Data verification method, data verification system, and readable storage medium

Abstract

Embodiments of the present invention provide a data verification method, a data verification system, and a readable storage medium. Among them, the data verification method includes sending a data verification request to a service system; receiving a start verification instruction sent by the service system, and controlling a first electronic device to start working according to the start verification instruction; sending verification data obtained by the first electronic device to the service system for the service system to perform a data verification operation on the verification data; receiving a verification result of the verification data sent by the service system, and controlling the first electronic device to work according to the verification result. By sending a data verification request to the service system, on the one hand, it can avoid artificial interruption of the first electronic device from sending verification data to the service system for data verification operations during the insurance sales process. On the other hand, it can also avoid the operator forgetting to establish a connection with the service system due to work negligence, resulting in the service system failing to start in time for data verification operations.

Description

Technical Field

[0001] The present invention relates to the technical field of compliance inspection, and in particular, to a data inspection method, a data inspection system, and a readable storage medium. Background Art

[0002] With the rapid development of Internet applications, the method of selling financial products through the Internet has been widely used. To standardize insurance sales behaviors in the Internet environment, safeguard the legitimate rights and interests of insurance consumers, and promote the sustainable and healthy development of the industry, the Banking and Insurance Regulatory Commission requires on-site synchronous recording and video (hereinafter referred to as "dual recording") of insurance sales behaviors to record and save key links in the process of selling insurance products, so as to provide a basis for subsequent query of important information and determination of problem responsibilities.

[0003] The on-site synchronous recording and video of insurance sales behaviors should comply with the requirements of relevant business specifications. The audio-visual materials should be true, complete, and continuous, and should clearly identify the facial features of personnel, conversation content, and relevant certificates, documents, and signatures. No form of editing is allowed after recording. At the same time, insurance companies should establish a quality inspection system for audio-visual materials, formulate quality inspection systems, establish quality inspection information systems, and allocate quality inspection personnel separated from the positions of sales personnel to conduct full-process quality inspections on the audio-visual materials of concluded transactions at a ratio of not less than 30% during the hesitation period. Among them, 100% quality inspection should be achieved for the audio-visual materials of certain insurance products or insurance services for certain purchase groups.

[0004] The currently widely used quality inspection method is to conduct quality inspection by manually playing back video materials afterwards to complete the compliance quality inspection process, which leads to problems such as high labor costs, low compliance quality inspection efficiency, and lagging quality inspection results. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art or related technologies.

[0006] To this end, the first aspect of the embodiments of the present invention is to propose a data inspection method for a first electronic device.

[0007] The second aspect of the embodiments of the present invention is to propose a data inspection method for a service system.

[0008] The third aspect of the embodiments of the present invention is to propose a data inspection system.

[0009] The fourth aspect of the embodiments of the present invention is to propose a readable storage medium.

[0010] In view of this, according to the first aspect of the embodiments of the present invention, a data verification method for a first electronic device is proposed, including: sending a data verification request to a service system; receiving a start verification instruction sent by the service system, and controlling a data acquisition device to start working according to the start verification instruction; sending the verification data to be acquired by the data acquisition device to the service system for the service system to perform a data verification operation on the verification data; receiving the verification result of the verification data sent by the service system, and controlling the first electronic device to work according to the verification result.

[0011] The data verification method provided by the embodiments of the present invention is for a first electronic device. By sending a data verification request to the service system to obtain a start verification instruction returned by the service system, and then controlling the data acquisition device to start working according to the start verification instruction, that is, realizing that the service system instructs the data acquisition device to start working, thus avoiding the possibility of missed inspections. On the one hand, in the process of insurance sales, it can avoid the artificial control of the data acquisition device to work independently, so as to block the first electronic device from sending verification data to the service system for real-time data verification operations. On the other hand, it can also prevent the operator from forgetting to establish a connection with the service system due to work negligence, resulting in the service system failing to start the data verification working mode in time for data verification operations. Further, after the data acquisition device acquires the verification data, it automatically sends it to the service system for the service system to perform a verification operation on the verification data. On the one hand, it avoids the artificial tampering of data and improves the integrity and accuracy of the data. On the other hand, it realizes the data verification operation on the verification data during the data acquisition process, that is, realizes the synchronous progress of data acquisition and data verification, and improves the real-time nature of data verification. Further, since the verification result of the verification data can be returned during the data acquisition process, it is realized that when the verification data is unqualified, the supplementary recording work can be carried out in time, reducing the number of supplementary recordings afterwards and lowering the supplementary recording cost. In addition, it also reduces the labor cost and avoids the problems of missed inspections and misjudgments that are prone to occur during manual review. Specifically in the process of insurance sales, due to the real-time verification of the verification data, that is, realizing the real-time verification of the true purchase intention of the applicant, it can also reduce the potential compliance risk and claim dispute risk, and avoid the applicant's complaints and policy cancellations afterwards.

[0012] In addition, according to the data verification method for the first electronic device in the above technical solution provided by the present invention, it may also have the following additional technical features:

[0013] In the above technical solution, the step of controlling the data acquisition device to work according to the verification result specifically includes: when the verification result is unqualified, controlling the data acquisition device to re-acquire the verification data and send it to the service system.

[0014] In this technical solution, the step of controlling the operation of the data acquisition device according to the test result is specifically that when the test result is qualified, the data acquisition device is controlled to stop working. When the test result is unqualified, the data acquisition device is controlled to re-acquire the test data and send it to the service system, so that the service system can perform a test operation on the test data, until the service system returns a test result that the test data is qualified to the first electronic device. By setting the control data acquisition device to re-acquire the test data and send it to the service system when the test result is unqualified, it is realized that the data process is automatically supplemented, the number of subsequent supplementary recordings is reduced, and the supplementary recording cost is reduced. Specifically in the process of insurance sales, due to the real-time inspection and timely supplementary recording of the test data, it can avoid the insurance personnel from performing illegal operations, ensure that the insured takes out insurance based on their true intentions, and reduce the potential compliance and claims dispute risks.

[0015] In any of the above technical solutions, the data verification method also includes: receiving a verification sample sent by the service system; and obtaining verification data based on the verification sample.

