Maintenance shop recommendation method and device based on artificial intelligence, equipment and medium

Abstract

The invention provides a maintenance shop recommendation method and device based on artificial intelligence, equipment and a medium, and belongs to the field of artificial intelligence, and the method comprises the steps: obtaining a vehicle damage report of a damaged vehicle, and generating a plurality of candidate maintenance schemes based on the vehicle damage report through a preset maintenance scheme generation model; obtaining a candidate maintenance scheme selected by the user from the plurality of candidate maintenance schemes as a target maintenance scheme, and determining a plurality of candidate repair plants from the repair plant library according to the target maintenance scheme and attribute parameters of each repair plant in the repair plant library; obtaining a maintenance quotation submitted by each candidate repair factory based on the target maintenance scheme; and according to the attribute parameter and the maintenance quotation of each candidate repair factory, generating a recommendation list of the plurality of candidate repair factories, and pushing the recommendation list to the user. According to the method, the efficiency and the accuracy of selecting the maintenance factory with high cost performance by the user are greatly improved. The method can be applied to the financial field, and improves the user satisfaction of financial claim settlement products.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based repair shop recommendation method, device, equipment and medium. Background Art

[0002] As the number of cars increases, the density of vehicles on urban roads is increasing, and traffic accidents are also on the rise. In the financial sector, after a vehicle accident, the main challenges faced by users are the difficulty in quickly determining repair costs and choosing a suitable repair shop. Currently, insurance companies typically recommend designated or partnered repair shops to car owners based on their preferences and partnerships, allowing them to quickly find a suitable repair location. However, the recommendations for nearby repair shops during auto insurance claims processing lack personalization and intelligence, resulting in increased repair costs for users' vehicles and making it difficult for users to choose a cost-effective repair shop.

[0003] Therefore, how to recommend cost-effective repair shops to users is an urgent problem that needs to be solved. Summary of the Invention

[0004] The main purpose of this application is to provide an artificial intelligence-based repair shop recommendation method, device, equipment and medium, aiming to recommend cost-effective repair shops to users.

[0005] In a first aspect, the present application provides a repair shop recommendation method based on artificial intelligence, the method comprising the following steps:

[0006] Obtaining a vehicle damage report of a damaged vehicle, and generating a plurality of candidate repair plans based on the vehicle damage report using a preset repair plan generation model;

[0007] Acquire a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determine a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and attribute parameters of each repair shop in the repair shop library;

[0008] Obtaining a repair quotation submitted by each candidate repair shop based on the target repair plan;

[0009] A recommendation list of the plurality of candidate repair shops is generated according to the attribute parameters of each candidate repair shop and the repair quotation, and the recommendation list is pushed to the user.

[0010] In a second aspect, the present application further provides an artificial intelligence-based repair shop recommendation device, the artificial intelligence-based repair shop recommendation device comprising an acquisition module, a generation module, and a determination module, wherein:

[0011] The acquisition module is used to obtain a vehicle damage report of a damaged vehicle;

[0012] The generating module is configured to generate a plurality of candidate repair plans based on the vehicle damage report by using a preset repair plan generating model;

[0013] The determining module is configured to obtain a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determine a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and attribute parameters of each repair shop in the repair shop library;

[0014] The acquisition module is further configured to acquire a repair quotation submitted by each candidate repair shop based on the target repair plan;

[0015] The generating module is further configured to generate a recommendation list of the plurality of candidate repair shops according to the attribute parameters of each candidate repair shop and the repair quotation, and push the recommendation list to the user.

[0016] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the above-mentioned artificial intelligence-based repair shop recommendation method are implemented.

[0017] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based repair shop recommendation method are implemented.

[0018] The present application provides a method, apparatus, device, and medium for recommending repair shops based on artificial intelligence. The method obtains a vehicle damage report for a damaged vehicle and generates multiple candidate repair plans based on the vehicle damage report using a preset repair plan generation model. The method then obtains a user-selected candidate repair plan from the multiple candidate repair plans as a target repair plan, and determines multiple candidate repair shops from a repair shop library based on the target repair plan and attribute parameters of each repair shop in the repair shop library. The method obtains repair quotations submitted by each candidate repair shop based on the target repair plan, and generates a recommendation list of multiple candidate repair shops based on the attribute parameters and repair quotations of each candidate repair shop, and pushes the recommendation list to the user. The method obtains a user-selected candidate repair plan as a target repair plan, and accurately determines multiple candidate repair shops based on the target repair plan and the attribute parameters of each repair shop. The method then obtains repair quotations submitted by each candidate repair shop based on the target repair plan, and accurately generates a recommendation list of multiple candidate repair shops based on the repair quotations and attribute parameters of each candidate repair shop, and pushes the recommendation list to the user, greatly improving the efficiency and accuracy of users in selecting cost-effective repair shops. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A flowchart of a repair shop recommendation method based on artificial intelligence provided in an embodiment of the present application;

