Verification method and device, equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of research and development design, is applied to a vehicle claim settlement risk control scene, and relates to a verification method, device and equipment and a storage medium thereof.A living body detection function is triggered and started through an accident picture uploading request; carrying out living body authenticity verification on the picture uploading object; if so, acquiring an accident picture, and recording the uploading time and place of the accident picture; acquiring accident record information generated in the allowable deviation condition of the place and the time from the target authoritative data terminal; performing accident authenticity verification on the accident picture; and if so, sending an accident claim settlement request to the target underwriting party. According to the verification method provided by the invention, by carrying out living body authenticity verification on the picture uploading object, an illegal person can be effectively identified to carry out insurance fraud by adopting a virtual character, meanwhile, the authenticity of an accident is verified in combination with the accident picture uploading time and place, an insurance fraud behavior of a false accident can be effectively identified, and the security of the accident is improved. And the vehicle accident claim settlement auditing strictness is improved.

Description

Technical Field

[0001] The present application relates to the field of R&D and design technology, and is applied in vehicle claims risk control scenarios, and in particular to a verification method, device, equipment and storage medium thereof. Background Art

[0002] Cars are one of the most widely used means of transportation in daily life. When a car accident occurs, auto insurance claims will be involved. In the process of auto insurance claims, the authenticity of the inspection photos is crucial. The traditional auto insurance inspection process relies on manual on-site inspection and photography, and then uploading photos for claim application. This method not only requires waiting for the inspector to arrive at the scene, resulting in low efficiency, but is also easily affected by human factors, such as photo fraud or proxy photography.

[0003] Currently, although the vehicle claims APP has been launched, which allows car owners to upload vehicle accident pictures by themselves, solving the problem of low efficiency caused by waiting for the inspector to arrive at the scene, the current vehicle claims APP still has problems with insufficient audit security and strictness, and still cannot effectively identify the occurrence of fake vehicle accident pictures. In particular, the development of AI facial technology has made it even more difficult for some speculators to exploit loopholes in vehicle claims APPs and use vehicle accident pictures collected from multiple data sources to commit virtual face insurance fraud, which has increased the difficulty of identifying fake vehicle accident pictures. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a verification method, device, equipment and storage medium thereof to solve the problem that the existing vehicle claims APP lacks audit security and strictness and cannot effectively identify the falsification of vehicle accident pictures.

[0005] In order to solve the above technical problems, the present application embodiment provides a verification method, which adopts the following technical solutions:

[0006] A verification method comprises the following steps:

[0007] Triggering the start of a liveness detection function based on an accident picture upload request, wherein the accident picture upload request includes GPS latitude and longitude coordinate information of the user terminal;

[0008] Acquiring liveness information of the uploaded object detected by the liveness detection function;

[0009] Performing liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy;

[0010] If the liveness authenticity verification result is true, providing the user terminal with an accident picture upload window;

[0011] Obtain the accident picture uploaded by the user terminal through the accident picture upload window, and record the accident picture upload time in the form of a timestamp, and record the accident picture upload location in the form of the GPS latitude and longitude coordinate information;

[0012] Obtaining, from the target authoritative data terminal, the accident record information generated at the location where the accident picture is uploaded within the allowable deviation condition of the time when the accident picture is uploaded;

[0013] Verifying the authenticity of the accident pictures uploaded by the user terminal according to the accident record information;

[0014] If the authenticity verification result of the accident is true, the accident claim request is sent to the target insurer.

[0015] Furthermore, before executing the step of triggering the start of the liveness detection function based on the accident picture upload request, the method further includes:

[0016] Receiving the accident picture upload request sent by the user terminal through a preset service APP;

[0017] The liveness detection function includes a facial dynamic detection function and a voiceprint information detection function. The step of triggering the start of the liveness detection function based on the accident picture upload request specifically includes:

[0018] Triggering and starting the facial dynamic detection function and the voiceprint information detection function;

[0019] The step of obtaining the liveness information of the uploaded object detected by the liveness detection function specifically includes:

[0020] Acquire facial dynamic video information of the uploaded object detected by the facial dynamic detection function;

[0021] Acquire the voiceprint information of the upload object detected by the voiceprint information detection function.

[0022] Furthermore, before executing the step of receiving the accident picture upload request sent by the user terminal through a preset service APP, the method further includes:

[0023] Receiving an APP login request sent by the user end to the service APP;

[0024] Triggering and starting the liveness detection function based on the APP login request;

[0025] Acquire the living body information of the login object detected by the living body detection function.