[0016] In this technical solution, the data verification method also includes receiving a test sample sent by the service system, and obtaining test data based on the test sample. Specifically, the service system selects the speech and / or compliance questions of the corresponding link from the preset question library and / or speech library, and sends the speech and / or questions to the first electronic device in the form of text information and / or voice information, so as to guide the user or insurance agent to answer the compliance questions and / or read the prescribed speech on site according to the text information and / or voice information, thereby obtaining the test data, improving the accuracy of the test data, and thus improving the efficiency of data verification, avoiding the test data content being unqualified and causing the test results to be unqualified, so as to cause repeated re-entry and increase labor costs.

[0017] In any of the above technical solutions, the data acquisition device includes an image acquisition device.

[0018] In this technical solution, the data acquisition device includes an image acquisition device. The image acquisition device can acquire video data so as to synchronously identify and verify the identity information data of the insured and / or insurance agent, thereby avoiding the increase in compliance and claims dispute risks caused by post-auditing the identity information data.

[0019] In any of the above technical solutions, the data acquisition device includes an audio acquisition device.

[0020] In this technical solution, the data acquisition device includes an audio acquisition device. Audio data is acquired through the audio acquisition device, that is, the compliance questions answered by the user or insurance agent and / or the prescribed words are separately recorded, so as to conduct data verification on the audio data of the compliance questions and / or the prescribed words, avoiding data loss caused by separating speech from video data and affecting the accuracy of data verification.

[0021] In any of the above technical solutions, the data acquisition device includes an image acquisition device and an audio acquisition device.

[0022] In this technical solution, the data acquisition device includes an image acquisition device and an audio acquisition device. Video data can be acquired through the image acquisition device, and audio data is acquired through the audio acquisition device, realizing data verification on the identity information data of the applicant and / or insurance agent and the audio data of the compliance questions and / or the prescribed words at the same time. It avoids the risk of increasing compliance and claims disputes due to ex post facto review of identity information data, and also avoids data loss caused by separating speech from video data and affecting the accuracy of data verification. By separately acquiring audio data and video data with the image acquisition device and the audio device, on the one hand, the integrity and accuracy of the data are improved, and the service system can separately verify the video data acquired by the image acquisition device and the audio data acquired by the audio acquisition device, improving the verification efficiency. On the other hand, it avoids the problems of data loss and reduced data verification efficiency caused by splitting the acquired multimedia file (audio data and video data in the same file).

[0023] In any of the above technical solutions, the verification data includes: audio data; video data, and the video data includes face image data.

[0024] In this technical solution, the verification data includes audio data and video data, where the video data includes face image data. Through the video data containing face images, the identity information data of the applicant and / or insurance agent can be synchronously identified and verified, avoiding the risk of increasing compliance and claims disputes due to ex post facto review of identity information data. Through the audio data, data verification can be conducted on the audio data of the compliance questions and / or the prescribed words, avoiding data loss caused by separating speech from video data and affecting the accuracy of data verification.

[0025] According to the second aspect of the embodiments of the present invention, the present invention provides a data verification method for a service system. The data verification method includes: acquiring the verification data sent by the first electronic device and preprocessing the verification data; performing a data verification operation on the preprocessed verification data to generate a verification result of the verification data; and sending the verification result to the first electronic device.

[0026] The data verification method provided by the embodiments of the present invention is used in a service system. After receiving a data verification request from a first electronic device, the service system feeds back a start verification instruction to the first electronic device to control the data acquisition device to start working and initiate the working mode of data verification. Thus, it is realized that the service system instructs the data acquisition device to start working, thereby avoiding the possibility of missed inspections. On the one hand, during the insurance sales process, it can prevent the data acquisition device from working independently under manual control, blocking the first electronic device from sending verification data to the service system for real-time data verification operations. On the other hand, it can also prevent operators from forgetting to establish a connection with the service system due to work negligence, resulting in the service system failing to timely initiate the data verification working mode for data verification operations. Further, the service system acquires the verification data sent by the first electronic device and preprocesses the verification data. By performing data verification operations on the preprocessed verification data to generate the verification result of the verification data and sending the verification result to the first electronic device, the first electronic device can control and determine the working state of the data acquisition device according to the verification result. By setting the service system to directly acquire the verification data from the first electronic device and perform verification operations on the verification data, on the one hand, it avoids manual data tampering and improves the integrity and accuracy of the data. On the other hand, it realizes performing data verification operations on the verification data during the data acquisition process, that is, realizes the synchronous progress of data acquisition and data verification, improving the real-time performance of data verification. Further, since the verification result of the verification data can be returned during the data acquisition process, it is realized that when the verification data is unqualified, the supplementary recording work can be carried out in a timely manner, reducing the number of supplementary recordings afterwards and lowering the supplementary recording cost. In addition, it also reduces the labor cost and avoids the problems of missed inspections and misjudgments that are prone to occur during manual review. Specifically, during the insurance sales process, due to the real-time verification of the verification data, that is, it realizes the real-time verification of the true purchase intention of the applicant, and can also reduce the potential compliance and claims dispute risks.

[0027] In addition, according to the data verification method for a service system in the above technical solution provided by the present invention, it may further have the following additional technical features:

[0028] In the above technical solution, the verification data includes audio data. The step of performing data verification operations on the preprocessed verification data specifically includes: acquiring the audio feature information of the preprocessed audio data; generating a text to be verified according to the audio feature information; and performing keyword matching between the text to be verified and the verification sample to generate the verification result of the audio data.

[0029] In this technical solution, the preprocessing of the audio data includes performing noise reduction processing on the audio data, thereby improving the accuracy and efficiency of generating the text to be verified.

[0030] In this technical solution, the inspection data includes audio data. By directly obtaining the audio data, it is avoided to split the multimedia file to obtain the audio file. On the one hand, it can avoid data damage or loss caused during the splitting process. On the other hand, directly performing the inspection operation on the audio data can improve the efficiency of data inspection.

