Method, device and medium for compliance detection of dual-record video file

Abstract

This application discloses a compliance detection method, apparatus, and medium for dual-recorded video files. The method includes: determining the file type of the dual-recorded video file based on its source information; if the file type is a suspicious video file, then performing compliance detection on the suspicious video file based on the business processing time of the user corresponding to the suspicious video file and a preset tolerance time. This application's method of determining the file type through source information achieves preliminary filtering of suspicious video files and rapid classification of dual-recorded video files. The setting of the tolerance time range solves the problem of video files failing compliance detection due to minor adjustments made shortly after recording.

Description

Technical Field

[0001] This application relates to the field of dual recording technology, and more specifically, to a method, apparatus, electronic device, and computer-readable storage medium for compliance testing of dual-recorded video files. Background Technology

[0002] In recent years, the term "legal compliance" has been frequently used in the supervision and management of commercial banks in my country. However, many people's understanding of the concept of "compliance" is superficial. Some understand "compliance" as the requirement that the business management behavior of banks and their branches must comply with the rules and regulations formulated by the bank's head office; others simply understand "compliance" as conforming to regulations, and non-compliance as a violation. Traditional banking risks include three major risks: credit risk, market risk, and operational risk. Compliance risk is a more fundamental risk built upon these three risks. Compliance risk differs from, yet is closely related to, the three major banking risks. The difference is that compliance risk is simply the risk or loss incurred by banks for doing things they shouldn't have done (illegal, irregular, unethical, etc.). Dual recording (i.e., audio and video recording) is a mandatory requirement of the China Banking Regulatory Commission (CBRC). On the one hand, it prevents trust companies or third-party wealth management sales personnel from making false promises or illegally guaranteeing principal during communication with clients. On the other hand, it serves as a reminder to investors of their risk tolerance and understanding of product risks; its original intention remains to protect investors. However, because the financial market has a huge user base, no single company can sell all financial products through its own exclusive channels. To increase market share, almost all banks and insurance companies adopt a multi-channel sales model combining self-operated and partner distribution for the same product. This cooperative model faces a compliance issue: if a customer purchases wealth management or insurance products through a self-operated channel, the transaction is conducted through the bank's or insurance company's online system, and the process is strictly recorded and monitored in real time according to compliance procedures. However, partner sales channels face a different situation. Due to technical limitations and cost constraints, partners cannot provide real-time compliance recording capabilities for customers and can only rely on offline recording, uploading the video to the insurance company's or bank's system after the transaction is completed. This part of the business faces significant compliance risks. Insurance companies generally choose to use offline compliance monitoring systems to conduct offline compliance checks on the videos uploaded by third-party partners. The compliance checks include multi-dimensional and comprehensive compliance checks such as customer identification in the video, recognition of customer affirmative answers, customer signature recognition, wealth manager identification, wealth manager's script recognition, video creation time verification, video editing verification, and video integrity verification. The relevant video creation time verification is determined by judging whether the video creation time is consistent with the business processing time in the business system. However, this has the problem of low compliance detection accuracy due to the single judgment dimension and lack of support for error tolerance time. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, and computer-readable storage medium for compliance detection of dual-recording video files, which can solve at least one of the above-mentioned problems. The technical solution is as follows:

[0004] Firstly, a compliance detection method for dual-recorded video files is provided, the method comprising:

[0005] Based on the source information of the dual-recording video file to be processed, the file type of the dual-recording video file is determined;

[0006] If the file type is a suspicious video file, then the business processing time of the user corresponding to the suspicious video file will be recorded.

[0007] Based on the business processing time and the preset error tolerance time, the suspicious video files are subjected to compliance checks.

[0008] Secondly, a compliance detection device for dual-recorded video files is provided, the device comprising:

[0009] The file type determination module is used to determine the file type of the dual-recording video file based on the source information of the dual-recording video file to be processed.

[0010] The processing time determination module is used to determine the processing time of the user corresponding to the suspicious video file if the file type is a suspicious video file.

[0011] The compliance detection module is used to perform compliance detection on the suspicious video files based on the business processing time and the preset fault tolerance time.

[0012] Thirdly, an electronic device is provided, the electronic device comprising:

[0013] One or more processors;

[0014] Memory;

[0015] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: execute the above-described compliance detection method for dual-recorded video files.

[0016] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the above-mentioned compliance detection method for dual-recorded video files.

