conditions, three available repair service resources are obtained. Using an intelligent matching algorithm: fault urgency: severe faults are mapped to an urgency coefficient of 1; geographical distance and ETA standardized score are 0.8; service response capability: the cosine similarity between repairer A's service vector and the demand is 0.9; qualifications and evaluation: repairer A's historical rating is 4.8 stars, with a standardized score of 0.9; inventory matching: there are 5 compatible tires in stock, earning 1 point. Preset weights are 0.4, 0.3, 0.1, 0.1, and 0.1, respectively, resulting in a matching score of 0.92. Repairer A has the highest score and is therefore prioritized by the system.

[0064] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other.

[0065] In conclusion, 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 within the protection scope of the present invention.

Claims

1. A method for real-time tire fault location and repair service matching, characterized in that, It includes an information collection terminal, a fault diagnosis terminal, a report generation terminal, a service filtering terminal, and a service matching terminal, specifically including the following steps: S1. Real-time collection of vehicle tire status parameters and current precise geographical location information; S2. When the tire parameters are detected to exceed the normal threshold range preset by the dynamic threshold model based on the tire model parameters, actual usage time and historical health data, it is determined that the tire has failed and the fault information and location information are sent to the cloud server together. S3. After receiving tire fault information and location information, the cloud server starts the fault severity assessment model to calculate parameter deviation and impact factor correction values, and generates an assessment report by weighting the risk index. S4. Establish a maintenance service resource database. The cloud server filters based on basic matching conditions according to tire fault location information, automatically selects maintenance service providers, and forms a list of available maintenance service resources. S5. Based on the tire failure severity assessment results and the list of available repair service resources, the system uses an intelligent matching algorithm to dynamically calculate the matching score and perform repair service matching. At the same time, when a service provider accepts an order or its status changes, the system immediately recalculates the matching score of the remaining service providers and dynamically adjusts the list order. S6. The platform will send the list of matched repair service providers and related information to the user's terminal. The user can select a provider according to their own needs. If the user does not select one in time, the system will automatically select the provider with the highest matching degree. The fault severity assessment model includes: comparing the deviation of real-time parameters with normal thresholds and calculating the parameter deviation. Fault influencing factors include fault duration, vehicle driving status, environmental factors, vehicle model and tire type, and historical fault records. These influencing factors are standardized to obtain correction coefficients. Weights are assigned to each correction coefficient to derive the corrected value of the influencing factor, which can be expressed as: Where c is the impact factor correction value, u is the impact factor correction coefficient, and q is the weight of each impact factor correction coefficient; The risk index is calculated based on the parameter deviation and the preset weights of each parameter, using the following expression: Where K is the risk index, t is the parameter deviation, w is the weight of each parameter, and c is the impact factor correction value; when the risk index is less than a, it is judged as a minor fault; when the risk index is greater than a and less than b, it is judged as a moderate fault; when the risk index is greater than b, it is judged as a severe fault; where a and b are preset thresholds, obtained by collecting a large number of fault cases of tires of the same model and in the same usage scenario. The assessment report specifically includes: basic information such as vehicle information, time of failure, and location coordinates; failure details such as type, severity level, and parameter deviation; cause speculation such as possible causes based on model analysis; and recommended measures such as emergency handling plan, recommended repair items, and safety precautions.

2. The method for real-time tire fault location and repair service matching as described in claim 1, characterized in that: The vehicle's tire condition parameters and current precise geographic location information include one or more of the following: tire pressure, tire temperature, tire wear, tire speed, tire vibration frequency, and tread depth; the current precise geographic location information includes latitude and longitude coordinates, altitude, road name, landmark information of the area, and location of nearby transportation hubs.

3. The method for real-time tire fault location and repair service matching as described in claim 1, characterized in that: The preset normal threshold is specifically as follows: a dynamic threshold model is adopted, and the threshold is set based on tire model parameters including load index or speed rating, actual usage time and historical health data. A segmented threshold curve model is adopted, with the standard threshold used for the first x years of use, the safety threshold increasing by n% each year for the xy years of use, and the aging compensation algorithm being activated after y years.

4. The method for real-time tire fault location and repair service matching as described in claim 1, characterized in that: The maintenance service resource database includes: basic information of maintenance service providers, including company name, contact information, service type, and qualification certification; geographic information, including the specific address of the service provider, service coverage radius, and location marked by a GIS geographic information system; service capability parameters, including equipment type, inventory tire models, number of technicians, and qualification level; and dynamic status data, including real-time busy / idle status, number of currently dispatchable maintenance vehicles, and estimated response time.

5. The method for real-time tire fault location and repair service matching as described in claim 1, characterized in that: The automatic screening method for repair service providers is as follows: basic matching criteria are used for filtering, the service type must cover the fault type, the service provider's inventory must include the compatible tire model, and for emergency faults, service providers within the set time frame of ETA need to be screened.

6. The method for real-time tire fault location and repair service matching as described in claim 1, characterized in that: The method for matching repair services is as follows: a dynamic weighting formula is designed, which integrates geographical distance and ETA, service response capability, qualifications and evaluation, and inventory matching degree. Weights are set for each factor, and a matching score is calculated. For severe and moderate faults, priority is given to matching service providers with the shortest ETA and the highest service capability, with weights tilted towards geographical distance and response capability. For minor faults, the matching range can be expanded by adding service evaluation and price factors.

Images