WO2021175019A1 - Guide method for audio and video recording, apparatus, computer device, and storage medium - Google Patents

Abstract

Disclosed in the present application are a guide method for audio and video recording, an apparatus, a computer device, and a storage medium. The method comprises: a service signature request sent from a client end is received and a target service identifier is obtained from the service signature request; a target dual recording segment corresponding to the target service identifier is obtained from a preset rule base, the target dual recording segment including at least one base segment; AI speech information is subsequently generated on the basis of a dual recording rule, and each base segment of the target dual recording segment is guided and dual recording is performed by means of the AI speech information and according to an ordering of order IDs, and dual recording data corresponding to each base segment of the target dual recording segment is obtained; last, collection is performed on all dual recording data, and target dual recording information is obtained. This manner of performing guidance according to AI speech information prevents errors during the recording process, and segmentation into multiple base segments also facilitates a reduction in time spent re-recording audio and visual recordings that do not meet requirements, improving the audio and visual recording effect.

Description

Audio and video recording and guiding method, device, computer equipment and storage medium

This application is based on the Chinese invention patent application filed on March 5, 2020 with the application number 202010147531.9, titled "audio and video recording guidance method, device, computer equipment and storage medium", and claims its priority.

Technical field

This application relates to the field of computer technology, and in particular to a method, device, computer equipment, and storage medium for guiding audio and video recording.

Background technique

At present, in some business signing scenarios with high business requirements, it is necessary to perform dual recording of the business signing process, that is, audio and video recording. Dual recording mainly means that the business party needs to record audio and video and other technical means to collect audiovisual The method of data and electronic data records and saves the key links of the business signing process, so that the business signing behavior can be played back, important information can be inquired, and problem responsibilities can be confirmed, so as to avoid non-compliance.

With the development of social economy, each individual or organization is involved in more and more business transactions, and most businesses have higher requirements for security, that is, audio and video recording of the business signing process is required. Manually, guide the people at the time to sign and double-record the business, and check the double-recording video afterwards to perform quality inspection on the business signing process. In the process of realizing this application, the inventor realized that the existing technology has at least the following Problem: This method needs to re-record the audio and video when it is checked afterwards that the audio and video recording process has quality problems, resulting in low audio and video recording efficiency.

Summary of the invention

The embodiments of the present application provide a method, device, computer equipment, and storage medium for guiding audio and video recording, so as to improve the efficiency of current audio and video recording.

In order to solve the foregoing technical problems, an embodiment of the present application provides a method for guiding audio and video recording, including:

Receiving the service signing request sent by the client, and obtaining the target service identifier from the service signing request;

Obtain the target double-recording link corresponding to the target business identifier from the preset rule library. The target double-recording link includes at least one basic link, and each of the basic links corresponds to a sequence ID and a double-recording rule. ；

Based on the dual recording rule, AI voice information is generated, and through the AI voice information, in accordance with the sequence of the sequence ID, each basic link in the target dual recording link is guided to perform dual recording processing to obtain the The double-recording data corresponding to each basic link in the target double-recording link;

Summarize each of the double-recording data to obtain target double-recording information.

Optionally, the AI voice information is used to guide each basic link in the target dual-recording link to perform dual-recording processing in accordance with the sequence of the sequence ID, so as to obtain each of the target dual-recording links The double-recorded data corresponding to the basic links include:

When it is detected that the basic link is started, record the start time point, and obtain the entry method corresponding to the basic link;

According to the input method, perform voice-guided double recording, obtain temporary data, and record the end time point of the input;

Perform AI quality inspection on the temporary data to obtain the quality inspection result;

When the quality inspection result is passed, the temporary data is used as the dual recording data corresponding to the basic link, and the time range corresponding to the dual recording data is determined according to the start time point and the end time point information.

Optionally, the quality inspection method of the AI quality inspection is voice quality inspection, and performing AI quality inspection on the temporary data to obtain a quality inspection result includes:

Acquiring voice information in the temporary data, and performing voice recognition on the voice information to obtain text information corresponding to the voice information;

Perform semantic recognition on the text information to obtain a semantic recognition result;

According to the semantic recognition result and the preset judgment method, it is determined whether the voice information in the temporary data is qualified. If it is qualified, the voice quality inspection is confirmed to pass, and if it is unqualified, the voice quality inspection is confirmed to fail.

Optionally, the quality inspection method of the AI quality inspection is behavioral quality inspection, and performing AI quality inspection on the temporary data to obtain a quality inspection result includes:

Extracting video information in the temporary data, and extracting video frame images from the video information according to a preset interval;

Perform face recognition on each of the video frame images, and use the video frame image containing the face image as a target image;

Perform identity authentication on the target image, confirm the identity information corresponding to the target image, and check the identity information for consistency with the identity information in the business information to obtain the proofreading result, and determine the quality inspection result according to the proofreading result .

Optionally, the quality inspection method of the AI quality inspection is certificate quality inspection, and performing AI quality inspection on the temporary data to obtain a quality inspection result includes:

Obtain the picture file in the temporary data, and parse the image file by means of OCR recognition to obtain the credential information contained in the image file;

The certificate information and business information are checked, and the certificate quality inspection result is determined according to the check result.

Optionally, after the AI quality inspection is performed on the temporary data, and the quality inspection result is obtained, and when the quality inspection result is passed, the temporary data is used as the dual data corresponding to the basic link. Recording data, and after determining the time range information corresponding to the dual recording data according to the start time point and the end time point, the audio and video recording guidance method further includes:

If the quality inspection result is a quality inspection failure, generate corresponding voice guidance information according to the reason for the quality inspection failure, and generate an updated starting time point;

Play the voice guidance information so that the user can re-enter according to the voice guidance information to obtain updated temporary data, generate the updated end time point, and return to the AI quality inspection of the temporary data, The steps for obtaining the quality inspection result are continued until the quality inspection result obtained is the quality inspection passed.