[0017] This application embodiment determines the file type of the dual-recording video file based on the source information of the file to be processed. In the case of a suspicious video file, it determines the business processing time of the user corresponding to the suspicious video file. The suspicious video file is then processed according to the business processing time and a preset error tolerance time range, thereby completing the compliance detection of the dual-recording video file. This method of determining the file type through the source information achieves the effect of initially filtering suspicious video files and quickly classifying dual-recording video files. The setting of the error tolerance time range solves the problem that video files cannot pass the compliance detection due to minor adjustments made in a short period of time after the dual-recording video file is recorded. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0019] Figure 1 A flowchart illustrating the compliance detection method for dual-recorded video files provided in this application embodiment;

[0020] Figure 2 This is a flowchart illustrating the process of handling suspicious video files in the compliance detection method for dual-recording video files provided in this application embodiment;

[0021] Figure 3 This is a schematic diagram of the structure of the compliance detection device for dual-recorded video files provided in this application embodiment. Detailed Implementation

[0022] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0023] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0024] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0025] This application provides a method for compliance detection of dual-recorded video files, such as... Figure 1 As shown, the method includes:

[0026] Step S101: Determine the file type of the dual-recording video file based on the source information of the dual-recording video file to be processed;

[0027] In this embodiment, source information is used to characterize the creation time of the video file, including the creation time of the overall file, the creation time of the image portion, and the creation time of the audio portion. Specifically, the source information can be determined by reading the attribute information of the dual-recording video file.

[0028] In this embodiment, the file type is used to characterize whether the dual-recording video file is suspected of being tampered with. For example, if the source information includes several consistent times, it indicates that the dual-recording video file has not been tampered with and its file type is a compliant video file; if the source information includes several inconsistent times or several times are all empty, it indicates that the dual-recording video file is suspected of being tampered with, and the file type is determined to be a suspicious video file.

[0029] In application, different file types correspond to different processing procedures. For example, if the file type is a compliant video file, no further processing is required; if the file type is a suspicious video file, a compliance detection strategy for suspicious video files will be executed.

[0030] Step S103: If the file type is a suspicious video file, determine the business processing time of the user corresponding to the suspicious video file.

[0031] Specifically, the business processing time of the user corresponding to the suspicious video file can be determined from the preset business system. In application, the file identifier of the dual-recorded video file can be used to query the preset business system to obtain the business processing time of the user corresponding to the dual-recorded video file, and this business processing time can be used as the comparison source time. The file identifier of the dual-recorded video file can be a business order number, transaction number, user identity-related information, etc.

[0032] Step S104: Process the suspicious video files according to the business processing time and the preset fault tolerance time range to complete the compliance test of the dual-recorded video files.

[0033] Specifically, the handling method for suspicious video files can be determined by judging whether the business processing time is within the preset tolerance time range. For example, if the business processing time is within the preset tolerance time range, the suspicious video file needs to pass the compliance check; otherwise, the suspicious video file is marked as failing the compliance check.

[0034] This application embodiment determines the file type of the dual-recording video file based on the source information of the file to be processed. In the case of a suspicious video file, it determines the business processing time of the user corresponding to the suspicious video file. The suspicious video file is then processed according to the business processing time and a preset error tolerance time range, thereby completing the compliance detection of the dual-recording video file. This method of determining the file type through the source information achieves the effect of initially filtering suspicious video files and quickly classifying dual-recording video files. The setting of the error tolerance time range solves the problem that video files cannot pass the compliance detection due to minor adjustments made in a short period of time after the dual-recording video file is recorded.

[0035] In some embodiments, step S104, which involves processing suspicious video files based on the business processing time and a preset fault tolerance time range, includes steps S1041 to S1045 (not shown in the figure).

[0036] Step S1041: If the business processing time is within the tolerance time range, then the suspicious video file is marked as an imperfectly passed video file, and the business processing time is determined as the comparison source time of the suspicious video file;

[0037] Step S1042: Extract several image frames from the suspicious video file;

[0038] Step S1043: Using a preset watermark recognition algorithm, determine the watermark time corresponding to several image frames respectively;

[0039] Step S1044: Determine the comparison time of the suspicious video file based on the watermark time corresponding to several image frames respectively;

[0040] Step S1045: Based on the comparison source time and comparison time, perform compliance checks on the imperfectly passed video files.

