Audio and video call method, device, equipment and storage medium based on insurance business

Abstract

The present application provides an audio and video call method, device, equipment and storage medium based on insurance business. Applied to the server, the method includes: receiving a call request from a first client, and pushing the call request to a second client; if an agreement to the call request is received from the second client, establishing an audio and video call between the first client and the second client; performing information identification services and insurance calculation services through the audio and video call to complete online insurance claims. By receiving call requests and agreeing to call requests, an audio and video call connection is established between clients of multiple platforms, and information identification services and insurance calculation services are completed during the audio and video call process, and the claim results are quickly obtained, thereby completing a convenient and fast online insurance claim, improving the efficiency of insurance claims, and reducing the consumption of manpower and material resources.

Description

Technical Field

[0001] The present application relates to the field of communications, and more specifically, to an insurance business-based audio and video call method, device, equipment and storage medium. Background Art

[0002] Existing insurance business generally needs to be conducted offline. Business personnel are arranged to connect with customers according to their requests. By checking the basic situation on site, a rough estimate of the insurance claim results can be made, and the entire claim work can be completed.

[0003] Since the offline claims process is cumbersome, labor-intensive and time-consuming, the claims results can only be guaranteed by the professional capabilities of business personnel and cannot satisfy customers. Online communication methods are limited and can only communicate general situations. It is impossible to understand the actual situation on the scene, and the claims results are not professional enough. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an insurance-based audio and video call method, device, equipment and storage medium to improve the efficiency of insurance claims.

[0005] In a first aspect, an embodiment of the present application provides an audio and video call method based on insurance business, which is applied to a server, including: receiving a call request from a first client, and pushing the call request to a second client; if an agreement to the call request is received from the second client, establishing an audio and video call between the first client and the second client; performing information identification services and insurance calculation services through the audio and video call to complete online insurance claims.

[0006] In an embodiment of the present application, a call request from a first client is received and pushed to a second client. If the second client agrees to the call request, an audio and video call is established between the first client and the second client. Then, information identification services and insurance calculation services are performed through the audio and video call, thereby completing the online insurance claim. Through the online audio and video call, a more convenient and quick online call is achieved, further improving the efficiency of the insurance claim.

[0007] Furthermore, the first client and the second client are any one of a mobile terminal, a mini-program terminal or a web terminal, and the mobile terminal, the mini-program terminal and the web terminal respectively run corresponding SDK components. The establishment of an audio and video call between the first client and the second client includes: creating a room number, and the room number is used to identify the audio and video call room between the first client and the second client; using the SDK components corresponding to the first client and the second client respectively to call the RTC audio and video stream according to the room number to realize the audio and video call between the first client and the second client.

[0008] In the embodiment of the present application, the first client and the second client are any one of a mobile terminal, a mini-program terminal or a web terminal, and each client runs the corresponding SDK component respectively. The audio and video call room between the first client and the second client is identified by creating a room number, and then the SDK components running by the first client and the second client themselves are used to call the RTC audio and video stream, thereby completing the audio and video call process between the first client and the second client. The SDK component is used to realize a cross-platform audio and video call process, thereby ensuring the stability of online calls.

[0009] Furthermore, the information identification service performed through the audio and video call includes: calling the AR video SDK to extract a first picture in the video stream, the first picture including a vehicle object for which insurance claim is to be made; extracting vehicle information by performing information identification on the first picture, the vehicle information including a license plate number and a frame number.

[0010] In the embodiment of the present application, the AR video SDK is called to provide the first picture in the video stream, and the first picture includes the vehicle object to be insured. The vehicle information is extracted by performing information recognition on the first picture, and the vehicle information includes the license plate number and the frame number. The AR video SDK is called to complete the information recognition service, extract the basic information of the vehicle, and complete the confirmation of the vehicle information, thereby ensuring the accurate recognition of the vehicle information.

[0011] Furthermore, the insurance calculation service provided through the audio and video call includes: receiving a photo request from the first client; capturing a second picture of the video stream according to the photo request, wherein the second picture includes a damaged part object of the vehicle; sending the second picture to the second client through an IM instant channel; performing insurance calculation on the second picture to obtain a claim result.