Optionally, after summarizing each of the dual recording data to obtain target dual recording information, the audio and video recording guidance method further includes:

If a random inspection request sent by the management terminal is received, obtain the preset key links corresponding to the business;

Obtain the time range information corresponding to each of the preset key links as the target sampling time;

From the target double-recording data, extract the data information corresponding to the target spot check time as the information to be spot checked, and send the information to be spot checked to the management terminal.

In order to solve the foregoing technical problems, an embodiment of the present application further provides an audio and video recording guide device, including:

The request receiving module is configured to receive the service signing request sent by the client, and obtain the target service identifier from the service signing request;

The link acquisition module is used to obtain the target double-recording link corresponding to the target business identifier from the preset rule library, the target double-recording link includes at least one basic link, and each of the basic links corresponds to a sequence ID and a double recording rule;

The dual recording module is used to generate AI voice information based on the dual recording rules, and use the AI voice information to guide each basic link in the target dual recording link to perform dual recording in accordance with the sequence of the sequence ID. Recording processing to obtain the double-recording data corresponding to each basic link in the target double-recording link;

The summary module is used for summarizing each of the double-recording data to obtain target double-recording information.

Optionally, the dual recording module includes:

The start entry unit is used to record the start time point when the start of the basic link is detected, and obtain the entry mode corresponding to the basic link;

The end entry unit is used to perform voice-guided double entry according to the entry method, obtain temporary data, and record the entry end time point;

The quality inspection unit is used to perform AI quality inspection on the temporary data to obtain the quality inspection result;

The data determining unit is configured to use the temporary data as the double-recorded data corresponding to the basic link when the quality inspection result is passed, and determine the double-recorded data according to the start time point and the end time point. Time range information corresponding to the recorded data.

Optionally, the quality inspection method of the AI quality inspection is voice quality inspection, and the quality inspection unit includes:

The voice recognition subunit is used to obtain voice information in the temporary data, and perform voice recognition on the voice information to obtain text information corresponding to the voice information;

The semantic recognition subunit is used to perform semantic recognition on the text information to obtain a semantic recognition result;

The result judgment subunit is used to determine whether the voice information in the temporary data is qualified according to the semantic recognition result and the preset judgment method. Check failed.

Optionally, the quality inspection method of the AI quality inspection is behavioral quality inspection, and the quality inspection unit includes:

An image extraction subunit, configured to extract video information in the temporary data, and extract video frame images from the video information according to a preset interval;

The face recognition subunit is configured to perform face recognition on each of the video frame images, and use the video frame image containing the face image as the target image;

The identity verification subunit is used to perform identity authentication on the target image, confirm the identity information corresponding to the target image, and check the identity information for consistency with the identity information in the business information to obtain the proofreading result, according to the The proofreading result determines the quality inspection result.

Optionally, the quality inspection method of the AI quality inspection is certificate quality inspection, and the quality inspection unit includes:

The image analysis subunit is used to obtain the picture file in the temporary data, and analyze the image file by OCR recognition method to obtain the credential information contained in the image file;

The certificate verification subunit is used to verify the certificate information and business information, and determine the certificate quality inspection result according to the verification result.

Optionally, the audio and video recording and guiding device further includes:

The guide information regeneration module is configured to, if the quality inspection result is a quality inspection failure, generate corresponding voice guidance information according to the cause of the quality inspection failure, and generate an updated starting time point;

The voice guidance module is used to play the voice guidance information so that the user can re-enter according to the voice guidance information to obtain updated temporary data, generate the updated end time point, and return to the temporary The data undergoes AI quality inspection, and the steps to obtain the quality inspection result continue until the quality inspection result obtained is the quality inspection passed.

Optionally, the audio and video recording and guiding device further includes:

The sampling check link acquisition module is used to obtain the preset key link corresponding to the business if the sampling check request sent by the management terminal is received;

The sampling inspection time determination module is used to obtain the time range information corresponding to each of the preset key links as the target sampling inspection time;

The sampling information determination module is configured to extract the data information corresponding to the target sampling time from the target double-recording data as the sampling information to be checked, and to send the sampling information to the management terminal.

In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, and the processor executes all When the computer-readable instructions are described, the steps of the above audio and video recording and guiding method are realized.

In order to solve the above technical problems, embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores computer-readable instructions, the computer-readable instructions are executed by a processor to achieve the above-mentioned audio and video recording Steps of the boot method.

The audio and video recording guidance method, device, computer equipment, and storage medium provided in the embodiments of the present application, on the one hand, receive the service signing request sent by the client, and obtain the target service identifier from the service signing request, and obtain the target service identifier from the preset rules In the library, obtain the target double-recording link corresponding to the target business identifier. The target double-recording link contains at least one basic link. Each basic link corresponds to a sequence ID and a double-recording rule. Based on the double-recording rule, AI voice information is generated. , And through the AI voice information, in accordance with the sequence of the sequence ID, guide each basic link in the target dual-recording link to perform dual-recording processing, and obtain the dual-recording data corresponding to each basic link in the target dual-recording link. The double-recording data is summarized to obtain the target double-recording information. This guidance method based on AI voice information is more efficient than the traditional manual method. At the same time, the double-recording link is divided into multiple basic links, which is also conducive to When there is an error in audio and video recording, the time cost of re-recording audio and video is reduced, and the efficiency of audio and video recording is improved.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

2 is a flowchart of an embodiment of the audio and video recording guidance method of the present application;

Fig. 3 is a schematic structural diagram of an embodiment of an audio and video recording and guiding device according to the present application;

Fig. 4 is a schematic structural diagram of an embodiment of a computer device according to the present application.

Detailed ways

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

The reference to "embodiments" herein means that a specific feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described herein can be combined with other embodiments.

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Please refer to FIG. 1. As shown in FIG. 1, the system architecture 100 may include terminal devices 101, 102, and 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.