[0031] Further, the steps of performing the data inspection operation on the preprocessed inspection data are as follows: obtaining the audio feature information of the preprocessed audio data, generating the text to be inspected according to the audio feature information, and then generating the inspection result of the audio data by matching the text to be inspected with the inspection sample for keywords. By matching the text to be inspected generated from the audio data with the inspection sample for keywords, it can accurately judge whether the conversation between the insurance agent and the user complies with the regulations and avoid illegal operations during the insurance sales process. In addition, by matching keywords for the text information, it is avoided to manually replay the audio file to review the conversation content, reducing the labor verification cost and improving the review efficiency.

[0032] In any of the above technical solutions, the inspection data further includes video data. The steps of performing the data inspection operation on the preprocessed inspection data further include: obtaining the identity feature information according to the preprocessed video data; obtaining the identity information to be inspected according to the identity feature information; and matching the identity information to be inspected with the pre-stored identity information to generate the inspection result of the video data.

[0033] In this technical solution, the inspection data includes video data. By directly obtaining the video data, it is avoided to split the multimedia file to obtain the video data. On the one hand, it can avoid the picture distortion caused during the splitting process, which affects the accuracy of identity information recognition. On the other hand, directly performing the inspection operation on the video data can improve the efficiency of data inspection.

[0034] Further, identity feature information is obtained based on the preprocessed video data, and the identity information to be verified is obtained based on the identity feature information. Specifically, in one implementation, the identity feature information is input into a preset face model for comparison to obtain the identity information to be verified. Among them, the preset face model can be set from multiple sources, such as third-party verification units like the face database of the Ministry of Public Security, ID card photos, photo information of old customers reserved in the system, etc., which will not be listed one by one here. The obtained identity information to be verified is matched with the pre-stored identity information to generate the verification result of the video data. Specifically, if the information to be verified matches the pre-stored identity information successfully, it is confirmed that the verification result of the video data is qualified; if the information to be verified does not match the pre-stored identity information, it is confirmed that the verification result of the video data is unqualified. In one implementation, the pre-stored identity information comes from the identity information of the user and / or insurance agent input by the first electronic device. The identity information of the user and / or insurance agent is verified through the video data, avoiding problems such as high cost, lagging quality inspection results, low quality inspection efficiency, easy post-dispute, and poor user experience when using manual inspection.

[0035] In any of the above technical solutions, the data verification method further includes: generating the verification result of the verification data according to the verification result of the audio data and the verification result of the video data; the step of generating the verification result of the verification data according to the verification result of the audio data and the verification result of the video data specifically includes: when the verification result of the audio data is unqualified, and / or the verification result of the video data is unqualified, it is determined that the verification result of the verification data is unqualified.

[0036] In this technical solution, the data verification method further includes generating the verification result of the verification data according to the verification result of the audio data and the verification result of the video data. Specifically, when both the verification result of the audio data and the verification result of the video data are qualified, it is confirmed that the verification result of the verification data is qualified. When either the verification result of the audio data or the verification result of the video data is unqualified, it is confirmed that the verification result of the verification data is unqualified. That is to say, only when the identity information of the user and / or insurance agent and the conversation information both meet the regulations, the service system sends a verification result of qualified verification data to the first electronic device, improving the accuracy of data verification, that is, improving the compliance in the insurance sales process and avoiding inspection loopholes that may lead to claims disputes.

[0037] In any of the above technical solutions, the step of generating the text to be verified according to the audio feature information specifically includes: identifying the audio feature information according to a preset acoustic model to obtain syllable feature information; identifying the syllable feature information according to a preset language model to generate the text to be verified.

[0038] In this technical solution, in this embodiment, the steps of generating the text to be inspected based on the audio feature information are as follows: identifying the syllable feature information by identifying the audio feature information according to a preset acoustic model, and then identifying the speech recognition text by identifying the syllable feature information according to a preset language model, which improves the accuracy and conversion efficiency of the text information, thereby improving the accuracy and efficiency of data inspection. In addition, taking the speech recognition text as the text to be inspected, the conversation information between the insurance agent and the user is audited by inspecting the speech recognition text, avoiding illegal operations during the insurance sales process. In addition, by performing keyword matching on the text information, the manual playback of the audio file for auditing the conversation content is avoided, reducing the human verification cost and improving the auditing efficiency.

[0039] In any of the above technical solutions, the steps of performing keyword matching between the text to be inspected and the inspection sample specifically include: performing required keyword matching between the text to be inspected and the inspection sample; and / or performing sensitive keyword matching between the text to be inspected and the inspection sample; and / or performing misleading keyword matching between the text to be inspected and the inspection sample.

[0040] In this technical solution, by performing required keyword matching between the text to be inspected and the inspection text, the purpose of whether the insurance agent has accurately informed the user of the necessary information during the insurance sales process is achieved, avoiding the situation where the insurance agent conceals information during the insurance sales process, resulting in the user purchasing insurance under information asymmetry, and causing disputes afterwards, so that claims cannot be settled. By performing sensitive keyword matching between the text to be inspected and the inspection text, it is avoided that the insurance agent uses sensitive language to the user during the insurance sales process, inducing the user to purchase insurance, and causing disputes afterwards, so that claims cannot be settled. By performing misleading keyword matching between the text to be inspected and the inspection text, it is avoided that the insurance agent uses misleading language to the user during the insurance sales process, causing the user to misunderstand the insurance-related terms and purchase insurance against their true will, and causing disputes afterwards, so that claims cannot be settled.

[0041] It should be noted that when performing data inspection operations on audio data, if all required keywords are matched, it is confirmed that the required keyword matching is successful, and the inspection result of the audio data is confirmed to be qualified. If there are required keywords that are not matched, synonym keyword matching is performed for the unmatched required keywords. If all the to-be-identified synonyms are matched, it is confirmed that the synonym keyword matching is successful, and the inspection result of the audio data is confirmed to be qualified. If there are to-be-identified synonyms that are not matched, it is confirmed that the synonym keyword matching fails, and the inspection result of the audio data is confirmed to be unqualified.

[0042] And / or, if all misleading keywords are not matched, confirm that the misleading keyword matching is successful and confirm that the inspection result of the audio data is qualified. If there are any matched misleading keywords, confirm that the misleading keyword matching fails and confirm that the inspection result of the audio data is unqualified.