[0012] In the embodiment of the present application, a second picture of the video stream is captured according to the photo request by receiving the photo request of the first client, and the second picture includes the damaged part object of the vehicle, and then the second picture is sent to the second client through the IM instant channel, and the insurance calculation is performed on the second picture to obtain the claim result. By receiving the photo request of the first client to capture the second picture in the video stream, the claim result is calculated on the second picture, and the claim result is returned, the calculation function of online insurance is realized.

[0013] Furthermore, after performing the information identification service and the insurance calculation service through the audio and video call, the method further includes: receiving a hang-up request from the first client or the second client; and disconnecting the audio and video call.

[0014] In the embodiment of the present application, after performing the information identification service and the insurance calculation service, a hang-up request from the first client or the second client may be received, and then the connection of the audio and video call may be disconnected. After completing the online insurance claim, the audio and video call may be disconnected by receiving a hang-up request from the first client or the second client, thereby realizing the disconnection of the audio and video call.

[0015] Furthermore, after disconnecting the audio and video call, the method further includes: obtaining an audio and video mixed stream file generated by the audio and video call; storing the audio and video mixed stream file and obtaining a callback address; calling the callback address to process the audio and video mixed stream file.

[0016] In the embodiment of the present application, after the audio and video call is disconnected, the audio and video mixed stream file generated by the audio and video call is obtained, the audio and video mixed stream file is stored, and a callback address is obtained, and the audio and video file can be processed by calling the callback address. By obtaining the audio and video mixed stream file generated by the audio and video call, the audio and video mixed stream file is stored and processed, thereby realizing the storage and processing of the audio and video mixed stream file, ensuring the archiving of files in the insurance claim, and facilitating the query of subsequent insurance claims.

[0017] Furthermore, calling the video callback address to process the audio and video mixed stream file includes: downloading the audio and video mixed stream file according to the callback address; performing a separation operation on the audio and video mixed stream file to obtain an audio file and a video file; processing the video file, and the processing includes adding subtitles, video screenshots, adding watermarks and format conversion. One or more.

[0018] In the embodiment of the present application, the audio and video mixed stream file is downloaded according to the callback address stored in the audio and video mixed stream file, and then the audio and video mixed stream file is separated to obtain the audio file and the video file, and the video file is processed, and the processing can be one or more of adding subtitles, video screenshots, adding watermarks, and format conversion. The audio and video mixed stream file is downloaded and separated through the callback address, and the separated video file is processed, thereby completing the processing of the online insurance claim video file and obtaining the required file for insurance claim.

[0019] In a second aspect, an embodiment of the present application is an audio and video call device based on insurance business, the device comprising: a receiving module, used to receive a call request from a first client and push the call request to a second client; an establishing module, used to establish an audio and video call between the first client and the second client if an agreement call request from the second client is received; a service module, used to perform information identification services and insurance calculation services through the audio and video call to complete online insurance claims.

[0020] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and a bus, wherein the processor and the memory interact with each other through the bus;

[0021] The memory stores program instructions that can be executed by the processor, and the processor can execute the method of the first aspect by calling the program instructions.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including:

[0023] The computer-readable storage medium stores computer instructions, which cause the computer to execute the method of the first aspect.

[0024] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1A flowchart of an audio and video call method based on insurance business provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of the structure of an audio and video call system based on insurance business provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram of a separation process of an audio and video mixed stream file based on insurance business provided in an embodiment of the present application;

[0029] Figure 4 A schematic diagram of the structure of an audio and video call device based on insurance business provided in an embodiment of the present application;

[0030] Figure 5 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0032] Before introducing the audio and video call method based on insurance business provided in the embodiment of the present application, some concepts involved in the embodiment of the present application are first introduced:

[0033] SDK (Software Development Kit): A collection of documents, examples, and tools that assist in developing a certain type of software. Through SDK, you can obtain the software development kit from system application developers, so as to quickly build your own business functions.

[0034] RTC (Real-Time Communication): An API that supports real-time voice or video conversations. It is a low-level communication capability that implements real-time audio and video call capabilities by calling real-time audio and video APIs.