The user can use the terminal devices 101, 102, and 103 to interact with the server 105 through the network 104 to receive or send messages and so on.

The terminal devices 101, 102, 103 may be various electronic devices that have a display screen and support web browsing, including but not limited to smart phones, tablets, e-book readers, MP3 players (Moving Picture E interface display perts Group Audio Layer III , Motion Picture Expert compresses standard audio layer 3), MP4 (Moving Picture E interface displays perts Group Audio Layer IV, Motion Picture Expert compresses standard audio layer 4) Players, laptop portable computers and desktop computers, etc.

The server 105 may be a server that provides various services, for example, a background server that provides support for pages displayed on the terminal devices 101, 102, and 103.

It should be noted that the audio and video recording guidance method provided in the embodiments of the present application is executed by the server, and accordingly, the audio and video recording guidance device is provided in the server.

It should be understood that the numbers of terminal devices, networks, and servers in FIG. 1 are merely illustrative. According to implementation needs, there may be any number of terminal devices, networks, and servers. The terminal devices 101, 102, and 103 in the embodiments of the present application may specifically correspond to application systems in actual production.

Please refer to FIG. 2. FIG. 2 shows an audio and video recording guidance method provided by an embodiment of the present application. The method is applied to the server in FIG. 1 as an example for description, and the details are as follows:

S201: Receive a service signing request sent by a client, and obtain a target service identifier from the service signing request.

Specifically, the client is deployed with a business signing smart double-recording system, which contains the business signing smart double-recording task. The business signatory uses a personal account to log in to the client’s business signing smart double-recording system, and select from the system The business signs the task of intelligent double recording.

Among them, the client is equipped with a camera device for recording audio and video images of the business signatory during the business signing process.

Among them, the business identifier refers to the symbol used to uniquely identify the business, which can specifically be one of Chinese characters, letters, numbers, and symbols, or a combination of multiple, and the target business identifier refers to the business included in the business signing request It should be understood that the service ID is pre-configured in the database of the server. When receiving the service signing request sent by the client, the service ID identified in the service signing request is used as the target service ID, and the target service is subsequently passed ID to obtain the corresponding double-recording rules.

It should be noted that, in this embodiment, each business identifier corresponds to at least one business requirement, and the double-entry rule corresponding to the business identifier is pre-configured according to the organization, product type, age and other dimensions included in the business requirement. The setting of specific double recording rules can be selected according to actual needs and is not limited here.

For example, in a specific embodiment, a service is "New User Guided Registration", the service ID is represented as "Register_Newuser", and the corresponding dual-recording rules are face authentication, registration information verification, and certificate authentication.

S202: Obtain the target double-recording link corresponding to the target business identifier from the preset rule library. The target double-recording link includes at least one basic link, wherein each basic link corresponds to a sequence ID and a double-recording rule.

Specifically, in the rule library preset on the server side, each business identifier corresponds to a double-recording link. After obtaining the target business identifier, select the target double-recording link corresponding to the target business identifier from the rule database, so that The follow-up double-recording process is carried out according to the target double-recording link.

Among them, the target dual-recording link includes at least one basic link, and each basic link has its own dual-recording rules, including independent dual-recording scenes and dual-recording tasks, such as the face authentication link. Authenticated face image, and transfer the image to the server to perform face verification processing.

It is easy to understand that each basic link has a unique link identifier. At the same time, in this embodiment, the target double-recording link contains multiple basic links. Therefore, in the target double-recording link corresponding to each business identifier, the target double-recording link is pre-registered A sequence ID is set for each basic link.

For example, in a specific implementation, the basic links included in the target double recording link of a contract signing business are in order of ID: basic information recognition, face verification, business signing video collection, certificate confirmation, and signature video collection Wait.

S203: Based on the dual-recording rules, generate AI voice information, and use AI voice information to guide each basic link in the target dual-recording link to perform dual-recording processing in accordance with the sequence of the sequence ID to obtain each basic link in the target dual-recording link The double-recorded data corresponding to the link.

Specifically, according to the dual recording rules of each basic link, the voice guidance information corresponding to the basic link is generated, and the voice guidance information is summarized according to the sequence ID corresponding to the basic link to generate AI voice information, and then through AI voice information, According to the sequence ID from small to large, each basic link is guided to perform dual recording processing, so as to obtain the dual recording data corresponding to each basic link.

In this embodiment, the AI voice information is generated based on the double-recording rules by analyzing the double-recording rules to obtain the text semantics corresponding to the double-recording rules, and then use the text-to-speech method to obtain the voice guidance information, and then according to the order ID, generate AI voice information.

Among them, the AI voice information is used to guide the user through voice broadcast, and after the user completes the current dual recording link, enter the next link.

Preferably, the text-to-speech method in this embodiment adopts TTS (Text To Speech). TTS is again referred to as voice broadcast, which refers to the technology of converting text content into audio content and playing it. With the support of the built-in chip, through the design of neural network, text is intelligently converted into natural speech stream. TTS is a kind of speech synthesis application, which converts files stored in the computer, such as help files or web pages, into natural speech. Voice output is widely used to help visually impaired people to read or scenes that are not suitable for obtaining information through vision. TTS can not only help visually impaired people read the information on the computer, but also increase the readability of text documents.

In this embodiment, through AI intelligent voice information, the parties are guided to sign the business, and the specific process is double-recorded, that is, audio and video recording, which can effectively improve the accuracy of the double-recording.

S204: Summarize each double-recording data to obtain target double-recording information.

Specifically, according to the start time point and end time point of each double-recorded data, the double-recorded data is summarized according to the sequence ID, and the start time point and end time point of each link are marked for subsequent manual sampling inspections. , You can conduct quick spot checks on individual links.