[0026] Furthermore, the step of triggering the activation of the liveness detection function based on the APP login request specifically includes:

[0027] Triggering and starting the facial dynamic detection function and the voiceprint information detection function;

[0028] The step of obtaining the living body information of the login object detected by the living body detection function specifically includes:

[0029] Acquire facial dynamic video information of the login object detected by the facial dynamic detection function;

[0030] Acquire the voiceprint information of the login object detected by the voiceprint information detection function.

[0031] Furthermore, the step of performing liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy includes:

[0032] Sending the facial dynamic video information and the voice and sound print information of the uploaded object to a preset multimodal liveness detection model, wherein the multimodal liveness detection model includes a person picture liveness authenticity detection component and a voice and sound print liveness authenticity detection component;

[0033] Using the person picture liveness authenticity detection component to detect the facial dynamic video information of the uploaded object, and detecting whether the human face in the facial dynamic video information is a virtual human face;

[0034] Using the voice and voiceprint liveness authenticity detection component to detect the voice and voiceprint information of the uploaded object to detect whether the voice and voiceprint information belongs to a virtual human voice;

[0035] If the face in the facial dynamic video information is not a virtual face, and the voice print information does not belong to a virtual voice, then the liveness authenticity verification result is true;

[0036] Otherwise, the liveness authenticity verification result is false, and a first alarm prompt is sent to a preset monitoring terminal.

[0037] Furthermore, after the step of verifying the authenticity of the live body, the method further includes:

[0038] Comparing the facial dynamic video information of the uploaded object with the facial dynamic video information of the logged-in object to obtain a first comparison result;

[0039] Comparing the voice print information of the uploaded object with the voice print information of the logged-in object to obtain a second comparison result;

[0040] According to the first comparison result and the second comparison result, identifying whether the uploaded object and the logged-in object are the same object;

[0041] If the uploaded object and the logged-in object are the same object, the preliminary review is passed;

[0042] If the uploaded object and the logged-in object are not the same object, a second alarm prompt is sent to a preset monitoring terminal.

[0043] Further, the target authoritative data end includes an accident processing database of a traffic control department, the allowable deviation condition includes an allowable deviation location range of the accident picture upload location and an allowable delayed upload time of the accident picture upload time compared to the accident occurrence time, and the step of obtaining the accident record information generated by the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data end specifically includes:

[0044] Obtaining from the accident handling database of the traffic control department the allowable deviation location range of the accident picture upload location and all accident record information generated within the allowable delayed upload time period corresponding to the accident picture upload time, wherein the accident record information includes the license plate number information of the accident vehicle;

[0045] The step of verifying the authenticity of the accident picture uploaded by the user terminal according to the accident record information specifically includes:

[0046] Obtaining the license plate number information of the accident vehicles respectively contained in all the accident record information, and generating a license plate number list;

[0047] Extracting image information from the accident image uploaded by the user to extract the target license plate number;

[0048] Using the target license plate number as a search field, searching whether the license plate number list contains the target license plate number;

[0049] If the target license plate number is included in the license plate number list, the accident authenticity verification result is true;

[0050] If the target license plate number is not included in the license plate number list, the accident authenticity verification result is false, and a third alarm prompt is sent to a preset monitoring terminal.

[0051] In order to solve the above technical problems, the embodiment of the present application also provides a verification device, which adopts the following technical solution:

[0052] A verification device, comprising:

[0053] A liveness detection function triggering and starting module, used to trigger and start the liveness detection function based on an accident picture upload request, wherein the accident picture upload request includes the GPS latitude and longitude coordinate information of the user terminal;

[0054] An upload object liveness information acquisition module, used to acquire the liveness information of the upload object detected by the liveness detection function;

[0055] A liveness authenticity verification module, used to perform liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy;

[0056] An accident picture upload window providing module, used for providing an accident picture upload window to the user terminal if the liveness authenticity verification result is true;

[0057] The accident picture acquisition module is used to acquire the accident picture uploaded by the user terminal through the accident picture upload window, and record the accident picture upload time in the form of a timestamp, and record the accident picture upload location in the form of the GPS latitude and longitude coordinate information;

[0058] An accident record information acquisition module is used to acquire the accident record information generated at the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data terminal;

[0059] An accident authenticity verification module, used to verify the authenticity of the accident pictures uploaded by the user terminal according to the accident record information;

[0060] The accident claim request sending module is used to send the accident claim request to the target insurer if the accident authenticity verification result is true.

[0061] 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:

[0062] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the verification method described above when executing the computer-readable instructions.

[0063] 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:

[0064] A computer-readable storage medium stores computer-readable instructions, which implement the steps of the verification method described above when executed by a processor.

