Method, device, equipment and storage medium for generating business list data

Abstract

The present invention relates to the field of artificial intelligence, and discloses a method, device, equipment and storage medium for generating business list data, which are used to improve the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data. The method for generating business list data includes: obtaining a vehicle damage image and corresponding vehicle basic information corresponding to a vehicle damage assessment request; preprocessing the vehicle damage image to generate a preprocessed vehicle damage image; performing damage identification on the preprocessed vehicle damage image in combination with the basic information of the vehicle through a preset technology identification center, generating intelligent identification damage data and corresponding intelligent business list data; obtaining artificial damage data and corresponding artificial business list data, and generating target business list data based on the artificial damage data, artificial business list data, intelligent identification damage data and intelligent business list data. In addition, the present invention also relates to blockchain technology, and the vehicle damage image can be stored in the blockchain.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a method, device, equipment and storage medium for generating business list data. Background Art

[0002] With the development of life, vehicles have become an indispensable means of commuting in life. With the popularization of vehicles, various problems have also occurred in vehicles, such as damage to vehicles caused by traffic accidents or natural disasters. Car owners gradually pay attention to the property protection after the vehicle is damaged. Therefore, various companies' vehicle protection products have emerged. When a vehicle is damaged, each company determines the damage to the vehicle and generates corresponding business list data as a response strategy when the vehicle is damaged.

[0003] In existing technologies, when a vehicle is damaged, it is usually the damage assessors who make the loss assessment. This loss assessment method may be affected by other factors, resulting in inaccurate damage assessment results and the inability to generate accurate business list data. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for generating business list data, which are used to improve the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data.

[0005] The first aspect of the present invention provides a method for generating business list data, comprising: when a vehicle damage assessment request is received, obtaining a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request; preprocessing the vehicle damage image to generate a preprocessed vehicle damage image; performing damage identification on the preprocessed vehicle damage image in combination with the vehicle basic information through a preset technology identification center, generating intelligent identification damage data and corresponding intelligent business list data, and storing the intelligent identification damage data and the corresponding intelligent business list data in a database; obtaining artificial damage data and corresponding artificial business list data, and generating target business list data based on the artificial damage data, the artificial business list data, the intelligent identification damage data and the intelligent business list data.

[0006] Optionally, in a first implementation manner of the first aspect of the present invention, the preprocessing of the vehicle damage image to generate a preprocessed vehicle damage image includes: grayscale processing of the vehicle damage image to generate a grayscale processed vehicle damage image; binarization processing of the grayscale processed vehicle damage image to generate a binarized vehicle damage image; and refinement processing of the binarized vehicle damage image to generate a preprocessed vehicle damage image.

[0007] Optionally, in a second implementation method of the first aspect of the present invention, the pre-processed vehicle damage image is subjected to damage identification by a preset technology identification center in combination with the vehicle basic information, intelligent identification damage data and corresponding intelligent business list data are generated, and the intelligent identification damage data and the corresponding intelligent business list data are stored in a database, including: feature extraction of the pre-processed vehicle damage image to generate a vehicle damage feature image; reading target damage object parameters from the vehicle damage feature image, the target damage object parameters including target damage object coordinate parameters, target damage object length parameters and target damage object width parameters; extracting vehicle object basic parameters from the vehicle basic information, the vehicle object basic parameters including vehicle object coordinate parameters, vehicle object length parameters and vehicle object width parameters; calculating based on the target damage object parameters and the vehicle object basic parameters by a preset technology identification center to generate similarity parameters; and performing damage identification according to the similarity parameters to generate intelligent identification damage data and corresponding intelligent business list data.

[0008] Optionally, in a third implementation method of the first aspect of the present invention, the damage identification based on the similarity parameter to generate intelligent identification damage data and corresponding intelligent business list data includes: determining whether the similarity parameter is greater than or equal to a similarity threshold; if the similarity parameter is greater than or equal to the similarity threshold, matching the damage level of the similarity parameter in combination with a preset damage level to generate intelligent identification damage data; and generating corresponding intelligent business list data based on the intelligent identification damage data and the corresponding target damage object.

[0009] Optionally, in a fourth implementation method of the first aspect of the present invention, the obtaining of artificial damage data and corresponding manual business list data, and generating target business list data based on the artificial damage data, the manual business list data, the intelligent identification of damage data and the intelligent business list data includes: obtaining artificial damage data and corresponding manual business list data from a preset damage assessment platform; comparing the artificial identification of damage data and the intelligent identification of damage data to generate a damage data comparison result; calling a preset damage assessment task center to generate target business list data based on the damage data comparison result, the manual business list data and the intelligent business list data.

[0010] Optionally, in a fifth implementation method of the first aspect of the present invention, the calling of a preset damage assessment task center to generate target business list data based on the damage data comparison result, the manual business list data and the intelligent business list data includes: judging whether the damage data comparison result is an over-standard result; if the damage data comparison result is judged to be an over-standard result, the over-standard result, the manual damage data, the manual business list data, the intelligent identification damage data and the intelligent business list data are sent to a preset damage assessment task center; obtaining a damage assessment personnel modification result from a preset damage assessment task center, the damage assessment personnel modification result being a result generated by the damage assessment personnel based on the over-standard result, the manual damage data, the manual business list data, the intelligent identification damage data and the intelligent business list data, and determining the damage assessment personnel modification result as the target business list data; if the damage data comparison result is judged to be a standard result, calling a preset damage assessment task center to determine the intelligent business list data as the target business list data.

