Vehicle insurance survey evidence obtaining method and device, computer equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence and information security, and relates to a vehicle insurance survey evidence obtaining method, which comprises the steps of receiving a vehicle insurance survey request initiated by a user terminal, and extracting survey type features from the vehicle insurance survey request; sending a survey guide instruction to the user terminal according to the survey type feature; acquiring a survey data set corresponding to the vehicle insurance survey request according to the survey guide instruction; and identifying key information corresponding to each survey data in the survey data set by using an OCR technology, and classifying the survey data set according to a preset classification rule and the key information to obtain vehicle insurance survey evidence of the vehicle insurance survey request. The invention further provides a vehicle insurance survey evidence obtaining device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and privacy information and the like of the user can be stored in a block chain. According to the invention, the vehicle insurance survey evidence can be obtained more accurately, and the vehicle insurance survey efficiency is improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and information security technology, and in particular to a method for obtaining evidence for vehicle insurance investigation. Background Art

[0002] With the increase in the number of cars in my country, the auto insurance market has also shown a rapid development trend. The traditional auto insurance investigation method is generally for customers to wait for surveyors to arrive at the scene to collect evidence from the accident scene after reporting the accident. In the traditional auto insurance investigation method, the process of surveyors arriving at the scene not only causes traffic congestion, but the process is also cumbersome, time-consuming and labor-intensive.

[0003] With the continuous development and application of technologies such as big data and audio, online auto insurance investigation methods have gradually replaced traditional auto insurance investigation methods. Online auto insurance investigation methods generally use communication software, telephones and other tools, and collect evidence from the accident scene from text data, audio data, image data, etc. uploaded by users, thereby improving the efficiency of auto insurance investigations.

[0004] However, in the online auto insurance investigation method, due to the professionalism of the customers and other reasons, it is impossible to accurately obtain auto insurance investigation evidence from the text data, audio data, and image data uploaded by the users. At this time, the customers are required to re-upload the data until the auto insurance investigation evidence can be accurately obtained, resulting in poor efficiency of auto insurance investigation. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for obtaining evidence for vehicle insurance investigation, and its main purpose is to improve the accuracy of obtaining evidence for vehicle insurance investigation to improve the efficiency of vehicle insurance investigation.

[0006] In order to solve the above technical problems, the present application embodiment provides a method for obtaining vehicle insurance investigation evidence, which adopts the following technical solution:

[0007] receiving a vehicle insurance survey request initiated by a user terminal, and extracting survey type features from the vehicle insurance survey request;

[0008] Sending a survey guidance instruction to the user terminal according to the survey type characteristics;

[0009] collecting a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction;

[0010] The key information corresponding to each survey data in the survey data set is identified by using OCR technology, and the survey data set is classified according to a preset classification rule and the key information to obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

[0011] Furthermore, extracting the inspection type feature from the vehicle insurance inspection request includes:

[0012] Obtaining the accident information requested by the vehicle insurance investigation, and extracting text information of the accident information;

[0013] Splitting the text information to obtain a word segmentation set;

[0014] Extracting keywords from the word segmentation set using a pre-trained classification model;

[0015] The survey type characteristics are determined according to the keywords.

[0016] Furthermore, after receiving the vehicle insurance survey request initiated by the user terminal and extracting the survey type feature from the vehicle insurance survey request, the method further includes:

[0017] Get the list of surveyors in idle state and the corresponding processing levels;

[0018] Determining the accident type of the vehicle insurance investigation request according to the accident information;

[0019] According to the processing level and the accident type, a surveyor with the highest matching degree with the vehicle insurance survey request is determined.

[0020] Further, the sending of the survey guidance instruction to the user terminal according to the survey type feature includes:

[0021] Establishing a video call connection between the user terminal and the surveyor terminal;

[0022] According to the video call and the accident information, a survey guidance instruction is sent to the user terminal.

[0023] Furthermore, the step of establishing a video call connection between the user terminal and the surveyor terminal includes:

[0024] receiving a first call request submitted by a user, and sending the first call request to the surveyor's survey terminal;

[0025] When the surveyor agrees to receive the first call request, the video call connection between the user terminal and the surveyor is successfully established.

[0026] Furthermore, the method of establishing a video call connection between the user terminal and the surveyor terminal further includes:

[0027] receiving a second call request submitted by the surveyor, and sending the second call request to the user terminal;

[0028] When the user agrees to receive the second call request at the user terminal, the video call connection between the user terminal and the surveyor is successfully established.