[0041] Specifically, a preset video extraction strategy can be used to process suspicious video files to obtain several image frames. More specifically, the video extraction strategy can include one, two, or more. In application, when multiple video extraction strategies are configured, one of them can be set as the default video extraction strategy. For example, assuming the preset video extraction strategy is to extract 5 frames every 10 seconds, if the duration of the dual-recorded video file is 30 seconds, then 15 frames can be extracted.

[0042] Specifically, image frames from dual-recording video files can be extracted by calling a third-party video extraction algorithm through a preset interface.

[0043] Specifically, a watermark recognition algorithm is used to identify each image frame, obtaining the watermark time corresponding to each image frame. In application, each image frame can be sent to a third-party watermark recognition algorithm through a preset interface to obtain the watermark time corresponding to each image frame from the third-party watermark recognition algorithm; or a locally configured watermark recognition algorithm can be called to identify each image frame.

[0044] In this embodiment, the comparison time is used to characterize the processing time of the dual-recording video file determined by the image frames. Specifically, different image frames correspond to different watermark times.

[0045] Specifically, the comparison time of a suspicious video file can be determined based on multiple dimensions within the watermark times corresponding to each image frame. In application, dimensions such as the most frequent occurrence, earliest time, latest time, and middle time can be used as criteria to determine the comparison time.

[0046] In some embodiments, after step S1043 uses a preset watermark recognition algorithm to determine the watermark time corresponding to several image frames respectively, the method further includes:

[0047] Determine the success rate of watermark recognition for a number of image frames;

[0048] If the success rate is less than the preset success rate threshold, then step S1042 is executed again, that is, the step of extracting a number of image frames from the suspicious video file is executed again until the success rate of watermark recognition of the re-extracted image frames is not less than the success rate threshold.

[0049] This application embodiment avoids the low accuracy of the determined comparison time due to a low success rate of watermark recognition, which in turn affects the compliance detection result of step S1045, by setting a success rate threshold.

[0050] In some embodiments, step S1042, which involves extracting several image frames from a suspicious video file, includes:

[0051] Keyframes are extracted from suspicious video files to obtain several image frames;

[0052] Extract a first predetermined number of image frames from suspicious video files according to a preset time period;

[0053] Extract a second predetermined number of image frames from a suspicious video file within a predetermined time period;

[0054] For suspicious video files, a predetermined number of image frames are extracted at predetermined intervals.

[0055] Specifically, the embodiments of this application can be configured with reference to the video extraction strategies provided in Table 1.

[0056] Table 1

[0057]

[0058]

[0059] When applying the application, at least one video extraction strategy from Table 1 can be configured. For example, the video extraction strategy is to extract N frames every n seconds, that is, to extract a first predetermined number of image frames from a suspicious video file according to a preset time period; the video extraction strategy is to extract frames in segments, that is, to extract a second predetermined number of image frames within a predetermined time period of a suspicious video file; the video extraction strategy is to extract frames at intervals, that is, to extract a predetermined number of image frames from a suspicious video file at predetermined time intervals.

[0060] It should be noted that the above video extraction strategy is an exemplary method provided by the embodiments of this application. Any video extraction strategy that extracts image frames from a video file is a protection method of this application, and will not be listed one by one here.

[0061] In some embodiments, step S1044, which determines the comparison time of a suspicious video file based on the watermark times corresponding to several image frames, includes:

[0062] Based on the watermark times corresponding to several image frames, determine the watermark time that appears most frequently.

[0063] The time of the watermark that appears most frequently is used as the comparison time for suspicious video files.

[0064] In this embodiment, the comparison time is used to characterize the creation time of the video determined based on the image frames.

[0065] This embodiment uses the dimension with the highest frequency of occurrence to determine the comparison time. The comparison time is used to characterize the creation time of the video, avoiding the problem of inaccurate video creation time determined based on image frames due to the tampering of individual videos.

[0066] When applying this method, the time frame with the highest frequency of occurrence can be selected as the comparison time. For example, if the image frame time of image frame A is T1, the image frame time of image frame B is T2, the image frame time of image frame C is T1, the image frame time of image frame D is T1, the image frame time of image frame E is T2, and the image frame time of image frame F is T3, then the time frame with the highest frequency of occurrence is T1, and T1 can be used as the comparison time.

[0067] In some embodiments, step S1045, which involves performing compliance checks on imperfectly passed video files based on the comparison source time and comparison time, includes at least one of the following:

[0068] If the source time and the comparison time are consistent, then the imperfect video file passes the compliance test.