[0065] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0066] The verification method described in the embodiment of the present application triggers the activation of the liveness detection function through an accident picture upload request; obtains the liveness information of the uploaded object; performs liveness authenticity verification; if true, provides an accident picture upload window to the user end; obtains the accident picture, records the time and location of the accident picture upload; obtains the accident record information generated by the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data end; verifies the accident authenticity of the accident picture according to the accident record information; if true, sends an accident claim request to the target underwriter. The verification method described in the present application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the object of the picture upload, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident can be verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents to defraud insurance and improve the strictness of the review of vehicle accident claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] 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.

[0068] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0069] Figure 2 is a flow chart of an embodiment of a verification method according to the present application;

[0070] Figure 3 is a flowchart of a specific embodiment of step 200 in the verification method described in the present application;

[0071] Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 202 is shown;

[0072] Figure 5 It is a flowchart of a specific embodiment of performing liveness detection on the business APP login object in the verification method described in this application;

[0073] Figure 6 yes Figure 5 A flowchart of a specific embodiment of step 503 is shown;

[0074] Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 203 is shown;

[0075] Figure 8 yes Figure 2 A flowchart of a specific embodiment of step 207 is shown;

[0076] Fig. 9 is a schematic structural diagram of an embodiment of a verification device according to the present application;

[0077] Fig.10 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the 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) player, a laptop computer and a desktop computer, etc.

[0084] 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 .

[0085] It should be noted that the verification method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the verification device is generally arranged in the terminal device.

[0086] 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.

[0087] Continue to refer Figure 2 , shows a flow chart of an embodiment of a verification method according to the present application. The verification method comprises the following steps:

[0088] Step 201, triggering the start of a liveness detection function based on an accident picture upload request, wherein the accident picture upload request includes GPS latitude and longitude coordinate information of the user terminal;

[0089] Specifically, the accident picture upload request includes an accident picture upload request initiated by a vehicle owner or surveyor through a preset claims APP when a vehicle accident occurs. The trigger action can be implemented according to a preset task trigger when the accident picture upload request is received.

[0090] This application triggers the start of the liveness detection function based on the accident picture upload request, and implements at least one liveness detection on the image upload object before the accident picture is uploaded to ensure that the accident picture upload object is a real person, rather than a virtual character who illegally uploads the picture by exploiting a loophole in the claims business, thereby improving the security of claims review.

[0091] Step 202, obtaining the liveness information of the uploaded object detected by the liveness detection function;

[0092] In this embodiment, the liveness detection function includes a facial dynamic detection function and a voiceprint information detection function. Therefore, the liveness information of the uploaded object detected by the liveness detection function includes the liveness information detected by the facial dynamic detection function and the voiceprint information detection function respectively. The uploaded object can be understood as the person who performs the accident picture uploading operation.

[0093] Through the facial dynamic detection function and the voiceprint information detection function, liveness recognition of the uploaded object is achieved from both the face and voice perspectives, which is more convincing.

[0094] Step 203, performing liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy;

[0095] In this embodiment, the preset verification strategy can be understood as follows: if both the face detection result and the voice detection result point to the uploaded object being a real person, then the uploaded object is a real person; if any one of the face detection result and the voice detection result points to the uploaded object being a virtual character, then the uploaded object is a questionable object. At this time, a first alarm prompt is sent to the preset monitoring terminal, and the preset monitoring terminal includes a claims review monitoring terminal.

[0096] By verifying the live authenticity of the uploaded object, it is ensured that the object of the accident picture upload is a real person, which improves the strictness of the vehicle accident claim review and reduces the use of virtual characters by illegal elements to defraud insurance to a certain extent.

[0097] Step 204, if the liveness authenticity verification result is true, providing the user terminal with an accident picture upload window;

[0098] Specifically, if the liveness authenticity verification result is true, an accident picture upload window is provided on the operation interface of the user terminal, for example, a picture import box, etc.

[0099] Step 205, obtaining the accident picture uploaded by the user terminal through the accident picture upload window, and recording the accident picture upload time in the form of a timestamp, and recording the accident picture upload location in the form of the GPS latitude and longitude coordinate information;

[0100] Specifically, the accident picture upload time is recorded in the form of a timestamp, and the accident picture upload location is recorded with the GPS latitude and longitude coordinate information. The purpose is to verify the authenticity of the accident in combination with the accident picture upload time and the accident picture upload location, which can effectively identify false accidents and insurance fraud, and improve the strictness of vehicle accident claims review.

[0101] Step 206, obtaining the accident record information generated at the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data terminal;

[0102] Specifically, the target authoritative data terminal includes the accident handling database of the traffic management department, and the allowable deviation condition includes the allowable deviation location range of the accident picture upload location and the allowable delayed upload time of the accident picture upload time compared to the accident occurrence time.

