Data processing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a data processing method and device, equipment, a storage medium and a program product, and relates to the field of artificial intelligence. The method comprises the following steps: receiving an investigation report of target diligence investigation submitted by target diligence personnel, and corresponding double-video image data; analyzing the double-record video data, and determining whether the investigation behavior of the target diligence personnel in the target diligence investigation process meets the diligence investigation requirement or not; and processing the survey report under the condition that the full-duty survey requirement is met. According to the method provided by the invention, the accuracy of judging whether the process of the diligence investigation meets the requirement or not is improved, and the auditing efficiency of the diligence investigation is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a data processing method, device, equipment, storage medium and program product. Background Art

[0002] Post-loan due diligence refers to the investigation and monitoring activities conducted by the lending institution on the due diligence object after the loan is issued to ensure the safety of the loan. In order to ensure the authenticity and effectiveness of the due diligence content, the post-loan due diligence process must meet the due diligence requirements. For example, there are corresponding requirements for the communication content, investigation scenarios, and due diligence personnel of the due diligence.

[0003] At present, the determination of whether the post-loan due diligence process meets the requirements depends solely on the manual review of the post-loan due diligence report or form by auditors. This review process is time-consuming and highly subjective, which may lead to inaccurate audits.

[0004] Therefore, how to improve the accuracy of determining whether the post-loan due diligence process meets the requirements, as well as how to improve the efficiency of the review of post-loan due diligence are issues that need to be addressed urgently. Summary of the invention

[0005] The present application provides a data processing method, device, equipment, storage medium and product to solve the technical problems of improving the accuracy of determining whether the post-loan due diligence process meets the requirements, and improving the review efficiency of the post-loan due diligence.

[0006] In a first aspect, the present application provides a data processing method, comprising:

[0007] Receive the target due diligence investigation report submitted by the target due diligence personnel, as well as the corresponding dual-recording video data;

[0008] Analyze the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements;

[0009] Subject to due diligence requirements, the investigation report will be processed.

[0010] In a second aspect, the present application provides a data processing device, including:

[0011] A receiving module is used to receive the target due diligence investigation report submitted by the target due diligence personnel, as well as the corresponding dual-recording image data;

[0012] An analysis module, used to analyze the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements;

[0013] The processing module is used to process the investigation report in compliance with due diligence requirements.

[0014] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0015] The memory stores computer-executable instructions;

[0016] The processor executes the computer-executable instructions stored in the memory to implement the method described in any one of the first aspects.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in any one of the first aspects.

[0018] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method described in any one of the first aspects when executed by a processor.

[0019] The data processing method, device, equipment, storage medium and program product provided by the present application conduct multi-faceted analysis of the dual-recording image data submitted by the due diligence personnel, so as to determine whether the due diligence process meets the due diligence requirements. Compared with the prior art that only manually determines whether the due diligence process meets the due diligence requirements based on the due diligence report or form, the content considered in the embodiments of the present application is more comprehensive and objective, and the speed is faster. Therefore, the embodiments of the present application can improve the accuracy and efficiency of determining whether the due diligence process meets the due diligence requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a process flow of a post-loan due diligence double-recording image data processing method provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0025] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0027] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0028] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0029] It should be noted that the data processing methods, devices, equipment, storage media and program products provided in this application can be used in the field of artificial intelligence, and can also be used in any field other than artificial intelligence. The application fields of the data processing methods, devices, equipment, storage media and program products in this application are not limited.

[0030] Due diligence can refer to the process in which due diligence personnel conduct a comprehensive and detailed investigation and review of the due diligence object. Among them, due diligence personnel can be relevant business personnel involved in the target due diligence, and the due diligence object can be any one or more of the following: enterprises, assets, projects, individuals, teams, etc.

[0031] Taking post-loan due diligence as an example, as a key link in the loan process, its core purpose is to implement a series of detailed investigations and continuous monitoring activities on the due diligence subjects after the loan is issued, aiming to closely monitor the use of the loan, timely identify and prevent potential risks, and thus ensure the safety of loan assets.

[0032] During the due diligence process, the post-loan due diligence personnel's investigation behavior must comply with the requirements of post-loan due diligence. Post-loan due diligence personnel must thoroughly collect and analyze the multi-dimensional data such as the financial information, operating conditions, credit status and repayment ability of the post-loan due diligence object, and must also ensure that all post-loan due diligence activities comply with laws, regulations and rules.