[0029] Furthermore, after establishing the video call connection between the user terminal and the surveyor terminal, the method further includes:

[0030] extracting audio data from the video call data;

[0031] Converting the audio data into text data;

[0032] A quality detection operation is performed on the audio data and the text data.

[0033] In order to solve the above technical problems, the embodiment of the present application further provides a device for obtaining evidence for vehicle insurance investigation, which adopts the following technical solution:

[0034] A receiving module, configured to receive a vehicle insurance survey request initiated by a user terminal, and extract survey type features from the vehicle insurance survey request;

[0035] A sending module, used for sending a survey guidance instruction to the user terminal according to the survey type characteristics;

[0036] A collection module, used for collecting a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction;

[0037] The classification module is used to use OCR technology to identify key information corresponding to each survey data in the survey data set, and after classifying the survey data set according to preset classification rules and the key information, obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

[0038] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0039] receiving a vehicle insurance survey request initiated by a user terminal, and extracting survey type features from the vehicle insurance survey request;

[0040] Sending a survey guidance instruction to the user terminal according to the survey type characteristics;

[0041] collecting a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction;

[0042] The key information corresponding to each survey data in the survey data set is identified by using OCR technology, and the survey data set is classified according to a preset classification rule and the key information to obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0044] receiving a vehicle insurance survey request initiated by a user terminal, and extracting survey type features from the vehicle insurance survey request;

[0045] Sending a survey guidance instruction to the user terminal according to the survey type characteristics;

[0046] collecting a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction;

[0047] The key information corresponding to each survey data in the survey data set is identified by using OCR technology, and the survey data set is classified according to a preset classification rule and the key information to obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

[0048] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0049] It can automatically identify the type of vehicle insurance investigation request, improve the processing efficiency of vehicle insurance investigation request, and also improve user satisfaction.

[0050] By sending survey guidance instructions to users, users can accurately capture and upload correct data as evidence for auto insurance surveys, avoiding the need for surveyors to find evidence for auto insurance surveys in the information uploaded by users and preventing the situation where evidence for auto insurance surveys cannot be obtained, thereby improving the efficiency of auto insurance surveys and the accuracy of obtaining evidence for auto insurance surveys.

[0051] By collecting the survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction, vehicle insurance survey evidence can be accurately obtained, thereby improving the efficiency of vehicle insurance survey and the accuracy of vehicle insurance survey evidence.

[0052] OCR technology can automatically identify and classify the evidence obtained during vehicle insurance investigation, which indirectly improves the efficiency of vehicle insurance investigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0055] Figure 2A flowchart of an embodiment of a method for obtaining automobile insurance investigation evidence according to the present application;

[0056] Figure 3 It is a structural schematic diagram of an embodiment of a device for obtaining evidence for automobile insurance investigation according to the present application;

[0057] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0059] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0060] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0061] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0062] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0063] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0064] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0065] It should be noted that the method for obtaining vehicle insurance investigation evidence provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the device for obtaining vehicle insurance investigation evidence is generally set in the server / terminal device.

[0066] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0067] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for obtaining vehicle insurance investigation evidence according to the present application. The method for obtaining vehicle insurance investigation evidence comprises the following steps:

[0068] S201. Receive a vehicle insurance survey request initiated by a user terminal, and extract survey type features from the vehicle insurance survey request.

[0069] In this embodiment, the user terminal includes but is not limited to handheld terminals, such as mobile phones, iPads, etc.; the auto insurance investigation request refers to a request made by a user to the insurance company for an accident scene investigation after an accident occurs while driving a vehicle; the investigation type feature refers to a feature used to describe and classify specific types of investigation tasks, such as pedestrian collision events, vehicle collision events, and single-vehicle collision events; when a auto insurance investigation request initiated by a user through a user terminal or an online platform is received, a confirmation notification is automatically sent to the user, informing the user that the auto insurance investigation request has been accepted and is being processed in the next step, and the investigation type feature corresponding to the auto insurance investigation request is extracted from the auto insurance investigation request.

[0070] In one embodiment, extracting the survey type feature from the vehicle insurance survey request includes:

[0071] Obtaining the accident information requested by the vehicle insurance investigation, and extracting text information of the accident information;

[0072] Splitting the text information to obtain a word segmentation set;

[0073] Extracting keywords from the word segmentation set using a pre-trained classification model;

[0074] The survey type characteristics are determined according to the keywords.

