Data processing method and device for vehicle maintenance quotation

Abstract

The invention provides a data processing method and device for vehicle maintenance quotation, and the method comprises the steps: receiving accident information data, uploaded by any user side, of a vehicle accident, and the accident information data at least comprise accident description text data, a vehicle model and vehicle position data; determining a target replacement and repair accessory list according to the accident description text data, the trained text classification model and the corresponding historical accident description text data; determining position data of the target maintenance point according to the vehicle position data; inputting the position data of the target maintenance point, the vehicle model and the target replacement and repair accessory list into a trained replacement and repair cost quotation model for processing to obtain a replacement and repair accessory loss estimation amount list; and outputting the replacement and repair accessory loss estimation amount list to the user side, so that the error rate of subsequent vehicle maintenance quotation is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle maintenance technology, and in particular to a data processing method and device for vehicle maintenance quotation. Background Art

[0002] The vehicle parts damage estimate list refers to the list of items and costs required to repair the vehicle listed by the insurance company based on the results of on-site inspection and diagnosis when the vehicle is involved in an accident or damage. This list details the parts that need to be replaced and their costs, repair costs and other related costs, so as to facilitate the push of subsequent vehicle repair quotes.

[0003] In the prior art, traditional vehicle repair quotes are mainly obtained by guiding customers to take photos of the accident scene and the accident vehicle. The data center automatically identifies the damaged parts and the degree of damage of the vehicle based on the photos, and intelligently pushes the vehicle repair quote based on the current parts replacement cost and labor time expenses.

[0004] However, in the prior art, by guiding customers to take photos of the accident scene and the accident vehicle, the data center automatically identifies the damaged parts of the vehicle and the degree of damage based on the photos. However, photos with low image quality are prone to identification bias, which increases the error rate of subsequent vehicle repair quotations. Summary of the invention

[0005] The present application provides a data processing method and device for vehicle repair quotation, so as to solve the problem that when guiding customers to take photos of the accident scene and the accident vehicle and the data center automatically identifies the damaged parts of the vehicle and the degree of damage based on the photos, photos with low image quality are prone to identification deviations, thereby increasing the error rate of subsequent vehicle repair quotation.

[0006] In a first aspect, the present application provides a data processing method for vehicle maintenance quotation, which is applied to a server and includes:

[0007] Receiving accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data;

[0008] Inputting the accident description text data into a trained text classification model for processing to obtain accident feature data;

[0009] Retrieving all historical accident cases, and inputting the historical accident description text data corresponding to each historical accident case into the trained text classification model for processing to obtain corresponding historical accident feature data;

[0010] Calculating the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data;

[0011] Determining a preset number of target historical accident cases from all the historical accident cases according to the similarities;

[0012] Determine all replacement parts before a preset percentage according to the historical replacement parts list of each target historical accident case to obtain a target replacement parts list;

[0013] Determining the location data of the target maintenance point according to the vehicle location data;

[0014] Inputting the location data of the target maintenance point, the vehicle model, and the target replacement parts list into the trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list;

[0015] The list of estimated damage amounts of replacement parts is output to the user terminal.

[0016] In one possible design, the training process of the text classification model includes: obtaining multiple first historical sample data corresponding to each historical accident case, wherein the multiple first historical sample data at least include a historical replacement parts list and corresponding historical accident description text data; classifying each historical replacement parts list according to the same parts catalog to obtain multiple categories of historical replacement parts lists; determining all historical accident description text data corresponding to each category of historical replacement parts list; and inputting all historical accident description text data into the created text classification model for training to obtain a trained text classification model.

[0017] In one possible design, the training process of the replacement cost quotation model includes: obtaining multiple second historical sample data corresponding to each historical accident case, wherein the multiple second historical sample data include multiple replacement information data; inputting the multiple replacement information data into a preset replacement cost quotation model for training to obtain a trained replacement cost quotation model.

[0018] In a possible design, the similarity is the Euclidean distance; accordingly, the calculation formula for calculating the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data includes:

[0019]

[0020] Where d is the Euclidean distance; is the i-th dimension coordinate of the vector corresponding to the accident characteristic data; is the i-th dimension coordinate of the vector corresponding to the historical accident characteristic data.