[0033] At present, the assessment of whether the post-loan due diligence process complies with the due diligence requirements mainly relies on the auditors' manual review of the post-loan due diligence report or form, which is generated by the post-loan due diligence personnel after the due diligence is completed.

[0034] For example, based on the post-loan due diligence report or form, the post-loan due diligence process can be evaluated from the following dimensions to determine whether it complies with the post-loan due diligence requirements:

[0035] First, the due diligence investigators involved in post-loan due diligence must meet certain quantity requirements. For example, two or more post-loan due diligence investigators must participate in the due diligence. The participation of multiple post-loan due diligence investigators helps to enhance the objectivity and independence of the post-loan due diligence and avoid the situation where a certain post-loan due diligence investigator’s personal relationships or conflicts of interest affect the fairness and objectivity of the post-loan due diligence.

[0036] Secondly, post-loan due diligence personnel involved in post-loan due diligence must have professional qualifications and experience. For example, post-loan due diligence personnel must have credit qualifications to ensure the professionalism and accuracy of post-loan due diligence and enhance the authority and credibility of post-loan due diligence.

[0037] Third, during the post-loan due diligence process, the communication between the post-loan due diligence personnel and the post-loan due diligence subjects must be complete and comprehensive to ensure the accuracy and completeness of the post-loan due diligence.

[0038] In addition, there are multiple dimensions to determine whether the post-loan due diligence process complies with due diligence requirements, which this application does not limit.

[0039] Post-loan due diligence personnel can upload the post-loan due diligence report or form to the data processing system, and the auditors can obtain the post-loan due diligence report or form from the data processing system and evaluate whether the post-loan due diligence process meets the due diligence requirements based on the above dimensions.

[0040] Since the above-mentioned review process of whether the post-loan due diligence process complies with the post-loan due diligence requirements is completed manually, this method is not only inefficient and time-consuming, but also easily introduces human errors due to differences in subjective judgment of auditors, affecting the objectivity and accuracy of the audit results.

[0041] In view of this, the embodiment of the present application provides a method of data processing, which can be applied in the scenario of reviewing whether the due diligence process meets the due diligence requirements. The execution subject of the present application can be a data processing system. The embodiment of the present application provides that according to the dual-recording image data submitted by the due diligence personnel in the data processing system, that is, the audio and video recordings of the due diligence process, the dual-recording image data can be analyzed in the data processing system to determine whether the due diligence process meets the due diligence requirements. Compared with the method in the prior art that requires manual review, the accuracy and efficiency of judging whether the post-loan due diligence process meets the requirements are improved, as well as the intelligence of reviewing whether the due diligence process meets the due diligence requirements.

[0042] The due diligence mentioned here may be, for example, the post-loan due diligence mentioned above, or other scenarios requiring due diligence, and the embodiments of the present application are not limited thereto.

[0043] The data processing system can be deployed entirely in a cloud environment. For example, if the computing resources included in the cloud environment are servers running virtual machines, the data processing system can be independently deployed on a server or virtual machine in the cloud environment, or the data processing system can be distributedly deployed on multiple servers in the cloud environment, or distributedly deployed on multiple virtual machines in the cloud environment, or distributedly deployed on servers and virtual machines in the cloud environment.

[0044] The data processing system provided by the embodiment of the present application can also be deployed in different environments in a distributed manner. The data processing system provided by the present application can be logically divided into multiple parts, each of which has different functions. The various parts in the data processing system can be deployed in any two or three of the terminal computing device (located on the user side), the edge environment, and the cloud environment. The various parts of the data processing system deployed in different environments or devices collaborate to realize the function of data processing. It should be understood that the embodiment of the present application does not restrictively divide which parts of the data processing system are deployed in what environment. In actual application, it can be adaptively deployed according to the computing power of the terminal computing device, the resource occupancy of the edge environment and the cloud environment, or the specific application requirements.

[0045] The data processing system can also be deployed separately on a computing device in any environment (for example, separately deployed on an edge server in an edge environment).

[0046] The naming of the above data processing system is only an exemplary naming, which can be adjusted according to the specific application scenario. For example, taking post-loan due diligence as an example, in this scenario, the data processing system can be, for example, a bank post-loan management system.

[0047] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0048] Figure 1 A flow chart of a data processing method provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0049] S101. Receive a target due diligence investigation report submitted by a target due diligence investigator, and corresponding dual-recording video data.