[0103] By obtaining the accident record information generated at the accident picture uploading location within the allowable deviation condition of the accident picture uploading time from the target authoritative data terminal, it is avoided that the accident pictures uploaded by the uploading object are insurance fraud pictures, or pictures of vehicle damage not caused by this accident, thereby improving the standardization and strictness of vehicle claims review, and can effectively identify insurance fraud incidents.

[0104] Step 207, verifying the authenticity of the accident picture uploaded by the user terminal according to the accident record information;

[0105] Specifically, combined with the accident record information recorded in the accident handling database of the traffic management department, as well as the location and time of uploading the accident picture, it is verified whether the accident picture uploaded by the user terminal is the accident picture corresponding to the accident that occurred at that time and place, thereby ensuring the verification of the authenticity of the accident, being able to effectively identify insurance fraud, and improving the security and strictness of claims review.

[0106] Step 208: If the result of the accident authenticity verification is true, then send the accident claim request to the target insurer.

[0107] In this embodiment, the liveness detection function is triggered by the accident picture upload request; the liveness information of the uploaded object is obtained; the liveness authenticity verification is performed; if it is true, an accident picture upload window is provided to the user end; the accident picture is obtained, and the time and location of the accident picture upload are recorded; the accident record information generated by the accident picture upload location within the allowable deviation condition of the accident picture upload time is obtained from the target authoritative data end; the accident authenticity is verified for the accident picture according to the accident record information; if it is true, an accident claim request is sent to the target underwriter. The verification method described in this application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the uploaded picture object, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident can be verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents and defraud insurance, thereby improving the strictness of vehicle accident claim review.

[0108] Continue to refer Figure 3In some optional implementations, step 200 is further included before executing step 201. Figure 3 It is a flowchart of a specific embodiment of step 200 in the verification method described in the present application, including: step 200, receiving the accident picture upload request sent by the user terminal through a preset business APP;

[0109] Specifically, the user end includes a user mobile phone terminal, and the preset business APP includes a car insurance claim APP.

[0110] In some optional implementations, the step of triggering the activation of the liveness detection function based on the accident picture upload request, i.e., step 201, specifically includes: triggering the activation of the facial dynamic detection function and the voiceprint information detection function;

[0111] Continue to refer Figure 4 , in some optional implementations, Figure 4 yes Figure 2 The flowchart of a specific embodiment of step 202 shown includes the following steps:

[0112] Step 401, obtaining facial dynamic video information of the uploaded object detected by the facial dynamic detection function;

[0113] Step 402: Acquire the voiceprint information of the upload object detected by the voiceprint information detection function.

[0114] Through the facial dynamic detection function and the voiceprint information detection function, liveness recognition of the uploaded object is achieved from both the face and voice angles, which is more convincing and ensures the accuracy of liveness authenticity detection.

[0115] Continue to refer Figure 5 In some optional implementations, before executing step 200, a liveness detection step is also included for the business APP login object. Figure 5 It is a flowchart of a specific embodiment of performing liveness detection on the business APP login object in the verification method described in this application, including:

[0116] Step 501, receiving an APP login request sent by the user terminal to the service APP;

[0117] Step 502: triggering and starting the liveness detection function based on the APP login request;

[0118] Step 503: Acquire the liveness information of the login object detected by the liveness detection function.

[0119] In some optional implementations, the step of triggering the activation of the liveness detection function based on the APP login request, i.e., step 502, specifically includes: triggering the activation of the facial dynamic detection function and the voiceprint information detection function;

[0120] Continue to refer Figure 6 , in some optional implementations, Figure 6 yes Figure 5 The flowchart of a specific embodiment of step 503 shown includes the following steps:

[0121] Step 601, acquiring facial dynamic video information of the login object detected by the facial dynamic detection function;

[0122] Step 602: Acquire the voiceprint information of the login object detected by the voiceprint information detection function.

[0123] By performing liveness detection on the login object of the business APP, it is easy to ensure that the person logging into the car insurance claim APP is a real living object. Combined with the subsequent liveness detection of the uploaded object, two liveness detections of human objects are performed before and after, which further ensures the security and strictness of the car insurance claim review and can reduce the success rate of insurance fraud to a certain extent.

