A data review method and system

Abstract

This application relates to the field of artificial intelligence technology and provides a data review method, including: obtaining detection information; determining review items according to a data review request and the detection information; invoking a rule verification model according to the review items; verifying the detection information based on a preset rule of the rule verification model; generating a review prompt message according to the verification result. After determining the review items based on the detection information generated by the on-board diagnostic system and the data review request submitted by the user, it can automatically invoke the rule verification model of the review item to verify the detection information, and can automatically conduct loss appraisal based on the detection information and the data review request, effectively improving the efficiency and accuracy of vehicle loss appraisal, and effectively solving the problem that the current vehicle loss appraisal method cannot efficiently and accurately conduct loss appraisal on vehicles.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to a data audit method and system. Background Art

[0002] With the continuous improvement of the electronic level of automobiles, electronic components are constantly updated and iterated. In the work of vehicle survey and damage assessment, the loss appraisal of electronic components has high technical requirements and is difficult to judge, requiring professional personnel for loss appraisal. Moreover, as there are more and more social vehicles, the business volume of survey and damage assessment has also increased accordingly. Therefore, the current vehicle damage assessment method can no longer meet the requirements of efficiently and accurately appraising vehicle losses.

[0003] In summary, the current vehicle loss appraisal method has the problem of being unable to efficiently and accurately appraise vehicle losses. Summary of the Invention

[0004] The embodiments of this application provide a data audit method and system, which can solve the problem that the current vehicle loss appraisal method is unable to efficiently and accurately appraise vehicle losses.

[0005] In a first aspect, the embodiments of this application provide a data audit method, including:

[0006] Obtain detection information;

[0007] Input a data audit request and the detection information into a project determination model for processing to obtain an audit project corresponding to the data audit request and the detection information; the project determination model is obtained by training a data audit request sample set and a detection information sample set through a machine learning algorithm;

[0008] Call a rule verification model corresponding to the audit project according to the audit project;

[0009] Verify the detection information based on the preset rules of the rule verification model;

[0010] Generate an audit prompt message according to the verification result.

[0011] Further, the obtaining of the detection information includes:

[0012] Obtain a fault information identification code; the fault information identification code is an identification code generated by an on-vehicle diagnostic system according to the fault information of vehicle components;

[0013] Identify the fault information identification code to determine the detection information of the vehicle.

[0014] Exemplarily, the detection information of the vehicle is obtained by scanning the fault identification code with a handheld terminal.

[0015] In a possible implementation of the first aspect, the above detection information is obtained by the handheld terminal scanning the fault identification code generated by the on-vehicle diagnostic system according to the component fault information of the vehicle.

[0016] Further, determining the audit items according to the data audit request and the detection information includes:

[0017] Obtaining vehicle pictures according to the data audit request; the vehicle pictures are images obtained by photographing the vehicle from multiple preset directions;

[0018] Inputting the vehicle images and detection information into a project determination model for processing to obtain the probabilities of the vehicle for each preset audit item; the project determination model is obtained by training a vehicle sample set through a machine learning algorithm;

[0019] Determining the audit items corresponding to the data audit request based on the probabilities of each audit item.

[0020] It should be understood that by using the project determination model to determine the audit items according to the vehicle pictures, the audit items corresponding to the data audit request and the detection information can be determined quickly and accurately.

[0021] Further, the above verification of the detection information according to the preset rules of the rule verification model includes:

[0022] Obtaining information fields according to the detection information;

[0023] Obtaining verification fields corresponding to the information fields;

[0024] Matching and verifying the information fields with the corresponding verification fields according to the preset rules.

[0025] In a possible implementation of the first aspect, before calling the rule verification model according to the audit items, it further includes:

[0026] Setting preset rules according to identification factors;

[0027] Setting the rule verification model according to the identification factors corresponding to each audit item.

[0028] In a possible implementation of the first aspect, after generating the audit prompt information according to the verification result, it further includes:

[0029] Sending the generated audit prompt information to the terminal.