[0069] If the source time and comparison time are inconsistent, the video file is determined to be imperfect and has failed the compliance test.

[0070] When applying the application, if a video file that does not pass the compliance check perfectly is determined to be imperfectly passed, the dual-recorded video file can be marked as having imperfectly passed the compliance check and stored in the database of files that have passed the compliance check.

[0071] This application embodiment achieves a rapid filtering effect between compliant and non-compliant videos by identifying suspicious and imperfectly passed video files. This further diverts suspicious video files to a secondary stream, providing an initial screening effect for their compliance. Then, a secondary compliance check is performed on the suspicious video files that pass the initial screening. This compliance check is divided into two stages, solving the problem of poor compliance detection accuracy caused by performing only a one-time compliance check in existing technologies, and reducing the high cost of compliance detection due to the low pass rate of audio compliance checks requiring manual review.

[0072] In some embodiments, step S103, which involves performing compliance checks on suspicious video files based on business processing time and a preset fault tolerance time range, further includes:

[0073] If the processing time is outside the tolerance period, the suspicious video file is determined to have failed the compliance test and is marked as a non-compliant video file.

[0074] Non-compliant video files are stored in a non-compliant file database for manual review.

[0075] Specifically, the database of non-compliant documents can be stored in the cloud or locally. When used, it can generate manual review records for non-compliant video documents, which can be provided to users via email, floating windows, or other means.

[0076] In some embodiments, the source information includes the global creation time of the dual-recording video file, the image file creation time of the image data portion of the dual-recording video file, and the audio file creation time of the audio data portion of the dual-recording video file; the step of determining the file type of the dual-recording video file based on the source information includes:

[0077] If the global creation time, image file creation time, and audio file creation time are consistent, then the file type of the dual-recorded video file is determined to be a compliant file.

[0078] If at least one of the global creation time, the image file creation time, and the audio file creation time is inconsistent, the file type of the dual-recorded video file is determined to be a suspicious video file.

[0079] Specifically, the consistency of several timestamps in the file creation time source information can be used to determine if a dual-recording video file has been tampered with. In application, if the timestamps are inconsistent, the dual-recording video file is suspected of being tampered with and is therefore deemed suspicious; if the timestamps are consistent, the dual-recording video file is not suspected of being tampered with and is therefore not suspicious. In application, if the global creation time, image file creation time, and audio file creation time are consistent, the dual-recording video file can be marked as a perfectly compliant file.

[0080] To further illustrate the method provided in the embodiments of this application, the following is combined with... Figure 2 The dual-recorded video files to be processed are described in detail.

[0081] First, the video source information is obtained from the video files submitted by the system. Since a video contains both visuals and audio, the creation time (creation_time) of the video file is obtained through FFMPEG. This includes the global creation time of the video, the creation time of the video itself, and the creation time of the audio (i.e., the creation time of the audio portion). If the global creation time of the video is inconsistent with the creation times of the video and audio, the time in the metadata is not used as the comparison source time, and the video is marked as suspicious. The system prompts that the video needs to be manually reviewed for secondary confirmation. Alternatively, if the creation time is not obtained or the global creation time of the video is inconsistent with the creation times of the video and audio, the processing date of the current business is obtained from the business system as the comparison source time. Second, video frames are extracted. Specifically, video frame images can be extracted using the video extraction strategy provided in Table 1 above for watermark recognition. Then, watermark recognition is performed by calling a watermark recognition algorithm (such as watermarkOcr, which can use algorithms developed by other third-party vendors on the market) through a multi-threaded approach to obtain the watermark date in the image. Because anomalies may occur during the recognition process (failure to recognize, recognition error), we need to process the recognition results as follows: 1) Extract the numeric dates from the recognition results using regular expressions; 2) Store the recognized dates in a Map collection, where the key is the recognized date and the value is the number of times that date was recognized; 3) Sort the final map by value and take the value with the most recognitions as the final recognition result and comparison time. See the table below for an example: {"20220512":10,"20360401":2,"20190112":1}. Finally, perform date verification, comparing the source time with the comparison time. If the dates match, it passes (true); if the times do not match, it fails (false).

[0082] Another embodiment of this application provides a compliance detection device for dual-recorded video files, such as... Figure 3 As shown, the device 30 includes: a document type determination module 301, a processing time determination module 302, and a compliance detection module 303.

[0083] The file type determination module 301 is used to determine the file type of the dual-recording video file based on the source information of the dual-recording video file to be processed.