[0043] And / or, if all sensitive keywords are not matched, confirm that the sensitive keyword matching is successful and confirm that the inspection result of the audio data is qualified. If there are any matched sensitive keywords, confirm that the sensitive keyword matching fails and confirm that the inspection result of the audio data is unqualified.

[0044] In any of the above technical solutions, the step of performing keyword matching between the text to be inspected and the inspection sample further includes: obtaining the required reading keywords that are not matched in the text to be inspected to generate the near-synonyms to be identified; performing near-synonym keyword matching between the near-synonyms to be identified and the inspection sample.

[0045] In this technical solution, after the required reading keyword matching between the text to be inspected and the inspection sample, the unmatched keywords are used as the near-synonyms to be identified, so as to perform near-synonym keyword matching on the near-synonyms to be identified, further improving the accuracy of audio data inspection. In an implementation manner, a near-synonym sample word library can be generated based on the inspection sample, and the near-synonyms to be identified are matched with the near-synonym sample word library. If the matching is successful, it indicates that the required reading keyword matching is successful.

[0046] Further, in the above embodiment, the step of obtaining the face image according to the first video data specifically includes: intercepting the video frame in the video data to obtain the facial image information; preprocessing the facial image information to generate the face image, where the preprocessing includes one or more of image sharpening, background removal, geometric normalization, and gray-scale normalization.

[0047] In this embodiment, the preprocessing of the video data includes face localization on the video frame and cropping according to the localization result, so as to obtain the face image for obtaining the identity information data of the user and / or insurance agent, and then inspect the identity information data of the user and / or insurance agent to avoid sending illegal operations, such as reimbursing and purchasing and / or selling insurance in the name of others.

[0048] In this embodiment, the video screen in the video message data is intercepted to obtain the facial image information of the user and / or the insurance agent, and the facial image information is preprocessed to generate the face image of the user and / or the insurance agent, so that the obtained face image is clear and highly accurate, facilitating the acquisition of the identity information to be verified of the user / or the insurance agent through face recognition technology. Thus, the identity information data of the user and / or the insurance agent is verified to avoid sending illegal operations, such as reimbursement purchases and / or insurance sales work in the name of others.

[0049] According to the third aspect of the embodiments of the present invention, the present invention provides a data verification system, including: a first electronic device, the first electronic device includes: a first memory and a first processor, the first memory stores programs or instructions, and the first processor executes the programs or instructions to implement the steps of the data verification method provided by any one of the technical solutions in the first aspect; a service system, the service system includes: a third memory and a third processor, the third memory stores programs or instructions, and the third processor executes the programs or instructions to implement the steps of the data verification method provided by any one of the technical solutions in the second aspect.

[0050] The data verification system provided by the embodiments of the present invention can implement the steps of the data verification method provided by any one of the technical solutions in the first aspect and the steps of the data verification method provided by any one of the technical solutions in the second aspect. Therefore, it has all the beneficial technical effects of the data verification method provided by any one of the technical solutions in the first aspect and the data verification method provided by any one of the technical solutions in the second aspect, which will not be elaborated here.

[0051] According to the fourth aspect of the embodiments of the present invention, the present invention provides a readable storage medium, on which programs or instructions are stored, and when the programs or instructions are executed by a processor, the steps of the data verification method provided by any one of the technical solutions in the first aspect are implemented; or when the programs or instructions are executed by a processor, the steps of the data verification method provided by any one of the technical solutions in the second aspect are implemented.

[0052] The readable storage medium provided by the embodiments of the present invention can implement the steps of the data verification method provided by any one of the technical solutions in the first aspect or the steps of the data verification method provided by any one of the technical solutions in the second aspect. Therefore, it has all the beneficial technical effects of the data verification method provided by any one of the technical solutions in the first aspect or the data verification method provided by any one of the technical solutions in the second aspect, which will not be elaborated here.

[0053] The additional aspects and advantages of the present invention will become apparent in the following description section or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of embodiments in conjunction with the accompanying drawings, in which:

[0055] Figure 1 The flowchart of a data verification method according to an embodiment of the present invention is shown;

[0056] Figure 2 The flowchart of a data verification method according to another embodiment of the present invention is shown;

[0057] Figure 3 The flowchart of a data verification method according to another embodiment of the present invention is shown;

[0058] Figure 4 The schematic diagram of a data verification system according to an embodiment of the present invention is shown;

[0059] Figure 5 The schematic diagram of a data verification system according to another embodiment of the present invention is shown;

[0060] Figure 6 The schematic diagram of a data verification system according to another embodiment of the present invention is shown.

[0061] Wherein, the correspondence between the reference numerals and the component names is as follows:

[0062] 400 data verification system, 402 first electronic device, 404 service system, 406 image acquisition device, 408 audio acquisition device, 410 server, 412 synchronous quality inspection system. Detailed implementation manners

[0063] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

[0064] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0065] The following refers to Figures 1 to 6 Describe a data verification method, a data verification system and a readable storage medium provided according to some embodiments of the present invention.

[0066] Embodiment 1

[0067] As Figure 1As shown in the figure, Embodiment 1 provides a data verification method for a first electronic device, including:

[0068] Step 102, sending a data verification request to the service system;

[0069] Step 104, receiving the start verification instruction sent by the service system, and controlling the data acquisition device to start working according to the start verification instruction;

[0070] Step 106, sending the verification data acquired by the data acquisition device to the service system for the service system to perform data verification operations on the verification data;

[0071] Step 108, receiving the verification result of the verification data sent by the service system, and controlling the data acquisition device to work according to the verification result.