[0030] In a second aspect, an embodiment of the present application provides a data audit system, including:

[0031] An acquisition module for acquiring detection information;

[0032] A determination module for inputting a data review request and the detection information into a project determination model for processing to obtain a review project corresponding to the data review request and the detection information;

[0033] An invocation module for invoking a rule verification model corresponding to the review project according to the review project;

[0034] A verification module for verifying the detection information based on a preset rule of the rule verification model;

[0035] A prompt module for generating a review prompt message according to a verification result.

[0036] In a third aspect, an embodiment of the present application provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the data review method described in the foregoing first aspect are implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the data review method described in the foregoing first aspect are implemented.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, and when the computer program product runs on a terminal device, the terminal device is enabled to execute the data review method described in any one of the foregoing first aspects.

[0039] It can be understood that the beneficial effects of the foregoing second aspect to fifth aspect can refer to the relevant descriptions in the foregoing first aspect, and will not be elaborated herein.

[0040] The beneficial effects of the embodiment of the present application compared with the prior art are:

[0041] The data review method and system provided by the embodiment of the present application can, after determining a review project based on detection information generated by an on-vehicle diagnostic system and a data review request submitted by a user, automatically invoke a rule verification model of the review project to verify the detection information, and can automatically perform loss appraisal based on the detection information and the data review request, effectively improving the efficiency and accuracy of vehicle loss appraisal, and effectively solving the problem that the existing vehicle loss appraisal method cannot efficiently and accurately appraise the loss of a vehicle. Description of the Drawings

[0042] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0043] Figure 1 is a schematic flowchart of a data review method according to an embodiment of the present application;

[0044] Figure 2 is a schematic structural diagram of a data review system of the present application;

[0045] Figure 3 is a schematic structural diagram of a server provided by an embodiment of the present application. Detailed implementation manners

[0046] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0047] It should be understood that when used in the specification and claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0048] It should also be understood that the term "and / or" used in the specification and claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0049] As used in the specification and claims of the present application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0050] In addition, in the description of the specification and claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0051] References to "one embodiment" or "some embodiments" or the like described in the specification of this application mean that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0052] The data review method mentioned in this application is mainly used for data review of the loss assessment and pricing for the repair of vehicles involved in accidents, that is, the survey and loss assessment of vehicles. The survey and loss assessment of vehicles refers to comprehensively analyzing the vehicle collision and accident scene through scientific and systematic professional inspection, testing, and survey means, and using vehicle loss assessment materials and repair data to assess the loss and price the vehicle collision repair.

[0053] The data review method provided by the embodiments of this application can be applied to terminal devices such as mobile phones, tablet computers, servers, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiments of this application do not impose any restrictions on the specific types of terminal devices.

[0054] This application relates to artificial intelligence technology. In all embodiments of this application, the above data review method can be based on existing machine learning models, neural network models, and deep learning network models. By obtaining the detection information and data review requests, the corresponding review items can be quickly determined, thereby effectively improving the efficiency of loss appraisal, enhancing the operating efficiency of the computer, and reducing the occupation of computer resources.

[0055] Please refer to Figure 1 , Figure 1 shows a schematic flowchart of the data review method provided by this application. By way of example and not limitation, the above data review method includes:

[0056] S101: Obtain detection information.

[0057] Specifically, the detection information of the vehicle can be obtained by setting a scan fault information identification code through a terminal.

[0058] Specifically, the detection information of the vehicle is obtained by scanning a fault identification code with a handheld terminal.

[0059] Specifically, the fault information of automotive electronic components is read through an On-Board Diagnostics (OBD) system, and a corresponding fault information identification code is generated according to the fault information. That is, the automotive electronic components are subjected to fault detection through the on-board diagnostic system. When a fault is detected in a certain electronic component, the fault detection information of the electronic component is stored in a coded manner, and the fault information identification code is stored in a memory (such as the memory of the vehicle's control system and the storage module of a terminal device communicatively connected to the vehicle). Exemplarily, the detection information is stored in the form of a two-dimensional code, a bar code, an AR code, etc. Specifically, the coded information with fault information can be scanned by a handheld device (including a mobile phone, a tablet computer, etc.) or a computer PC, and after the scanned information code is imported into a data review system, the fault information identification code is stored in the database of the data review system.