[0021] In one possible design, determining the location data of the target maintenance point based on the vehicle location data includes: converting the vehicle location data into longitude and latitude coordinates; querying all maintenance points within a preset range based on the longitude and latitude coordinates; selecting the maintenance point that has processed the vehicle model the most times from all the maintenance points as the target maintenance point; and determining the location data of the target maintenance point.

[0022] In a possible design, the accident information data also includes accident images and vehicle driving information; accordingly, after calculating the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data, it also includes: determining a preset number of initial historical accident cases from all the historical accident cases based on the similarities; acquiring corresponding accident images and vehicle driving information based on the accident information data; analyzing and processing the accident images and the vehicle driving information according to a preset accident analysis method to calibrate the accident description text data; determining the initial historical accident cases to be eliminated based on the calibrated accident description text data and the historical accident description text data corresponding to each initial historical accident case; eliminating the initial historical accident cases to be eliminated from the preset number of initial historical accident cases to obtain the remaining initial historical accident cases; and determining the remaining initial historical accident cases as target historical accident cases.

[0023] In a second aspect, the present application provides a data processing device for vehicle maintenance quotation, applied to a server, comprising:

[0024] A receiving module, used to receive accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data;

[0025] A first processing module is used to input the accident description text data into a trained text classification model for processing to obtain accident feature data;

[0026] A retrieval module is used to retrieve all historical accident cases, and input the historical accident description text data corresponding to each historical accident case into the trained text classification model for processing to obtain the corresponding historical accident feature data;

[0027] A calculation module, used for calculating each similarity between the vehicle accident and each historical accident case according to the accident characteristic data and each historical accident characteristic data;

[0028] A first determination module, configured to determine a preset number of target historical accident cases from all the historical accident cases according to the similarities;

[0029] The second determination module is used to determine all replacement parts with a preset percentage according to the historical replacement parts list of each target historical accident case to obtain a target replacement parts list;

[0030] A third determination module, configured to determine the location data of a target maintenance point according to the vehicle location data;

[0031] A second processing module is used to input the location data of the target maintenance point, the vehicle model and the target replacement parts list into the trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list;

[0032] The output module is used to output the estimated loss amount list of replacement parts to the user end.

[0033] In a third aspect, the present application provides a server, comprising: at least one processor and a memory;

[0034] The memory stores computer-executable instructions;

[0035] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the data processing method for vehicle maintenance quotation as described in the first aspect and various possible designs of the first aspect.

[0036] In a fourth aspect, the present application provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the data processing method for vehicle maintenance quotation as described in the first aspect and various possible designs of the first aspect is implemented.

[0037] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the data processing method for vehicle repair quotation as described in the first aspect and various possible designs of the first aspect.

[0038] The data processing method and device for vehicle repair quotation provided in the present application receive accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data; determine a target replacement parts list based on the accident description text data, a trained text classification model and corresponding historical accident description text data; determine the location data of a target repair point based on the vehicle location data; input the location data of the target repair point, the vehicle model and the target replacement parts list into a trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list; output the replacement parts estimated loss amount list to the user terminal, so that the vehicle repair quotation does not need to rely too much on photos and improves the accuracy of subsequent vehicle repair quotations. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative labor.

[0040] Figure 1 A schematic diagram of an application scenario of the data processing method for vehicle maintenance quotation provided in an embodiment of the present application;

[0041] Figure 2 Schematic diagram of the process of the data processing method for vehicle maintenance quotation provided in the embodiment of the present application Figure 1 ;

[0042] Figure 3 Schematic diagram of the process of the data processing method for vehicle maintenance quotation provided in the embodiment of the present application Figure 2 ;

[0043] Figure 4 A schematic diagram of the structure of a data processing device for vehicle maintenance quotation provided in an embodiment of the present application;