[0011] Optionally, in a sixth implementation manner of the first aspect of the present invention, after obtaining the artificial damage data and the corresponding manual business list data, and generating the target business list data based on the artificial damage data, the manual business list data, the intelligent damage identification data and the intelligent business list data, the method for generating the business list data also includes: determining whether the status of a preset damage assessment task center is in a working status; if it is determined that the status of the preset damage assessment task center is not in a working status, transmitting the target identification data and the target business list data to the preset damage assessment task center.

[0012] The second aspect of the present invention provides a device for generating business list data, including: an acquisition module, which is used to acquire a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request when a vehicle damage assessment request is received; a preprocessing module, which is used to preprocess the vehicle damage image and generate a preprocessed vehicle damage image; a damage identification module, which is used to identify damage to the preprocessed vehicle damage image through a preset technology identification center in combination with the vehicle basic information, generate intelligent identification damage data and corresponding intelligent business list data, and store the intelligent identification damage data and the corresponding intelligent business list data in a database; a business list data generation module, which is used to acquire artificial damage data and corresponding artificial business list data, and generate target business list data based on the artificial damage data, the artificial business list data, the intelligent identification damage data and the intelligent business list data.

[0013] Optionally, in the first implementation method of the second aspect of the present invention, the preprocessing module can also be specifically used to: grayscale the vehicle damage image to generate a grayscale processed vehicle damage image; binarize the grayscale processed vehicle damage image to generate a binarized vehicle damage image; and refine the binarized vehicle damage image to generate a preprocessed vehicle damage image.

[0014] Optionally, in a second implementation method of the second aspect of the present invention, the damage identification module includes: a feature extraction unit, used to extract features from the preprocessed vehicle damage image to generate a vehicle damage feature image; a damage parameter reading unit, used to read target damage object parameters from the vehicle damage feature image, the target damage object parameters including target damage object coordinate parameters, target damage object length parameters and target damage object width parameters; a vehicle parameter extraction unit, used to extract vehicle object basic parameters from the vehicle basic information, the vehicle object basic parameters including vehicle object coordinate parameters, vehicle object length parameters and vehicle object width parameters; a calculation unit, used to calculate based on the target damage object parameters and the vehicle object basic parameters through a preset technology identification center to generate similarity parameters; a damage identification unit, used to perform damage identification according to the similarity parameters to generate intelligent identification damage data and corresponding intelligent business list data.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the damage identification unit can also be specifically used to: determine whether the similarity parameter is greater than or equal to a similarity threshold; if the similarity parameter is greater than or equal to the similarity threshold, matching the similarity parameter with a damage level in combination with a preset damage level to generate intelligent identification damage data; and generating corresponding intelligent business list data based on the intelligent identification damage data and the corresponding target damage object.

[0016] Optionally, in a fourth implementation method of the second aspect of the present invention, the business list data generation module includes: a manual data acquisition unit, used to acquire manual damage data and corresponding manual business list data from a preset damage assessment platform; a comparison unit, used to compare the manually identified damage data and the intelligently identified damage data to generate a damage data comparison result; a business list data generation unit, used to call a preset damage assessment task center to generate target business list data based on the damage data comparison result, the manual business list data and the intelligent business list data.

[0017] Optionally, in a fifth implementation manner of the second aspect of the present invention, the business list data generation unit can also be specifically used to: determine whether the damage data comparison result is an over-standard result; if the damage data comparison result is determined to be an over-standard result, the over-standard result, the artificial damage data, the artificial business list data, the intelligent identification of damage data and the intelligent business list data are sent to a preset damage assessment task center; obtain the damage assessor's modification result from the preset damage assessment task center, the damage assessor's modification result is a result generated by the damage assessor based on the over-standard result, the artificial damage data, the artificial business list data, the intelligent identification of damage data and the intelligent business list data, and determine the damage assessor's modification result as the target business list data; if the damage data comparison result is determined to be a standard result, call the preset damage assessment task center to determine the intelligent business list data as the target business list data.

[0018] Optionally, in a sixth implementation method of the second aspect of the present invention, the device for generating the business list data also includes: a judgment module, used to judge whether the status of the preset damage assessment task center is in a working state; and a transmission module, which is used to transmit the target identification data and the target business list data to the preset damage assessment task center if it is determined that the status of the preset damage assessment task center is not in a working state.

[0019] The third aspect of the present invention provides a device for generating business list data, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the device for generating business list data executes the above-mentioned method for generating business list data.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for generating business list data.

[0021] In the technical solution provided by the present invention, when a vehicle damage assessment request is received, a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request are obtained; the vehicle damage image is preprocessed to generate a preprocessed vehicle damage image; damage recognition is performed on the preprocessed vehicle damage image by combining the vehicle basic information with a preset technology recognition center to generate intelligent recognition damage data and corresponding intelligent business list data, and the intelligent recognition damage data and the corresponding intelligent business list data are stored in a database; artificial damage data and corresponding artificial business list data are obtained, and target business list data are generated according to the artificial damage data, the artificial business list data, the intelligent recognition damage data and the intelligent business list data. In the embodiment of the present invention, the technology recognition center is used to perform damage recognition on the preprocessed damage image, and intelligent recognition damage data and corresponding intelligent business list data are generated, and then the target business list data are generated according to the artificial damage data, the artificial business list data, the intelligent recognition damage data and the intelligent business list data, and the intelligent recognition damage data and the intelligent business list data are introduced to perform vehicle damage assessment, thereby improving the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an embodiment of a method for generating service list data in an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of another embodiment of a method for generating service list data in an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of an embodiment of a device for generating service list data in an embodiment of the present invention;

[0025] Figure 4 It is a schematic diagram of another embodiment of a device for generating service list data in an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of an embodiment of a device for generating service list data in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] Embodiments of the present invention provide a method, apparatus, device and storage medium for generating business list data, which are used to improve the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data.