[0035] IM (instant communication): An instant communication software based on the Internet. Major platforms provide various basic IM capabilities. Through the SDK, you can call the IM API to achieve the effect of sending and receiving text and voice messages.

[0036] Figure 1 A flowchart of an audio and video call method based on insurance business provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method can be applied to the server to manage the call requests of multiple clients, thereby realizing audio and video calls between multiple clients. The method includes:

[0037] Step 101: receiving a call request from a first client, and pushing the call request to a second client.

[0038] In the specific implementation process, the first client and the second client can both be the client where the user is located or the client where the salesperson is located. The user can actively send a call request to the salesperson, and the salesperson can also initiate a call request to the user. This application does not limit the initiator of the call request. It should be understood that the number of second clients is not limited. The client of the audio and video call can be two or more parties. For example, the user initiates a call request, and the salesperson can continue to invite experts to join the audio and video communication. Any party can initiate a call request to multiple parties, and the service end pushes the call message. This application does not limit the number of second clients, and during the audio and video call, other clients can continue to be invited to join the audio and video call. The push of the call request can be notified via an IM message.

[0039] Step 102: If a call approval request from the second client is received, an audio or video call between the first client and the second client is established.

[0040] In a specific implementation process, when the server receives the call approval request from the second client, it means that the second client agrees to the call request for the audio and video call, and an audio and video call is established between the first client and the second client.

[0041] Step 103: Provide information identification services and insurance calculation services through the audio and video call to complete online insurance claims.

[0042] In the specific implementation process, during the audio and video call, the client where the customer is located can transmit messages to the client where the salesperson is located, and upload pictures of the scene to perform information recognition and insurance calculation services. For example, the information recognition service can identify the basic information of the vehicle through the vehicle pictures uploaded by the customer, confirm the basic situation of the vehicle, and make accurate claims analysis. The insurance calculation service can perform insurance calculations through the damaged parts of the vehicle uploaded by the customer to confirm the loss of the vehicle.

[0043] Based on the above embodiment, the first client and the second client are any one of a mobile terminal, a mini program terminal or a web terminal, and the mobile terminal, the mini program terminal and the web terminal respectively run corresponding SDK components, and the establishing of an audio and video call between the first client and the second client includes:

[0044] Creating a room number, where the room number is used to identify an audio or video call room between the first client and the second client;

[0045] The SDK components corresponding to the first client and the second client are used to call the RTC audio and video stream according to the room number to implement an audio and video call between the first client and the second client.

[0046] In a specific implementation, the first client and the second client can be any one of a mobile terminal, a mini program terminal or a web terminal. For example, the mobile terminal can be an Android terminal or an Apple terminal. The mini program terminal includes but is not limited to a WeChat mini program or an enterprise WeChat mini program. The web terminal is a desktop version of Google Chrome, a desktop version of Safari, and other browsers. The corresponding SDK components are respectively run in the mobile terminal, the mini program terminal, and the web terminal. The mobile terminal SDK, the mini program terminal SDK, and the web terminal SDK can be based on the TRTC SDK provided by Tencent, and the corresponding public components are encapsulated. Each party SDK performs functions such as initiating, receiving, establishing and maintaining calls through interaction with the server. For example, in the process of creating a room number, when it is found that a room has been established during the call between the two parties, there is no need to repeatedly establish the room. The current audio and video call between the two parties is directly determined based on the room number. If it has not been established, the room number is created, and the RTC audio and video mixing API of Tencent's bottom layer is called according to the room number to complete the call establishment process. When both parties enter the room, the first client and the second client can interact with data by publishing the local video stream and subscribing to the remote video stream to achieve real-time audio and video calls.

[0047] like Figure 2 The structure diagram of the audio and video call system based on insurance business is shown in FIG. Figure 2 As shown, Figure 2 It includes public network and intranet parts. The public network part is used to receive external business requests, including three business systems, namely APP mobile terminal, mini program terminal and PC web terminal. Call interaction is carried out through the SDK components running by itself, realizing cross-platform audio and video calls. The intranet part also includes three background service clusters, which correspond to the three business systems of the external network. The data flow processing of the entire audio and video call system is completed through the background service. The intranet also includes its own encapsulated component SunRTC. SunRTC is a self-developed RTC component. Through SunRTC, the RTC audio and video stream basic service function is called, and the room number is created to identify the audio and video call room to ensure non-interference.