In this embodiment, by receiving the service signing request sent by the client, the target service identifier is obtained from the service signing request, and the target double recording link corresponding to the target service identifier is obtained from the preset rule library. The target double recording The link includes at least one basic link. Each basic link corresponds to a sequence ID and a double recording rule. Based on the double recording rule, AI voice information is generated, and the AI voice information is used to guide the target double according to the sequence of the sequence ID. Each basic link in the recording link is subjected to dual recording processing to obtain the dual recording data corresponding to each basic link in the target dual recording link. Finally, each dual recording data is summarized to obtain the target dual recording information. This is based on the AI voice The method of information guidance is more efficient than the traditional manual method. At the same time, dividing the double-recording link into multiple basic links is also helpful to reduce the time cost of double-recording again when there is an error in the double-recording, and improve the double-recording s efficiency.

In some optional implementations of this embodiment, in step S203, the AI voice information is used to guide each basic link in the target dual recording link to perform dual recording processing in accordance with the sequence of the sequence ID to obtain the target dual recording link The double-recorded data corresponding to each basic link in the book includes:

When detecting the start of the basic link, record the start time and obtain the corresponding entry method of the basic link;

According to the input method, perform voice-guided double recording, obtain temporary data, and record the end time of the input;

Perform AI quality inspection on temporary data and obtain quality inspection results;

When the quality inspection result is passed, the temporary data is used as the double-recorded data corresponding to the basic link, and the time range information corresponding to the double-recorded data is determined according to the start time point and the end time point.

Specifically, when each basic link is started, the starting time point is recorded, so that after the quality inspection of the basic link is carried out, if the basic link is not qualified in double recording, the start time of the basic link is determined according to the starting time point. Position, double record again.

Among them, the entry method refers to the specific items entered, including but not limited to face entry, behavior entry, information entry, and certificate entry, etc.

Further, each basic link corresponds to a list of items that need to be entered. According to the entry method and voice guidance information, intelligently guided dual recording is performed. During the dual recording process, it is judged whether or not according to the received pictures, voice, and video signals. Whether the items that need to be entered have been entered, and after the entry is completed, record the end time of entry, and obtain temporary data.

Among them, according to the received picture, voice, and video signal, it is judged whether the entry needs to be entered whether the entry is completed or not is passively verified by setting a buried point.

For example, when it is necessary to enter the face information of both parties, after the first party’s face information is recorded, a confirmation message is generated, and then the second party’s face information is entered through voice guidance. The face information is also entered successfully. After the confirmation message is generated, a message indicating that the face information items of both parties have been entered is generated, and the voice broadcast is performed. After the broadcast is completed, the next item entry is executed.

For another example, when it is necessary to enter the party’s credential information, fast image recognition is used to monitor whether there is a credential image in the video image. When a credential image exists, a screenshot of the corresponding picture is taken, and a message indicating that the credential information entry is completed is generated. , And carry out voice broadcast, after finishing the broadcast, execute the next item entry.

It is easy to understand that the record entry end time point has the same effect as the record start time point. Both are to quickly locate the link when the quality inspection fails, so as to re-enter the temporary data of the link.

Further, this embodiment also selects the corresponding AI quality inspection method according to the input method, performs quality inspection on the temporary data, and obtains the quality inspection result. The AI quality inspection method includes but is not limited to voice quality inspection, behavior quality inspection, and certificate quality inspection. Check etc.

In this embodiment, the target dual-recording link is divided into multiple basic links to perform dual-recording of audio and video, and quality inspection is performed after the dual-recording of each basic link is completed to ensure the effectiveness of the dual-recording of the basic link. Conducive to improving the efficiency of audio and video recording.

In some optional implementation manners of this embodiment, the quality inspection method of AI quality inspection is voice quality inspection. Performing AI quality inspection on temporary data and obtaining quality inspection results include:

Acquire voice information in the temporary data, perform voice recognition on the voice information, and obtain text information corresponding to the voice information;

Perform semantic recognition on text information and obtain semantic recognition results;

According to the semantic recognition result and the preset judgment method, it is determined whether the voice information in the temporary data is qualified. If it is qualified, it is confirmed that the voice quality inspection has passed, and if it is unqualified, it is confirmed that the voice quality inspection has failed.

Specifically, in this embodiment, the input voice information is converted into text information, and the text information is semantically recognized, and then according to the recognized semantics, it is confirmed whether the party’s wishes meet the business needs, and rapid and intelligent voice quality inspection is realized. , Improve the efficiency of quality inspection.

For example, in a specific implementation, the voice guidance information is "Did you carefully read the content of this contract and agree to the agreement in this contract", and the semantic recognition result after the conversion of the obtained party’s voice information is "I have read and agreed "This reading" is deemed to have passed the quality inspection.

Among them, speech recognition can use third-party speech recognition tools or speech recognition algorithms. Common third-party speech recognition tools include but are not limited to: IBM Watson, Xunfei Voice Point, AVST, etc. Commonly used speech recognition algorithms include but Not limited to: Connectionist temporal classification (CTC) algorithm, Automatic Speech Recognition (ASR), algorithm based on Dynamic Time Warping and algorithm based on Dynamic Time Warping, etc.

Among them, the semantic recognition of the text may specifically adopt the natural language processing (Natural Language Processing, NLP) method for recognition.

Among them, the preset judgment method can be set according to actual needs, and there is no specific limitation here.

In this embodiment, the speech information is converted into text information, and then the text information is semantically recognized, and the obtained semantics are compared with the preset judgment method. When the obtained semantics conforms to the preset judgment method, it is confirmed The passing of this quality inspection intelligently performs quality inspection on the voice information in the data, which improves the efficiency of quality inspection in the basic links.

In some optional implementation manners of this embodiment, the quality inspection method of AI quality inspection is behavioral quality inspection. Performing AI quality inspection on temporary data, and obtaining quality inspection results include:

Extract the video information in the temporary data, and extract the video frame images from the video information according to the preset interval;

Perform face recognition on each video frame image, and use the video frame image containing the face image as the target image;

Perform identity authentication on the target image, confirm the identity information corresponding to the target image, and check the identity information for consistency with the identity information in the business information to obtain the proofreading result, and determine the quality inspection result according to the proofreading result.