[0050] The investigation report of target due diligence can be an investigation report formed after a comprehensive assessment of the target due diligence object during the target due diligence process. Taking post-loan due diligence as an example, the investigation report of target due diligence can include any one or more of the target due diligence object's financial information, operating conditions, credit status, repayment ability, etc.

[0051] The dual-recording image may be an audio or video recording of the entire process of due diligence on the target, and the dual-recording image data may include any one or more of the audio data, image data, voiceprint data, etc. in the dual-recording image.

[0052] Optionally, the target due diligence investigation report and the corresponding dual-recording image data can be uploaded by the target due diligence personnel through the client of the data processing system. Exemplarily, the client can be a browser client or a mobile application client.

[0053] S102. Analyze the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements.

[0054] As mentioned above, there may be multiple dimensions to determine whether the due diligence personnel's investigation behavior complies with the due diligence requirements, for example, the due diligence personnel participating in the due diligence meet certain quantity requirements, the due diligence personnel participating in the due diligence have professional qualifications and experience, and the due diligence personnel's communication with the target due diligence subjects during the due diligence process is complete and comprehensive, etc. This application does not limit this.

[0055] Optionally, the data processing system can determine whether the investigation behavior of the due diligence personnel meets the due diligence requirements for each dimension according to the pre-set judgment process for each dimension. It can also use a pre-trained model to analyze the dual-recording image data to obtain the result of whether it meets the due diligence requirements. It can also use a large model and pre-set due diligence prompt information to obtain the result of whether it meets the due diligence requirements. This application does not limit this.

[0056] If yes, that is, in the case of meeting the due diligence requirements, step S103 is executed. If no, that is, in the case of not meeting the due diligence requirements, the investigation report may not be processed, or a result of failure of the investigation report may be returned, etc., which is not limited.

[0057] S103. Process the investigation report.

[0058] Optionally, compliance with due diligence requirements may include that during the due diligence process, the due diligence personnel involved in the due diligence meet certain quantitative requirements, the due diligence personnel involved in the due diligence have professional qualifications and experience, and the due diligence personnel's communication with the due diligence subjects during the due diligence process is complete and comprehensive.

[0059] In the case of meeting due diligence requirements, processing the investigation report may include further analysis of the target due diligence object based on the information in the investigation report. Taking post-loan due diligence as an example, processing the investigation report may include analysis of multi-dimensional data such as the financial information, operating conditions, credit status and repayment ability of the due diligence object in the investigation report, so as to adjust the loan strategy in a timely manner and ensure the safe recovery of loan funds.

[0060] It should be understood that the above content describes the process of determining the reliability of a due diligence report based on the dual-recording video data of the due diligence investigators when submitting the due diligence report. In specific implementation, the above analysis of the dual-recording video data of the due diligence investigators to determine whether the investigation behavior of the target due diligence investigators during the target due diligence process meets the due diligence requirements can also be applied to other scenarios where the results need to be obtained, such as the work assessment scenario for due diligence investigators.

[0061] The embodiment of the present application conducts a multi-faceted analysis of the dual-recording video data submitted by the due diligence personnel to determine whether the due diligence process meets the due diligence requirements. Compared with the prior art that only manually determines whether the due diligence process meets the due diligence requirements based on the due diligence report or form, the embodiment of the present application considers more comprehensive and objective content, and is faster. Therefore, the embodiment of the present application can improve the accuracy and efficiency of determining whether the due diligence process meets the due diligence requirements.

[0062] The following is a further detailed explanation of determining whether the investigation behavior of the target due diligence personnel during the target due diligence process complies with the due diligence requirements based on the audio data and image data in the dual-recording video data.

[0063] On the one hand, the data processing system can determine whether the target communication content of the target due diligence personnel during the target due diligence process meets the due diligence requirements for communication content based on the audio data in the dual-recording image data.

[0064] Optionally, the data processing system can directly analyze the audio data in the dual-recorded image data to determine whether the target communication content of the target due diligence personnel during the target due diligence process meets the due diligence requirements for communication content, or it can convert the audio data in the dual-recorded image data into corresponding text data for further analysis.

[0065] The following is a further description of converting the audio data in the dual-recorded image data into corresponding text data for further analysis.

[0066] The data processing system can obtain text data corresponding to the audio data of the target due diligence personnel based on the audio data. Then, the text data and the due diligence requirements for the communication content are input into the judgment model to obtain a judgment result, which is used to characterize whether the target communication content meets the due diligence requirements for the communication content.