[0028] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of a method for generating service list data in an embodiment of the present invention includes:

[0030] 101. When a vehicle damage assessment request is received, a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request are obtained;

[0031] When receiving a vehicle damage assessment request, the server obtains the vehicle damage image and the corresponding vehicle basic information. It should be emphasized that in order to further ensure the privacy and security of the above-mentioned vehicle damage image, the above-mentioned vehicle damage image can also be stored in a blockchain node.

[0032] The vehicle damage image can be a vehicle image taken by a camera terminal, or a frame of image captured from a vehicle video. The vehicle damage image includes a target damaged object. In this embodiment, the damage assessor first uploads the vehicle image or the vehicle video to a preset image platform, and then the server obtains the vehicle damage image from the image platform according to the vehicle damage assessment request. It should be noted that the vehicle damage image is not limited to one image. The server can obtain all vehicle damage images corresponding to the vehicle damage assessment request uploaded by the damage assessor to the image platform. For ease of understanding, this embodiment is described with one vehicle damage image. In fact, the server identification is more accurate. The server performs damage assessment identification on each vehicle damage image. The server can parse the vehicle identification or customer identification from the vehicle damage assessment request, and the server obtains the corresponding vehicle damage image and the corresponding vehicle basic information according to the vehicle identification or customer identification. For example, the vehicle identification is the license plate number AABBCC. The server determines the corresponding vehicle damage image based on the license plate number, and then determines the corresponding vehicle basic information based on the license plate number. The vehicle basic information includes basic information such as the vehicle model, the vehicle price, and the vehicle picture.

[0033] It is understandable that the execution subject of the present invention can be a device for generating business list data, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0034] 102. Preprocessing the vehicle damage image to generate a preprocessed vehicle damage image;

[0035] The server preprocesses the vehicle damage image into a preprocessed vehicle damage image.

[0036] The server first preprocesses the vehicle damage image to generate a preprocessed vehicle damage image, wherein the vehicle damage image is essentially the image data of the target damaged object, so the server needs to perform some preliminary preprocessing on the target damaged object to facilitate the subsequent damage assessment of the target damaged object. The goal of this step is to strengthen the target damaged object part and obtain data that is easier to extract features, that is, the preprocessed vehicle damage image, so as to more accurately assess the vehicle damage.

[0037] 103. Perform damage recognition on the pre-processed vehicle damage image by combining the basic information of the vehicle through the preset technology recognition center, generate intelligent recognition damage data and corresponding intelligent business list data, and store the intelligent recognition damage data and the corresponding intelligent business list data in the database;

[0038] The server performs damage identification on the pre-processed vehicle damage image through a preset technology identification center. When performing damage identification, the server also needs to identify the vehicle's basic information to generate intelligent identification damage data and corresponding intelligent business list data, and store the intelligent identification damage data and corresponding intelligent business list data in the database.

[0039] The preset technology recognition center is used for damage recognition. When performing damage recognition on a vehicle damage image, the technology recognition center needs to combine a reference standard for recognition. In this embodiment, the reference standard is the basic information of the vehicle. The technology recognition center can extract features from the basic information of the vehicle and extract features from the preprocessed vehicle damage image, and then compare the two features to generate intelligent recognition damage data. After obtaining the intelligent recognition damage data, the server generates the corresponding intelligent business list data through the technology recognition center. It should be noted that the intelligent business list data includes repair shop data, parts data, working hours data, and cost data.

[0040] It should be noted that in the damage assessment process of this solution, the server combines the preset technology identification center, the preset damage assessment task center, the preset damage assessment platform and the preset imaging platform to perform damage assessment identification. In addition, the intelligently identified damage data and the corresponding intelligent business list data are stored in the database to facilitate the query of historical damage assessment records. When customers or other personnel have objections to the damage assessment results, they can query the corresponding intelligently identified damage data and the corresponding intelligent business list data to re-assess the damage.

[0041] 104. Obtain artificial damage data and corresponding artificial business list data, and generate target business list data according to the artificial damage data, the artificial business list data, the intelligently identified damage data, and the intelligent business list data.

[0042] The server obtains the artificial damage data and the corresponding artificial business list data, then compares the artificial damage data and the intelligent identification damage data to generate a comparison result, and generates the target business list data according to the comparison result, the artificial business list data and the intelligent business list data.

[0043] Since there may be differences between manual damage data and intelligently identified damage data, when generating the target business list data, the server needs to combine the identification results of the two types of damage data to generate the target business list data, that is, retain the same damage identification results obtained by the two identification methods. For damage identification results that are different, it is necessary to modify the intelligent business list data in combination with the modification opinions of the damage assessor to obtain the target business list data.