[0044] Figure 5 A schematic diagram of the hardware structure of the server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] The vehicle parts damage estimate list refers to a detailed list issued by an insurance company or a professional third-party damage assessment agency after a vehicle accident, which is used to assess the cost of repairing or replacing damaged parts of the vehicle. This list lists in detail the parts that need to be replaced and their costs, repair costs, and other related costs to facilitate the push of subsequent vehicle repair quotations. In the prior art, traditional vehicle repair quotations are mainly obtained by guiding customers to take photos of the accident scene and the accident vehicle. The data center automatically identifies the damaged parts and the degree of damage of the vehicle based on the photos, and intelligently pushes the vehicle repair quotation based on the current parts replacement cost and labor hours. However, in the prior art, by guiding customers to take photos of the accident scene and the accident vehicle, the data center automatically identifies the damaged parts and the degree of damage of the vehicle based on the photos. For photos with low image quality, it is easy to cause recognition deviations, which increases the error rate of subsequent vehicle repair quotations.

[0047] In order to solve the above-mentioned technical problems, the embodiments of the present application propose the following technical concepts: the inventor considers the accident description text data, vehicle model and vehicle location data of the vehicle accident, determines the target replacement parts list based on the trained text classification model, the accident description text data and each historical accident description text data, determines the location data of the target maintenance point based on the vehicle location data, and uses the trained replacement cost quotation model to process the location data, vehicle model and target replacement parts list of the target maintenance point to obtain a replacement parts estimated loss amount list, thereby improving the accuracy of the vehicle maintenance quotation.

[0048] Figure 1 It is a schematic diagram of an application scenario of a data processing method for vehicle maintenance quotation provided in an embodiment of the present application.

[0049] like Figure 1 As shown, the scenario includes: a user terminal 101 and a server 102.

[0050] The user terminal 101 may be a mobile phone terminal or a personal computer or other terminal.

[0051] The server 102 may be an independent server or a cluster consisting of multiple servers.

[0052] The user terminal 101 transmits the accident information data including the accident description text data, the vehicle model and the vehicle location data to the server 102 via a wireless network. The server 102 determines the target replacement parts list based on the trained text classification model, the accident description text data and the corresponding historical accident description text data; determines the location data of the target maintenance point based on the vehicle location data; inputs the location data of the target maintenance point, the vehicle model and the target replacement parts list into the trained replacement cost quotation model for processing to obtain the replacement parts estimated loss amount list; and outputs the replacement parts estimated loss amount list to the user terminal 101. The following is a detailed description using a detailed embodiment.

[0053] Figure 2 Schematic diagram of the process of the data processing method for vehicle maintenance quotation provided in the embodiment of the present application Figure 1 , the execution subject of this embodiment can be Figure 1 The server in the embodiment shown is not particularly limited in this embodiment. Figure 2 As shown, the method includes:

[0054] S201: receiving accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data.

[0055] S202: Input the accident description text data into the trained text classification model for processing to obtain accident feature data.

[0056] In this embodiment, the accident feature data is a multi-dimensional V1 vector.

[0057] In this embodiment, the training process of the text classification model specifically includes:

[0058] S2021: Obtain multiple first historical sample data corresponding to each historical accident case, wherein the multiple first historical sample data at least include a historical replacement parts list and corresponding historical accident description text data.

[0059] In this embodiment, the multiple pieces of first historical sample data also include accident location data, vehicle model, and repair shop / 4S shop.

[0060] S2022: Classify each historical replacement parts list according to the same parts catalog to obtain historical replacement parts lists of multiple categories.

[0061] In addition, instead of classifying by the same accessory catalog, you can also classify by similar accessory catalog.

[0062] S2023: Determine all historical accident description text data corresponding to the historical replacement parts list of each category.

[0063] S2024: Input all historical accident description text data into the created text classification model for training to obtain a trained text classification model.

[0064] S203: Retrieve all historical accident cases, and input the historical accident description text data corresponding to each historical accident case into the trained text classification model for processing to obtain the corresponding historical accident feature data.

[0065] In this embodiment, the trained text classification model is the Modeldesc model.

[0066] In this embodiment, the historical accident feature data is a 128-dimensional feature vector, which corresponds to the dimension of the accident feature data.

[0067] S204: Calculate the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data.

[0068] In this embodiment, the similarity is the Euclidean distance; accordingly, the similarities between the vehicle accident and each historical accident case are calculated based on the accident feature data and each historical accident feature data, and the calculation formula includes:

[0069]

[0070] Where d is the Euclidean distance; is the i-th dimension coordinate of the vector corresponding to the accident characteristic data; is the i-th dimension coordinate of the vector corresponding to the historical accident characteristic data.