[0060] As a possible implementation manner of this embodiment, the above S101 may include the following steps:

[0061] Obtain a fault information identification code; the fault information identification code is an identification code generated by an on-board diagnostic system according to the fault information of the vehicle's components;

[0062] Identify the fault information identification code to determine the detection information of the vehicle.

[0063] Specifically, the fault information identification code can be scanned by a handheld device (such as a mobile phone, a tablet computer, a barcode scanner connected to a computer, etc.), and the fault information of the vehicle included in the fault information identification code is identified. The above fault information code is stored in a coded form, and each code corresponds to a fault type.

[0064] S102: Input the data review request and the detection information into a project determination model for processing to obtain a review project corresponding to the data review request and the detection information.

[0065] Specifically, the project determination model is obtained by training a data review request sample set and a detection information sample set through a machine learning algorithm.

[0066] Specifically, the above data review request can be a request initiated by a claims adjuster in the data review system. The request includes the review items that need to be surveyed and determined, that is, the data review system can analyze the review items that need to be surveyed and determined based on the received data review request. Among them, the above data review system can be installed and run on a server. Exemplarily, the above server can be an insurance server of an insurance company. The above server can be communicatively connected to at least one terminal device. After the data review request is input through the input device of the terminal, the data review system can receive the data review request.

[0067] Specifically, the above data review system can also obtain vehicle pictures of the damaged vehicle to be surveyed and determined according to the data review request.

[0068] As a possible implementation manner of this embodiment, the above S102 may include the following steps:

[0069] Obtain vehicle pictures according to the data review request; the vehicle pictures are images obtained by photographing the vehicle from multiple preset directions;

[0070] Input the vehicle images and detection information into the project determination model for processing to obtain the probabilities of the vehicle for each preset review item; the project determination model is obtained by training a vehicle sample set through a machine learning algorithm;

[0071] Determine the review items corresponding to the data review request based on the probabilities of each review item.

[0072] Specifically, when receiving a data review request, obtain the fault information identification code in the data review request and the image of the damaged vehicle. The image of the damaged vehicle is an image obtained by photographing the damaged vehicle from multiple preset directions. The preset directions may include but are not limited to: directly in front, front left, left side, rear left, directly behind, rear right, right side, and front right. That is, when determining the damage of the damaged vehicle, it is necessary to take pictures of the damaged vehicle from directly in front, front left, left side, rear left, directly behind, rear right, right side, and front right of the damaged vehicle respectively, so as to obtain the directly in front image, front left image, left side image, rear left image, directly behind image, rear right image, right side image, and front right image of the damaged vehicle.

[0073] Input the multiple images and the fault information identification code into a preset audit item determination model for processing to obtain the probabilities of the damaged vehicle for each preset audit item. The preset audit item determination model is obtained by training a damaged vehicle sample set and a fault information identification code sample set through a machine learning algorithm. Each sample data in the damaged vehicle sample set includes multiple images of the damaged vehicle, the fault information identification code, and the damage items of the damaged vehicle. When training the audit item determination model, use the multiple images of the damaged vehicle and the fault information identification code included in each sample data as the input of the audit item determination model, and use the audit items of the damaged vehicle as the output of the audit item determination model.

[0074] The preset item determination model may include a convolutional neural network (CNN) and a long short-term memory network (LSTM) connected in sequence. Among them, the CNN is used to determine the feature vector of the image; the LSTM is used to determine the probabilities of the damaged vehicle for each preset audit item based on the feature vectors of multiple images of the same damaged vehicle.

[0075] Determine the audit item corresponding to the data audit request based on the probabilities of each audit item, and use the preset item with the highest probability as the audit item corresponding to the data audit request. Therefore, based on the multiple images of the damaged vehicle and the OBD detection code in the data audit request, the corresponding audit item can be determined.