[0075] In this embodiment, the accident information refers to the accident information that the user brings when initiating an investigation request, such as a panoramic view of the accident, the location of the accident, the time of the accident, information about vehicles involved in the accident, a simple description of the accident, etc.; in this embodiment, the text information of the accident information is obtained, the text information is segmented to obtain multiple segmentations, and the multiple segmentation word sets are obtained into a segmentation set, and the statistical method (TF-IDF) or the Word2Vec technology of a pre-trained classification model is used to extract keywords from the segmentation set, and the investigation type characteristics are determined according to the keywords.

[0076] In this embodiment, when the accident information includes a panoramic image of the accident, a pre-trained convolutional neural model is used to extract features of the panoramic image of the accident to determine the survey type features of the vehicle insurance survey request.

[0077] In this embodiment, before extracting the inspection type features from the vehicle insurance inspection request, the classification model needs to be trained. The specific training method includes: obtaining a text sample set, preprocessing the text sample set, wherein the preprocessing includes removing irrelevant characters, punctuation marks, etc., performing word segmentation on the preprocessed text sample set to obtain a word segmentation sample set, annotating the word segmentation sample set, training the classification model using the annotated word segmentation sample set, obtaining a sample test set, and testing the trained classification model using the sample test set until the accuracy of the classification model reaches a preset threshold, and then terminating the training to obtain a trained classification model.

[0078] In one embodiment, after receiving the vehicle insurance survey request initiated by the user terminal and obtaining the accident information from the vehicle insurance survey request, the method further includes:

[0079] Get the list of surveyors in idle state and the corresponding processing levels;

[0080] Determining the accident type of the vehicle insurance investigation request according to the accident information;

[0081] According to the processing level and the accident type, a surveyor with the highest matching degree with the vehicle insurance survey request is determined.

[0082] In this embodiment, all surveyors have corresponding status identifiers, such as busy state, idle state and away state, etc. Busy state means that they are processing survey cases, idle state means that they can process survey cases, and away state means that they are not in normal working state, such as taking leave, etc. A list of surveyors in idle state and the corresponding processing level are obtained from all surveyors. The processing level refers to the processing level of the surveyor for a certain type of case, which corresponds to the survey type characteristics mentioned above. For example, the level of surveyor Xiao Li in processing pedestrian collision events is 5, the level of processing vehicle collision events is 10, and the level of processing vehicle single-body collision events is 10. 3. Surveyor Xiao Huang's level for handling pedestrian collision events is 10, the level for handling vehicle collision events is 5, and the level for handling single-vehicle collision events is 1. The pedestrian collision event refers to an event in which a vehicle hits a pedestrian, the vehicle collision event refers to an event in which at least two vehicles involved collide, and the single-vehicle collision event refers to a collision in which only one vehicle collides, such as a vehicle hitting a guardrail, a vehicle hitting a wall, etc. The processing level increases step by step from 0 to 10; preliminarily determine the accident type of the auto insurance investigation request based on the acquired accident information, and select the surveyor with the highest matching degree according to the accident type as the surveyor corresponding to the auto insurance investigation request.

[0083] In another embodiment, when the matching degree of at least two surveyors is the same, confirmation is performed based on the surveyor's years of service, etc.

[0084] In an implementable example, for example, vehicle A driven by a user has purchased Ping An auto insurance. When vehicle A driven by the user rear-ends another person's vehicle B, a panoramic picture of the accident of vehicle A rear-ending vehicle B is taken, and a mobile phone terminal is used to apply for an auto insurance investigation request on the Ping An Good Car Owner APP, and the accident information is obtained from the auto insurance investigation request. The accident information includes a panoramic picture of the accident of vehicle A rear-ending vehicle B, information about the vehicles involved in the accident (license plate numbers and frame numbers of vehicles A and B), the location of the rear-end collision, the time of the rear-end collision, a simple description of the rear-end collision, etc. When a user-initiated auto insurance investigation request is received, the user is automatically notified. A confirmation notification is sent to inform the user that the vehicle inspection request has been accepted and further processed to reassure the user. The inspection type of the auto insurance inspection request applied for by the user is extracted based on the accident information, which is the vehicle collision type. Surveyors C and D who are idle are obtained, and the level of vehicle collision events of surveyor C is 10 and the level of vehicle collision events of surveyor D is 5. The levels of corresponding vehicle collision events of surveyors C and surveyor D are compared, and according to the comparison result, it is determined that the match degree between surveyor C and the auto insurance inspection request is higher, and surveyor C is determined as the surveyor corresponding to the auto insurance inspection request.