[0071] S205: Determine a preset number of target historical accident cases from all historical accident cases according to the similarities.

[0072] Specifically, according to each similarity, a preset number of target historical accident cases with high similarity are determined from all historical accident cases.

[0073] In this embodiment, the preset number may be any number among 50, 100 or 150, or other numbers.

[0074] S206: Determine all replacement parts within a preset percentage according to the historical replacement parts list of each target historical accident case to obtain a target replacement parts list.

[0075] In this embodiment, the preset top percentage may be any one of 20 top%, 30 top% or 50 top%, or may be other top percentages.

[0076] S207: Determine the location data of the target maintenance point according to the vehicle location data.

[0077] Specifically, step S207 includes:

[0078] S2071: Convert the vehicle position data into longitude and latitude coordinates.

[0079] In this embodiment, the vehicle position data may be a text description of the position or a vehicle computer positioning position.

[0080] S2072: Query all maintenance points within a preset range according to the longitude and latitude coordinates.

[0081] In this embodiment, the preset range may be any range of 2 kilometers, 3 kilometers, or 5 kilometers, or may be other ranges.

[0082] In this embodiment, the maintenance point can be a repair shop or a 4S shop.

[0083] S2073: Filter out the maintenance point that has processed the most vehicle models from all maintenance points to serve as the target maintenance point.

[0084] S2074: Determine the location data of the target maintenance point.

[0085] S208: Inputting the location data of the target maintenance point, the vehicle model, and the target replacement parts list into the trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list.

[0086] In addition to the location data of the target repair point, the vehicle model, and the target replacement parts list, the provincial agency data can also be input into the trained replacement cost quotation model for processing to calibrate the replacement parts estimated loss amount list.

[0087] In this embodiment, the training process of the replacement and repair cost quotation model specifically includes:

[0088] S2081: Acquire multiple pieces of second historical sample data corresponding to each historical accident case, wherein the multiple pieces of second historical sample data include multiple pieces of replacement and repair information data.

[0089] In this embodiment, the plurality of second historical sample data are over 100 data indicators according to the organization, repair shop / 4S shop, vehicle model, accessory type, damage assessment amount, etc.

[0090] S2082: Inputting a plurality of replacement repair information data into a preset replacement repair cost quotation model for training to obtain a trained replacement repair cost quotation model.

[0091] In this embodiment, the trained replacement and repair cost quotation model is a Modelcharge model for each organization, repair shop / 4S shop, vehicle model and accessory code.

[0092] S209: Outputting the list of estimated damage amounts of replacement parts to the user end.

[0093] In summary, the data processing method for vehicle repair quotation provided in this embodiment receives accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data; determines a target replacement parts list based on the accident description text data, a trained text classification model and corresponding historical accident description text data; determines the location data of a target repair point based on the vehicle location data; inputs the location data of the target repair point, the vehicle model and the target replacement parts list into a trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list; outputs the replacement parts estimated loss amount list to the user terminal, so that the vehicle repair quotation does not need to rely too much on photos and improves the accuracy of subsequent vehicle repair quotations.

[0094] In addition, the data processing method for vehicle maintenance quotation provided in the present embodiment converts vehicle location data into longitude and latitude coordinates; queries all maintenance points within a preset range according to the longitude and latitude coordinates; selects the maintenance point that has processed the most vehicle models from all maintenance points as the target maintenance point; determines the location data of the target maintenance point, and can select the maintenance point that is closest and has the most experience, thereby improving the efficiency of subsequent vehicle maintenance and enhancing the user experience.

[0095] In addition, the data processing method for vehicle maintenance quotation provided in this embodiment processes vehicle maintenance quotation through a trained text classification model and a trained replacement repair cost quotation model, thereby further improving the accuracy of vehicle maintenance quotation.