[0021] Figure 2 for Figure 1 A flowchart of the sub-steps of the AI-based repair shop recommendation method;

[0022] Figure 3 A schematic block diagram of an artificial intelligence-based repair shop recommendation method provided in an embodiment of the present application;

[0023] Figure 4 for Figure 3 A schematic block diagram of the submodules of the repair shop recommendation method based on artificial intelligence;

[0024] Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0025] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0028] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0029] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0030] As the number of cars increases, the density of vehicles on urban roads is increasing, and traffic accidents are also on the rise. In the financial sector, after a vehicle accident, the main challenges faced by users are the difficulty in quickly determining repair costs and choosing a suitable repair shop. Currently, insurance companies typically recommend designated or partnered repair shops to car owners based on their preferences and partnerships, allowing them to quickly find a suitable repair location. However, the recommendations for nearby repair shops during auto insurance claims processing lack personalization and intelligence, resulting in increased repair costs for users' vehicles and making it difficult for users to choose a cost-effective repair shop.

[0031] To address the aforementioned issues, embodiments of the present application provide an artificial intelligence-based repair shop recommendation method, apparatus, device, and medium. The artificial intelligence-based repair shop recommendation method includes obtaining a vehicle damage report for a damaged vehicle and generating multiple candidate repair plans based on the vehicle damage report using a preset repair plan generation model; obtaining a user-selected candidate repair plan from the multiple candidate repair plans as a target repair plan, and determining multiple candidate repair shops from a repair shop library based on the target repair plan and attribute parameters of each repair shop in the repair shop library; obtaining a repair quote submitted by each candidate repair shop based on the target repair plan; and generating a recommended list of multiple candidate repair shops based on the attribute parameters and repair quote of each candidate repair shop, and pushing the recommended list to the user.

[0032] Among them, the artificial intelligence-based repair shop recommendation method can be applied to computer devices, which can be electronic devices such as mobile phones, tablets, laptops, desktop computers, personal digital assistants and wearable devices.

[0033] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0034] Please refer to Figure 1 , Figure 1 A flowchart of a repair shop recommendation method based on artificial intelligence is provided in an embodiment of the present application.

[0035] like Figure 1 As shown, the repair shop recommendation method based on artificial intelligence includes steps S101 to S104.

[0036] Step S101: Obtain a vehicle damage report of a damaged vehicle, and generate a plurality of candidate repair plans based on the vehicle damage report using a preset repair plan generation model.

[0037] The vehicle damage report is the damage information of the vehicle, and includes at least the damage location, damage type, damage extent, repair suggestions, damage area, repair difficulty, repair time, etc. The repair plan includes the repair method and repair cost of the damaged vehicle.

[0038] In some embodiments, as Figure 2 As shown, the step S101 includes sub-steps S1011 to S1012.

[0039] Sub-step S1011: Obtain accident information of the damaged vehicle, where the accident information includes a photo of the damaged vehicle and accident description information.

[0040] Among them, the accident information includes photos of the damaged vehicle and accident description information. The photos of the damaged vehicle include but are not limited to photos of the damaged parts of the damaged vehicle and photos of the entire vehicle. The accident description information includes the impact position and driving speed of the damaged vehicle during the accident, etc.

[0041] In some embodiments, a user-uploaded photo of the damaged vehicle and a description of the accident are obtained. For example, the user uses a mobile terminal to capture a photo of the damaged vehicle, enters the accident description on the mobile terminal, and then uploads the photo and accident description to a computer device. The mobile terminal can be selected based on actual circumstances and is not specifically limited in this embodiment of the application. For example, the mobile terminal can be a mobile phone, tablet computer, etc.