[0085] In this embodiment, the type of the vehicle insurance survey request can be automatically identified, and the most suitable surveyor can be determined for the user, thereby improving the processing efficiency of the vehicle insurance survey request and improving the user satisfaction.

[0086] S202: Send a survey guidance instruction to the user terminal according to the survey type characteristics.

[0087] Since it is often difficult to obtain correct automobile insurance investigation evidence from text data, audio data, image data, etc. uploaded by users without guidance, in this embodiment, investigation guidance instructions are sent to users based on the accident information, and users use the text data, audio data, image data, etc. uploaded by the user terminal to obtain correct automobile insurance investigation evidence based on the investigation guidance instructions.

[0088] In one embodiment, the sending of the survey guidance instruction to the user terminal according to the accident information includes:

[0089] Establishing a video call connection between the user terminal and the surveyor terminal;

[0090] According to the video call and the accident information, a survey guidance instruction is sent to the user terminal.

[0091] In this embodiment, the call interface of the user terminal in the video call is designed with a special interactive area called "mask guidance area" for displaying the interface of guidance instructions. The call interface of the surveyor terminal in the video call is designed with a special interactive area called "instruction sending area" for the user to send guidance instructions. The interfaces of both parties contain conventional operation control buttons, such as hanging up, screenshot, mute, switching cameras, turning on flash, etc.

[0092] When the video call between the user terminal and the surveyor terminal is successfully connected, the real-time image transmitted by the camera of the user terminal is received and sent to the surveyor terminal. The surveyor selects the corresponding instruction in the instruction sending area according to the real-time image and sends it, such as instructions to walk forward, walk backward, etc. After the user terminal receives the guidance instruction sent by the surveyor terminal in the mask guidance area, it adjusts the position operation according to the instruction to meet the needs of the surveyor.

[0093] In this embodiment, the guiding instruction includes but is not limited to animation form, text form or image form.

[0094] It is worth mentioning that when the user performs actions according to the guidance instructions, the user does not need to perform additional operations.

[0095] In another embodiment, establishing a video call connection between the user terminal and the surveyor terminal includes:

[0096] receiving a first call request submitted by a user, and sending the first call request to the surveyor's survey terminal;

[0097] When the surveyor agrees to receive the first call request, the video call connection between the user terminal and the surveyor is successfully established.

[0098] In this embodiment, the first call request refers to a call request initiated by the user. When the first call request initiated by the user is received, the SDK is initialized. After the SDK is successfully initialized, the first call request is sent to the surveyor terminal. At this time, the surveyor terminal will display an incoming call reminder. When the surveyor clicks to connect on the surveyor terminal, the surveyor terminal and the user terminal successfully establish a connection through a network communication protocol (such as websoket).

[0099] Because in the related art, the surveyor is waiting for the customer's call when processing the auto insurance survey request, resulting in the surveyor's processing efficiency being slow.

[0100] In another embodiment, the method of establishing a video call connection between the user terminal and the surveyor terminal further includes:

[0101] receiving a second call request submitted by the surveyor, and sending the second call request to the user terminal provider;

[0102] When the user agrees to receive the second call request at the user terminal, the video call connection between the user terminal and the surveyor is successfully established.

[0103] In this embodiment, the second call request refers to a video call request initiated by the surveyor to the user terminal at the surveyor terminal; when the second call request initiated by the surveyor is received, the SDK is initialized, and after the SDK is successfully initialized, the second call request is sent to the user terminal, at which time the user terminal will display an incoming call reminder, and when the user clicks to connect at the user terminal, the surveyor terminal and the user terminal successfully establish a connection through a network communication protocol (such as websoket).