[0067] Alternatively, existing audio-to-text technology may be used to convert all audio data into text data, from which the text data of the target due diligence investigator may be selected. The selection method may be to find all the questions in the text data as the text data of the target due diligence investigator. Alternatively, only the audio data of the target due diligence investigator may be converted into text data. For example, the audio data of the target due diligence investigator may be extracted from the audio data based on the voiceprint data of the target due diligence investigator.

[0068] Optionally, the voiceprint data of the target due diligence investigator may include any one or more of the target due diligence investigator's tone, timbre, speaking speed, etc. that can reflect the voice characteristics of the target due diligence investigator. The data processing system can compare the voiceprint data of the target due diligence investigator with the voice in the audio data, identify the part of the audio data that matches the voiceprint of the target due diligence investigator, and extract this part of the content from the audio data.

[0069] The extracted audio data of the target due diligence personnel is converted into initial text data. In this way, the content irrelevant to the target due diligence personnel can be filtered out, further ensuring the accuracy of the extracted text content, reducing the processing volume of subsequent analysis, and at the same time avoiding the conclusion being affected by the audio data of other personnel, further improving the accuracy and efficiency of the review.

[0070] Optionally, the initial text data can be further screened to reduce the amount of processing for subsequent analysis. For example, based on the starting keyword and ending keyword of due diligence, the content irrelevant to due diligence in the initial text data is filtered out to obtain text data. Exemplarily, the starting keyword of due diligence can be "due diligence starts"; the ending keyword of due diligence can be "due diligence completes".

[0071] Filtering out content that is not related to due diligence in the initial text data can make the text data more focused on the target due diligence personnel's communication content about the target, so as to more efficiently judge whether the target communication content meets the due diligence requirements.

[0072] Optionally, due diligence may have multiple requirements for communication content. For example, the target due diligence personnel need to involve specified keywords in the communication process with the due diligence object. Taking post-loan due diligence as an example, the keywords may include any one or more of the loan term, repayment method, and guarantee measures. If the target communication content of the target due diligence personnel touches on all the specified keywords, it is determined that the target communication content of the target due diligence personnel in the target due diligence process meets the due diligence requirements for communication content.

[0073] The embodiments of the present application do not limit the form of expression of the due diligence requirements for communication content. For example, it may be the requirements for the communication content in the due diligence requirements document, or keywords extracted based on the requirements, or one or more of the judgment conditions, judgment strategies, judgment constraints, etc. extracted based on the content.

[0074] Optionally, the determination model can be an artificial intelligence-based data processing and semantic understanding algorithm, or any model that can perform semantic processing, which is not limited in this application. The determination model can be used to perform global semantic encoding of the text content based on word granularity on the text data. Among them, the global semantic encoding of the text content based on word granularity can be to divide the text data into words or phrases as the basic processing units of the determination model, convert the information in the text data into a coding form that can be understood and processed by the determination model, and perform a comprehensive and in-depth semantic understanding and representation of the text content.

[0075] Optionally, the data processing system can determine whether the text data meets the due diligence requirements for communication content through a determination model, and obtain a determination result. The determination result can be that the text data meets the due diligence requirements for communication content, or that the text data does not meet the due diligence requirements for communication content.

[0076] Optionally, the judgment result for non-compliance may further include the reason for non-compliance with the due diligence requirements for communication content. Taking post-loan due diligence as an example, the judgment result may indicate that the text data does not meet the due diligence requirements for communication content due to the lack of the keyword "guarantee measures". The specific content included in the judgment result is related to the training data used in the training of the judgment model.

[0077] The determination result includes the reasons for non-compliance with the due diligence requirements for communication content, which helps the target due diligence personnel to identify the specific reasons for non-compliance during the due diligence process and take corresponding solutions to the reasons, so that the due diligence can proceed smoothly and the efficiency of the due diligence can be improved.

[0078] The embodiment of the present application converts audio data into text data, and uses a judgment model to determine whether the text data meets the due diligence requirements for communication content. Compared with the manual review method, the efficiency and accuracy of judging whether the communication content of the due diligence meets the requirements are improved.

[0079] On the other hand, the data processing system can determine whether the target investigation scenario of the target due diligence meets the due diligence requirements for the investigation scenario based on the image data in the dual-recorded image data, and whether the target due diligence personnel meets the due diligence requirements for due diligence personnel.