[0072] The data verification method provided by the embodiment of the present invention is used for a first electronic device. By sending a data verification request to the service system to obtain the start verification instruction returned by the service system, thereby controlling the first electronic device to start working according to the start verification instruction, that is, realizing that the service system instructs the first electronic device to start working, thus avoiding the possibility of missed inspections. On the one hand, in the process of insurance sales, it can avoid the independent operation of the data acquisition device controlled by humans to block the first electronic device from sending verification data to the service system for real-time data verification operations. On the other hand, it can also prevent operators from forgetting to establish a connection with the service system due to work negligence, resulting in the service system failing to start the data verification working mode in time for data verification operations. Further, after the data acquisition device acquires the verification data, it automatically sends it to the service system for the service system to perform verification operations on the verification data. On the one hand, it avoids human tampering with the data, improves the integrity and accuracy of the data. On the other hand, it realizes data verification operations on the verification data during the data acquisition process, that is, realizes the synchronous progress of data acquisition and data verification, and improves the real-time performance of data verification. Further, since the verification result of the verification data can be returned during the data acquisition process, it is realized that when the verification data is unqualified, the supplementary recording work can be carried out in time, reducing the number of supplementary recordings afterwards and lowering the supplementary recording cost. In addition, it also reduces the labor cost and at the same time avoids the problems of missed inspections and misjudgments that are prone to occur during manual review. Specifically in the process of insurance sales, due to the real-time verification of the verification data, that is, realizing the real-time verification of the true purchase intention of the applicant, it can also reduce the potential compliance risk and claim dispute risk, and avoid post-event complaints and policy cancellations by the applicant.

[0073] Further, in this technical solution, when the verification result returned by the service system is unqualified, the unqualified items are simultaneously returned to the first electronic device, so that the on-site terminal can specifically re-acquire the verification data to improve the efficiency of data verification.

[0074] In one embodiment, the first electronic device is a front-end client, that is, a field terminal, wherein the first electronic device may be any one of a user client, an insurance agent client, and an insurance company field client.

[0075] Embodiment 2

[0076] Based on the first embodiment, the second embodiment provides a data verification method, which further defines the steps of controlling the operation of the data acquisition device according to the inspection result, specifically including: when the inspection result is unqualified, controlling the data acquisition device to re-acquire the inspection data and send it to the service system.

[0077] In a specific embodiment, Figure 2 As shown, the data verification method includes:

[0078] Step 202, sending a data verification request to the service system;

[0079] Step 204, receiving a start inspection instruction sent by the service system, and controlling the data acquisition device to start working according to the start inspection instruction;

[0080] Step 206, sending the inspection data acquired by the data acquisition device to the service system, so that the service system can perform a data inspection operation on the inspection data;

[0081] Step 208, receiving the inspection result of the inspection data sent by the service system;

[0082] Step 210, determine whether the data inspection result is qualified. If the determination result is no, execute step 206. If the determination result is yes, control the data acquisition device to end the work.

[0083] In this embodiment, the step of controlling the operation of the data acquisition device according to the test result is specifically that when the test result is qualified, the data acquisition device is controlled to stop working. When the test result is unqualified, the data acquisition device re-acquires the test data and sends it to the service system, so that the service system can perform a test operation on the test data, until the service system returns a test result that the test data is qualified to the first electronic device. By setting the control of the data acquisition device to re-acquire the test data and send it to the service system when the test result is unqualified, it is realized that the data process is automatically supplemented, the number of subsequent supplementary recordings is reduced, and the supplementary recording cost is reduced. Specifically in the process of insurance sales, due to the real-time inspection and timely supplementary recording of the test data, it can avoid the insurance personnel from performing illegal operations, ensure that the insured takes out insurance based on their true intentions, and reduce the potential compliance and claims dispute risks.

[0084] Embodiment 3

[0085] Based on any of the above embodiments, the data verification method further includes: receiving a verification sample sent by a service system; and obtaining verification data according to the verification sample.

[0086] In this embodiment, the data verification method further includes receiving a verification sample sent by a service system and obtaining verification data according to the verification sample. Specifically, the service system selects the corresponding link's conversation words and / or compliance questions from a preset question bank and / or conversation word bank, and sends the conversation words and / or questions to the first electronic device in the form of text information and / or voice information, so as to guide the user or insurance agent to answer the compliance questions and / or read the specified conversation words according to the text information and / or voice information on site, thereby obtaining verification data, improving the accuracy of the verification data, thus improving the efficiency of data verification, and avoiding the situation that the content of the verification data is unqualified, resulting in an unqualified verification result, and further causing repeated supplementary recording and increasing labor costs.

[0087] Further, in the above embodiment, as Figure 6 shown, the data acquisition device includes an image acquisition device 406 and / or an audio acquisition device 408.

[0088] In one implementation manner, the data acquisition device includes an image acquisition device 406. Through the image acquisition device 406, video data can be acquired, so as to synchronously identify and verify the identity information data of the applicant and / or insurance agent, and avoid increasing the risks of compliance and claims disputes due to ex post facto review of the identity information data.

[0089] In another implementation manner, the data acquisition device includes an audio acquisition device 408. Audio data is acquired through the audio acquisition device 408, that is, the compliance questions answered by the user or insurance agent and / or the specified conversation words read are separately recorded, so as to perform data verification on the audio data of the compliance questions and / or the specified conversation words, and avoid data loss caused by separating voices from video data, which affects the accuracy of data verification.

[0090] In yet another embodiment, the data acquisition device includes an image acquisition device 406 and an audio acquisition device 408. The video data can be acquired through the image acquisition device, and the audio data can be acquired through the audio acquisition device, so as to realize the data verification of the identity information data of the applicant and / or insurance agent and the audio data of compliance issues and / or prescribed words. This avoids the risk of increasing compliance and claims disputes due to post-event review of identity information data, and also avoids data loss caused by separating speech from video data, which affects the accuracy of data verification. By separately acquiring audio data and video data through the image acquisition device and the audio device, on the one hand, the integrity and accuracy of the data are improved, and the service system can separately verify the video data acquired by the image acquisition device and the audio data acquired by the audio acquisition device, improving the verification efficiency. On the other hand, it avoids the problems of data loss and reduced data verification efficiency caused by splitting the multimedia file (audio data and video data in the same file).

[0091] Further, in the above embodiment, the verification data includes: audio data; video data, and the video data includes face image data.

[0092] In this embodiment, the verification data includes audio data and video data, wherein the video data includes face image data. Through the video data including face images, the identity information data of the applicant and / or insurance agent can be synchronously identified and verified, avoiding the risk of increasing compliance and claims disputes due to post-event review of identity information data. Through the audio data, the audio data of compliance issues and / or prescribed words can be verified, avoiding data loss caused by separating speech from video data, which affects the accuracy of data verification.