[0104] Continuing with the example in step S1, after confirming the corresponding surveyor C, the user opens the car owner applet, clicks to initiate a video, and the SDK begins to initialize. When the SDK is initialized successfully, the surveyor terminal displays an incoming call. When the surveyor clicks the connect button on the surveyor, the surveyor terminal and the user terminal successfully establish a connection through the websoket communication protocol, or when surveyor C receives the user's auto insurance survey request, a call request is initiated to the user terminal through the surveyor terminal. When the user clicks the connect button on the user terminal, the surveyor terminal and the user terminal successfully establish a connection through the websoket communication protocol. When the surveyor terminal and the user terminal are successfully connected, the surveyor terminal displays the corresponding interface, and the user terminal displays the corresponding interface. The surveyor sends guidance instructions to the user in the interactive area of ​​the "instruction sending area" based on the real-time image transmitted by the user, prompting the user to aim the camera at the rear-end collision site and take a picture of the driver's license, etc.

[0105] In this embodiment, by sending survey guidance instructions to users, users can accurately capture and upload correct data as evidence for auto insurance surveys, avoiding the need for surveyors to find evidence for auto insurance surveys in the materials uploaded by users and preventing the situation where evidence for auto insurance surveys cannot be obtained, thereby improving the efficiency of auto insurance surveys and the accuracy of obtaining evidence for auto insurance surveys; a two-way video call mechanism is established to avoid the situation where surveyors are always waiting for customer calls. Surveyors can actively send video call invitations to users, thereby improving the efficiency of auto insurance survey requests.

[0106] S203: Collect a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction.

[0107] In this embodiment, after the surveyor terminal successfully establishes a connection with the user terminal, the user terminal shoots the survey data (such as driver's license information, license plate number information, etc.) according to the guidance instructions of the mask guidance area of ​​the call interface, and the user terminal adjusts the direction and angle according to the mask guidance area of ​​the call interface. The surveyor terminal performs screenshot or recording operations in the real-time image transmitted by the user to obtain the corresponding survey data (the location of vehicle damage, etc.), and summarizes the multiple survey data obtained to obtain a survey data set corresponding to the motor vehicle insurance survey request.

[0108] In one embodiment, collecting the survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction includes:

[0109] instructing the user terminal to adjust the shooting angle and position according to the survey guidance instruction, and obtaining a real-time image after the user terminal adjusts the shooting angle and position;

[0110] Performing a capture operation or a recording operation on the real-time image to obtain a first image data set;

[0111] Acquire images taken by the user terminal according to the survey guidance instruction to obtain a second image data set;

[0112] The first image data set, the second image data set and the accident information included in the vehicle insurance survey request are aggregated to obtain a survey data set.

[0113] In this embodiment, the first image data set refers to the real-time image transmitted by the user terminal when the user terminal continuously adjusts the camera position and angle of the user terminal according to the survey guidance instruction until evidence of the motor vehicle insurance survey can be obtained, and the multiple image data generated by the surveyor performing screenshot and recording operations on the real-time image; the second image data set refers to the multiple image data (such as driver's license image, vehicle registration certificate image, identity card image, etc.) taken by the user terminal according to the survey guidance instruction, and the first image data set and the second image data set obtained and the accident information contained in the motor vehicle insurance survey request initiated by the user terminal are summarized to obtain the survey data set.

[0114] In an implementable example of steps S1 and S2, after the user terminal receives the survey guidance instruction sent by the surveyor C terminal in the mask guidance area, the user terminal aims the camera at the rear-end collision site according to the survey guidance instruction so that the surveyor terminal can intercept and record the real-time image, and make some minor adjustments to the angle and position through the surveyor's audio. When the text instruction sent by the surveyor is not understood, the surveyor can be asked to change to another form of survey guidance instruction (such as animation instruction) through audio or text until the first image data set is collected. Then, according to the survey guidance instruction sent by the surveyor terminal received by the user terminal in the mask guidance area, the driver's license, vehicle registration and ID card information are photographed, or the camera is aimed at the driver's license, vehicle registration and ID card for the surveyor to intercept; after collecting all the image data, the surveyor extracts the rear-end collision information sent by the user, summarizes all the image data and rear-end collision information, and generates a survey data set.

[0115] In this embodiment, the survey data set corresponding to the vehicle insurance survey request is collected according to the survey guidance instruction, so that the vehicle insurance survey evidence can be accurately obtained, thereby improving the efficiency of the vehicle insurance survey and the accuracy of the vehicle insurance survey evidence.

[0116] S204, using OCR technology to identify key information corresponding to each survey data in the survey data set, and after classifying the survey data set according to a preset classification rule and the key information, obtaining the vehicle insurance survey evidence of the vehicle insurance survey request.