Specifically, the server extracts the video information in the temporary data, and extracts video frame images from the video information at a preset interval; performs face recognition on each video frame image, and uses the video frame image containing the face image as the target image , And then verify the identity of the business signatory based on the target image, and determine the quality inspection result based on the proofreading result.

Among them, identity consistency proofing includes, but is not limited to: verification of personal information, recognition of facial images, and verification of video images that answer questionnaire questions.

When the three data of personal information, face image and video image are all verified successfully, the verification result is that the identity of the business signatory is legal. Otherwise, when there is at least one data verification failure, the verification result is that the identity of the business signatory is not legitimate.

Further, in order to improve the security of the business signing and ensure the principle of the parties' voluntariness, this embodiment also combines micro-expressions to confirm the parties' wishes.

In a specific embodiment, the micro-expression recognition is performed on the video image of the service signatory, and the emotion of the service signatory is determined according to the recognition result. If the emotion meets the preset emotion requirement, it is confirmed that the verification of the video image is successful .

For example, in a specific embodiment, the basic information such as personal identity information, company information, business-related information, etc. is asked through preset questionnaire questions, and the video images of these questionnaire questions returned by the business signatories are asked. The facial micro-expression is captured, and the captured micro-expression is compared with the existing facial motion coding system to determine the emotion conveyed in the micro-expression of the business signatory, and judge whether the business signatory has abnormal behavior based on the emotion. For example, if the emotion conveyed in the micro-expression of the business signatory is anxiety or nervousness, it can be judged that the contract signatory has an abnormal signing behavior. At this time, the identity authentication is confirmed to fail.

In this embodiment, the facial image is extracted from the video information of the temporary data, and then the identity is checked for consistency, so as to ensure the legality of the identities of both parties signing the business and the voluntariness of the behaviors during the signing of the business.

In some optional implementation manners of this embodiment, the quality inspection method of AI quality inspection is certificate quality inspection. AI quality inspection is performed on temporary data, and the quality inspection results obtained include:

Obtain the picture file in the temporary data, and use the OCR recognition method to parse the image file to obtain the credential information contained in the image file;

The certificate information and business information are checked, and the certificate quality inspection result is determined based on the result of the check.

Specifically, when the quality inspection method of AI quality inspection is certificate quality inspection, first obtain the image file from the temporary data, and use the OCR method to analyze the image file to obtain the certificate information contained in the image file, and then follow the next step. The business information verifies the certificate information to determine the quality inspection result.

Among them, the ocr method is used to analyze the image file to obtain the credential information contained in the image file. Specifically, it includes: preprocessing the image; performing edge detection on the preprocessed image, and obtaining the area that meets the preset conditions as the candidate area ; Determine whether the image in the candidate area is a credential image, and if so, analyze the credential image to obtain credential information contained in the credential image.

In this embodiment, when the quality inspection method is the certificate quality inspection, the certificate image is first determined from the picture file in the temporary data, and then the certificate image is analyzed to obtain the certificate information, and the certificate information is consistent with the business information. Verification and confirmation of the certificate quality inspection results are conducive to improving the efficiency of quality inspection.

In some optional implementations of this embodiment, after the AI quality inspection is performed on the temporary data and the quality inspection result is obtained, and when the quality inspection result is passed, the temporary data is used as the double record corresponding to the basic link Data, and after determining the time range information corresponding to the dual recording data according to the start time point and the end time point, the audio and video recording guidance method further includes:

If the quality inspection result is that the quality inspection failed, the corresponding voice guidance information will be generated according to the reason of the quality inspection failure, and the updated starting time point will be generated;

Play the voice guidance information, so that the user can re-enter according to the voice guidance information, get the updated temporary data, generate the updated end time point, and return to the AI quality inspection of the temporary data to obtain the quality inspection result. Continue to execute , Until the quality inspection result is passed.

Specifically, the server presets that when the quality inspection result is a quality inspection failure, the reason for the quality inspection failure is converted into voice guidance information through TTS, and the updated start time point is regenerated, and the voice guidance is played Information, so that the client personnel according to the voice guidance information to re-dual-record the basic link until the quality inspection result is passed.

In this embodiment, for the basic link that failed the quality inspection, voice guidance information is generated to guide the client user to re-dual-record the basic link, which is conducive to timely correcting the substandard dual-recording operation and avoids double-recording of all basic links. After the recording is completed, it is corrected to improve the efficiency of double recording.

In some optional implementation manners of this embodiment, after step S204, the audio and video recording guidance method further includes:

If the sampling request sent by the management terminal is received, the preset key links corresponding to the business are obtained;

Obtain the time range information corresponding to each preset key link as the target sampling time;

From the target double recording data, extract the data information corresponding to the target sampling time as the information to be sampled, and send the information to the management terminal.

Specifically, the key links corresponding to the target business identification can be configured in advance according to actual needs. After the double recording is completed, the management end will perform random inspections on the key links according to the configured information. When performing random inspections on the key links, obtain the The time range information corresponding to the key link is used as the target sampling time, and then the data information corresponding to the target sampling time is extracted from the target double recording data as the information to be selected, and the information to be selected is sent to the management terminal.

Among them, the key link can be the more important or error-prone link in the business double recording link. The specific link can be determined according to the actual situation, and there is no restriction here.