[0096] Figure 3 Schematic diagram of the process of the data processing method for vehicle maintenance quotation provided in the embodiment of the present application Figure 2 In the embodiment of the present application, Figure 2 Based on the embodiment provided, if the accident information data also includes accident images and vehicle driving information, the specific implementation method for determining each target historical accident case after step S204 is described in detail. Figure 3 As shown, the method includes:

[0097] S301: Determine a preset number of initial historical accident cases from all historical accident cases according to the similarities.

[0098] In this embodiment, the discussion on the preset number has been explained in step S205 and will not be repeated here.

[0099] S302: Acquire corresponding accident images and vehicle driving information according to the accident information data.

[0100] In this embodiment, the accident image may be image information, pictures, and videos.

[0101] In this embodiment, the vehicle driving information is the vehicle operation data before the vehicle accident occurs.

[0102] S303: Analyze and process the accident image and vehicle driving information according to a preset accident analysis method to calibrate the accident description text data.

[0103] In this embodiment, the preset accident analysis methods are an image classification method, a target detection method, a scar feature point extraction method, and a driving feature analysis method.

[0104] S304: Determine the initial historical accident cases to be eliminated based on the calibrated accident description text data and the historical accident description text data corresponding to each initial historical accident case.

[0105] Specifically, step S304 includes steps a to c:

[0106] Step a: Calculate the difference rates between the calibrated accident description text data and the historical accident description text data corresponding to each initial historical accident case.

[0107] In this embodiment, each difference rate may be calculated using a difference rate calculation formula.

[0108] Step b: Determine each target difference rate that is greater than a preset difference value.

[0109] In this embodiment, the preset difference value may be any difference value among 10%, 20% or 30%, or may be other difference values.

[0110] Step c: Determine the historical accident description text data corresponding to the initial historical accident cases corresponding to each target difference rate as the initial historical accident cases to be eliminated.

[0111] S305: Eliminating the initial historical accident cases to be eliminated from a preset number of initial historical accident cases to obtain the remaining initial historical accident cases.

[0112] S306: Determine the remaining initial historical accident cases as target historical accident cases.

[0113] In summary, the data processing method for vehicle maintenance quotation provided in the present embodiment determines a preset number of initial historical accident cases from all historical accident cases according to various similarities; obtains corresponding accident images and vehicle driving information according to the accident information data; analyzes and processes the accident images and vehicle driving information according to a preset accident analysis method to calibrate the accident description text data; determines the initial historical accident cases to be eliminated according to the calibrated accident description text data and the historical accident description text data corresponding to each initial historical accident case; eliminates the initial historical accident cases to be eliminated from the preset number of initial historical accident cases to obtain the remaining initial historical accident cases; determines the remaining initial historical accident cases as target historical accident cases, and further screens the initial historical accident cases with large differences through accident images and vehicle driving information, so as to further improve the accuracy of subsequent vehicle maintenance quotations.

[0114] Figure 4 This is a schematic diagram of the structure of a data processing device for vehicle maintenance quotation provided in an embodiment of the present application. Figure 4 As shown, the data processing device for vehicle maintenance quotation includes: a receiving module 401, a first processing module 402, a retrieval module 403, a calculation module 404, a first determination module 405, a second determination module 406, a third determination module 407, a second processing module 408 and an output module 409.

[0115] The receiving module 401 is used to receive accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data;

[0116] The first processing module 402 is used to input the accident description text data into the trained text classification model for processing to obtain accident feature data;

[0117] The retrieval module 403 is used to retrieve all historical accident cases, and input the historical accident description text data corresponding to each historical accident case into the trained text classification model for processing to obtain the corresponding historical accident feature data;

[0118] A calculation module 404, configured to calculate the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data;

[0119] A first determination module 405 is used to determine a preset number of target historical accident cases from all the historical accident cases according to the similarities;

[0120] The second determination module 406 is used to determine all replacement parts with a preset percentage according to the historical replacement parts list of each target historical accident case to obtain a target replacement parts list;

[0121] A third determination module 407, configured to determine the location data of the target maintenance point according to the vehicle location data;

[0122] The second processing module 408 is used to input the location data of the target maintenance point, the vehicle model and the target replacement parts list into the trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list;

[0123] The output module 409 is used to output the estimated damage amount list of replacement parts to the user end.