[0117] In this embodiment, OCR technology refers to optical character recognition technology; the preset classification rules include classifying document type image data into one category and accident photo type into another category; using OCR technology to automatically identify key information of each survey data, using preset classification rules and key information to classify the survey data set, and also numbering each survey data according to the number of the mask guidance area to obtain structured motor vehicle insurance survey evidence for the motor vehicle insurance survey request.

[0118] In one embodiment, the identifying key information corresponding to each survey data in the survey data set by using OCR technology includes:

[0119] Identifying image survey data in the form of images and performing preprocessing operations on the image survey data;

[0120] Use OCR technology to extract survey data features of each image survey data;

[0121] The survey data features are converted into text format to obtain key information corresponding to each survey data.

[0122] In this embodiment, the preprocessing operations include but are not limited to image enhancement, binarization, noise removal, etc. to improve the accuracy of feature extraction, use OCR technology to scan the pixels in the image, and extract the features of the image, convert the text, numbers, and graphics in the image into text format, and obtain the key information corresponding to each survey data.

[0123] In the example that can be implemented following the above steps S1, S2, and S3, after all the survey data sets are collected, the key information of each survey data is automatically identified using OCR technology, the user's driver's license, vehicle registration certificate, and license plate number are classified into one category, and the photos of the accident are classified into one category, thereby obtaining structured vehicle insurance survey evidence for the vehicle insurance survey request.

[0124] In one embodiment, after the video call connection between the user terminal and the surveyor terminal is disconnected, the method further includes:

[0125] extracting audio data from the video call data;

[0126] Converting the audio data into text data;

[0127] A quality detection operation is performed on the audio data and the text data.

[0128] In this embodiment, a preset audio extraction tool is used to extract audio data from the video call data, for example, a trained convolutional model is used for extraction; a preset speech recognition tool is used to convert the audio data into text data, and quality detection is performed on the audio data and text data. The quality detection includes detecting the volume in the surveyor's audio data and counting the required and prohibited words in the text data.

[0129] Specifically, for example, audio data is extracted from the video call data through a trained convolutional model, speech sequences of different timbres are extracted from the audio data, the timbre similarities of speech sequences of different timbres and the preset speech features in the speech feature library are calculated respectively, the timbre sequence of the surveyor is determined according to the timbre similarity, at least one volume threshold (such as the minimum acceptable volume, comfortable volume, and irritable volume) is pre-set, and the volume corresponding to the surveyor's timbre sequence is compared with at least one pre-set volume threshold to determine whether the volume corresponding to the surveyor's timbre sequence is within that threshold, thereby completing the detection of the surveyor's audio data; if the audio data has a lot of noise, the surveyor's audio data needs to be pre-processed before the volume comparison, including noise removal, etc., wherein the speech feature library stores the timbre sequences of all surveyors;

[0130] A preset speech recognition tool is used to convert the surveyor's timbre sequence into the surveyor's text data; the vocabulary of the must-say and forbidden words in the resume is matched and counted in the surveyor's text data through a string matching algorithm (such as the KMP algorithm, etc.) to complete the detection of the surveyor's text data.

[0131] In this embodiment, the OCR technology can automatically identify and classify the acquired auto insurance investigation evidence, which indirectly improves the efficiency of the auto insurance investigation. By performing quality inspection on the audio data and text data of the video, it not only assesses the work standardization of the investigation staff, but also improves customer satisfaction.

[0132] The present application receives a vehicle insurance survey request initiated by a user terminal, extracts survey type features from the vehicle insurance survey request, can automatically identify the type of vehicle insurance survey request, and determine the most suitable surveyor for the user, thereby improving the processing efficiency of vehicle insurance survey requests and user satisfaction.

[0133] The present application sends survey guidance instructions to the user terminal according to the survey type characteristics, so that the user can accurately capture and upload correct data as motor vehicle insurance survey evidence, avoiding the need for surveyors to find motor vehicle insurance survey evidence in the materials uploaded by users and preventing the situation where motor vehicle insurance survey evidence cannot be obtained, thereby improving the efficiency of motor vehicle insurance surveys and the accuracy of obtaining motor vehicle insurance survey evidence.

[0134] The present application collects the survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction, and can accurately obtain vehicle insurance survey evidence, thereby improving the efficiency of vehicle insurance survey and the accuracy of vehicle insurance survey evidence.