[0042] Sub-step S1012: generating a vehicle damage report for the damaged vehicle based on the accident information using a preset damage report generation model, wherein the preset damage report generation model is a pre-trained neural network model.

[0043] The preset damage report generation model is a pre-trained neural network model, which includes but is not limited to a convolutional neural network model and a recurrent convolutional neural network model.

[0044] In some embodiments, a first sample data set is obtained, the first sample data set including a plurality of first sample data, the first sample data including sample accident information and annotated vehicle damage reports corresponding to the sample accident information. A first sample data is selected from the first sample data set as target first sample data, the sample accident information in the target first sample data is input into a preset neural network model for damage report recognition, and a predicted vehicle damage report is obtained. Based on the predicted vehicle damage report and the annotated vehicle damage report, it is determined whether the neural network model has converged. If the neural network model has not converged, the step of selecting a first sample data from the first sample data set as the target first sample data is continued until the neural network model converges, thereby obtaining a preset damage report generation model.

[0045] In some embodiments, the method for determining whether the neural network model has converged based on the predicted vehicle damage report and the annotated vehicle damage report can be: determining the loss value of the neural network model based on the predicted vehicle damage report and the annotated vehicle damage report, if the loss value is less than or equal to a preset loss value, determining that the neural network model has converged; if the loss value is greater than the preset loss value, determining that the neural network model has not converged. Among them, the preset loss value can be set according to actual conditions, and the embodiments of the present application do not specifically limit this. For example, the preset loss value can be set to 0.02.

[0046] In some embodiments, the loss value of the neural network model can be determined based on the predicted vehicle damage report and the labeled vehicle damage report by performing cosine similarity calculation on the predicted vehicle damage report and the labeled vehicle damage report to obtain a cosine similarity value, and subtracting the cosine similarity value from 1 as the loss value of the neural network model.

[0047] In some embodiments, the accident information is subjected to a damage report generation process using the preset damage report generation model to generate a vehicle damage report for the damaged vehicle. The preset damage report generation model can accurately generate a vehicle damage report for the damaged vehicle.

[0048] In some embodiments, a preset repair solution generation model is used to match vehicle damage reports with vehicle damage repair options to obtain multiple candidate repair options, and the repair cost of each candidate repair option is obtained. By matching vehicle damage reports with a preset repair solution generation model, multiple candidate vehicle repair options can be accurately obtained.

[0049] It should be noted that the preset maintenance plan generation model includes but is not limited to a neural network model, a linear regression model, a decision tree algorithm, a random forest algorithm, and the like.

[0050] In some embodiments, when the preset repair solution generation model is a neural network model, the vehicle damage report is input into the neural network model for identification to obtain multiple candidate repair solutions. The neural network model is trained based on the second sample dataset. The training of the neural network model can refer to the training process of the damage report generation model described above and is not further described here.

[0051] In some embodiments, the method for obtaining the maintenance cost of each candidate maintenance method can be: obtaining the unit price of each spare part and the unit price of labor cost, adding the unit price of each spare part and the total labor cost in each candidate maintenance method, and obtaining the maintenance cost of each candidate maintenance method.

[0052] Step S102: obtaining a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determining a plurality of candidate repair shops from the repair shop library according to the target maintenance plan and attribute parameters of each repair shop in the repair shop library.

[0053] In some embodiments, multiple candidate repair plans are sent to a mobile terminal used by a user. After receiving each candidate repair plan, the mobile terminal displays the repair method and repair cost of each candidate repair plan on a display screen. After reviewing each candidate repair plan, the user selects a candidate repair plan. The mobile terminal sends the candidate repair plan selected by the user to a computer device and uses the candidate repair plan as the target repair plan.

[0054] In some embodiments, a first recommendation score is determined for each repair shop based on the target repair plan and the business area in each repair shop's attribute parameters; a second recommendation score is determined for each repair shop based on the attribute parameters of each repair shop; the first and second recommendation scores of each repair shop are added together to obtain a target recommendation score for each repair shop; and repair shops in the repair shop database whose target recommendation scores are greater than or equal to a preset recommendation score are determined as candidate repair shops. The preset recommendation score can be set based on actual circumstances and is not specifically limited in this embodiment of the present application. For example, the preset recommendation score can be set to 80 points.