[0093] Embodiment 4

[0094] As Figure 3 shown, Embodiment 4 provides a data verification method for a service system, including:

[0095] Step 302: Acquire the verification data sent by the first electronic device and preprocess the verification data;

[0096] Step 304: Perform a data verification operation on the preprocessed verification data to generate a verification result of the verification data;

[0097] Step 306: Send the verification result to the first electronic device.

[0098] The data verification method provided by the embodiment of the present invention is used for a service system. After receiving a data verification request from a first electronic device, the service system feeds back a start verification instruction to the first electronic device to control the data acquisition device to start working and starts the working mode of data verification. Thus, it is realized that the service system instructs the data acquisition device to start working, thereby avoiding the possibility of missed inspection. On the one hand, during the insurance sales process, it can avoid the independent operation of the data acquisition device controlled manually to block the first electronic device from sending verification data to the service system for real-time data verification operations. On the other hand, it can also prevent the operator from forgetting to establish a connection with the service system due to work negligence, resulting in the service system failing to start the data verification working mode in time for data verification operations. Further, the service system acquires the verification data sent by the first electronic device and preprocesses the verification data. By performing data verification operations on the preprocessed verification data to generate the verification result of the verification data and sending the verification result to the first electronic device, the first electronic device can control and determine the working state of the data acquisition device according to the verification result. By setting the service system to directly acquire the verification data and perform verification operations on the verification data, on the one hand, it avoids the manual tampering of data, improves the integrity and accuracy of the data. On the other hand, it realizes the data verification operations on the verification data during the data acquisition process, that is, realizes the synchronous progress of data acquisition and data verification, and improves the real-time performance of data verification. Further, since the verification result of the verification data can be returned during the data acquisition process, it is realized that when the verification data is unqualified, the supplementary recording work can be carried out in time, reducing the number of supplementary recordings afterwards and reducing the supplementary recording cost. In addition, it also reduces the labor cost and avoids the problems of missed inspection and wrong inspection that are prone to occur during manual review. Specifically, during the insurance sales process, due to the real-time verification of the verification data, that is, the real-time verification of the true purchase intention of the applicant is realized, and the potential compliance and claims dispute risks can also be reduced.

[0099] Further, in this technical solution, when the service system returns a verification result of unqualified to the first electronic device, it also returns the unqualified items to the first electronic device at the same time, so that the field end can obtain the verification data again targeted, improving the efficiency of data verification.

[0100] In one implementation, such as Figure 4 and Figure 6As shown, the service system 404 includes a server 410 and a synchronization quality inspection system 412. Among them, the server 410 is mainly used for information interaction with the first electronic device 402, and the synchronization quality inspection system 412 is mainly used for the inspection operation of data. Specifically, when the server 410 sends a start inspection instruction to the first electronic device 402, the synchronization quality inspection system 412 is started simultaneously. Further, after the server 410 receives the inspection data sent by the first electronic device 402, it first preprocesses the inspection data, and then the synchronization quality inspection system 412 performs a data inspection operation on the preprocessed inspection data. Finally, the server 410 sends the inspection result to the first electronic device 402.

[0101] Embodiment 5

[0102] Based on Embodiment 4, Embodiment 5 provides a data inspection method, further defining that the inspection data includes audio data. The steps of performing a data inspection operation on the preprocessed inspection data specifically include: obtaining the audio feature information of the preprocessed audio data; generating a text to be inspected according to the audio feature information; and performing keyword matching between the text to be inspected and the inspection sample to generate the inspection result of the audio data.

[0103] In this embodiment, the inspection data includes audio data. By directly obtaining the audio data, it is avoided to split the multimedia file to obtain the audio file. On the one hand, it can avoid data damage or data loss caused during the splitting process, so as not to affect the integrity of the inspection data. On the other hand, directly performing the inspection operation on the audio data can improve the efficiency of data inspection.

[0104] Further, the steps of performing a data inspection operation on the preprocessed inspection data are to obtain the audio feature information of the preprocessed audio data, generate a text to be inspected according to the audio feature information, and then perform keyword matching between the text to be inspected and the inspection sample to generate the inspection result of the audio data. By performing keyword matching between the text to be inspected generated from the audio data and the inspection sample, it can accurately determine whether the conversation between the insurance agent and the user complies with the regulations, and avoid illegal operations during the insurance sales process. In addition, by performing keyword matching on the text information, it is avoided to manually play back the audio file to review the conversation content, reducing the human verification cost and improving the review efficiency.

[0105] In this embodiment, the preprocessing of the audio data includes performing noise reduction processing on the audio data, thereby improving the accuracy and efficiency of generating the text to be inspected.

[0106] Further, in this embodiment, the inspection sample is that the service system selects the corresponding link's conversation scripts and / or compliance issues from a preset question bank and / or conversation script bank, and generates text information from the conversation scripts and / or issues as the inspection sample, so as to perform keyword matching on the text to be inspected converted from the audio data, and review whether the conversation between the insurance agent and the user complies with the regulations.

[0107] Further, in the above embodiment, the step of generating the text to be inspected according to the audio feature information specifically includes: identifying the audio feature information according to a preset acoustic model to obtain syllable feature information; and identifying the syllable feature information according to a preset language model to generate the text to be inspected.

[0108] In this embodiment, the step of generating the text to be inspected according to the audio feature information is to identify the audio feature information according to a preset acoustic model to obtain syllable feature information, and then identify the syllable feature information according to a preset language model to obtain the speech recognition text, which improves the accuracy and conversion efficiency of the text information, thereby improving the accuracy and efficiency of data inspection. In addition, using the speech recognition text as the text to be inspected, the conversation information between the insurance agent and the user is reviewed by inspecting the speech recognition text, avoiding illegal operations in the insurance sales process. In addition, by performing keyword matching on the text information, it is avoided to manually replay the audio file to review the conversation content, reducing the human verification cost and improving the review efficiency.

[0109] Further, in the above embodiment, the step of performing keyword matching between the text to be inspected and the inspection sample specifically includes: performing required keyword matching between the text to be inspected and the inspection sample; and / or performing sensitive keyword matching between the text to be inspected and the inspection sample; and / or performing misleading keyword matching between the text to be inspected and the inspection sample.