[0044] In an embodiment of the present invention, a technology identification center is used to perform damage identification on the pre-processed damaged image to generate intelligent identification damage data and corresponding intelligent business list data, and then target business list data is generated based on the artificial damage data, the artificial business list data, the intelligent identification damage data and the intelligent business list data. The intelligent identification damage data and the intelligent business list data obtained by the identification of the technology identification center are introduced to perform vehicle damage assessment, thereby improving the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data.

[0045] See also Figure 2 Another embodiment of the method for generating service list data in the embodiment of the present invention includes:

[0046] 201. When a vehicle damage assessment request is received, a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request are obtained;

[0047] When receiving a vehicle damage assessment request, the server obtains the vehicle damage image and the corresponding vehicle basic information. It should be emphasized that in order to further ensure the privacy and security of the above-mentioned vehicle damage image, the above-mentioned vehicle damage image can also be stored in a blockchain node.

[0048] The vehicle damage image can be a vehicle image taken by a camera terminal, or a frame of image captured from a vehicle video. The vehicle damage image includes a target damaged object. In this embodiment, the damage assessor first uploads the vehicle image or the vehicle video to the image platform, and then the server obtains the vehicle damage image from the image platform according to the vehicle damage assessment request. It should be noted that the vehicle damage image is not limited to one. The server can obtain all vehicle damage images corresponding to the vehicle damage assessment request uploaded by the damage assessor to the image platform. For ease of understanding, this embodiment is described with one vehicle damage image. In fact, the server identification is more accurate. The server performs damage assessment identification on each vehicle damage image. The server can parse the vehicle identification or customer identification from the vehicle damage assessment request, and the server obtains the corresponding vehicle damage image and the corresponding vehicle basic information according to the vehicle identification or customer identification. For example, the vehicle identification is the license plate number AABBCC. The server determines the corresponding vehicle damage image based on the license plate number, and then determines the corresponding vehicle basic information based on the license plate number. The vehicle basic information includes basic information such as the vehicle model, the vehicle price, and the vehicle picture.

[0049] 202. Preprocessing the vehicle damage image to generate a preprocessed vehicle damage image;

[0050] The server preprocesses the vehicle damage image into a preprocessed vehicle damage image.

[0051] The server first preprocesses the vehicle damage image to generate a preprocessed vehicle damage image, wherein the vehicle damage image is essentially the image data of the target damaged object, so the server needs to perform some preliminary preprocessing on the target damaged object to facilitate the subsequent damage assessment of the target damaged object. The goal of this step is to strengthen the target damaged object part and obtain data that is easier to extract features, that is, the preprocessed vehicle damage image, so as to more accurately assess the vehicle damage.

[0052] Specifically, the server first performs grayscale processing on the vehicle damage image to generate a grayscale processed vehicle damage image, then binarizes the vehicle damage image into a binarized vehicle damage image, and then refines the binarized vehicle damage image to generate a preprocessed vehicle damage image.

[0053] In this embodiment, each pixel in the vehicle damage image includes three color values ​​of RGB. The server calculates the gray value through the gray value formula. The gray value formula is: gray=R 0.299+G*0.587+B*0.114. Then the server forms the following corresponding relationship R=G=B=gray between the three color values ​​and the gray value of each pixel, and the gray processing is completed to generate the gray vehicle damage image. Then the server performs binarization processing on the gray vehicle damage image. The server sets the gray value of the pixel points in the gray vehicle damage image to 0 and 1, and then deletes the pixels that are 0 to complete the binarization processing, and generates the binarized vehicle damage image. The binarized vehicle damage image is the image data with the background part removed. It should be noted that the binarized vehicle damage image includes the target damage object. After obtaining the binarized vehicle damage image, the server removes the redundant pixels without destroying the connectivity of the target damage object, that is, thinning processing, thereby generating the pre-processed vehicle damage image.

[0054] 203. Perform damage recognition on the pre-processed vehicle damage image by combining the basic information of the vehicle through the preset technology recognition center, generate intelligent recognition damage data and corresponding intelligent business list data, and store the intelligent recognition damage data and the corresponding intelligent business list data in the database;

[0055] The server performs damage identification on the pre-processed vehicle damage image through a preset technology identification center. When performing damage identification, the server also needs to identify the vehicle's basic information to generate intelligent identification damage data and corresponding intelligent business list data, and store the intelligent identification damage data and corresponding intelligent business list data in the database.

[0056] The preset technology recognition center is used for damage recognition. When performing damage recognition on vehicle damage images, the technology center needs to combine a reference standard for recognition. In this embodiment, the reference standard is the basic information of the vehicle. The technology recognition center can extract features from the basic information of the vehicle and extract features from the preprocessed vehicle damage image, and then compare the two features to generate intelligent recognition damage data. After obtaining the intelligent recognition damage data, the server generates the corresponding intelligent business list data through the technology recognition center. It should be noted that the intelligent business list data includes repair shop data, parts data, working hours data and cost data.

[0057] It should be noted that in the damage assessment process of this solution, the server combines the preset technology identification center, the preset damage assessment task center, the preset damage assessment platform and the preset imaging platform to perform damage assessment identification. In addition, the intelligently identified damage data and the corresponding intelligent business list data are stored in the database to facilitate the query of historical damage assessment records. When customers or other personnel have objections to the damage assessment results, they can query the corresponding intelligently identified damage data and the corresponding intelligent business list data to re-assess the damage.