[0048] Based on the above embodiment, the information identification service through the audio and video call includes:

[0049] Calling the AR video SDK to extract a first picture in the video stream, where the first picture includes a vehicle object for which insurance claim is to be made;

[0050] By performing information recognition on the first image, vehicle information is extracted, where the vehicle information includes a license plate number and a frame number.

[0051] In the specific implementation process, AR video SDK is an SDK component provided by a third party, which is embedded in the audio and video call. By calling the AR video SDK, the user's camera permissions are called to extract the picture frames of the audio and video call video stream, and the picture frames are converted into base64 pictures. By performing information recognition on the base64 pictures, the information recognition algorithm can be completed by the SDK provided by the third party. For example, the text recognition algorithm recognizes the license plate number or frame number in the current vehicle object. For example: During the audio and video call between the user and the salesperson, the user turns on AR scene recognition according to the prompts in the audio and video process, and points the mobile phone camera at the license plate number or frame number according to the on-screen instructions. The server extracts the picture frame according to the current video stream, converts the current picture frame into a base64 picture, and then extracts the vehicle information from the picture through the recognition algorithm to complete the information recognition.

[0052] Based on the above embodiment, the insurance calculation service provided through the audio and video call includes:

[0053] receiving a photo-taking request from the first client;

[0054] Capturing a second picture of the video stream according to the photo request, wherein the second picture includes a damaged part of the vehicle;

[0055] Sending the second picture to the second client via an IM instant channel;

[0056] Perform insurance calculation on the second image to obtain a claim result.

[0057] In the specific implementation process, during the audio and video call, the first client can also send a photo request. When the photo request of the first client is received, the camera permission of the client is called through the photo request to capture the second picture of the current video stream. The second picture is obtained by converting the current frame extracted from the video stream. The second picture is obtained by the first client pointing the camera at the damaged part of the vehicle and extracting the obtained picture during the audio and video call. The IM instant channel is an instant messaging transmission channel provided in the basic service, such as the IM instant messaging transmission function provided by Tencent. By calling the IM instant messaging channel, the rapid transmission of voice messages, text messages and picture messages can be realized. Insurance calculation can be an algorithm recognition of the damaged part of the current vehicle object. The algorithm recognition can also calculate the vehicle loss by calling the image loss analysis capability of the third-party SDK, and accurately provide the insurance claim result of the vehicle.

[0058] Based on the above embodiment, after performing the information identification service and the insurance calculation service through the audio and video call, the method further includes:

[0059] receiving a hang-up request from the first client or the second client;

[0060] Disconnect the audio or video call.

[0061] In the specific implementation process, when one of the participants in the audio and video call, such as the first client or the second client, can end the call, for example, when the video initiator initiates the end, it is sent to the server through the gateway status code, and the server closes the room through the parameters of the gateway status code. It is understandable that when there is a third client in the audio and video call, it is necessary to determine whether the end party is the initiator of the video, and whether to close the room and notify other video participants through IM based on whether it is the initiator. Disconnecting the audio and video connection can be done by disbanding the room through the above-mentioned audio and video call room number, thereby completing the disconnection.

[0062] Based on the above embodiment, after disconnecting the audio and video call, the method further includes:

[0063] Obtaining an audio and video mixed stream file generated by the audio and video call;

[0064] The audio and video mixed stream file is stored and a callback address is obtained;

[0065] The callback address is called to process the audio and video mixed stream file.

[0066] In the specific implementation process, after the audio and video call is disconnected, RTC audio and video can persist the audio and video mixed stream files generated by the audio and video call, store the audio and video mixed stream files in the cloud, and provide the video storage path as the callback address, and obtain the callback address of the audio and video file for further processing. For example, after the video ends, the real-time RTC provided by Tencent can set parameters in the cloud platform, the video file can be automatically stored in the cloud platform, and the video can be viewed on the public cloud platform. Configure the callback address in the public cloud platform, and after the video ends, call the video callback address configured by the gateway, and process the video through the parameters distributed by the gateway.