[0135] This application can automatically identify and classify the obtained auto insurance investigation evidence through OCR technology, which indirectly improves the efficiency of auto insurance investigation. By performing quality inspection on the audio data and text data of the video, it not only assesses the work standardization of the investigation staff, but also improves customer satisfaction.

[0136] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned auto insurance investigation evidence and user information, the above-mentioned auto insurance investigation evidence and user information can also be stored in a blockchain node.

[0137] The blockchain referred to in this application is a new application model 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.

[0138] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0139] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0140] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0141] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0142] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a device for obtaining evidence for vehicle insurance investigation. Figure 2 Corresponding to the method embodiment shown, the apparatus can be specifically applied to various computer devices.

[0143] like Figure 3 As shown, the device 300 for obtaining risk investigation evidence in this embodiment includes: a receiving module 301, a sending module 302, a collection module 303, and a classification module 304. Among them:

[0144] The receiving module 301 is used to receive a vehicle insurance survey request initiated by a user terminal, and extract survey type features from the vehicle insurance survey request;

[0145] A sending module 302, configured to send a survey guidance instruction to the user terminal according to the survey type characteristics;

[0146] A collection module 303, configured to collect a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction;

[0147] The classification module 304 is used to use OCR technology to identify key information corresponding to each survey data in the survey data set, and classify the survey data set according to a preset classification rule and the key information to obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

[0148] In this embodiment, the present application receives a vehicle insurance survey request initiated by a user terminal through a receiving module, extracts survey type features from the vehicle insurance survey request, can automatically identify the type of vehicle insurance survey request, and determine the most suitable surveyor for the user, thereby improving the processing efficiency of the vehicle insurance survey request and improving user satisfaction.

[0149] The present application sends an inspection guidance instruction to the user terminal according to the inspection type characteristics used by the sending module, so that the user can accurately capture and upload correct data as evidence for vehicle insurance inspection, avoiding the need for surveyors to find vehicle insurance inspection evidence in the materials uploaded by users and preventing the situation where vehicle insurance inspection evidence cannot be obtained, thereby improving the efficiency of vehicle insurance inspection and the accuracy of obtaining vehicle insurance inspection evidence.

[0150] This application collects the survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction used by the collection module, and can accurately obtain vehicle insurance survey evidence, thereby improving the efficiency of vehicle insurance survey and the accuracy of vehicle insurance survey evidence.

[0151] This application uses OCR technology in the classification module to automatically identify and classify the acquired auto insurance investigation evidence, which indirectly improves the efficiency of auto insurance investigation. By performing quality inspection on the audio data and text data of the video, it not only assesses the work standardization of the investigation staff, but also improves customer satisfaction.

[0152] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0153] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0154] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0155] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the method for obtaining evidence of vehicle insurance investigation, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0156] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the method for obtaining the vehicle insurance investigation evidence.

[0157] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0158] During the implementation of the electronic device of the present application, it can automatically identify the type of vehicle insurance investigation request and determine the most suitable surveyor for the user, thereby improving the processing efficiency of vehicle insurance investigation requests and improving user satisfaction; by sending an investigation guidance instruction to the user, the user can accurately shoot and upload the correct data as vehicle insurance investigation evidence, avoiding the need for the surveyor to find the vehicle insurance investigation evidence in the materials uploaded by the user and preventing the situation where the vehicle insurance investigation evidence cannot be obtained, thereby improving the efficiency of vehicle insurance investigation and the accuracy of obtaining vehicle insurance investigation evidence; according to the investigation guidance instruction, the investigation data set corresponding to the vehicle insurance investigation request is collected, and the vehicle insurance investigation evidence can be accurately obtained, thereby improving the efficiency of vehicle insurance investigation and the accuracy of vehicle insurance investigation evidence; through the OCR technology, the obtained vehicle insurance investigation evidence can be automatically identified and classified, indirectly improving the efficiency of vehicle insurance investigation, and by performing quality inspection on the audio data and text data of the video, while assessing the work standardization of the investigation staff, it also improves customer satisfaction.

[0159] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the method for obtaining vehicle insurance investigation evidence as described above.