[0110] In this embodiment, by performing required keyword matching between the text to be inspected and the inspection text, the purpose of whether the insurance agent has accurately informed the user of the necessary information during the insurance sales process is achieved, avoiding the problem that the insurance agent conceals information during the insurance sales process, resulting in the user purchasing insurance under information asymmetry, and causing disputes afterwards, so that claims cannot be settled. By performing sensitive keyword matching between the text to be inspected and the inspection text, it is avoided that the insurance agent uses sensitive language to the user during the insurance sales process, inducing the user to purchase insurance, resulting in disputes afterwards, so that claims cannot be settled. By performing misleading keyword matching between the text to be inspected and the inspection text, it is avoided that the insurance agent uses misleading language to the user during the insurance sales process, causing the user to misunderstand the insurance-related terms and purchase insurance under non-genuine will, resulting in disputes afterwards, so that claims cannot be settled.

[0111] Further, in the above embodiment, the step of performing keyword matching between the text to be tested and the test sample further includes: obtaining the required reading keywords that are not matched in the text to be tested to generate the near-synonyms to be recognized; and performing near-synonym keyword matching between the near-synonyms to be recognized and the test sample.

[0112] In this embodiment, after performing required reading keyword matching between the text to be tested and the test sample, the unmatched keywords are used as the near-synonyms to be recognized, so as to perform near-synonym keyword matching on the near-synonyms to be recognized, further improving the accuracy of audio data inspection. In one implementation manner, a near-synonym sample thesaurus can be generated based on the test sample, and the near-synonyms to be recognized are matched with the near-synonym sample thesaurus. If the matching is successful, it indicates that the required reading keyword matching is successful.

[0113] It should be noted that when performing data inspection operations on audio data, if all the required reading keywords are matched, it is confirmed that the required reading keyword matching is successful, and the inspection result of the audio data is confirmed to be qualified. If there are required reading keywords that are not matched, near-synonym keyword matching is performed on the unmatched required reading keywords. If all the near-synonyms to be recognized are matched, it is confirmed that the near-synonym keyword matching is successful, and the inspection result of the audio data is confirmed to be qualified. If there are near-synonyms to be recognized that are not matched, it is confirmed that the near-synonym keyword matching fails, and the inspection result of the audio data is confirmed to be unqualified.

[0114] And / or, if all the misleading keywords are not matched, it is confirmed that the misleading keyword matching is successful, and the inspection result of the audio data is confirmed to be qualified. If there are matched misleading keywords, it is confirmed that the misleading keyword matching fails, and the inspection result of the audio data is confirmed to be unqualified.

[0115] And / or, if all the sensitive keywords are not matched, it is confirmed that the sensitive keyword matching is successful, and the inspection result of the audio data is confirmed to be qualified. If there are matched sensitive keywords, it is confirmed that the sensitive keyword matching fails, and the inspection result of the audio data is confirmed to be unqualified.

[0116] In this embodiment, as Figure 6 shown, the step of performing data inspection operations on the preprocessed audio data is executed by the synchronous quality inspection system 412. The synchronous quality inspection system 412 generates the inspection result of the audio data and sends it to the server 410.

[0117] Embodiment 6

[0118] Based on any of the above embodiments, the inspection data includes video data. The steps of performing data inspection operations on the preprocessed inspection data further include: obtaining identity feature information according to the preprocessed video data; obtaining the identity information to be inspected according to the identity feature information; and matching the identity information to be inspected with the pre-stored identity information to generate an inspection result of the video data.

[0119] In this embodiment, the inspection data includes video data. By directly obtaining the video data, it is avoided to split the multimedia file to obtain the video data. On the one hand, it can avoid the picture distortion caused during the splitting process, which affects the accuracy of identity information recognition. On the other hand, directly performing inspection operations on the video data can improve the efficiency of data inspection.

[0120] In one implementation, as Figure 6 shown, the steps of obtaining identity feature information according to the preprocessed video data and obtaining the identity information to be inspected according to the identity feature information are executed by the synchronous quality inspection system 412. The step of matching the identity information to be inspected with the pre-stored identity information is executed by the server 410.

[0121] Further, obtain identity feature information according to the preprocessed video data, and obtain the identity information to be inspected according to the identity feature information. Specifically, in one implementation, the identity feature information is input into a preset face model for comparison to obtain the identity information to be inspected. Among them, the preset face model can be set from multiple sources, such as third-party verification units such as the face database of the Ministry of Public Security, ID card photos, old customer photo information reserved by the system, etc., which will not be listed one by one here. Match the obtained identity information to be inspected with the pre-stored identity information to generate an inspection result of the video data. Specifically, if the identity information to be inspected matches the pre-stored identity information successfully, it is confirmed that the inspection result of the video data is qualified. If the identity information to be inspected does not match the pre-stored identity information, it is confirmed that the inspection result of the video data is unqualified. In one implementation, the pre-stored identity information comes from the identity information of the user and / or insurance agent input by the first electronic device. Through video data, the identity information of the user and / or insurance agent is audited, avoiding problems such as high cost, lagging quality inspection results, low quality inspection efficiency, easy post-disputes and poor user experience when using manual inspection.

[0122] Further, in the above embodiment, the step of obtaining a face image according to the first video data specifically includes: intercepting a video frame in the video data to obtain facial image information; preprocessing the facial image information to generate a face image, where the preprocessing includes one or more of image sharpening, background removal, geometric normalization, and grayscale normalization.

[0123] In this embodiment, the preprocessing of the video data includes face positioning of the video frame and cropping according to the positioning result, so as to obtain a face image for obtaining the identity information data of the user and / or the insurance agent, and then to verify the identity information data of the user and / or the insurance agent, so as to avoid sending illegal operations, such as reimbursement purchases and / or insurance sales work in the name of others.

[0124] In this embodiment, the face image information of the user and / or the insurance agent is obtained by intercepting the video frame in the video data, and the face image of the user and / or the insurance agent is generated by preprocessing the face image information, so that the obtained face image is clear and highly accurate, so as to facilitate obtaining the identity information to be verified of the user / or the insurance agent through face recognition technology. Thus, the identity information data of the user and / or the insurance agent is verified to avoid sending illegal operations, such as reimbursement purchases and / or insurance sales work in the name of others.