[0076] S103: Invoke the rule verification model corresponding to the audit item according to the audit item.

[0077] Specifically, corresponding rule verification models can be set in the data audit system in advance according to different audit items. First, determine the identification factors according to the audit items (different scenarios, different items), and then form the rule verification model of the audit item according to the rules of all the identification factors of the audit item.

[0078] Exemplarily, if the audit item is night vehicle insurance, the rule verification model for night vehicle inspection includes the rules corresponding to the identification factor of the reporting time and the rules corresponding to the identification factor of the OBD detection time. Another example is that if the audit item is to detect whether the airbag computer needs to be replaced, the rule verification model for detecting whether the airbag computer needs to be replaced includes the rules corresponding to the identification factor of the vehicle model, the rules corresponding to the identification factor of the auto parts model, and the rules corresponding to the identification factor of the fault information identification code.

[0079] As a possible implementation manner of this embodiment, the following steps may further be included before the above S103:

[0080] Set preset rules according to the recognition factors;

[0081] Set up a rule verification model according to the recognition factors corresponding to each audit item.

[0082] Specifically, when presetting the rule verification model, determine the recognition factors according to the OBD detection information, set rules according to the recognition factors, and determine the rule verification model of the audit item according to all the recognition factors of each audit item.

[0083] Among them, the rules corresponding to each recognition factor are formulated according to the audit items. By storing the rule verification models of different items in the database, when the data audit system receives a data audit request, determine the audit item according to the data audit request, and then determine the rule verification model corresponding to the audit item through the database according to the audit item.

[0084] Specifically, a unique item code can be assigned to each audit item, and the item code, item name of the audit item, and the recognition factors of the audit item are stored relatedly. After the data audit system determines the item name of the audit item corresponding to the data audit request, find the corresponding item code through the item name, and then determine the relevant recognition factors, and then combine the rules of all recognition factors to obtain the rule verification model corresponding to the audit item.

[0085] Specifically, single / composite rules can also be composed of different factors according to multiple dimensions such as different brand models, audit items, and risk forms.

[0086] Set different vehicle type rules for different brand models, set different item rules for different audit items, set different risk rules for different risk forms, and combine the rules of these multiple dimensions to generate a composite rule, and this composite rule is the rule verification model of the audit item.

[0087] S104: Verify the detection information based on the preset rules of the rule verification model.

[0088] Specifically, determine the information fields related to the current loss assessment item according to the detection information, such as vehicle model, vehicle brand, failure time, failure type, failure component information and other fields.

[0089] Specifically, match the information fields determined according to the detection information with the corresponding fields in the claims settlement system, and judge the matching result according to the preset rules of the loss assessment item, so as to determine whether there is a risk or leakage. Exemplarily, if the accident time is the same as the fault time, there is no risk for the identification factor of the accident time; for another example, if the reported faulty component matches the fault information of the faulty component, there is a risk for this identification factor. After verifying the fields of the detection information according to the preset rules in the rule verification model, display the identification factors with risks.

[0090] Specifically, store various vehicle models, vehicle brands, and vehicle insurance information in the database of the claims settlement system. After receiving the detection information code, obtain the fields related to the loss assessment item in the database of the claims settlement system based on the loss assessment item. And perform matching verification on the fields of this field and the detection information.

[0091] As a possible implementation manner of this embodiment, the above S104 may include the following steps:

[0092] Obtain information fields according to the detection information;

[0093] Obtain the verification fields corresponding to the information fields;

[0094] Perform matching verification on the information fields and the corresponding verification fields according to the preset rules.

[0095] S105: Generate an audit prompt message according to the verification result.

[0096] Specifically, after all the rules are verified, generate an audit prompt message according to the identification factors with risks, and send the audit prompt message to the terminal for display through the display device of the terminal, so as to facilitate the surveyors to view the risk information in real time.

[0097] In one embodiment, the above audit prompt message is stored in a block created on the blockchain network, and the information is shared between different platforms through the blockchain. The audit prompt message includes vehicle image information, detection information, and the corresponding verification results.