[0084] The processing time determination module 302 is used to determine the business processing time of the user corresponding to the suspicious video file if the file type is a suspicious video file.

[0085] The compliance detection module 303 is used to perform compliance detection on the suspicious video file based on the business processing time and the preset fault tolerance time.

[0086] This application embodiment determines the file type of the dual-recording video file based on the source information of the file to be processed. In the case of a suspicious video file, it determines the business processing time of the user corresponding to the suspicious video file. The suspicious video file is then processed according to the business processing time and a preset error tolerance time range, thereby completing the compliance detection of the dual-recording video file. This method of determining the file type through the source information achieves the effect of initially filtering suspicious video files and quickly classifying dual-recording video files. The setting of the error tolerance time range solves the problem that video files cannot pass the compliance detection due to minor adjustments made in a short period of time after the dual-recording video file is recorded.

[0087] Furthermore, the compliance testing module includes:

[0088] The suspicious video comparison source time determination submodule is used to determine the suspicious video file as an imperfectly passed video file if the business processing time is within the fault tolerance time range, and to determine the business processing time as the comparison source time of the suspicious video file;

[0089] A suspicious video file frame extraction submodule is used to extract several image frames from the suspicious video file;

[0090] The frame watermark time determination submodule is used to determine the watermark time corresponding to several image frames using a preset watermark recognition algorithm.

[0091] The frame comparison time determination submodule is used to determine the comparison time of the suspicious video file based on the watermark time corresponding to several image frames respectively.

[0092] The Imperfect Video Compliance Detection Submodule is used to perform compliance checks on imperfect video files based on the comparison source time and comparison time.

[0093] Furthermore, the suspicious video file frame extraction submodule includes:

[0094] A keyframe extraction unit is used to extract keyframes from the suspicious video file to obtain several image frames.

[0095] The time-based frame extraction unit is used to extract a first predetermined number of image frames from the suspicious video file according to a preset time period.

[0096] The segmented frame extraction unit is used to extract a second predetermined number of image frames within a predetermined time period of the suspicious video file.

[0097] An interval frame extraction unit is used to extract a predetermined number of image frames from the suspected video file at predetermined intervals.

[0098] Furthermore, the extracted frame comparison time determination submodule includes:

[0099] The watermark time frequency sorting unit is used to determine the watermark time with the highest frequency of occurrence based on the watermark times corresponding to several image frames.

[0100] The comparison time determination unit is used to determine the watermark time that appears most frequently as the comparison time of the suspicious video file.

[0101] Furthermore, the imperfect video compliance detection submodule includes at least one of the following units:

[0102] The first imperfect video detection unit is used to determine that the imperfect video file passes the compliance test if the comparison source time and the comparison time are consistent.

[0103] The second imperfect video detection unit is used to determine that the imperfect video file fails the compliance test if the comparison source time and the comparison time are inconsistent.

[0104] Furthermore, the compliance testing module includes:

[0105] The suspicious video detection submodule is used to determine that the suspicious video file has failed the compliance test if the business processing time is not within the tolerance time range, and to mark the suspicious video file as a non-compliant video file, so as to store the non-compliant video file in the non-compliant file database and perform manual review of the non-compliant file database.

[0106] Further, the source information includes the global creation time of the dual-recording video file, the image file creation time of the image data portion of the dual-recording video file, and the audio file creation time of the audio data portion of the dual-recording video file; the file type determination module includes:

[0107] The first category determination submodule is used to determine that the file type of the dual-recording video file is a compliant file if the global creation time, the image file creation time, and the audio file creation time are the same.

[0108] The second classification determination submodule is used to determine the file type of the dual-recording video file as a suspicious video file if at least one of the global creation time, the image file creation time, and the audio file creation time is inconsistent.

[0109] The compliance detection device for dual-recorded video files in this embodiment can execute the compliance detection method for dual-recorded video files shown in Embodiment 1 of this application. The implementation principle is similar and will not be described again here.

[0110] Another embodiment of this application provides a terminal, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described compliance detection method for dual-recorded video files.

[0111] Specifically, the processor can be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0112] Specifically, the processor connects to the memory via a bus, which may include a path for transmitting information. The bus can be a PCI bus or an EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc.