[0055] In some embodiments, based on the target maintenance plan and the business field in the attribute parameters of each repair shop, the method for determining the first recommendation score of each repair shop can be: determining the business field of the maintenance method in the target maintenance plan, performing similarity calculation on the business field of the maintenance method and the business field of the repair shop to obtain a business similarity value, performing weighted processing on the business similarity value and the sixth preset weight coefficient, and using the obtained weight parameter as the first recommendation score. Among them, the sixth preset weight coefficient can be set according to actual conditions, and the embodiment of the present application does not make specific restrictions on this. By performing similarity calculation on the business field of the maintenance method and the business field of the repair shop, the first recommendation score of each repair shop can be accurately obtained.

[0056] In some embodiments, the second recommendation score for each repair shop can be determined based on the attribute parameters of each repair shop by: weighting the distance data of each repair shop according to a first preset weight coefficient to obtain a first weight parameter for each repair shop; weighting the service quality data of each repair shop according to a second preset weight coefficient to obtain a second weight parameter for each repair shop; weighting the price data of each repair shop according to a third preset weight coefficient to obtain a third weight parameter for each repair shop; superimposing the first, second, and third weight parameters of each repair shop to obtain a target weight parameter for each repair shop; and determining the second recommendation score for each repair shop using the target weight parameter for each repair shop. The first, second, and third preset weight coefficients can be set based on actual circumstances and are not specifically limited in this embodiment of the present application. For example, the first preset weight coefficient can be set to 0.2, the second preset weight coefficient can be set to 0.5, and the third preset weight coefficient can be set to 0.3. By weighting the attribute parameters of each repair shop, the second recommendation score for each repair shop can be accurately obtained.

[0057] In some embodiments, after obtaining the target recommendation score of each repair shop, the repair shops having the target recommendation score greater than or equal to the preset recommendation score are determined as candidate repair shops.

[0058] In some embodiments, after obtaining the target recommendation score for each repair shop, the repair shops are sorted according to the target recommendation score to obtain a repair shop queue. A preset number of repair shops at the front of the queue are selected from the repair shop queue to obtain multiple candidate repair shops. The preset number can be set based on actual conditions and is not specifically limited in this embodiment of the present application. For example, the preset number can be set to 5.

[0059] Step S103: Obtain a repair quotation submitted by each candidate repair shop based on the target repair plan.

[0060] A target repair plan is sent to each candidate repair shop. After receiving the target repair plan, each candidate repair shop formulates a repair quote and sends the quote to a computer device to obtain the repair quote submitted by each candidate repair shop based on the target repair plan. By obtaining the repair quotes of each candidate repair shop, users can effectively select the most cost-effective repair shop.

[0061] Step S104: Generate a recommendation list of the plurality of candidate repair shops based on the attribute parameters of each candidate repair shop and the repair quotation, and push the recommendation list to the user.

[0062] The recommendation list includes a plurality of candidate repair shops, and the candidate repair shops that are ranked higher in the recommendation list have higher cost-effectiveness.

[0063] In some embodiments, a first recommendation score determined by the attribute parameters of each candidate repair shop is multiplied by a fourth preset weight coefficient to obtain a first cost-effectiveness score for each candidate repair shop; a fifth preset weight coefficient is multiplied by the repair quote of each candidate repair shop to obtain a second cost-effectiveness score for each candidate repair shop; the first cost-effectiveness score and the second cost-effectiveness score of each candidate repair shop are added to obtain a target cost-effectiveness score for each candidate repair shop; and each candidate repair shop is ranked according to its target cost-effectiveness score to obtain a recommended list of multiple candidate repair shops. The fourth preset weight coefficient and the fifth preset weight coefficient can be set according to actual conditions and are not specifically limited in this embodiment of the present application. By calculating the target cost-effectiveness score for each candidate repair shop and then ranking the multiple candidate repair shops based on the target cost-effectiveness score, a recommended list of multiple candidate repair shops can be accurately obtained, greatly improving the efficiency and accuracy of repair shop recommendations.

[0064] In some embodiments, after obtaining a recommendation list of multiple candidate repair shops, the recommendation list is sent to the user's mobile terminal so that the user can access the recommendation list. By sending the recommendation list to the user's mobile terminal, the efficiency and accuracy of the user's selection of a cost-effective repair shop can be effectively improved.