In this embodiment, upon receiving the spot check request sent by the management terminal, the preset key links corresponding to the business are obtained, and the data information corresponding to these preset key links in the target double record data is obtained as the information to be spot checked. Subsequent sampling of the double-recording information of the business is quickly carried out through the information to be sampled, which improves the efficiency of random-checking the target double-recording data.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

FIG. 3 shows the principle block diagram of the audio and video recording and guiding device corresponding to the audio and video recording and guiding method of the foregoing embodiment one-to-one. As shown in FIG. 3, the audio and video recording guiding device includes a request receiving module 31, a link acquisition module 32, a dual recording module 33 and a summary module 34. The detailed description of each functional module is as follows:

The request receiving module 31 is configured to receive the service signing request sent by the client, and obtain the target service identifier from the service signing request;

The link acquisition module 32 is used to obtain the target double recording link corresponding to the target business identifier from the preset rule library. The target double recording link includes at least one basic link, wherein each basic link corresponds to a sequence ID and a double recording rule;

The dual recording module 33 is used to generate AI voice information based on the dual recording rules, and through the AI voice information, in accordance with the sequence of the sequence ID, guide each basic link in the target dual recording link to perform dual recording processing to obtain the target dual recording Double-record data corresponding to each basic link in the link;

The summary module 34 is used for summarizing each double-recording data to obtain target double-recording information.

Optionally, the dual recording module includes:

The start entry unit is used to record the start time when the basic link is detected and obtain the entry method corresponding to the basic link;

The end entry unit is used to perform voice-guided double entry according to the entry mode, obtain temporary data, and record the end time of entry;

The quality inspection unit is used to perform AI quality inspection on temporary data to obtain the quality inspection result;

The data determining unit is used to use the temporary data as the double-recorded data corresponding to the basic link when the quality inspection result is passed, and determine the time range information corresponding to the double-recorded data according to the start time point and the end time point.

Optionally, the quality inspection method of AI quality inspection is voice quality inspection, and the quality inspection unit includes:

The voice recognition subunit is used to obtain the voice information in the temporary data and perform voice recognition on the voice information to obtain the text information corresponding to the voice information;

The semantic recognition subunit is used to perform semantic recognition on text information and obtain the semantic recognition result;

The result judgment subunit is used to determine whether the voice information in the temporary data is qualified according to the semantic recognition result and the preset judgment method.

Optionally, the quality inspection method of AI quality inspection is behavioral quality inspection, and the quality inspection unit includes:

The image extraction subunit is used to extract the video information in the temporary data, and extract the video frame images from the video information according to a preset interval;

The face recognition subunit is used to perform face recognition on each video frame image, and use the video frame image containing the face image as the target image;

The identity verification subunit is used to authenticate the target image, confirm the identity information corresponding to the target image, and verify the identity information and the identity information in the business information to obtain the proofreading result, and determine the quality inspection result according to the proofreading result .

Optionally, the quality inspection method of AI quality inspection is certificate quality inspection, and the quality inspection unit includes:

The image analysis subunit is used to obtain the picture file in the temporary data, and use the OCR recognition method to analyze the image file to obtain the credential information contained in the image file;

The certificate verification sub-unit is used to verify the certificate information and business information, and determine the certificate quality inspection result based on the verification result.

Optionally, the audio and video recording guiding device further includes:

The guide information regeneration module is used to generate the corresponding voice guide information according to the reason of the quality inspection failure if the quality inspection result is a quality inspection failure, and generate the updated starting time point;

The voice guidance module is used to play the voice guidance information so that the user can re-enter according to the voice guidance information, obtain the updated temporary data, generate the updated end time point, and return to the AI quality inspection of the temporary data to obtain the quality The steps of the inspection result continue to be executed until the quality inspection result obtained is the quality inspection passed.

Optionally, the audio and video recording guiding device further includes:

Sampling check link acquisition module, which is used to obtain the preset key links corresponding to the business if the sampling check request sent by the management terminal is received;

The sampling time determination module is used to obtain the time range information corresponding to each preset key link as the target sampling time;

The sampling information determination module is used to extract the data information corresponding to the target sampling time from the target double-recording data as the sampling information to be checked, and to send the sampling information to the management terminal.

For the specific limitation of the audio and video recording and guiding device, please refer to the above limitation on the audio and video recording and guiding method, which will not be repeated here. Each module in the above audio and video recording and guiding device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

In order to solve the above technical problems, the embodiments of the present application also provide computer equipment. Please refer to FIG. 4 for details. FIG. 4 is a block diagram of the basic structure of the computer device in this embodiment.

The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are connected to each other in communication via a system bus. It should be pointed out that the figure only shows the computer device 4 with the components connected to the memory 41, the processor 42, and the network interface 43, but it should be understood that it is not required to implement all the shown components, and alternative implementations can be made. More or fewer components. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes, but is not limited to, a microprocessor, a dedicated Integrated Circuit (Application Specific Integrated Circuit, ASIC), Programmable Gate Array (Field-Programmable GateArray, FPGA), Digital Processor (Digital Signal Processor, DSP), embedded equipment, etc.

The computer device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device.

The memory 41 includes at least one type of readable storage medium, the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D interface display memory, etc.), random access memory (RAM) , Static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disks, optical disks, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), and a secure digital (Secure Digital, SD) card, Flash Card, etc. Of course, the memory 41 may also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store an operating system and various application software installed in the computer device 4, such as program codes for controlling electronic files. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to run program codes or process data stored in the memory 41, for example, run program codes for controlling electronic files.

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

This application also provides another implementation manner, that is, a computer-readable storage medium is provided. The computer-readable storage medium may be non-volatile or volatile, and the computer-readable storage medium stores An interface display program, the interface display program can be executed by at least one processor, so that the at least one processor executes the steps of the above-mentioned audio and video recording guidance method.

Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to make a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present application.

Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all of the embodiments. The drawings show preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these examples is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although this application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, it is still possible for those skilled in the art to modify the technical solutions described in each of the foregoing specific embodiments, or equivalently replace some of the technical features. . All equivalent structures made by using the contents of the description and drawings of this application, directly or indirectly used in other related technical fields, are similarly within the scope of patent protection of this application.