[0124] Continue to refer Figure 7 , in some optional implementations, Figure 7 yes Figure 2 The flowchart of a specific embodiment of step 203 shown includes the following steps:

[0125] Step 701, sending the facial dynamic video information of the uploaded object and the voice and soundprint information of the uploaded object to a preset multimodal liveness detection model, wherein the multimodal liveness detection model includes a person picture liveness authenticity detection component and a voice and soundprint liveness authenticity detection component;

[0126] Specifically, the multimodal liveness detection model refers to a model that can perform liveness detection on both face images and voiceprint information. For example, the character image liveness authenticity detection component is used to identify whether the character object is a virtual character based on changes in facial expressions when the character object speaks, or the character image liveness authenticity detection component is used to identify whether the character object is a virtual character based on changes in facial features generated by the character object according to preset facial action instructions, and the voiceprint liveness authenticity detection component is used to identify whether the character object is a virtual robot based on voiceprint information when the character object speaks, such as fluctuations in timbre, pitch, rhythm, and rhythm.

[0127] Step 702, using the person picture liveness authenticity detection component to detect the facial dynamic video information of the uploaded object, to detect whether the face in the facial dynamic video information is a virtual face;

[0128] Step 703, using the voice and voiceprint liveness authenticity detection component to detect the voice and voiceprint information of the uploaded object to detect whether the voice and voiceprint information belongs to a virtual human voice;

[0129] Step 704: if the face in the facial dynamic video information is not a virtual face, and the voice print information does not belong to a virtual voice, then the liveness authenticity verification result is true;

[0130] Step 705: Otherwise, the liveness authenticity verification result is false, and a first alarm prompt is sent to a preset monitoring terminal.

[0131] By adopting a preset multimodal liveness detection model, it is possible to detect whether the uploaded object is a real person by combining the facial dynamic video information and the voice voiceprint information of the uploaded object, and it is also possible to detect whether the logged-in object is a real person by combining the facial dynamic video information and the voice voiceprint information of the logged-in object. This enables two real-person operation detections when logging into the auto insurance claim APP and uploading vehicle accident pictures, thereby ensuring the security and strictness of the auto insurance claim review and reducing the success rate of insurance fraud to a certain extent.

[0132] In some optional implementations, after the step of verifying that the liveness authenticity result is true, the method further includes: comparing the facial dynamic video information of the uploaded object with the facial dynamic video information of the logged-in object to obtain a first comparison result; comparing the voice and voiceprint information of the uploaded object with the voice and voiceprint information of the logged-in object to obtain a second comparison result; identifying whether the uploaded object and the logged-in object are the same object based on the first comparison result and the second comparison result; if the uploaded object and the logged-in object are the same object, the preliminary review is passed; if the uploaded object and the logged-in object are not the same object, a second alarm prompt is sent to a preset monitoring terminal.

[0133] Specifically, if the first comparison result is that the facial dynamic video information of the uploaded object is consistent with the facial dynamic video information of the logged-in object, and the second comparison result is that the voice voiceprint information of the uploaded object is consistent with the voice voiceprint information of the logged-in object, then the uploaded object and the logged-in object are the same object. At this time, the preliminary review is passed, and the accident picture upload window can be directly provided to the user terminal. Otherwise, that is, the uploaded object and the logged-in object are not the same object, it is necessary to send a second alarm prompt to the preset monitoring terminal, that is, send a second alarm prompt to the claims review monitoring terminal, so that the claims review monitoring terminal can make a telephone consultation with the car owner to determine whether the logged-in object and the uploaded object are the car owner or a person authorized by the car owner.

[0134] By comparing the uploaded object with the logged-in object to determine that they are the same object, the security and strictness of the auto insurance claims review are further improved, and the success rate of insurance fraud can be reduced to a certain extent.

[0135] In some optional implementations, the target authoritative data terminal includes the accident handling database of the traffic management department, and the allowable deviation condition includes the allowable deviation location range of the accident picture upload location and the allowable delayed upload time of the accident picture upload time compared to the accident occurrence time.

[0136] Specifically, the allowed deviation location range of the accident picture upload location, for example: the allowed deviation location range is within 1 km, that is, the accident picture upload location is within 1 km of the accident site, then the accident authenticity verification result is true, and the accident picture upload time is allowed to be delayed compared to the accident time, that is, after the vehicle accident occurs, the allowed delayed upload time of the vehicle accident photo, for example: 2 hours, half a day, etc. Considering that the allowed delayed upload time is too long, it is impossible to guarantee that the vehicle damage is caused by this accident, which further improves the safety and strictness of the auto insurance claim review.