[0065] In some embodiments, insurance information for the damaged vehicle is obtained; based on the insurance information and the vehicle damage report, a claim settlement recommendation is provided to the user. The claim settlement recommendation includes at least one of the insurance claim amount and whether the repair is self-funded. Using the insurance information and the vehicle damage report, accurate claim settlement recommendations can be provided to the user, effectively preventing unnecessary losses.

[0066] It should be noted that the insurance information includes the insurance name, insurance terms and insurance contract, etc.

[0067] In some embodiments, based on the insurance information and vehicle damage report, a method for recommending a claim settlement suggestion to a user may include: determining the repair cost of the damaged vehicle based on the vehicle damage report, determining the insurance claim amount and the out-of-pocket amount based on the accident description and insurance information; and recommending a claim settlement suggestion to the user based on the insurance claim amount and the out-of-pocket amount. Claim settlement suggestions may be recommended to the user by calculating the insurance claim amount and the out-of-pocket amount.

[0068] In some embodiments, a method for recommending a claim settlement suggestion to a user based on the insurance claim amount and the self-payment amount may be as follows: if the insurance claim amount is lower than the insurance deductible, a self-payment suggestion is recommended to the user; and if the difference between the self-payment amount and the insurance claim amount is greater than or equal to a preset difference, a claim settlement suggestion is recommended to the user.

[0069] In some embodiments, if the user chooses an insurance claim settlement plan, a vehicle damage report is sent to the insurance company so that the insurance company can make insurance claims in a timely manner, thereby greatly improving the efficiency of insurance claims and improving user satisfaction with the insurance company.

[0070] The artificial intelligence-based repair shop recommendation method provided in the above embodiment obtains a vehicle damage report of a damaged vehicle and generates multiple candidate repair plans based on the vehicle damage report using a preset repair plan generation model; obtains a user-selected candidate repair plan from the multiple candidate repair plans as a target repair plan, and determines multiple candidate repair shops from the repair shop library based on the target repair plan and the attribute parameters of each repair shop in the repair shop library; obtains the repair quotes submitted by each candidate repair shop based on the target repair plan; generates a recommendation list of multiple candidate repair shops based on the attribute parameters and repair quotes of each candidate repair shop, and pushes the recommendation list to the user. In this application, by obtaining the user-selected candidate repair plan as the target repair plan and accurately determining multiple candidate repair shops based on the target repair plan and the attribute parameters of each repair shop; then obtaining the repair quotes submitted by each candidate repair shop based on the target repair plan, and accurately generating a recommendation list of multiple candidate repair shops based on the repair quotes and attribute parameters of each candidate repair shop, and pushing the recommendation list to the user, the efficiency and accuracy of the user's selection of cost-effective repair shops is greatly improved.

[0071] See also Figure 3 , Figure 3 A schematic block diagram of an artificial intelligence-based repair shop recommendation device provided in an embodiment of the present application.

[0072] like Figure 3 As shown, the repair shop recommendation device 200 based on artificial intelligence includes an acquisition module 210, a generation module 220 and a determination module 230, wherein:

[0073] The acquisition module 210 is used to obtain a vehicle damage report of a damaged vehicle;

[0074] The generating module 220 is configured to generate a plurality of candidate repair plans based on the vehicle damage report by using a preset repair plan generation model;

[0075] The determining module 230 is configured to obtain a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determine a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and attribute parameters of each repair shop in the repair shop library;

[0076] The acquisition module 210 is further configured to acquire a repair quotation submitted by each candidate repair shop based on the target repair plan;

[0077] The generating module 220 is further configured to generate a recommendation list of the plurality of candidate repair shops according to the attribute parameters of each candidate repair shop and the repair quotation, and push the recommendation list to the user.

[0078] In some embodiments, as Figure 4 As shown, the acquisition module 210 includes an acquisition submodule 211 and a generation submodule 212, wherein:

[0079] The acquisition submodule 211 is configured to acquire accident information of the damaged vehicle, wherein the accident information includes a photo of the damaged vehicle and accident description information;

[0080] The generating submodule 212 is configured to generate a vehicle damage report of the damaged vehicle based on the accident information using a preset damage report generating model, wherein the preset damage report generating model is a pre-trained neural network model.

[0081] In some embodiments, the generating module 220 is further configured to:

[0082] Matching the vehicle damage report with a vehicle damage repair method using the preset repair plan generation model to obtain multiple candidate repair methods;

[0083] Get the repair cost of each candidate repair method.