[0080] Optionally, the investigation scene of the due diligence target may be a scene that can characterize the target due diligence object. For example, when the target due diligence object is a company, the scene of the target due diligence object may be a logo unique to the company. The due diligence requirement for the investigation scene may be that all target due diligence personnel are in the scene of the target due diligence object.

[0081] The due diligence requirement for due diligence investigators may be that the target due diligence investigators have due diligence qualification requirements. Taking post-loan due diligence as an example, the target due diligence investigators have credit qualifications.

[0082] When the target communication content meets the due diligence requirements for communication content, the target investigation scenario meets the due diligence requirements for investigation scenario, and the target due diligence personnel meet the due diligence requirements for due diligence personnel, it is determined that the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements.

[0083] The embodiment of the present application can determine the target communication content, target investigation scenario, and whether the target due diligence personnel meet the corresponding due diligence requirements based on the audio data and image data in the dual-recorded image data, and judge whether the due diligence process meets the due diligence requirements from multiple aspects, thereby improving the comprehensiveness and accuracy of the judgment. In addition, by analyzing the dual-recorded images, the efficiency of the audit is improved compared to manual audit.

[0084] The following further explains how to determine whether the target investigation scenario of the target due diligence meets the due diligence requirements for the investigation scenario based on the image data in the dual-recording image data, and whether the target due diligence personnel meets the due diligence requirements for due diligence personnel.

[0085] The image frames in the image data of the dual-recorded image data are sorted based on the generation time of the image frames to obtain an image frame sequence.

[0086] An image frame can be a basic unit in image data, or a frame in image data. All image frame sequences arranged in the order of generation time constitute complete image data. The data processing system can obtain at least one key frame from the image frame sequence.

[0087] Optionally, the key frame may be a frame where a key action in the object motion change in the image frame sequence is located. Based on at least one key frame, it is determined whether the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene, and whether the target due diligence personnel meets the due diligence requirements for the due diligence personnel.

[0088] As mentioned above, the investigation scene of due diligence can be a scene that can characterize the target due diligence object. Taking post-loan due diligence as an example, when the target due diligence object is a company, the scene of the target due diligence object can be a unique symbol of the company. The requirement for due diligence on the investigation scene can be that all target due diligence personnel are in the scene of the target due diligence object.

[0089] The due diligence requirements for due diligence personnel may be that the target due diligence personnel meet the due diligence qualification requirements, for example, the target due diligence personnel have credit qualifications.

[0090] The following further describes how to determine whether a target investigation scenario of a target due diligence meets the due diligence requirements for investigation scenarios, and whether a target due diligence investigator meets the due diligence requirements for due diligence investigators, based on at least one key frame.

[0091] First, the data processing system can obtain information about the target due diligence object and identification information of the target due diligence personnel.

[0092] Optionally, the information of the target due diligence object may be information representing that the target due diligence personnel is located in the scene of the target due diligence object. Taking post-loan due diligence as an example, when the target due diligence object is a company. The information of the target due diligence object may include any one or more of the company's name, registered address and business address, business scope, etc. The identification information of the target due diligence personnel may include any one or more of the target due diligence personnel's name, employee number, etc.

[0093] Optionally, the data processing system can retrieve the target due diligence object information and the identification information of the target due diligence personnel from the database. Based on the identification information of the target due diligence personnel, the data processing system can obtain the target due diligence personnel's facial image and due diligence qualification information from the database.

[0094] Since the due diligence requirement for the investigation scene may be that all target due diligence personnel are in the scene of the target due diligence object, the target key frame may be selected as a key frame including all target due diligence personnel. The data processing system may determine whether there is a target key frame including all target due diligence personnel based on the face image in the key frame and the face image of the target due diligence personnel.

[0095] If there is a target key frame, based on the information of the target due diligence object, it is determined whether the background in the target key frame is the scene of the target due diligence object.

[0096] Exemplarily, if there is a target key frame, based on the information of the target due diligence object, such as a company-specific logo, it is determined whether the background in the target key frame is the scene of the target due diligence object. Optionally, the data processing system can extract the background from the target key frame by image segmentation technology, where the background can refer to the content in the target key frame other than the target due diligence personnel. Then, the data processing system can analyze whether the background in the target key frame is the scene of the target due diligence object based on the background and the information of the target investigation object.