[0137] In some optional implementations, the step of obtaining the accident record information generated at the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data terminal, i.e., step 206, specifically includes: obtaining the allowable deviation location range of the accident picture upload location and all accident record information generated within the allowable delayed upload time period corresponding to the accident picture upload time from the accident processing database of the traffic management department, wherein the accident record information includes the license plate number information of the accident vehicle;

[0138] Continue to refer Figure 8 , in some optional implementations, Figure 8 yes Figure 2 The flowchart of a specific embodiment of step 207 shown includes the following steps:

[0139] Step 801, obtaining the license plate number information of the accident vehicles respectively contained in all the accident record information, and generating a license plate number list;

[0140] Step 802, extracting image information from the accident image uploaded by the user terminal to extract the target license plate number;

[0141] Step 803, using the target license plate number as a search field, searching whether the license plate number list contains the target license plate number;

[0142] Step 804, if the target license plate number is included in the license plate number list, the accident authenticity verification result is true;

[0143] Step 805: If the target license plate number is not included in the license plate number list, the accident authenticity verification result is false, and a third alarm prompt is sent to a preset monitoring terminal.

[0144] The accident picture uploaded by the user is verified for authenticity through the accident record information. Specifically, all accident record information that occurred at the time and location of uploading the accident picture is collected from authoritative departments, combined with the uploaded accident picture, and the vehicle consistency is compared according to the license plate number, thereby once again ensuring the security and strictness of the vehicle claim application, identifying insurance fraud incidents as effectively as possible, and improving the standardization of vehicle claim applications.

[0145] This application triggers the activation of the liveness detection function through an accident picture upload request; obtains the liveness information of the uploaded object; performs liveness authenticity verification; if true, provides an accident picture upload window to the user end; obtains the accident picture, records the time and location of the accident picture upload; obtains the accident record information generated by the accident picture upload location within the allowable deviation conditions of the accident picture upload time from the target authoritative data end; verifies the accident authenticity of the accident picture according to the accident record information; if true, sends an accident claim request to the target underwriter. The verification method described in this application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the uploaded picture object, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident can be verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents and fraudulent insurance, and improve the strictness of vehicle accident claim review.

[0146] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0147] 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.

[0148] In the embodiment of the present application, the liveness detection function is triggered by the accident picture upload request; the liveness information of the uploaded object is obtained; the liveness authenticity verification is performed; if it is true, an accident picture upload window is provided to the user end; the accident picture is obtained, and the time and location of the accident picture upload are recorded; the accident record information generated by the accident picture upload location within the allowable deviation conditions of the accident picture upload time is obtained from the target authoritative data end; the accident authenticity is verified for the accident picture according to the accident record information; if it is true, an accident claim request is sent to the target underwriter. The verification method described in the present application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the uploaded picture object, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident can be verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents and defraud insurance, thereby improving the strictness of the review of vehicle accident claims.

[0149] Further references Fig. 9 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a verification device, which is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0150] like Fig. 9 As shown, the verification device 900 described in this embodiment includes: a liveness detection function triggering and starting module 901, an upload object liveness information acquisition module 902, a liveness authenticity verification module 903, an accident picture upload window providing module 904, an accident picture acquisition module 905, an accident record information acquisition module 906, an accident authenticity verification module 907 and an accident claim request sending module 908. Among them:

[0151] A liveness detection function triggering and starting module 901 is used to trigger and start the liveness detection function based on an accident picture upload request, wherein the accident picture upload request includes the GPS latitude and longitude coordinate information of the user terminal;

[0152] The upload object liveness information acquisition module 902 is used to acquire the liveness information of the upload object detected by the liveness detection function;

[0153] A liveness authenticity verification module 903, used to perform liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy;

[0154] An accident picture upload window providing module 904 is used to provide an accident picture upload window to the user terminal if the liveness authenticity verification result is true;

[0155] The accident picture acquisition module 905 is used to acquire the accident picture uploaded by the user terminal through the accident picture upload window, and record the accident picture upload time in the form of a timestamp, and record the accident picture upload location in the form of the GPS latitude and longitude coordinate information;

[0156] The accident record information acquisition module 906 is used to acquire the accident record information generated at the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data terminal;

[0157] The accident authenticity verification module 907 is used to verify the authenticity of the accident pictures uploaded by the user terminal according to the accident record information;

[0158] The accident claim request sending module 908 is used to send the accident claim request to the target insurer if the accident authenticity verification result is true.

[0159] This application triggers the activation of the liveness detection function through an accident picture upload request; obtains the liveness information of the uploaded object; performs liveness authenticity verification; if true, provides an accident picture upload window to the user end; obtains the accident picture, records the time and location of the accident picture upload; obtains the accident record information generated by the accident picture upload location within the allowable deviation conditions of the accident picture upload time from the target authoritative data end; verifies the accident authenticity of the accident picture according to the accident record information; if true, sends an accident claim request to the target underwriter. The verification method described in this application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the uploaded picture object, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident can be verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents and fraudulent insurance, and improve the strictness of vehicle accident claim review.