[0125] Embodiment 7

[0126] Based on any of the above embodiments, the data verification method for the service system further includes: generating a verification result of the verification data according to the verification result of the audio data and the verification result of the video data; the step of generating a verification result of the verification data according to the verification result of the audio data and the verification result of the video data specifically includes: when the verification result of the audio data is unqualified and / or the verification result of the video data is unqualified, determining that the verification result of the verification data is unqualified.

[0127] In this embodiment, the data verification method further includes generating a verification result of the verification data according to the verification result of the audio data and the verification result of the video data. Specifically, when both the verification result of the audio data and the verification result of the video data are qualified, it is confirmed that the verification result of the verification data is qualified. When one of the verification result of the audio data and the verification result of the video data is unqualified, it is confirmed that the verification result of the verification data is unqualified. That is to say, only when the identity information and the conversation information of the user and / or the insurance agent both meet the regulations, the service system sends a verification result of qualified verification data to the first electronic device, improving the accuracy of data verification, that is, improving the compliance in the insurance sales process and avoiding inspection loopholes that may lead to claims disputes.

[0128] Embodiment 8

[0129] Such as Figure 4 、 Figure 5 And Figure 6As shown in the figure, Embodiment 8 provides a data verification system 400, including: a first electronic device 402, the first electronic device 402 includes: a first memory and a first processor, the first memory stores programs or instructions, and the first processor executes the programs or instructions to implement the steps of the data verification method for the first electronic device 402 provided by any of the above technical solutions; a service system 404, the service system 404 includes: a third memory and a third processor, the third memory stores programs or instructions, and the third processor executes the programs or instructions to implement the steps of the data verification method for the service system 404 provided by any of the above technical solutions.

[0130] The data verification system provided by the embodiments of the present invention can implement the steps of the data verification method for the first electronic device 402 provided by any of the above technical solutions, and the steps of the data verification method for the service system 404 provided by any of the above technical solutions. Therefore, it has all the beneficial technical effects of the data verification method for the first electronic device 402 provided by any of the above technical solutions, and the data verification method for the service system 404 provided by any of the above technical solutions, which will not be elaborated here.

[0131] Embodiment 9

[0132] Embodiment 9 provides a readable storage medium, on which programs or instructions are stored, and when the programs or instructions are executed by a processor, the steps of the data verification method for the first electronic device provided by any of the above technical solutions are implemented; or when the programs or instructions are executed by a processor, the steps of the data verification method for the service system provided by any of the above technical solutions are implemented.

[0133] The readable storage medium provided by the embodiments of the present invention can implement the steps of the data verification method for the first electronic device provided by any of the above technical solutions, or the steps of the data verification method for the service system provided by any of the above technical solutions. Therefore, it has all the beneficial technical effects of the data verification method for the first electronic device provided by any of the above technical solutions, or the data verification method for the service system provided by any of the above technical solutions, which will not be elaborated here.

[0134] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several means, several of these means can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0135] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0136] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A data verification method for a first electronic device, characterized in that, Including: Send a data verification request to the service system; Receive the start verification instruction sent by the service system, and control the data acquisition device to start working according to the start verification instruction; Send the verification data acquired by the data acquisition device to the service system for the service system to perform data verification operations on the verification data; Receive the verification result of the verification data sent by the service system, and control the data acquisition device to work according to the verification result; When the verification result returned by the service system is unqualified, simultaneously return the unqualified items to the first electronic device; The service system selects the corresponding link's words and / or compliance issues from a preset question bank and / or a phrase bank, and sends the words and / or the compliance issues to the first electronic device in the form of text information and / or voice information. The data verification method further includes: Receive the verification sample sent by the service system; Obtain the verification data according to the verification sample.

2. The data verification method according to claim 1, wherein The step of controlling the data acquisition device to work according to the verification result specifically includes: When the verification result is unqualified, control the data acquisition device to re-acquire the verification data and send it to the service system.

3. A data verification method for a service system, characterized in that, The data verification method includes: Obtain the verification data sent by the first electronic device and preprocess the verification data; Perform data verification operations on the preprocessed verification data to generate the verification result of the verification data; Send the verification result to the first electronic device; The service system receives the data verification request from the first electronic device; Feedback the start verification instruction to the first electronic device to control the data acquisition device to start working; When the verification result returned by the service system is unqualified, simultaneously return the unqualified items to the first electronic device; The verification data includes audio data. The step of performing data verification operations on the preprocessed verification data specifically includes: Obtain the audio feature information of the preprocessed audio data; Generate a text to be verified according to the audio feature information; Match the keywords of the text to be verified with the verification sample to generate the verification result of the audio data; The step of matching the keywords of the text to be verified with the verification sample specifically includes: Match the required keywords of the text to be verified with the verification sample; and / or Match the sensitive keywords of the text to be verified with the verification sample; and / or Match the misleading keywords of the text to be verified with the verification sample; The step of matching the keywords of the text to be verified with the verification sample further includes: Obtain the required keywords that are not matched in the text to be verified to generate the near-synonyms to be identified; Match the near-synonyms to be identified with the verification sample for near-synonym keyword matching.

4. The data verification method according to claim 3, wherein The verification data further includes video data. The step of performing data verification operations on the preprocessed verification data further includes: Obtain the identity feature information according to the preprocessed video data; Obtain the identity information to be verified according to the identity feature information; Match the identity information to be verified with the pre-stored identity information to generate the verification result of the video data.

5. A data verification system, characterized in that, Including: A first electronic device, the first electronic device includes: a first memory and a first processor, the first memory stores programs or instructions, and the first processor executes the programs or instructions to implement the steps of the data verification method as described in claim 1 or 2; A service system, the service system includes: a third memory and a third processor, the third memory stores programs or instructions, and the third processor executes the programs or instructions to implement the steps of the data verification method as described in claim 3 or 4.

6. A readable storage medium having a program or instructions stored thereon, characterized in that, The programs or instructions, when executed by the processor, implement the steps of the data verification method as described in claim 1 or 2; or the programs or instructions, when executed by the processor, implement the steps of the data verification method as described in claim 3 or 4.

Images