[0097] The specific analysis method is related to the form of expression of the target investigation object's information. For example, the target investigation object's information may be a scene image of the target investigation object collected during the initial due diligence. In this implementation method, image comparison can be used to analyze whether the background in the target key frame is the scene of the target due diligence object.

[0098] If all target due diligence personnel are in the scenario of the target due diligence object, then the target investigation scenario of the target due diligence meets the requirements of due diligence for investigation scenarios; otherwise, the target investigation scenario of the target due diligence does not meet the requirements of due diligence for investigation scenarios.

[0099] The data processing system can determine whether the target due diligence investigator has due diligence qualifications based on the due diligence qualification information of the target due diligence investigator obtained from the database. For example, the due diligence qualification information can indicate whether the investigator has due diligence qualifications, or the database only stores information of personnel with due diligence qualifications. Therefore, whether the investigator has due diligence qualifications can also be determined by whether the due diligence qualification information of the target due diligence investigator can be queried from the database.

[0100] As described above, determining that the target due diligence investigator meets the due diligence requirements for due diligence investigators can be that all target due diligence investigators are in the scene of the target due diligence object, and the target due diligence investigators all have due diligence qualifications. Therefore, if there is a target key frame and the qualifications of the target due diligence investigators all meet the due diligence qualification requirements for due diligence investigators, it is determined that the target due diligence investigator meets the due diligence requirements for due diligence investigators.

[0101] The embodiment of the present application utilizes a data processing system to select key frames to review whether the target investigation scenario of the target due diligence meets the due diligence requirements for the investigation scenario, and whether the target due diligence personnel meet the due diligence requirements for the due diligence personnel. Compared with the method in the prior art that requires manual review of these two requirements, the accuracy and efficiency of the review are improved.

[0102] After the above-mentioned judgment on the target communication content, the target investigation scenario, and whether the target due diligence personnel meet the due diligence requirements is completed, for any situation that does not meet the requirements, the embodiment of the present application can add a target tag to the dual-recording image data. The target tag is used to characterize that the investigation behavior in the target due diligence process does not meet the due diligence requirements and / or the reasons for not meeting the requirements.

[0103] For example, if the data processing system identifies that the target due diligence personnel in the dual-recorded image data does not have the due diligence qualification, a target tag indicating that the target due diligence personnel does not have the due diligence qualification is added to the dual-recorded image data. Through the target tag, the target due diligence personnel and the auditor can clearly and intuitively understand that the investigation behavior of the target due diligence process in the dual-recorded image data does not meet the due diligence requirements and / or the reasons why it does not meet the requirements, thereby improving the work efficiency of the auditor and facilitating the target due diligence personnel to make improvements based on the reasons why the investigation behavior of the target due diligence process does not meet the due diligence requirements and / or does not meet the requirements.

[0104] In order to more intuitively demonstrate the entire process of the data processing method provided in the embodiment of the present application, Figure 2 The following is a flow chart of a post-loan due diligence double-recording image data processing method provided in an embodiment of the present application. Figure 2 As shown, the process includes:

[0105] 1. Receive double-recorded images of post-loan due diligence.

[0106] 2. Based on the audio data in the dual-recording images, artificial intelligence-based data processing and semantic understanding algorithms are used to perform global semantic encoding of the text content in the recording data in the dual-recording images based on word granularity.

[0107] 3. Ensure that the communication content complies with the post-loan due diligence requirements.

[0108] 4. Based on the image data in the dual-recording images, the image content sequence is generated according to the time frame order, the current time frame is determined to be a key frame, and the complete image of the key frame is inferred.

[0109] 5. Ensure that the post-loan scenario meets the requirements and that multiple target due diligence personnel are in the same scenario.

[0110] 6. Based on the image data in the dual-recording images, perform facial recognition on the target due diligence personnel in the video, and combine with the human resources system and qualification management system to determine the identity and credit qualifications of the identified target due diligence personnel.

[0111] 7. Determine multiple target due diligence personnel, and the identity and qualifications of the target due diligence personnel meet the requirements.

[0112] 8. Post-loan due diligence double-recording video is automatically reviewed and approved.

[0113] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0114] The above is an embodiment of the method provided by the present application. The following is a description of the device provided by the present application.

[0115] Figure 3 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. Figure 3 As shown, the data processing device 200 may include, for example: a receiving module 201 , an analyzing module 202 , and a processing module 203 .