[0067] Based on the above embodiment, calling the video callback address to process the audio and video mixed stream file includes:

[0068] Download the audio and video mixed stream file according to the callback address;

[0069] Separating the audio and video mixed stream file to obtain an audio file and a video file;

[0070] The video file is processed, and the processing includes one or more of adding subtitles, taking video screenshots, adding watermarks, and format conversion.

[0071] In the specific implementation process, the processing of audio and video mixed stream files can be divided into separation and uploading. First, the audio and video mixed stream file is downloaded according to the callback address, and the audio and video mixed stream file is separated to obtain audio files and video files for use as insurance claim records.

[0072] Figure 3 A schematic diagram of a separation process of an audio and video mixed stream file based on insurance business provided in an embodiment of the present application is as follows: Figure 3 As shown in the figure, the audio and video separation operation can be done by building an audio and video separation component based on the Springcloud framework. After the video ends, the component listens to MQ messages, intercepts the URL address of the video by receiving MQ messages, downloads and caches the audio and video streams in the cloud, separates the audio stream and transmits it back to the cloud. The component implements cloud audio and video caching, quasi-real-time and high-quality conversion of audio and video, calculation of audio and video related attributes, audio and video compression and other functions. It is built through the FFmpeg plug-in based on the Linux platform on the server, and the audio and video conversion function in the FFmpeg plug-in is invoked through the shell script to perform audio splitting. Then it is sent to the imaging system in the form of HTTP for synchronization. If the consumer fails to process the message, it will be enriched. When the consumer fails to process the message, it will retry 3 times. If it still fails after 3 retries, the message will be sent to the dead letter queue for operation and maintenance personnel to handle. The audio and video component function also supports scalability, which can realize audio and video merging, adding subtitles to audio and video, video screenshots, adding watermarks to videos, audio and video format conversion and other functions to solve the separation of video and audio and complete video processing.

[0073] Figure 4 This is a schematic diagram of the structure of an audio and video call device based on insurance business provided in an embodiment of the present application. The device may be a module, program segment or code on an electronic device. It should be understood that the device is similar to the above-mentioned Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device can be found in the above description. To avoid repetition, detailed description is appropriately omitted here. The embodiment of the present application provides an audio and video call device based on insurance business, which includes:

[0074] The receiving module 401 is used to receive a call request from a first client and push the call request to a second client;

[0075] Establishing module 402, for establishing an audio and video call between the first client and the second client if a call approval request from the second client is received;

[0076] The service module 403 is used to perform information identification service and insurance calculation service through the audio and video call to complete the online insurance claim.

[0077] Based on the above embodiment, the first client and the second client are any one of a mobile terminal, a mini program terminal or a web terminal, and the mobile terminal, the mini program terminal and the web terminal respectively run corresponding SDK components.

[0078] Based on the above embodiment, the establishment module 402 is specifically used for:

[0079] Creating a room number, where the room number is used to identify an audio or video call room between the first client and the second client;

[0080] The SDK components corresponding to the first client and the second client are used to call the RTC audio and video stream according to the room number to implement an audio and video call between the first client and the second client.

[0081] Based on the above embodiment, the service module 403 is specifically used for:

[0082] Calling the AR video SDK to extract a first picture in the video stream, where the first picture includes a vehicle object for which insurance claim is to be made;

[0083] By performing information recognition on the first image, vehicle information is extracted, where the vehicle information includes a license plate number and a frame number.

[0084] Based on the above embodiment, the service module 403 is specifically used for:

[0085] receiving a photo-taking request from the first client;

[0086] Capturing a second picture of the video stream according to the photo request, wherein the second picture includes a damaged part of the vehicle;

[0087] Sending the second picture to the second client via an IM instant channel;

[0088] Perform insurance calculation on the second image to obtain a claim result.