[0084] In some embodiments, the determining module 230 is further configured to:

[0085] determining a first recommendation score for each of the repair shops according to the target maintenance plan and the business field in the attribute parameters of each of the repair shops;

[0086] determining a second recommendation score for each of the repair shops according to the attribute parameters of each of the repair shops;

[0087] performing an addition operation on the first recommendation score and the second recommendation score of each repair shop to obtain a target recommendation score for each repair shop;

[0088] The repair shops in the repair shop database whose target recommendation scores are greater than or equal to the preset recommendation scores are determined as candidate repair shops.

[0089] In some embodiments, the determining module 230 is further configured to:

[0090] performing weighted processing on the distance data of each of the repair shops according to a first preset weight coefficient to obtain a first weight parameter for each of the repair shops;

[0091] performing weighted processing on the service quality data of each of the repair shops according to a second preset weight coefficient to obtain a second weight parameter for each of the repair shops;

[0092] performing weighted processing on the price data of each of the repair shops according to a third preset weight coefficient to obtain a third weight parameter for each of the repair shops;

[0093] superimposing the first weight parameter, the second weight parameter, and the third weight parameter of each repair shop to obtain a target weight parameter of each repair shop;

[0094] The target weight parameter of each repair shop is used to determine a second recommendation score for each repair shop.

[0095] In some embodiments, the generating module 220 is further configured to:

[0096] performing a multiplication operation on the first recommendation score determined by the attribute parameters of each candidate repair shop according to the fourth preset weight coefficient to obtain a first cost-effectiveness score for each candidate repair shop;

[0097] multiplying the repair price quote of each candidate repair shop by the fifth preset weight coefficient to obtain a second cost-performance score for each candidate repair shop;

[0098] performing an addition operation on the first cost-performance score and the second cost-performance score of each candidate repair shop respectively to obtain a target cost-performance score for each candidate repair shop;

[0099] Each candidate repair shop is sorted according to the target cost-performance score of each candidate repair shop to obtain a recommendation list of multiple candidate repair shops.

[0100] In some embodiments, the repair shop recommendation device 200 based on artificial intelligence is further configured to:

[0101] Obtaining insurance information of the damaged vehicle;

[0102] Based on the insurance information and the vehicle damage report, a claim settlement suggestion is recommended to the user, wherein the claim settlement suggestion includes at least one of the insurance claim amount and whether to repair at one's own expense.

[0103] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned artificial intelligence-based repair shop recommendation device can refer to the corresponding process in the aforementioned artificial intelligence-based repair shop recommendation method embodiment, and will not be repeated here.

[0104] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0105] like Figure 5As shown, the computer device 300 includes a processor 302 and a memory 303 connected via a system bus 301 , wherein the memory 303 may include a storage medium and an internal memory.

[0106] The storage medium may store a computer program including program instructions, which, when executed, may cause the processor to execute any one of the repair shop recommendation methods based on artificial intelligence.

[0107] The processor 302 is used to provide computing and control capabilities and support the operation of the entire computer device.

[0108] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any one of the repair shop recommendation methods based on artificial intelligence.

[0109] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0110] It should be understood that the processor 302 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0111] In one embodiment, the processor 302 is configured to execute a computer program stored in a memory to implement the following steps:

[0112] Obtaining a vehicle damage report of a damaged vehicle, and generating a plurality of candidate repair plans based on the vehicle damage report using a preset repair plan generation model;

[0113] Acquire a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determine a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and attribute parameters of each repair shop in the repair shop library;

[0114] Obtaining a repair quotation submitted by each candidate repair shop based on the target repair plan;

[0115] A recommendation list of the plurality of candidate repair shops is generated according to the attribute parameters of each candidate repair shop and the repair quotation, and the recommendation list is pushed to the user.

[0116] In one embodiment, when obtaining the vehicle damage report of the damaged vehicle, the processor 302 is configured to:

[0117] Obtaining accident information of the damaged vehicle, the accident information including a photo of the damaged vehicle and accident description information;

[0118] A vehicle damage report of the damaged vehicle is generated based on the accident information through a preset damage report generation model, and the preset damage report generation model is a pre-trained neural network model.