[0058] Specifically, the server performs feature extraction on the preprocessed vehicle damage image to generate a vehicle damage feature image; the server reads target damage object parameters from the vehicle damage feature image, and the target damage object parameters include target damage object coordinate parameters, target damage object length parameters, and target damage object width parameters; the server extracts vehicle object basic parameters from the vehicle basic information, and the vehicle object basic parameters include vehicle object coordinate parameters, vehicle object length parameters, and vehicle object width parameters; the server calculates based on the target damage object parameters and the vehicle object basic parameters through a preset technology identification center to generate similarity parameters; the server identifies damage based on the similarity parameters to generate intelligent identification damage data and corresponding intelligent business list data.

[0059] The server extracts features based on the preprocessed vehicle damage image through the preset technology recognition center to generate a vehicle damage feature image. It should be noted that the vehicle damage feature image includes a detection frame, and the content of the detection frame is the target damage object. The detection frame is annotated with a series of parameters, namely, the target damage object parameters. The target damage object parameters are (x a ,y a ,w a ,h a ), where (x a ,y a ) represents the coordinate parameters of the target damaged object, w a Indicates the target damage object length parameter and h a The server then extracts features from the image information in the basic information of the vehicle, generates a basic feature image of the vehicle information, and then extracts the basic parameters of the vehicle object from the basic feature image of the vehicle information. The basic parameters of the vehicle object are (x b ,y b ,w b ,h b ), where (x b ,y b ) represents the vehicle object coordinate parameters, w b Indicates the vehicle object length parameter and h bRepresents the width parameter of the vehicle object. The server calculates the target damaged object parameters and the basic parameters of the vehicle object through the technology identification center to generate similarity parameters. During the calculation process, it is necessary to call the preset similarity function for calculation. The preset similarity function is:

[0060]

[0061] Among them, D(u,v) is the similarity parameter, X is the vehicle damage feature image, Y is the basic feature image of vehicle information, m is the length information (target damaged object length parameter or vehicle object length parameter), n is the width information (target damaged object width parameter or vehicle object width parameter), j is the variable of length information, k is the variable of width information, u is the offset of length information, and v is the offset of width information.

[0062] The server finally performs damage identification based on the similarity parameter, and generates intelligently identified damage data and corresponding intelligent service list data. In this embodiment, the larger the similarity parameter, the lower the damage level. The damage level is divided into nine levels according to the similarity parameter, where damage level one is [1-0.9), damage level two is [0.9-0.8), damage level three is [0.8-0.7), damage level four is [0.7-0.6), damage level five is [0.6-0.5), damage level six is ​​[0.5-0.4), damage level seven is [0.4-0.3), damage level eight is [0.3-0.2), and damage level nine is [0.2-0.1]. In other embodiments, the damage level can be divided into other levels according to the similarity parameter, and this is not limited.

[0063] The server identifies damage based on similarity parameters and generates intelligently identified damage data and corresponding intelligent service list data including:

[0064] First, the server determines whether the similarity parameter is greater than or equal to the similarity threshold. If the similarity parameter is greater than or equal to the similarity threshold, the server matches the similarity parameter with the above damage level to determine the target damage level of the target damaged object, that is, intelligently identify the damage data, and match based on the intelligent identification of the damage data to generate corresponding intelligent business list data including repair shop data, accessories data, working hours data and cost data. Intelligent identification of damage data can match working hours data and cost data, and the target damaged object can be matched to the corresponding accessories data and repair shop data in combination with the intelligent identification of damage data. If the similarity parameter is less than the similarity threshold, it means that the target damaged object does not reach the damage level, and the server will no longer identify the damage.

[0065] 204. Obtaining artificial damage data and corresponding artificial business list data, and generating target business list data according to the artificial damage data, the artificial business list data, the intelligent recognition damage data, and the intelligent business list data;

[0066] The server obtains the artificial damage data and the corresponding artificial business list data, then compares the artificial damage data and the intelligent identification damage data to generate a comparison result, and generates the target business list data according to the comparison result, the artificial business list data and the intelligent business list data.

[0067] Since there may be differences between manual damage data and intelligently identified damage data, when generating the target business list data, the server needs to combine the identification results of the two types of damage data to generate the target business list data, that is, retain the same damage identification results obtained by the two identification methods. For damage identification results that are different, it is necessary to modify the intelligent business list data in combination with the modification opinions of the damage assessor to obtain the target business list data.

[0068] Specifically, the server obtains artificial damage data and corresponding manual business list data from a preset damage assessment platform; the server compares the manually identified damage data and the intelligently identified damage data to generate a damage data comparison result; the server calls a preset damage assessment task center to generate target business list data based on the damage data comparison result, manual business list data, and intelligent business list data.

[0069] The server first needs to obtain the artificial damage data and the corresponding manual business list data from the preset damage assessment platform. The artificial damage data is the damage assessment result obtained by the damage assessor based on the damage image of the vehicle. The personnel business list data is the list data generated by the damage assessor based on the artificial damage data. The personnel business list data includes the corresponding repair shop data, parts data, working hours data and cost data, etc. The server compares the artificial damage data and the intelligent damage data to generate the damage data comparison result. The server calls the preset damage assessment task center to generate the target business list data based on the damage data comparison result combined with the manual business list data and the intelligent business list data.