[0089] Based on the above embodiment, the device further includes a disconnection module, which is used to:

[0090] receiving a hang-up request from the first client or the second client;

[0091] Disconnect the audio or video call.

[0092] Based on the above embodiment, the device further includes a receiving storage module, which is used to:

[0093] Obtaining an audio and video mixed stream file generated by the audio and video call;

[0094] The audio and video mixed stream file is stored and a callback address is obtained;

[0095] The callback address is called to process the audio and video mixed stream file.

[0096] Based on the above embodiment, the device further includes a processing module, which is used to:

[0097] Download the audio and video mixed stream file according to the callback address;

[0098] Separating the audio and video mixed stream file to obtain an audio file and a video file;

[0099] The video file is processed, and the processing includes one or more of adding subtitles, taking video screenshots, adding watermarks, and format conversion.

[0100] Figure 5 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application, such as Figure 5 As shown, the electronic device includes: a processor (processor) 501, a memory (memory) 502 and a bus 503; wherein,

[0101] The processor 501 and the memory 502 interact with each other via the bus 503;

[0102] The processor 501 is used to call the program instructions in the memory 502 to execute the methods provided by the above method embodiments.

[0103] The processor 501 can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 501 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. It can implement or execute various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0104] The memory 502 may include, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), etc.

[0105] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0106] This embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the methods provided by the above-mentioned method embodiments.

[0107] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or interactive connection shown or discussed can be through some interactive interfaces, and the indirect coupling or interactive connection of devices or units can be electrical, mechanical or other forms.

[0108] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0110] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0111] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An audio and video call method based on insurance business, characterized in that: Applied to the server, including: Receiving a call request from a first client, and pushing the call request to a second client; If a call approval request from the second client is received, establishing an audio and video call between the first client and the second client; Providing information identification services and insurance calculation services through the audio and video calls to complete online insurance claims; The first client and the second client are any one of a mobile terminal, a mini program terminal or a web terminal, and the mobile terminal, the mini program terminal and the web terminal respectively run corresponding SDK components, and the establishing of an audio and video call between the first client and the second client includes: Creating a room number, where the room number is used to identify an audio and video call channel between the first client and the second client; Using the SDK components corresponding to the first client and the second client respectively to call the RTC audio and video stream according to the room number, so as to realize the audio and video call between the first client and the second client; The information identification service performed through the audio and video call includes: Calling the AR video SDK to extract a first picture in the video stream, where the first picture includes a vehicle object for which insurance claim is to be made; By performing information recognition on the first image, the vehicle information is extracted, the vehicle information includes the license plate number and the frame number; The insurance calculation service provided through the audio and video call includes: receiving a photo-taking request from the first client; Capturing a second picture of the video stream according to the photo request, wherein the second picture includes a damaged part of the vehicle; Sending the second picture to the second client via an IM instant channel; Performing insurance calculation on the second image to obtain a claim result; Sending the claim settlement result to the first client; After performing the information identification service and the insurance calculation service through the audio and video call, the method further includes: receiving a hang-up request from the first client or the second client; Disconnecting the audio and video call; After disconnecting the audio and video call, the method further includes: Obtaining an audio and video mixed stream file generated by the audio and video call; The audio and video mixed stream file is stored and a callback address is obtained; Calling the callback address to process the audio and video mixed stream file; The calling of the callback address to process the audio and video mixed stream file includes: Download the audio and video mixed stream file according to the callback address; Separating the audio and video mixed stream file to obtain an audio file and a video file; The video file is processed, and the processing includes one or more of adding subtitles, taking video screenshots, adding watermarks, and format conversion.

2. An audio and video communication device based on insurance business, characterized in that: The device is used to perform the method according to claim 1, and the device comprises: A receiving module, configured to receive a call request from a first client and push the call request to a second client; An establishing module, configured to establish an audio and video call between the first client and the second client upon receiving a call approval request from the second client; The service module is used to perform information identification services and insurance calculation services through the audio and video calls to complete online insurance claims.

3. An electronic device, characterized in that: include: processor, memory and bus, wherein, The processor and the memory communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method according to claim 1.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when executed by a computer, cause the computer to perform the method of claim 1 .

Images