[0119] In one embodiment, when the candidate repair plans include a repair method and a repair cost, and the processor 302 generates multiple candidate repair plans based on the vehicle damage report using a preset repair plan generation model, it is configured to:

[0120] Matching the vehicle damage report with a vehicle damage repair method using the preset repair plan generation model to obtain multiple candidate repair methods;

[0121] Get the repair cost of each candidate repair method.

[0122] In one embodiment, when determining a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and the attribute parameters of each repair shop in the repair shop library, the processor 302 is configured to:

[0123] determining a first recommendation score for each of the repair shops according to the target maintenance plan and the business field in the attribute parameters of each of the repair shops;

[0124] determining a second recommendation score for each of the repair shops according to the attribute parameters of each of the repair shops;

[0125] performing an addition operation on the first recommendation score and the second recommendation score of each repair shop to obtain a target recommendation score for each repair shop;

[0126] The repair shops in the repair shop database whose target recommendation scores are greater than or equal to the preset recommendation scores are determined as candidate repair shops.

[0127] In one embodiment, the attribute parameters include distance data, service quality data, and price data; when determining the second recommendation score for each repair shop based on the attribute parameters of each repair shop, the processor 302 is configured to:

[0128] performing weighted processing on the distance data of each of the repair shops according to a first preset weight coefficient to obtain a first weight parameter for each of the repair shops;

[0129] performing weighted processing on the service quality data of each of the repair shops according to a second preset weight coefficient to obtain a second weight parameter for each of the repair shops;

[0130] performing weighted processing on the price data of each of the repair shops according to a third preset weight coefficient to obtain a third weight parameter for each of the repair shops;

[0131] superimposing the first weight parameter, the second weight parameter, and the third weight parameter of each repair shop to obtain a target weight parameter of each repair shop;

[0132] The target weight parameter of each repair shop is used to determine a second recommendation score for each repair shop.

[0133] In one embodiment, when generating the recommendation list of the plurality of candidate repair shops based on the attribute parameters of each candidate repair shop and the repair quotation, the processor 302 is configured to implement:

[0134] performing a multiplication operation on the first recommendation score determined by the attribute parameters of each candidate repair shop according to the fourth preset weight coefficient to obtain a first cost-effectiveness score for each candidate repair shop;

[0135] multiplying the repair price quote of each candidate repair shop by the fifth preset weight coefficient to obtain a second cost-performance score for each candidate repair shop;

[0136] performing an addition operation on the first cost-performance score and the second cost-performance score of each candidate repair shop respectively to obtain a target cost-performance score for each candidate repair shop;

[0137] Each candidate repair shop is sorted according to the target cost-performance score of each candidate repair shop to obtain a recommendation list of multiple candidate repair shops.

[0138] In one embodiment, after pushing the recommendation list to the user, the processor 302 is further configured to:

[0139] Obtaining insurance information of the damaged vehicle;

[0140] Based on the insurance information and the vehicle damage report, a claim settlement suggestion is recommended to the user, wherein the claim settlement suggestion includes at least one of the insurance claim amount and whether to repair at one's own expense.

[0141] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the computer equipment described above can refer to the corresponding process in the aforementioned embodiment of the artificial intelligence-based repair shop recommendation method, and will not be repeated here.

[0142] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the artificial intelligence-based repair shop recommendation method of the present application.

[0143] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0144] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0145] Blockchain, as used in this article, refers to a novel application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each block contains information about a batch of online transactions, used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0146] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0147] It should also be understood that the term "and / or" used in this specification refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0148] The serial numbers of the embodiments of the present application are for descriptive purposes only and do not represent the merits of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A repair shop recommendation method based on artificial intelligence, characterized in that: include: Obtaining a vehicle damage report of a damaged vehicle, and generating a plurality of candidate repair plans based on the vehicle damage report using a preset repair plan generation model; Acquire a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determine a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and attribute parameters of each repair shop in the repair shop library; Obtaining a repair quotation submitted by each candidate repair shop based on the target repair plan; A recommendation list of the plurality of candidate repair shops is generated according to the attribute parameters of each candidate repair shop and the repair quotation, and the recommendation list is pushed to the user.

2. The repair shop recommendation method based on artificial intelligence according to claim 1, characterized in that: Obtaining a vehicle damage report of a damaged vehicle includes: Obtaining accident information of the damaged vehicle, the accident information including a photo of the damaged vehicle and accident description information; A vehicle damage report of the damaged vehicle is generated based on the accident information through a preset damage report generation model, and the preset damage report generation model is a pre-trained neural network model.