[0124] In a possible implementation manner, the device further includes:

[0125] A first acquisition module 410 is used to acquire multiple first historical sample data corresponding to each historical accident case, wherein the multiple first historical sample data at least include a historical replacement parts list and corresponding historical accident description text data;

[0126] A classification module 411 is used to classify each historical replacement parts list according to the same parts catalog to obtain a plurality of categories of historical replacement parts lists;

[0127] A fourth determination module 412 is used to determine all historical accident description text data corresponding to the historical replacement parts list of each category;

[0128] The first input module 413 is used to input all the historical accident description text data into the created text classification model for training, so as to obtain a trained text classification model.

[0129] In a possible implementation manner, the device further includes:

[0130] A second acquisition module 414 is used to acquire multiple pieces of second historical sample data corresponding to each historical accident case, wherein the multiple pieces of second historical sample data include multiple pieces of replacement and repair information data;

[0131] The second input module 415 is used to input the plurality of replacement and repair information data into a preset replacement and repair cost quotation model for training, so as to obtain a trained replacement and repair cost quotation model.

[0132] In a possible implementation, the similarity is the Euclidean distance; accordingly, the calculation formula for calculating the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data includes:

[0133]

[0134] Where d is the Euclidean distance; is the i-th dimension coordinate of the vector corresponding to the accident characteristic data; is the i-th dimension coordinate of the vector corresponding to the historical accident characteristic data.

[0135] In a possible implementation, the third determining module 407 specifically includes:

[0136] A conversion unit 4071, used to convert the vehicle position data into longitude and latitude coordinates;

[0137] A query unit 4072, configured to query all maintenance points within a preset range according to the latitude and longitude coordinates;

[0138] A screening unit 4073 is used to screen out the maintenance point that has processed the vehicle model the most times from all the maintenance points, to serve as the target maintenance point;

[0139] The determination unit 4074 is used to determine the location data of the target maintenance point.

[0140] In a possible implementation, the accident information data further includes accident images and vehicle driving information; accordingly, the device further includes:

[0141] A fifth determining module 416, configured to determine a preset number of initial historical accident cases from all the historical accident cases according to the similarities;

[0142] A third acquisition module 417, used to acquire corresponding accident images and vehicle driving information according to the accident information data;

[0143] A third processing module 418 is used to analyze and process the accident image and the vehicle driving information according to a preset accident analysis method to calibrate the accident description text data;

[0144] A sixth determination module 419, configured to determine the initial historical accident cases to be eliminated based on the calibrated accident description text data and the historical accident description text data corresponding to each initial historical accident case;

[0145] The fourth processing module 420 is used to remove the initial historical accident cases to be removed from the preset number of initial historical accident cases to obtain the remaining initial historical accident cases;

[0146] The seventh determination module 421 is used to determine the remaining initial historical accident cases as target historical accident cases.

[0147] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0148] Figure 5 The hardware structure diagram of the server provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the server of this embodiment includes: a processor 501 and a memory 502; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the above data processing method for vehicle maintenance quotation.

[0149] Optionally, the memory 502 may be independent or integrated with the processor 501 .

[0150] When the memory 502 is independently provided, the server further includes a bus 503 for connecting the memory 502 and the processor 501 .

[0151] An embodiment of the present application further provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the data processing method for vehicle maintenance quotation as described above is implemented.

[0152] An embodiment of the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the data processing method for vehicle maintenance quotation as described above is implemented.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0154] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0155] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0156] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.

[0157] It should be understood that the above processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0158] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0159] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0160] The above storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium may be any available medium that can be accessed by a general or special purpose computer.

[0161] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0162] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A data processing method for vehicle maintenance quotation, characterized in that: Applicable to servers, including: Receiving accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data; Inputting the accident description text data into a trained text classification model for processing to obtain accident feature data; Retrieving all historical accident cases, and inputting the historical accident description text data corresponding to each historical accident case into the trained text classification model for processing to obtain corresponding historical accident feature data; Calculating the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data; Determining a preset number of target historical accident cases from all the historical accident cases according to the similarities; Determine all replacement parts before a preset percentage according to the historical replacement parts list of each target historical accident case to obtain a target replacement parts list; Determining the location data of the target maintenance point according to the vehicle location data; Inputting the location data of the target maintenance point, the vehicle model, and the target replacement parts list into the trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list; The list of estimated damage amounts of replacement parts is output to the user terminal.