Claims (20)

1. An audio and video recording and guiding method, wherein the audio and video recording and guiding method includes:

   Receiving the service signing request sent by the client, and obtaining the target service identifier from the service signing request;

   Obtain the target double-recording link corresponding to the target business identifier from the preset rule library. The target double-recording link includes at least one basic link, and each of the basic links corresponds to a sequence ID and a double-recording rule. ；

   Based on the dual recording rule, AI voice information is generated, and through the AI voice information, in accordance with the sequence of the sequence ID, each basic link in the target dual recording link is guided to perform dual recording processing to obtain the The double-recording data corresponding to each basic link in the target double-recording link;

   Summarize each of the double-recording data to obtain target double-recording information.
2. The audio and video recording guidance method of claim 1, wherein the AI voice information guides each basic link in the target dual recording link to perform dual recording processing in accordance with the sequence of the sequence ID , Obtaining the double-recording data corresponding to each basic link in the target double-recording link includes:

   When it is detected that the basic link is started, record the start time point, and obtain the entry method corresponding to the basic link;

   According to the input method, perform voice-guided double recording, obtain temporary data, and record the end time point of the input;

   Perform AI quality inspection on the temporary data to obtain the quality inspection result;

   When the quality inspection result is passed, the temporary data is used as the dual recording data corresponding to the basic link, and the time range corresponding to the dual recording data is determined according to the start time point and the end time point information.
3. 3. The audio and video recording guidance method according to claim 2, wherein the quality inspection method of the AI quality inspection is voice quality inspection, and performing the AI quality inspection on the temporary data to obtain the quality inspection result includes:

   Acquiring voice information in the temporary data, and performing voice recognition on the voice information to obtain text information corresponding to the voice information;

   Perform semantic recognition on the text information to obtain a semantic recognition result;

   According to the semantic recognition result and the preset judgment method, it is determined whether the voice information in the temporary data is qualified. If it is qualified, the voice quality inspection is confirmed to pass, and if it is unqualified, the voice quality inspection is confirmed to fail.
4. The audio and video recording guidance method of claim 2, wherein the quality inspection method of the AI quality inspection is behavioral quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result includes:

   Extracting video information in the temporary data, and extracting video frame images from the video information according to a preset interval;

   Perform face recognition on each of the video frame images, and use the video frame image containing the face image as a target image;

   Perform identity authentication on the target image, confirm the identity information corresponding to the target image, and check the identity information for consistency with the identity information in the business information to obtain the proofreading result, and determine the quality inspection result according to the proofreading result .
5. The audio and video recording guidance method of claim 2, wherein the quality inspection method of the AI quality inspection is certificate quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result includes:

   Obtain the picture file in the temporary data, and parse the image file by means of OCR recognition to obtain the credential information contained in the image file;

   The certificate information and business information are checked, and the certificate quality inspection result is determined according to the check result.
6. The audio and video recording guidance method of claim 2, wherein after the AI quality inspection is performed on the temporary data to obtain the quality inspection result, and when the quality inspection result is passed, the The temporary data is used as the dual recording data corresponding to the basic link, and after the time range information corresponding to the dual recording data is determined according to the start time point and the end time point, the audio and video recording guidance method further includes :

   If the quality inspection result is a quality inspection failure, generate corresponding voice guidance information according to the cause of the quality inspection failure, and generate an updated starting time point;

   Play the voice guidance information so that the user can re-enter according to the voice guidance information to obtain updated temporary data, generate the updated end time point, and return to the AI quality inspection of the temporary data, The steps for obtaining the quality inspection result are continued until the quality inspection result obtained is the quality inspection passed.
7. 5. The audio and video recording guidance method according to claim 1, wherein, after the summary of each of the double recording data to obtain target double recording information, the audio and video recording guidance method further comprises:

   If a random inspection request sent by the management terminal is received, obtain the preset key links corresponding to the business;

   Obtain the time range information corresponding to each of the preset key links as the target sampling time;

   From the target double-recording data, extract the data information corresponding to the target spot check time as the information to be spot checked, and send the information to be spot checked to the management terminal.
8. An audio and video recording and guiding device, wherein the audio and video recording and guiding device includes:

   The request receiving module is configured to receive the service signing request sent by the client, and obtain the target service identifier from the service signing request;

   The link acquisition module is used to obtain the target double-recording link corresponding to the target business identifier from the preset rule library, the target double-recording link includes at least one basic link, and each of the basic links corresponds to a sequence ID and a double recording rule;

   The dual recording module is used to generate AI voice information based on the dual recording rules, and use the AI voice information to guide each basic link in the target dual recording link to perform dual recording in accordance with the sequence of the sequence ID. Recording processing to obtain the double-recording data corresponding to each basic link in the target double-recording link;

   The summary module is used for summarizing each of the double-recording data to obtain target double-recording information.
9. A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor, wherein, when the processor executes the computer-readable instructions, the following sound Video recording guide method:

   Receiving the service signing request sent by the client, and obtaining the target service identifier from the service signing request;

   Obtain the target double-recording link corresponding to the target business identifier from the preset rule library. The target double-recording link includes at least one basic link, and each of the basic links corresponds to a sequence ID and a double-recording rule. ；

   Based on the dual recording rule, AI voice information is generated, and through the AI voice information, in accordance with the sequence of the sequence ID, each basic link in the target dual recording link is guided to perform dual recording processing to obtain the The double-recording data corresponding to each basic link in the target double-recording link;

   Summarize each of the double-recording data to obtain target double-recording information.
10. The computer device of claim 9, wherein the AI voice information guides each basic link in the target dual-recording link to perform dual-recording processing in accordance with the sequence of the sequence ID to obtain the The double-recording data corresponding to each basic link in the target double-recording link includes:

    When it is detected that the basic link is started, record the start time point, and obtain the entry method corresponding to the basic link;

    According to the input method, perform voice-guided double recording, obtain temporary data, and record the end time point of the input;

    Perform AI quality inspection on the temporary data to obtain the quality inspection result;

    When the quality inspection result is passed, the temporary data is used as the dual recording data corresponding to the basic link, and the time range corresponding to the dual recording data is determined according to the start time point and the end time point information.
11. 10. The computer device of claim 10, wherein the quality inspection method of the AI quality inspection is voice quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result comprises:

    Acquiring voice information in the temporary data, and performing voice recognition on the voice information to obtain text information corresponding to the voice information;

    Perform semantic recognition on the text information to obtain a semantic recognition result;

    According to the semantic recognition result and the preset judgment method, it is determined whether the voice information in the temporary data is qualified. If it is qualified, it is confirmed that the voice quality inspection has passed, and if it is unqualified, it is confirmed that the voice quality inspection has failed.
12. 10. The computer device according to claim 10, wherein the quality inspection method of the AI quality inspection is behavioral quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result comprises:

    Extracting video information in the temporary data, and extracting video frame images from the video information according to a preset interval;

    Perform face recognition on each of the video frame images, and use the video frame image containing the face image as a target image;

    Perform identity authentication on the target image, confirm the identity information corresponding to the target image, and check the identity information for consistency with the identity information in the business information to obtain the proofreading result, and determine the quality inspection result according to the proofreading result .
13. 10. The computer device according to claim 10, wherein the quality inspection method of the AI quality inspection is certificate quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result includes:

    Obtain the picture file in the temporary data, and parse the image file by means of OCR recognition to obtain the credential information contained in the image file;

    The certificate information and business information are checked, and the certificate quality inspection result is determined according to the check result.
14. The computer device according to claim 10, wherein after the AI quality inspection is performed on the temporary data to obtain the quality inspection result, and when the quality inspection result is passed, the temporary data As the dual recording data corresponding to the basic link, and after determining the time range information corresponding to the dual recording data according to the start time point and the end time point, when the processor executes the computer-readable instruction , It also implements the following audio and video recording guide methods:

    If the quality inspection result is a quality inspection failure, generate corresponding voice guidance information according to the reason for the quality inspection failure, and generate an updated starting time point;

    Play the voice guidance information so that the user can re-enter according to the voice guidance information to obtain updated temporary data, generate the updated end time point, and return to the AI quality inspection of the temporary data, The steps for obtaining the quality inspection result are continued until the quality inspection result obtained is the quality inspection passed.
15. A computer-readable storage medium, the computer-readable storage medium stores computer-readable instructions, wherein, when the computer-readable instructions are executed by a processor, the following methods for guiding audio and video recording are implemented:

    Receiving the service signing request sent by the client, and obtaining the target service identifier from the service signing request;

    Obtain the target double-recording link corresponding to the target business identifier from the preset rule library. The target double-recording link includes at least one basic link, and each of the basic links corresponds to a sequence ID and a double-recording rule. ；

    Based on the dual recording rule, AI voice information is generated, and through the AI voice information, in accordance with the sequence of the sequence ID, each basic link in the target dual recording link is guided to perform dual recording processing to obtain the The double-recording data corresponding to each basic link in the target double-recording link;

    Summarize each of the double-recording data to obtain target double-recording information.
16. The computer-readable storage medium of claim 15, wherein the AI voice information guides each basic link in the target dual-recording link to perform dual-recording processing in accordance with the sequence of the sequence ID , Obtaining the double-recording data corresponding to each basic link in the target double-recording link includes:

    When it is detected that the basic link is started, record the start time point, and obtain the entry method corresponding to the basic link;

    According to the input method, perform voice-guided double recording, obtain temporary data, and record the end time point of the input;

    Perform AI quality inspection on the temporary data to obtain the quality inspection result;

    When the quality inspection result is passed, the temporary data is used as the dual recording data corresponding to the basic link, and the time range corresponding to the dual recording data is determined according to the start time point and the end time point information.
17. 15. The computer-readable storage medium of claim 15, wherein the quality inspection method of the AI quality inspection is voice quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result comprises:

    Acquiring voice information in the temporary data, and performing voice recognition on the voice information to obtain text information corresponding to the voice information;

    Perform semantic recognition on the text information to obtain a semantic recognition result;

    According to the semantic recognition result and the preset judgment method, it is determined whether the voice information in the temporary data is qualified. If it is qualified, the voice quality inspection is confirmed to pass, and if it is unqualified, the voice quality inspection is confirmed to fail.
18. 15. The computer-readable storage medium according to claim 15, wherein the quality inspection method of the AI quality inspection is behavioral quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result comprises:

    Extracting video information in the temporary data, and extracting video frame images from the video information according to a preset interval;

    Perform face recognition on each of the video frame images, and use the video frame image containing the face image as a target image;

    Perform identity authentication on the target image, confirm the identity information corresponding to the target image, and check the identity information for consistency with the identity information in the business information to obtain the proofreading result, and determine the quality inspection result according to the proofreading result .
19. 15. The computer-readable storage medium of claim 15, wherein the quality inspection method of the AI quality inspection is certificate quality inspection, and the AI quality inspection on the temporary data to obtain the quality inspection result includes:

    Obtain the picture file in the temporary data, and parse the image file by means of OCR recognition to obtain the credential information contained in the image file;

    The certificate information and business information are checked, and the certificate quality inspection result is determined according to the check result.
20. The computer-readable storage medium according to claim 15, wherein after the AI quality inspection is performed on the temporary data to obtain the quality inspection result, and when the quality inspection result is passed, the The temporary data is used as the double-recorded data corresponding to the basic link, and after the time range information corresponding to the double-recorded data is determined according to the start time point and the end time point, the computer-readable instructions are processed by the processor When executed, the following audio and video recording guidance methods are also implemented:

    If the quality inspection result is a quality inspection failure, generate corresponding voice guidance information according to the reason for the quality inspection failure, and generate an updated starting time point;

    Play the voice guidance information so that the user can re-enter according to the voice guidance information to obtain updated temporary data, generate the updated end time point, and return to the AI quality inspection of the temporary data, The steps for obtaining the quality inspection result are continued until the quality inspection result obtained is the quality inspection passed.

Images