[0116] The receiving module 201 is used to receive the target due diligence investigation report submitted by the target due diligence personnel, and the corresponding dual-recording image data;

[0117] The analysis module 202 is used to analyze the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements;

[0118] The processing module 203 is used to process the investigation report in compliance with due diligence requirements.

[0119] Optionally, the analysis module 202 is specifically used to determine whether the target communication content of the target due diligence personnel during the target due diligence process meets the due diligence requirements for communication content based on the audio data in the dual-recorded image data. Based on the image data in the dual-recorded image data, determine whether the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene, and whether the target due diligence personnel meet the due diligence requirements for due diligence personnel. When the target communication content meets the due diligence requirements for communication content, the target investigation scene meets the due diligence requirements for the investigation scene, and the target due diligence personnel meets the due diligence requirements for due diligence personnel, it is determined that the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements.

[0120] For example, the analysis module 202 is specifically used to obtain text data corresponding to the audio data of the target due diligence personnel based on the audio data. The text data and the due diligence requirements for the communication content are input into the judgment model to obtain a judgment result, which is used to characterize whether the target communication content meets the due diligence requirements for the communication content.

[0121] Optionally, when the determination result indicates that the target communication content does not meet the due diligence requirements for the communication content, the determination result further includes: the reason for not meeting the due diligence requirements for the communication content.

[0122] Exemplarily, the analysis module 202 is specifically used to extract the audio data of the target due diligence personnel from the audio data based on the voiceprint data of the target due diligence personnel. The audio data of the target due diligence personnel is converted into initial text data. The text data is obtained based on the initial text data. In a possible implementation, the analysis module 202 is specifically used to filter out the content unrelated to the due diligence in the initial text data based on the starting keyword and the ending keyword of the due diligence to obtain the text data.

[0123] Optionally, the analysis module 202 is specifically configured to sort the image frames based on the generation time of the image frames in the image data in the dual-recording image data to obtain an image frame sequence. At least one key frame is obtained from the image frame sequence. Based on the at least one key frame, it is determined whether the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene, and whether the target due diligence personnel meets the due diligence requirements for the due diligence personnel.

[0124] For example, the analysis module 202 is specifically used to obtain information about the target due diligence object and identification information of the target due diligence personnel. Based on the identification information of the target due diligence personnel, the facial image of the target due diligence personnel and the due diligence qualification information are obtained from the database. Based on the facial image in the key frame and the facial image of the target due diligence personnel, it is determined whether there is a target key frame including all target due diligence personnel. When there is a target key frame, based on the information of the target due diligence object, it is determined whether the background in the target key frame is the scene of the target due diligence object. When the background in the target key frame is the scene of the target due diligence object, it is determined that the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene. When there is a target key frame and the qualifications of the target due diligence personnel meet the due diligence qualification requirements for the due diligence personnel, it is determined that the target due diligence personnel meets the due diligence requirements for the due diligence personnel.

[0125] Optionally, the processing module 203 is also used to add a target tag to the dual-recording image data when any of the target communication content, the target investigation scenario, and the target due diligence personnel do not meet the requirements. The target tag is used to characterize that the investigation behavior in the target due diligence process does not meet the due diligence requirements and / or the reasons for not meeting the requirements.

[0126] The data processing device 200 provided in the embodiment of the present application can be used to implement the actions performed by the electronic device in any of the aforementioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0127] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown, the electronic device 300 may include: a memory 301 and a processor 302. The electronic device may be, for example, the data processing system mentioned above. Optionally, the electronic device may also include a transceiver 303, wherein the memory 301 and the processor 302 communicate; illustratively, the memory 301, the processor 302 and the transceiver 303 may communicate via a communication bus 303, the memory 301 is used to store a computer program, and the processor 302 executes the computer program to implement the method of the above embodiment.

[0128] Optionally, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps in the method embodiments disclosed in the present application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0129] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, a method in any of the above method embodiments is implemented.

[0130] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in any of the above method embodiments when the computer program is executed by a processor.

[0131] All or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions. The above-mentioned program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the above-mentioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc and any combination thereof.

[0132] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processing unit of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0136] In the present application, the term "include" and its variations may refer to non-restrictive inclusion; the term "or" and its variations may refer to "and / or". The terms "first", "second", etc. in the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. In the present application, "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship.