[0160] During the implementation process, the computer-readable storage medium of the present application can automatically identify the type of vehicle insurance survey request and determine the most suitable surveyor for the user, thereby improving the processing efficiency of vehicle insurance survey requests and improving user satisfaction; by sending survey guidance instructions to the user, the user can accurately shoot and upload correct data as vehicle insurance survey evidence, avoiding the need for the surveyor to find vehicle insurance survey evidence in the materials uploaded by the user and preventing the situation where the vehicle insurance survey evidence cannot be obtained, thereby improving the efficiency of vehicle insurance survey and the accuracy of obtaining vehicle insurance survey evidence; according to the survey guidance instructions, the survey data set corresponding to the vehicle insurance survey request is collected, and the vehicle insurance survey evidence can be accurately obtained, thereby improving the efficiency of vehicle insurance survey and the accuracy of vehicle insurance survey evidence; the obtained vehicle insurance survey evidence can be automatically identified and classified through OCR technology, thereby indirectly improving the efficiency of vehicle insurance survey, and by performing quality inspection on the audio data and text data of the video, while assessing the work standardization of the survey staff, it also improves customer satisfaction.

[0161] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0162] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0163] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for obtaining evidence for vehicle insurance investigation, characterized in that: The steps include: receiving a vehicle insurance survey request initiated by a user terminal, and extracting survey type features from the vehicle insurance survey request; Sending a survey guidance instruction to the user terminal according to the survey type characteristics; collecting a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction; The key information corresponding to each survey data in the survey data set is identified by using OCR technology, and the survey data set is classified according to a preset classification rule and the key information to obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

2. The method for obtaining automobile insurance investigation evidence according to claim 1, characterized in that: The extracting of the survey type feature from the vehicle insurance survey request includes: Obtaining the accident information requested by the vehicle insurance investigation, and extracting text information of the accident information; Splitting the text information to obtain a word segmentation set; Extracting keywords from the word segmentation set using a pre-trained classification model; The survey type characteristics are determined according to the keywords.

3. The method for obtaining automobile insurance investigation evidence according to claim 2, characterized in that: After receiving the vehicle insurance survey request initiated by the user terminal and extracting the survey type feature from the vehicle insurance survey request, the method further includes: Get the list of surveyors in idle state and the corresponding processing levels; Determining the accident type of the vehicle insurance investigation request according to the accident information; According to the processing level and the accident type, a surveyor with the highest matching degree with the vehicle insurance survey request is determined.

4. The method for obtaining automobile insurance investigation evidence according to claim 3, characterized in that: The sending a survey guidance instruction to the user terminal according to the survey type feature includes: Establishing a video call connection between the user terminal and the surveyor terminal; According to the video call and the accident information, a survey guidance instruction is sent to the user terminal.

5. The method for obtaining automobile insurance investigation evidence according to claim 4, characterized in that: The establishing of the video call connection between the user terminal and the surveyor terminal includes: receiving a first call request submitted by a user, and sending the first call request to the surveyor's survey terminal; When the surveyor agrees to receive the first call request, the video call connection between the user terminal and the surveyor is successfully established.

6. The method for obtaining automobile insurance investigation evidence according to claim 4, characterized in that: The method of establishing a video call connection between the user terminal and the surveyor terminal further includes: receiving a second call request submitted by the surveyor, and sending the second call request to the user terminal; When the user agrees to receive the second call request at the user terminal, the video call connection between the user terminal and the surveyor is successfully established.

7. The method for obtaining automobile insurance investigation evidence according to claim 5 or 6, characterized in that: After establishing the video call connection between the user terminal and the surveyor terminal, the method further includes: extracting audio data from the video call data; Converting the audio data into text data; A quality detection operation is performed on the audio data and the text data.

8. A device for obtaining evidence for vehicle insurance investigation, characterized in that: The device comprises: A receiving module, configured to receive a vehicle insurance survey request initiated by a user terminal, and extract survey type features from the vehicle insurance survey request; A sending module, used for sending a survey guidance instruction to the user terminal according to the survey type characteristics; A collection module, used for collecting a survey data set corresponding to the vehicle insurance survey request according to the survey guidance instruction; The classification module is used to use OCR technology to identify key information corresponding to each survey data in the survey data set, and after classifying the survey data set according to preset classification rules and the key information, obtain the vehicle insurance survey evidence of the vehicle insurance survey request.

9. A computer device, characterized in that: The computer device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for obtaining vehicle insurance investigation evidence as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for obtaining vehicle insurance investigation evidence as described in any one of claims 1 to 7 is implemented.

Images