3. The repair shop recommendation method based on artificial intelligence according to claim 1, characterized in that: The candidate maintenance plan includes maintenance method and maintenance cost; The generating of a plurality of candidate repair plans based on the vehicle damage report by using a preset repair plan generation model includes: Matching the vehicle damage report with a vehicle damage repair method using the preset repair plan generation model to obtain multiple candidate repair methods; Get the repair cost of each candidate repair method.

4. The repair shop recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of determining a plurality of candidate repair shops from the repair shop library according to the target repair plan and the attribute parameters of each repair shop in the repair shop library comprises: determining a first recommendation score for each of the repair shops according to the target maintenance plan and the business field in the attribute parameters of each of the repair shops; determining a second recommendation score for each of the repair shops according to the attribute parameters of each of the repair shops; performing an addition operation on the first recommendation score and the second recommendation score of each repair shop to obtain a target recommendation score for each repair shop; The repair shops in the repair shop database whose target recommendation scores are greater than or equal to the preset recommendation scores are determined as candidate repair shops.

5. The repair shop recommendation method based on artificial intelligence according to claim 1, characterized in that: The attribute parameters include distance data, service quality data and price data; Determining a second recommendation score for each repair shop based on the attribute parameters of each repair shop includes: performing weighted processing on the distance data of each of the repair shops according to a first preset weight coefficient to obtain a first weight parameter for each of the repair shops; performing weighted processing on the service quality data of each of the repair shops according to a second preset weight coefficient to obtain a second weight parameter for each of the repair shops; performing weighted processing on the price data of each of the repair shops according to a third preset weight coefficient to obtain a third weight parameter for each of the repair shops; superimposing the first weight parameter, the second weight parameter, and the third weight parameter of each repair shop to obtain a target weight parameter of each repair shop; The target weight parameter of each repair shop is used to determine a second recommendation score for each repair shop.

6. The repair shop recommendation method based on artificial intelligence according to claim 4, characterized in that: Generating a recommendation list of the plurality of candidate repair shops according to the attribute parameters of each candidate repair shop and the repair quotation includes: performing a multiplication operation on the first recommendation score determined by the attribute parameters of each candidate repair shop according to the fourth preset weight coefficient to obtain a first cost-effectiveness score for each candidate repair shop; multiplying the repair price quote of each candidate repair shop by the fifth preset weight coefficient to obtain a second cost-performance score for each candidate repair shop; performing an addition operation on the first cost-performance score and the second cost-performance score of each candidate repair shop respectively to obtain a target cost-performance score for each candidate repair shop; Each candidate repair shop is sorted according to the target cost-performance score of each candidate repair shop to obtain a recommendation list of multiple candidate repair shops.

7. The repair shop recommendation method based on artificial intelligence according to any one of claims 1 to 5, characterized in that: After pushing the recommendation list to the user, the method further includes: Obtaining insurance information of the damaged vehicle; Based on the insurance information and the vehicle damage report, a claim settlement suggestion is recommended to the user, wherein the claim settlement suggestion includes at least one of the insurance claim amount and whether to repair at one's own expense.

8. A repair shop recommendation method based on artificial intelligence, characterized in that: The repair shop recommendation device based on artificial intelligence includes an acquisition module, a generation module and a determination module, wherein: The acquisition module is used to obtain a vehicle damage report of a damaged vehicle; The generating module is configured to generate a plurality of candidate repair plans based on the vehicle damage report by using a preset repair plan generating model; The determining module is configured to obtain a candidate maintenance plan selected by the user from the plurality of candidate maintenance plans as a target maintenance plan, and determine a plurality of candidate repair shops from the repair shop library based on the target maintenance plan and attribute parameters of each repair shop in the repair shop library; The acquisition module is further configured to acquire a repair quotation submitted by each candidate repair shop based on the target repair plan; The generating module is further configured to generate a recommendation list of the plurality of candidate repair shops according to the attribute parameters of each candidate repair shop and the repair quotation, and push the recommendation list to the user.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the repair shop recommendation method based on artificial intelligence are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the repair shop recommendation method based on artificial intelligence as claimed in any one of claims 1 to 7 are implemented.

Images