Claims

1. A data processing method, characterized in that: The method comprises: Receive the target due diligence investigation report submitted by the target due diligence personnel, as well as the corresponding dual-recording video data; Analyze the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements; Subject to due diligence requirements, the investigation report will be processed.

2. The method according to claim 1, characterized in that The analysis of the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements includes: Based on the audio data in the dual-recording video data, determining whether the target communication content of the target due diligence personnel during the target due diligence process meets the due diligence requirements for communication content; Based on the image data in the dual-recorded image data, determining whether the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene, and whether the target due diligence personnel meets the due diligence requirements for due diligence personnel; When the target communication content meets the due diligence requirements for communication content, the target investigation scenario meets the due diligence requirements for investigation scenario, and the target due diligence investigator meets the due diligence requirements for due diligence investigators, it is determined that the investigation behavior of the target due diligence investigator during the target due diligence process meets the due diligence requirements.

3. The method according to claim 2, characterized in that The determining, based on the audio data in the dual-recording video data, whether the target communication content of the target due diligence personnel during the target due diligence process meets the due diligence requirements for communication content includes: Based on the audio data, obtaining text data corresponding to the audio data of the target due diligence investigator; The text data and the due diligence requirements for communication content are input into a determination model to obtain a determination result, which is used to characterize whether the target communication content meets the due diligence requirements for communication content.

4. The method according to claim 3, characterized in that If the determination result indicates that the target communication content does not meet the due diligence requirements for communication content, the determination result further includes: the reason for not meeting the due diligence requirements for communication content.

5. The method according to claim 3, characterized in that: The obtaining, based on the audio data, text data corresponding to the audio data of the target due diligence investigator includes: Based on the voiceprint data of the target due diligence investigator, extracting the audio data of the target due diligence investigator from the audio data; Converting the audio data of the target due diligence investigator into initial text data; The text data is obtained based on the initial text data.

6. The method according to claim 5, characterized in that The obtaining of the text data based on the initial text data comprises: Based on the starting keyword and the ending keyword of the due diligence, the content irrelevant to the due diligence in the initial text data is filtered out to obtain the text data.

7. The method according to claim 2, characterized in that The determining, based on the image data in the dual-recorded image data, whether the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene, and whether the target due diligence personnel meets the due diligence requirements for the due diligence personnel, includes: Sorting the image frames based on the generation time of the image frames in the image data in the dual-recorded image data to obtain an image frame sequence; Acquire at least one key frame from the image frame sequence; Based on the at least one key frame, it is determined whether the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene, and whether the target due diligence personnel meets the due diligence requirements for due diligence personnel.

8. The method according to claim 7, characterized in that The determining, based on the at least one key frame, whether the target investigation scenario of the target due diligence meets the due diligence requirements for the investigation scenario, and whether the target due diligence personnel meets the due diligence requirements for the due diligence personnel, comprises: Obtaining information of the target due diligence subject and identification information of the target due diligence personnel; Based on the identification information of the target due diligence investigator, a facial image and due diligence qualification information of the target due diligence investigator are obtained from a database; Based on the face images in the key frames and the face images of the target due diligence personnel, determining whether there is a target key frame including all target due diligence personnel; If there is a target key frame, determining whether the background in the target key frame is a scene of the target due diligence object based on the information of the target due diligence object; If the background in the target key frame is a scene of a target due diligence object, it is determined that the target investigation scene of the target due diligence meets the due diligence requirements for the investigation scene; If there is a target keyframe, and the qualifications of the target due diligence investigator all meet the due diligence qualification requirements for due diligence investigators, then it is determined that the target due diligence investigator meets the due diligence requirements for due diligence investigators.

9. The method according to any one of claims 2 to 8, characterized in that: The method further comprises: In the case that any one of the target communication content, the target investigation scenario, and the target due diligence personnel does not meet the requirements, a target tag is added to the dual-recording image data, and the target tag is used to characterize that the investigation behavior in the target due diligence process does not meet the due diligence requirements and / or the reasons for not meeting the requirements.

10. A data processing device, characterized in that: The device comprises: A receiving module is used to receive the target due diligence investigation report submitted by the target due diligence personnel, as well as the corresponding dual-recording image data; An analysis module, used to analyze the dual-recording video data to determine whether the investigation behavior of the target due diligence personnel during the target due diligence process meets the due diligence requirements; The processing module is used to process the investigation report in compliance with due diligence requirements.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed by a processor.

Images