[0160] 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).

[0161] 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.

[0162] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0163] The computer device 10 includes a memory 10a, a processor 10b, and a network interface 10c which are interconnected and communicated via a system bus. It should be noted that: Fig.10 Only a computer device 10 having a component memory 10a, a processor 10b, and a network interface 10c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may 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 a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0164] 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.

[0165] The memory 10a 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, magnetic disk, optical disk, etc. In some embodiments, the memory 10a can be an internal storage unit of the computer device 10, such as a hard disk or memory of the computer device 10. In other embodiments, the memory 10a can also be an external storage device of the computer device 10, such as a plug-in hard disk equipped on the computer device 10, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10a can also include both the internal storage unit of the computer device 10 and its external storage device. In this embodiment, the memory 10a is generally used to store an operating system and various application software installed on the computer device 10, such as a computer-readable instruction of a verification method, etc. In addition, the memory 10a can also be used to temporarily store various data that have been output or will be output.

[0166] The processor 10b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 10b is generally used to control the overall operation of the computer device 10. In this embodiment, the processor 10b is used to run the computer-readable instructions or process data stored in the memory 10a, such as the computer-readable instructions for running the verification method.

[0167] The network interface 10c may include a wireless network interface or a wired network interface. The network interface 10c is generally used to establish a communication connection between the computer device 10 and other electronic devices.

[0168] The computer device proposed in this embodiment belongs to the field of research and development design technology, and is applied to vehicle claims risk control scenarios. This application triggers the start of the liveness detection function through an accident picture upload request; obtains the liveness information of the uploaded object; performs liveness authenticity verification; if true, provides an accident picture upload window to the user end; obtains the accident picture, records the time and location of the accident picture upload; obtains the accident record information generated by the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data end; verifies the accident authenticity of the accident picture according to the accident record information; if true, sends an accident claim request to the target underwriter. The verification method described in this application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the object of the picture upload, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident can be verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents and fraudulent insurance, and improve the strictness of vehicle accident claims review.

[0169] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the verification method as described above.

[0170] The computer-readable storage medium proposed in this embodiment belongs to the field of research and development design technology, and is applied to vehicle claims risk control scenarios. This application triggers the start of the liveness detection function through an accident picture upload request; obtains the liveness information of the uploaded object; performs liveness authenticity verification; if true, provides an accident picture upload window to the user end; obtains the accident picture, records the time and location of the accident picture upload; obtains the accident record information generated by the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data end; verifies the accident authenticity of the accident picture according to the accident record information; if true, sends an accident claim request to the target underwriter. The verification method described in this application ensures that the object of the accident picture upload is a real person by performing liveness authenticity verification on the object of the picture upload, and can effectively identify illegal elements using virtual characters to defraud insurance. At the same time, the authenticity of the accident is verified in combination with the time and location of the accident picture upload, which can effectively identify fake accidents and fraudulent insurance, and improve the strictness of vehicle accident claims review.

[0171] 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.

[0172] 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 verification method, characterized in that: The steps include: Triggering the start of a liveness detection function based on an accident picture upload request, wherein the accident picture upload request includes GPS latitude and longitude coordinate information of the user terminal; Acquiring liveness information of the uploaded object detected by the liveness detection function; Performing liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy; If the liveness authenticity verification result is true, providing the user terminal with an accident picture upload window; Obtain the accident picture uploaded by the user terminal through the accident picture upload window, and record the accident picture upload time in the form of a timestamp, and record the accident picture upload location in the form of the GPS latitude and longitude coordinate information; Obtaining, from the target authoritative data terminal, the accident record information generated at the location where the accident picture is uploaded within the allowable deviation condition of the time when the accident picture is uploaded; Verifying the authenticity of the accident pictures uploaded by the user terminal according to the accident record information; If the authenticity verification result of the accident is true, the accident claim request is sent to the target insurer.

2. The verification method according to claim 1, characterized in that: Before executing the step of triggering the start of the liveness detection function based on the accident picture upload request, the method further includes: Receiving the accident picture upload request sent by the user terminal through a preset service APP; The liveness detection function includes a facial dynamic detection function and a voiceprint information detection function. The step of triggering the start of the liveness detection function based on the accident picture upload request specifically includes: Triggering and starting the facial dynamic detection function and the voiceprint information detection function; The step of obtaining the liveness information of the uploaded object detected by the liveness detection function specifically includes: Acquire facial dynamic video information of the uploaded object detected by the facial dynamic detection function; Acquire the voiceprint information of the upload object detected by the voiceprint information detection function.