[0113] The memory may be ROM or other types of static storage devices that can store static information and instructions, RAM or other types of dynamic storage devices that can store information and instructions, or EEPROM, CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0114] Optionally, the memory stores the code of the computer program that executes the solution of this application, and the execution is controlled by the processor. The processor executes the application code stored in the memory to implement the operation of the compliance detection device for dual-recording video files provided in the above embodiments.

[0115] Another embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described compliance detection method for dual-recorded video files.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0118] The above is a detailed description of the preferred embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for compliance detection of dual-recorded video files, characterized in that, include: Based on the source information of the dual-recording video file to be processed, determine the file type to which the dual-recording video file belongs; If the file type is a suspicious video file, then the business processing time of the user corresponding to the suspicious video file will be recorded. Based on the business processing time and the preset error tolerance time, the suspicious video files are subjected to compliance checks; The step of performing compliance checks on the suspicious video files based on the business processing time and a preset error tolerance time range includes: If the business processing time is within the fault tolerance time range, the suspicious video file is marked as an imperfectly passed video file, and the business processing time is determined as the comparison source time of the suspicious video file; Extract several image frames from the suspicious video file; Using a pre-defined watermark recognition algorithm, the watermark time corresponding to several image frames is determined. The comparison time of the suspicious video file is determined based on the watermark time corresponding to several image frames. Based on the comparison source time and the comparison time, the imperfect video file is subjected to compliance detection.

2. The method according to claim 1, characterized in that, The step of extracting several image frames from the suspicious video file includes: Keyframes were extracted from the suspicious video file to obtain several image frames; A first predetermined number of image frames are extracted from the suspicious video file according to a preset time period; Extract a second predetermined number of image frames within a predetermined time period of the suspected video file; A predetermined number of image frames are extracted from the suspicious video file at predetermined intervals.

3. The method according to claim 1, characterized in that, The step of determining the comparison time of the suspicious video file based on the watermark times corresponding to several image frames includes: Based on the watermark times corresponding to several image frames, determine the watermark time that appears most frequently. The time of the watermark that appears most frequently is used as the comparison time for the suspicious video file.

4. The method according to claim 1, characterized in that, The step of performing compliance detection on the imperfect video file based on the comparison source time and the comparison time includes at least one of the following: If the source time and the comparison time are consistent, then the imperfect video file is determined to have passed the compliance test. If the source time and the comparison time are inconsistent, then the imperfect video file is determined to have failed the compliance test.

5. The method according to claim 1, characterized in that, The step of performing compliance checks on the suspicious video files based on the business processing time and a preset error tolerance time range further includes: If the business processing time is outside the tolerance time range, the suspicious video file is determined to have failed the compliance test and is marked as a non-compliant video file. The non-compliant video files are stored in a non-compliant file database for manual review.

6. The method according to claim 1, characterized in that, The source information includes the global creation time of the dual-recording video file, the image file creation time of the image data portion of the dual-recording video file, and the audio file creation time of the audio data portion of the dual-recording video file; The step of determining the file type of the dual-recording video file based on the source information includes: If the global creation time, the image file creation time, and the audio file creation time are the same, then the file type of the dual-recorded video file is determined to be a compliant file. If at least one of the global creation time, the image file creation time, and the audio file creation time is inconsistent, then the file type of the dual-recording video file is determined to be a suspicious video file.

7. A compliance detection device for dual-recording video files, characterized in that, include: The file type determination module is used to determine the file type of the dual-recording video file based on the source information of the dual-recording video file to be processed. The processing time determination module is used to determine the processing time of the user corresponding to the suspicious video file if the file type is a suspicious video file. The compliance detection module is used to perform compliance detection on the suspicious video files based on the business processing time and the preset fault tolerance time. The compliance detection module includes: The suspicious video comparison source time determination submodule is used to determine the suspicious video file as an imperfectly passed video file if the business processing time is within the fault tolerance time range, and to determine the business processing time as the comparison source time of the suspicious video file; A suspicious video file frame extraction submodule is used to extract several image frames from the suspicious video file; The frame watermark time determination submodule is used to determine the watermark time corresponding to several image frames using a preset watermark recognition algorithm. The frame comparison time determination submodule is used to determine the comparison time of the suspicious video file based on the watermark time corresponding to several image frames respectively. The Imperfect Video Compliance Detection Submodule is used to perform compliance checks on imperfect video files based on the comparison source time and comparison time.

8. An electronic device, characterized in that, It includes: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: perform the compliance detection method for dual-recorded video files according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the compliance detection method for dual-recorded video files as described in any one of claims 1-6.

Images