[0098] Blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms. Blockchain, in essence, is a decentralized database, a string of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0099] As can be seen from the above, the data review method provided in this embodiment can, after determining the review items based on the detection information generated by the on-vehicle diagnostic system and the data review request submitted by the user, automatically call the rule verification model of the review item to verify the detection information, and can automatically conduct loss appraisal based on the detection information and the data review request, effectively improving the efficiency and accuracy of vehicle loss appraisal, and effectively solving the problem that the existing vehicle loss appraisal methods cannot efficiently and accurately conduct vehicle loss appraisal.

[0100] Corresponding to the data review method described in the above embodiment, Figure 2 the structural block diagram of the data review system provided in an embodiment of the present application is shown. For ease of description, only the parts related to the embodiment of the present application are shown.

[0101] Referring to Figure 2 , the data review system includes an acquisition module 11, a determination module 12, a call module 13, a verification module 14, and a prompt module 15.

[0102] The acquisition module 11 is used to acquire detection information.

[0103] The determination module 12 is used to input the data review request and the detection information into the item determination model for processing to obtain the review items corresponding to the data review request and the detection information.

[0104] The call module 13 is used to call the rule verification model corresponding to the review item according to the review item.

[0105] The verification module 14 is used to verify the detection information based on the preset rules of the rule verification model.

[0106] The prompt module 15 is used to generate a review prompt message according to the verification result.

[0107] As an embodiment of the present application, the determination module 12 includes a picture acquisition unit, a processing unit, and a determination unit.

[0108] The picture acquisition unit is used to acquire vehicle pictures according to the data review request; the vehicle pictures are images taken of the vehicle from multiple preset orientations;

[0109] The processing unit is used to input the vehicle images and the detection information into the item determination model for processing to obtain the probabilities of the vehicle for each preset review item; the item determination model is obtained by training a vehicle sample set through a machine learning algorithm;

[0110] The determination unit is used to determine the review items corresponding to the data review request based on the probabilities of each review item.

[0111] As an embodiment of the present application, the above verification module 14 includes: an information field acquisition unit, a verification field acquisition unit, and a verification unit.

[0112] The information field acquisition unit is used to acquire the information field according to the detection information;

[0113] The verification field acquisition unit is used to acquire the verification field corresponding to the information field;

[0114] The verification unit is used to perform matching verification on the information field and the corresponding verification field according to a preset rule.

[0115] As an embodiment of the present application, the above acquisition module 11 includes an identification code acquisition unit and an identification unit.

[0116] The above identification code acquisition unit is used to acquire a fault information identification code; the fault information identification code is an identification code generated by an on-vehicle diagnostic system according to the fault information of vehicle components;

[0117] The above identification unit is used to identify the fault information identification code to determine the detection information of the vehicle.

[0118] As an embodiment of the present application, the above acquisition module 11 acquires the detection information of the vehicle by scanning the fault identification code with a handheld terminal.

[0119] As an embodiment of the present application, the above data review system further includes a rule setting module and a model setting module.

[0120] The above rule setting module is used to set a preset rule according to an identification factor;

[0121] The above model setting module is used to set a rule verification model according to the identification factors corresponding to each review item.

[0122] As an embodiment of the present application, the above data review system further includes a sending module.

[0123] The above sending module is used to send the generated review prompt information to the terminal.

[0124] It should be noted that for the information interaction, execution process, etc. between the above modules / units, since they are based on the same concept as the method embodiment of the present application, their specific functions and the technical effects brought can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0126] As can be seen from the above, the data review system provided in this embodiment can also, after determining the review items based on the detection information generated by the on-board diagnostic system and the data review request submitted by the user, automatically call the rule verification model of the review item to verify the detection information, and can automatically perform loss appraisal based on the detection information and the data review request, effectively improving the efficiency and accuracy of vehicle loss appraisal, and effectively solving the problem that the current vehicle loss appraisal method cannot efficiently and accurately appraise the vehicle loss.