2. The method according to claim 1, characterized in that The training process of the text classification model includes: Acquire multiple first historical sample data corresponding to each historical accident case, wherein the multiple first historical sample data at least include a historical replacement parts list and corresponding historical accident description text data; Classifying each historical replacement parts list according to the same parts catalog to obtain historical replacement parts lists of multiple categories; Determine all historical accident description text data corresponding to each category of historical replacement parts list; All the historical accident description text data are input into the created text classification model for training to obtain a trained text classification model.

3. The method according to claim 1, characterized in that The training process of the replacement and repair cost quotation model includes: Acquire multiple pieces of second historical sample data corresponding to each historical accident case, wherein the multiple pieces of second historical sample data include multiple pieces of replacement and repair information data; The plurality of replacement and repair information data are input into a preset replacement and repair cost quotation model for training to obtain a trained replacement and repair cost quotation model.

4. The method according to claim 1, characterized in that: Wherein the similarity is the Euclidean distance; Accordingly, the calculation formula for calculating the similarities between the vehicle accident and each historical accident case based on the accident feature data and each historical accident feature data includes: Where d is the Euclidean distance; is the i-th dimension coordinate of the vector corresponding to the accident characteristic data; is the i-th dimension coordinate of the vector corresponding to the historical accident characteristic data.

5. The method according to claim 1, characterized in that: The step of determining the location data of the target maintenance point according to the vehicle location data comprises: Converting the vehicle position data into longitude and latitude coordinates; Query all maintenance points within a preset range according to the latitude and longitude coordinates; Filter out the maintenance point that has processed the vehicle model the most times from all the maintenance points to serve as the target maintenance point; Determine the location data of the target maintenance point.

6. The method according to any one of claims 1 to 5, characterized in that: The accident information data also includes accident images and vehicle driving information; Accordingly, after calculating the similarities between the vehicle accident and each historical accident case according to the accident feature data and each historical accident feature data, the method further includes: Determining a preset number of initial historical accident cases from all the historical accident cases according to the similarities; Acquiring corresponding accident images and vehicle driving information according to the accident information data; Analyzing and processing the accident image and the vehicle driving information according to a preset accident analysis method to calibrate the accident description text data; Determine the initial historical accident cases to be eliminated based on the calibrated accident description text data and the historical accident description text data corresponding to each initial historical accident case; Eliminating the initial historical accident cases to be eliminated from the preset number of initial historical accident cases to obtain the remaining initial historical accident cases; The remaining initial historical accident cases are determined as target historical accident cases.

7. A data processing device for vehicle maintenance quotation, characterized in that: Applicable to servers, including: A receiving module, used to receive accident information data of a vehicle accident uploaded by any user terminal, wherein the accident information data at least includes accident description text data, vehicle model and vehicle location data; A first processing module is used to input the accident description text data into a trained text classification model for processing to obtain accident feature data; A retrieval module is used to retrieve all historical accident cases, and input the historical accident description text data corresponding to each historical accident case into the trained text classification model for processing to obtain the corresponding historical accident feature data; A calculation module, used for calculating each similarity between the vehicle accident and each historical accident case according to the accident characteristic data and each historical accident characteristic data; A first determination module, configured to determine a preset number of target historical accident cases from all the historical accident cases according to the similarities; The second determination module is used to determine all replacement parts with a preset percentage according to the historical replacement parts list of each target historical accident case to obtain a target replacement parts list; A third determination module, configured to determine the location data of a target maintenance point according to the vehicle location data; A second processing module is used to input the location data of the target maintenance point, the vehicle model and the target replacement parts list into the trained replacement cost quotation model for processing to obtain a replacement parts estimated loss amount list; The output module is used to output the estimated loss amount list of replacement parts to the user end.

8. A server, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the data processing method for vehicle maintenance quotation according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that: The computer storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the data processing method for vehicle maintenance quotation according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data processing method for vehicle maintenance quotation according to any one of claims 1 to 6 is implemented.

Images