3. The verification method according to claim 2, characterized in that: Before executing the step of receiving the accident picture upload request sent by the user terminal through a preset service APP, the method further includes: Receiving an APP login request sent by the user end to the service APP; Triggering and starting the liveness detection function based on the APP login request; Acquire the living body information of the login object detected by the living body detection function.

4. The verification method according to claim 3, characterized in that: The step of triggering and starting the liveness detection function based on the APP login request specifically includes: Triggering and starting the facial dynamic detection function and the voiceprint information detection function; The step of obtaining the living body information of the login object detected by the living body detection function specifically includes: Acquire facial dynamic video information of the login object detected by the facial dynamic detection function; Acquire the voiceprint information of the login object detected by the voiceprint information detection function.

5. The verification method according to claim 4, characterized in that: The step of performing liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy includes: Sending the facial dynamic video information and the voice and sound print information of the uploaded object to a preset multimodal liveness detection model, wherein the multimodal liveness detection model includes a person picture liveness authenticity detection component and a voice and sound print liveness authenticity detection component; Using the person picture liveness authenticity detection component to detect the facial dynamic video information of the uploaded object, and detecting whether the human face in the facial dynamic video information is a virtual human face; Using the voice and voiceprint liveness authenticity detection component to detect the voice and voiceprint information of the uploaded object to detect whether the voice and voiceprint information belongs to a virtual human voice; If the face in the facial dynamic video information is not a virtual face, and the voice print information does not belong to a virtual voice, then the liveness authenticity verification result is true; Otherwise, the liveness authenticity verification result is false, and a first alarm prompt is sent to a preset monitoring terminal.

6. The verification method according to claim 4 or 5, characterized in that: After the step of verifying the authenticity of the live body, the method further includes: Comparing the facial dynamic video information of the uploaded object with the facial dynamic video information of the logged-in object to obtain a first comparison result; Comparing the voice print information of the uploaded object with the voice print information of the logged-in object to obtain a second comparison result; According to the first comparison result and the second comparison result, identifying whether the uploaded object and the logged-in object are the same object; If the uploaded object and the logged-in object are the same object, the preliminary review is passed; If the uploaded object and the logged-in object are not the same object, a second alarm prompt is sent to a preset monitoring terminal.

7. The verification method according to claim 1, characterized in that: The target authoritative data end includes an accident processing database of a traffic control department, the allowable deviation condition includes an allowable deviation location range of the accident picture upload location and an allowable delayed upload time of the accident picture upload time compared to the accident occurrence time, and the step of obtaining the accident record information generated by the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data end specifically includes: Obtaining from the accident handling database of the traffic control department the allowable deviation location range of the accident picture upload location and all accident record information generated within the allowable delayed upload time period corresponding to the accident picture upload time, wherein the accident record information includes the license plate number information of the accident vehicle; The step of verifying the authenticity of the accident picture uploaded by the user terminal according to the accident record information specifically includes: Obtaining the license plate number information of the accident vehicles respectively contained in all the accident record information, and generating a license plate number list; Extracting image information from the accident image uploaded by the user to extract the target license plate number; Using the target license plate number as a search field, searching whether the license plate number list contains the target license plate number; If the target license plate number is included in the license plate number list, the accident authenticity verification result is true; If the target license plate number is not included in the license plate number list, the accident authenticity verification result is false, and a third alarm prompt is sent to a preset monitoring terminal.

8. A verification device, characterized in that: include: A liveness detection function triggering and starting module, used to trigger and start the liveness detection function based on an accident picture upload request, wherein the accident picture upload request includes the GPS latitude and longitude coordinate information of the user terminal; An upload object liveness information acquisition module, used to acquire the liveness information of the upload object detected by the liveness detection function; A liveness authenticity verification module, used to perform liveness authenticity verification according to the liveness information of the uploaded object and a preset verification strategy; An accident picture upload window providing module, used for providing an accident picture upload window to the user terminal if the liveness authenticity verification result is true; The accident picture acquisition module is used to acquire the accident picture uploaded by the user terminal through the accident picture upload window, and record the accident picture upload time in the form of a timestamp, and record the accident picture upload location in the form of the GPS latitude and longitude coordinate information; An accident record information acquisition module is used to acquire the accident record information generated at the accident picture upload location within the allowable deviation condition of the accident picture upload time from the target authoritative data terminal; An accident authenticity verification module, used to verify the authenticity of the accident pictures uploaded by the user terminal according to the accident record information; The accident claim request sending module is used to send the accident claim request to the target insurer if the accident authenticity verification result is true.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the verification method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the verification method according to any one of claims 1 to 7 are implemented.

Images