[0070] The server calls the preset damage assessment task center to generate the target business list data based on the damage data comparison results, manual business list data, and intelligent business list data, including:

[0071] The server first determines whether the damage data comparison result is an over-standard result. The over-standard result is the result that the intelligently identified damage data is more serious than the manual damage data. For example, the intelligently identified damage data shows that the damage level is damage level seven, and the manual damage data shows that the damage level is damage level six. The comparison result is determined to be an over-standard result. At this time, the server needs to send the over-standard result, manual damage data, manual business list data, intelligently identified damage data, and intelligent business list data to the damage assessment task center. The damage assessor obtains the over-standard result, manual damage data, manual business list data, intelligently identified damage data, and intelligent business list data through the preset damage assessment task center, and modifies the intelligent business list data based on the over-standard result, manual damage data, intelligently identified damage data, and manual business list data to generate a modification result. Then the server obtains the modification result of the damage assessor from the preset damage assessment task center and determines the modification result as the target business list data. If the damage data comparison result is determined not to be an over-standard result, that is, the comparison result is a standard result or does not reach the standard result, the server calls the preset damage assessment task center to directly determine the intelligent business list data as the target business list data.

[0072] 205. Determine whether the status of the preset damage assessment task center is in working status;

[0073] After obtaining the target business list data, the server needs to send the target business list data to the preset damage assessment task center. Since it is explained in step 1 that there can be multiple vehicle damage images, in order to ensure that the target business list data can be sent to the damage assessment task center smoothly and accurately, before sending the target business list data, the server first determines whether the preset damage assessment task center is in working condition.

[0074] 206. If it is determined that the status of the preset damage assessment task center is not in working status, the target identification data and the target business list data are transmitted to the damage assessment task center.

[0075] If it is determined that the preset damage assessment task center is not in working state, it means that the damage identification work is completed. At this time, the server can transmit the target business list data to the preset damage assessment task center. If the server determines that the damage assessment task center is in working state, it means that the preset damage assessment task center is still performing damage identification on other vehicle damage images. At this time, the target business list data will not be sent to the preset damage assessment task center, and the preset damage assessment task center will be waited for to change its working state.

[0076] In an embodiment of the present invention, a technology identification center is used to perform damage identification on the pre-processed damaged image to generate intelligent identification damage data and corresponding intelligent business list data, and then target business list data is generated based on the artificial damage data, the artificial business list data, the intelligent identification damage data and the intelligent business list data. The intelligent identification damage data and the intelligent business list data obtained by the identification of the technology identification center are introduced to perform vehicle damage assessment, thereby improving the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data.

[0077] The above describes the method for generating the service list data in the embodiment of the present invention. The following describes the device for generating the service list data in the embodiment of the present invention. Figure 3 , an embodiment of a device for generating service list data in an embodiment of the present invention includes:

[0078] The acquisition module 301 is used to acquire the vehicle damage image and the corresponding vehicle basic information corresponding to the vehicle damage assessment request when receiving the vehicle damage assessment request;

[0079] A preprocessing module 302, used to preprocess the vehicle damage image to generate a preprocessed vehicle damage image;

[0080] The damage identification module 303 is used to perform damage identification on the pre-processed vehicle damage image by combining the vehicle basic information with a preset technology identification center, generate intelligent identification damage data and corresponding intelligent service list data, and store the intelligent identification damage data and the corresponding intelligent service list data in a database;

[0081] The service list data generation module 304 is used to obtain the artificial damage data and the corresponding artificial service list data, and generate the target service list data according to the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data.

[0082] In an embodiment of the present invention, a technology identification center is used to perform damage identification on the pre-processed damaged image to generate intelligent identification damage data and corresponding intelligent business list data, and then target business list data is generated based on the artificial damage data, the artificial business list data, the intelligent identification damage data and the intelligent business list data. The intelligent identification damage data and the intelligent business list data obtained by the identification of the technology identification center are introduced to perform vehicle damage assessment, thereby improving the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data.

[0083] See also Figure 4 Another embodiment of the device for generating service list data in the embodiment of the present invention includes:

[0084] The acquisition module 301 is used to acquire the vehicle damage image and the corresponding vehicle basic information corresponding to the vehicle damage assessment request when receiving the vehicle damage assessment request;

[0085] A preprocessing module 302, used to preprocess the vehicle damage image to generate a preprocessed vehicle damage image;

[0086] The damage identification module 303 is used to perform damage identification on the pre-processed vehicle damage image by combining the vehicle basic information with a preset technology identification center, generate intelligent identification damage data and corresponding intelligent service list data, and store the intelligent identification damage data and the corresponding intelligent service list data in a database;

[0087] The service list data generation module 304 is used to obtain the artificial damage data and the corresponding artificial service list data, and generate the target service list data according to the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data.

[0088] Optionally, the preprocessing module 302 may also be specifically used for:

[0089] grayscale the damaged vehicle image to generate a grayscale-processed damaged vehicle image;

[0090] Binarizing the grayscale-processed damaged vehicle image to generate a binary damaged vehicle image;

[0091] The binarized vehicle damage image is subjected to thinning processing to generate a preprocessed vehicle damage image.