[0127] Figure 3 It is a schematic structural diagram of a server provided in an embodiment of this application. As Figure 3 shown, the server 3 of this embodiment includes: at least one processor 30 ( Figure 3 only one is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30. When the processor 30 executes the computer program 32, the steps in any of the foregoing data review method embodiments are implemented.

[0128] The server 3 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The server may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art can understand that Figure 3 this is only an example of the server 3 and does not constitute a limitation on the server 3. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0129] The so-called processor 30 may be a Central Processing Unit (CPU), and the processor 30 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0130] In some embodiments, the memory 31 may be an internal storage unit of the server 3, such as the hard disk or memory of the server 3. In other embodiments, the memory 31 may also be an external storage device of the server 3, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the server 3. Further, the memory 31 may also include both the internal storage unit of the server 3 and the external storage device. The memory 31 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been output or will be output.

[0131] An embodiment of the present application further provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, the steps in any of the above method embodiments are implemented.

[0132] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above method embodiments can be implemented.

[0133] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal is caused to implement the steps in the above method embodiments when executed.

[0134] When 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, to implement all or part of the processes in the above method embodiments of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0135] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0137] In the embodiments provided in this application, it should be understood that the disclosed device / equipment and method can be implemented in other ways. For example, the device / network equipment embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0138] The unit described as the separating component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A data audit method, characterized in that, it includes: Obtain detection information; Input the data audit request and the detection information into a project determination model for processing to obtain an audit project corresponding to the data audit request and the detection information; vehicle pictures of the damaged vehicle to be surveyed and appraised can be obtained according to the data audit request, and the project determination model is obtained by training a data audit request sample set and a detection information sample set through a machine learning algorithm; Call a rule verification model corresponding to the audit project according to the audit project; Verify the detection information based on the preset rules of the rule verification model; Generate an audit prompt message according to the verification result; Among them, the obtaining of the detection information includes: Obtain a fault information identification code; the fault information identification code is an identification code generated by an on-vehicle diagnostic system according to the fault information of vehicle components; Scan and identify the fault information identification code through a handheld terminal to determine the detection information of the vehicle.

2. The data audit method according to claim 1, characterized in that, Determining an audit project according to the data audit request and the detection information includes: Obtain vehicle pictures according to the data audit request; the vehicle pictures are images obtained by photographing the vehicle from multiple preset directions; Input the vehicle pictures and the detection information into a project determination model for processing to obtain the probability of the vehicle for each preset audit project; Determine the audit project corresponding to the data audit request based on the probabilities of each audit project.

3. The data audit method according to claim 1, characterized in that, The verifying the detection information based on the preset rules of the rule verification model includes: Obtain information fields according to the detection information; Obtain verification fields corresponding to the information fields; Match and verify the information fields with the corresponding verification fields according to the preset rules.

4. The data audit method according to claim 1, characterized in that, Before calling the rule verification model corresponding to the audit project according to the audit project, it further includes: Set preset rules according to identification factors; Set the rule verification model according to the identification factors corresponding to each audit project.

5. The data audit method according to claim 1, characterized in that, Store the audit prompt message in a blockchain network.

6. A data audit system, characterized in that, it includes: An obtaining module for obtaining detection information; A determining module for inputting the data audit request and the detection information into a project determination model for processing to obtain an audit project corresponding to the data audit request and the detection information; vehicle pictures of the damaged vehicle to be surveyed and appraised can be obtained according to the data audit request, and the project determination model is obtained by training a data audit request sample set and a detection information sample set through a machine learning algorithm; A calling module for calling a rule verification model according to the audit project; A verifying module for verifying the detection information based on the preset rules of the rule verification model; A prompting module for generating an audit prompt message according to the verification result; Among them, the obtaining module includes an identification code obtaining unit and an identifying unit; The identification code obtaining unit is used to obtain a fault information identification code; the fault information identification code is an identification code generated by an on-vehicle diagnostic system according to the fault information of components of a vehicle; The identifying unit is used to scan and identify the fault information identification code through a handheld terminal to determine the detection information of the vehicle.

7. A server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, when the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, wherein, when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images