[0092] Optionally, the damage identification module 303 includes:

[0093] A feature extraction unit 3031 is used to extract features from the preprocessed vehicle damage image to generate a vehicle damage feature image;

[0094] A damage parameter reading unit 3032 is used to read target damaged object parameters from the vehicle damage feature image, wherein the target damaged object parameters include target damaged object coordinate parameters, target damaged object length parameters and target damaged object width parameters;

[0095] A vehicle parameter extraction unit 3033 is used to extract vehicle object basic parameters from the vehicle basic information, wherein the vehicle object basic parameters include vehicle object coordinate parameters, vehicle object length parameters and vehicle object width parameters;

[0096] A calculation unit 3034, configured to generate a similarity parameter by performing calculation based on the target damaged object parameters and the vehicle object basic parameters through a preset technology identification center;

[0097] The damage identification unit 3035 is used to perform damage identification according to the similarity parameter and generate intelligently identified damage data and corresponding intelligent service list data.

[0098] Optionally, the damage identification unit 3035 may also be specifically used for:

[0099] Determining whether the similarity parameter is greater than or equal to a similarity threshold;

[0100] If the similarity parameter is greater than or equal to the similarity threshold, matching the similarity parameter with the preset damage level is performed to generate intelligently identified damage data;

[0101] Corresponding intelligent service list data is generated based on the intelligently identified damage data and the corresponding target damaged object.

[0102] Optionally, the service list data generating module 304 includes:

[0103] The manual data acquisition unit 3041 is used to acquire the manual damage data and the corresponding manual business list data from the preset damage assessment platform;

[0104] A comparison unit 3042, used to compare the manually identified damage data with the intelligently identified damage data to generate a damage data comparison result;

[0105] The business list data generating unit 3043 is used to call the preset damage assessment task center to generate target business list data based on the damage data comparison result, the manual business list data and the intelligent business list data.

[0106] Optionally, the service list data generating unit 3043 may also be specifically used for:

[0107] Determining whether the damage data comparison result is an over-standard result;

[0108] If it is determined that the damage data comparison result is an over-standard result, the over-standard result, the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data are sent to a preset damage task center;

[0109] Acquire the loss assessor's modification result from a preset loss assessment task center, wherein the loss assessor's modification result is a result generated by the loss assessor based on the over-standard result, the manual damage data, the manual business list data, the intelligently identified damage data, and the intelligent business list data, and determine the loss assessor's modification result as the target business list data;

[0110] If the damage data comparison result is determined to be a standard result, the preset damage assessment task center is called to determine the intelligent business list data as the target business list data.

[0111] Optionally, the device for generating the service list data further includes:

[0112] The judgment module 305 is used to judge whether the status of the preset damage assessment task center is in working status;

[0113] The transmission module 306 is used to transmit the target identification data and the target business list data to the preset damage assessment task center if it is determined that the status of the preset damage assessment task center is not in the working status.

[0114] In an embodiment of the present invention, a technology identification center is used to perform damage identification on the pre-processed damaged image to generate intelligent identification damage data and corresponding intelligent business list data, and then target business list data is generated based on the artificial damage data, the artificial business list data, the intelligent identification damage data and the intelligent business list data. The intelligent identification damage data and the intelligent business list data obtained by the identification of the technology identification center are introduced to perform vehicle damage assessment, thereby improving the accuracy of vehicle damage assessment, thereby improving the accuracy of generating business list data.

[0115] above Figure 3 and Figure 4 The device for generating service list data in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The device for generating service list data in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0116] Figure 51 is a schematic diagram of the structure of a device for generating business list data provided by an embodiment of the present invention. The device 500 for generating business list data may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 may be temporary storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the device 500 for generating business list data. Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the device 500 for generating business list data.

[0117] The device 500 for generating the service list data may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 5 The structure of the device for generating service list data shown does not constitute a limitation on the device for generating service list data, and may include more or less components than shown in the figure, or may combine certain components, or may have different component arrangements.

[0118] The present invention also provides a device for generating business list data, wherein the computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for generating business list data in the above-mentioned embodiments.

[0119] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the method for generating business inventory data.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0123] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating business list data, characterized in that: The method for generating the service list data comprises: When a vehicle damage assessment request is received, a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request are obtained; Preprocessing the vehicle damage image to generate a preprocessed vehicle damage image; Perform damage recognition on the pre-processed vehicle damage image in combination with the basic information of the vehicle through a preset technology recognition center, generate intelligent recognition damage data and corresponding intelligent service list data, and store the intelligent recognition damage data and the corresponding intelligent service list data in a database; Acquire artificial damage data and corresponding artificial service list data, and generate target service list data according to the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data; The pre-processed vehicle damage image is subjected to damage recognition by combining the pre-set technology recognition center with the basic vehicle information to generate intelligent recognition damage data and corresponding intelligent business list data, including: Extracting features from the preprocessed vehicle damage image to generate a vehicle damage feature image; Reading target damaged object parameters from the vehicle damage feature image, the target damaged object parameters including target damaged object coordinate parameters, target damaged object length parameters and target damaged object width parameters; Extracting basic parameters of a vehicle object from the basic vehicle information, wherein the basic parameters of the vehicle object include a vehicle object coordinate parameter, a vehicle object length parameter, and a vehicle object width parameter; The preset similarity function is called by the preset technology identification center to calculate based on the target damaged object parameters and the basic parameters of the vehicle object to generate similarity parameters; Perform damage identification according to the similarity parameters, and generate intelligently identified damage data and corresponding intelligent service list data; The similarity function is: Among them, D(u,v) is the similarity parameter, X is the vehicle damage feature image, Y is the basic feature image of the vehicle information, m is the length information, the length information is the target damaged object length parameter or the vehicle object length parameter, n is the width information, the width information is the target damaged object width parameter or the vehicle object width parameter, j is the variable of the length information, k is the variable of the width information, u is the offset of the length information, and v is the offset of the width information.

2. The method for generating business list data according to claim 1, characterized in that: The preprocessing of the vehicle damage image to generate the preprocessed vehicle damage image comprises: grayscale the damaged vehicle image to generate a grayscale-processed damaged vehicle image; Binarizing the grayscale-processed damaged vehicle image to generate a binary damaged vehicle image; The binarized vehicle damage image is subjected to thinning processing to generate a preprocessed vehicle damage image.

3. The method for generating business list data according to claim 1, characterized in that: The performing damage identification according to the similarity parameter and generating intelligently identified damage data and corresponding intelligent service list data comprises: Determining whether the similarity parameter is greater than or equal to a similarity threshold; If the similarity parameter is greater than or equal to the similarity threshold, matching the similarity parameter with the preset damage level is performed to generate intelligently identified damage data; Corresponding intelligent service list data is generated based on the intelligently identified damage data and the corresponding target damaged object.

4. The method for generating business list data according to claim 1, characterized in that: The acquiring of artificial damage data and corresponding artificial service list data, and generating target service list data according to the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data comprises: Obtain artificial damage data and corresponding manual business list data from the preset damage assessment platform; Comparing the manually identified damage data with the intelligently identified damage data to generate a damage data comparison result; The preset damage assessment task center is called to generate target business list data based on the damage data comparison result, the manual business list data and the intelligent business list data.

5. According to the method for generating business list data of claim 4, the calling of a preset damage assessment task center to generate target business list data based on the damage data comparison result, the manual business list data and the intelligent business list data comprises: Determining whether the damage data comparison result is an over-standard result; If it is determined that the damage data comparison result is an over-standard result, the over-standard result, the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data are sent to a preset damage assessment task center; Acquire the loss assessor's modification result from a preset loss assessment task center, wherein the loss assessor's modification result is a result generated by the loss assessor based on the over-standard result, the manual damage data, the manual business list data, the intelligently identified damage data, and the intelligent business list data, and determine the loss assessor's modification result as the target business list data; If the damage data comparison result is determined to be a standard result, the preset damage assessment task center is called to determine the intelligent business list data as the target business list data.

6. The method for generating service list data according to any one of claims 1 to 5, characterized in that: After acquiring the artificial damage data and the corresponding artificial service list data, and generating the target service list data according to the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data, the service list data generating method further includes: Determine whether the status of the preset damage assessment task center is in working status; If it is determined that the status of the preset damage assessment task center is not in a working state, the target identification data and the target business list data are transmitted to the preset damage assessment task center.

7. A device for generating business list data, characterized in that: The device for generating the service list data comprises: An acquisition module, when receiving a vehicle damage assessment request, is used to acquire a vehicle damage image and corresponding vehicle basic information corresponding to the vehicle damage assessment request; A preprocessing module, used for preprocessing the vehicle damage image to generate a preprocessed vehicle damage image; A damage identification module, used to perform damage identification on the pre-processed vehicle damage image in combination with the vehicle basic information through a preset technology identification center, generate intelligent identification damage data and corresponding intelligent service list data, and store the intelligent identification damage data and the corresponding intelligent service list data in a database; A service list data generation module, used to obtain artificial damage data and corresponding artificial service list data, and generate target service list data according to the artificial damage data, the artificial service list data, the intelligently identified damage data and the intelligent service list data; The damage identification module comprises: A feature extraction unit, used for extracting features from the preprocessed vehicle damage image to generate a vehicle damage feature image; A damage parameter reading unit, used for reading target damaged object parameters from the vehicle damage characteristic image, wherein the target damaged object parameters include target damaged object coordinate parameters, target damaged object length parameters and target damaged object width parameters; A vehicle parameter extraction unit, used to extract vehicle object basic parameters from the vehicle basic information, wherein the vehicle object basic parameters include vehicle object coordinate parameters, vehicle object length parameters and vehicle object width parameters; A calculation unit, configured to call a preset similarity function through a preset technology identification center to perform calculation based on the target damaged object parameters and the vehicle object basic parameters to generate a similarity parameter; A damage identification unit, used to perform damage identification according to the similarity parameter, and generate intelligently identified damage data and corresponding intelligent service list data; The similarity function is: Among them, D(u,v) is the similarity parameter, X is the vehicle damage feature image, Y is the basic feature image of the vehicle information, m is the length information, the length information is the target damaged object length parameter or the vehicle object length parameter, n is the width information, the width information is the target damaged object width parameter or the vehicle object width parameter, j is the variable of the length information, k is the variable of the width information, u is the offset of the length information, and v is the offset of the width information.

8. The device for generating business list data according to claim 7, characterized in that: The damage identification unit is specifically used for: Determining whether the similarity parameter is greater than or equal to a similarity threshold; If the similarity parameter is greater than or equal to the similarity threshold, matching the similarity parameter with the preset damage level is performed to generate intelligently identified damage data; Corresponding intelligent service list data is generated based on the intelligently identified damage data and the corresponding target damaged object.

9. A device for generating business list data, characterized in that: The device for generating the service list data includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory to enable the device for generating service list data to execute the method for generating service list data according to any one of claims 1 to 6.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the method for generating service list data as described in any one of claims 1 to 6 is implemented.

Images