Transaction backtracking method and device based on video stream and storage medium

Abstract

The invention discloses a transaction backtracking method and device based on a video stream and a storage medium, and relates to the field of financial science and technology. The method comprises the steps that under the condition of user authorization, when it is detected that a user conducts one-time touch operation in a transaction interface, a screenshot image of the transaction interface is collected, and the collection moment is recorded; the method comprises the following steps: after a user finishes a transaction through N times of touch operation, generating an image sequence from acquired N screenshot images, and generating a time sequence from N acquisition moments corresponding to the N screenshot images; deleting a target screenshot image in the image sequence according to the time sequence, and taking an image sequence formed by the remaining screenshot images as a target image sequence; generating a video stream according to the target image sequence; and the transaction behavior information of the user is backtracked according to the video stream. According to the method and the device, the technical problem of low analysis efficiency of transaction backtracking caused by overlarge data volume of the screen recording video due to the existence of a large number of redundant images in the transaction screen recording video in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and more specifically, to a transaction backtracking method, device, and storage medium based on video streaming. Background Art

[0002] Currently, more and more scenarios in industries such as banking, finance, insurance, retail, and e-commerce require the tracing and analysis of customer behavior. For example, when a customer withdraws money from a bank ATM or buys goods at a 24-hour convenience store, it is necessary to record customer behavior and consumption records. These behaviors and records can be reviewed and analyzed through video playback.

[0003] In traditional video playback, it is impossible to call and capture the customer's behavior in the video. However, through transaction backtracking video, the customer's behavior during the transaction process can be recorded. For example, when a customer withdraws money from an ATM, the customer can enter the password, insert the bank card, press the withdrawal amount, and take out the banknotes. The video playback here can clearly record the complete process of the customer's withdrawal, including the customer entering the password, the withdrawal amount, etc., rather than just recording the final withdrawal result. However, in traditional technology, the photos used to record the customer's behavior during the transaction process always have a lot of redundancy, resulting in too much screen recording video data, which results in low analysis efficiency of transaction backtracking.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The main purpose of the present application is to provide a transaction backtracking method, device and storage medium based on video stream, so as to at least solve the technical problem in the prior art that due to the presence of a large number of redundant images in the transaction screen recording video, the amount of screen recording video data is too large, resulting in low analysis efficiency of transaction backtracking.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of an embodiment of the present application, a transaction backtracking method based on video stream is provided, including: with user authorization, each time a touch operation of the user in the transaction interface is detected, a screenshot image of the transaction interface is collected and the collection time is recorded; after detecting that the user ends the transaction through N touch operations, the N collected screenshot images are used to generate an image sequence, and the N collection times corresponding to the N screenshot images are used to generate a time sequence, wherein N is an integer greater than 1; the target screenshot image in the image sequence is deleted according to the time sequence, and the image sequence composed of the remaining screenshot images is used as the target image sequence, wherein the target screenshot image is determined by the collection interval duration of at least two adjacent screenshot images in the image sequence; a video stream is generated according to the target image sequence; and the user's transaction behavior information is backtracked based on the video stream.

[0007] Optionally, after detecting that the user completes the transaction through N touch operations, the N captured screenshot images are used to generate an image sequence, and the N capture moments corresponding to the N screenshot images are used to generate a time sequence, including: taking the screenshot image captured when the user performs the j-th touch operation as the j-th screenshot image in the image sequence, where j is a positive integer less than or equal to N; and taking the capture moment corresponding to the j-th screenshot image as the j-th moment in the time series.

[0008] Optionally, before deleting the target screenshot image in the image sequence according to the time series and taking the image sequence composed of the remaining screenshot images as the target image sequence, the transaction backtracking method based on video stream also includes: calculating the interval duration between each two adjacent moments in the time series to obtain N-1 interval durations; forming a first time series with the N-1 interval durations and the value 0, wherein the value 0 is the first element of the first time series, and the kth interval duration among the N-1 interval durations is the k+1th element in the first time series, wherein k is a positive integer less than or equal to N-1; and determining the target screenshot image in the image sequence according to the first time series.

[0009] Optionally, determining a target screenshot image in an image sequence according to a first time series includes: performing multiple target operations on the first time series until the first N-1 elements in the first time series all participate in the target operation, wherein each target operation is used to calculate the sum of a first element and a second element of the first time series, and determining to delete the second element or move the first element and the second element to a target set based on the sum; moving the last element in the first time series to the target set; and determining the target screenshot image in the image sequence according to the target set.

[0010] Optionally, the target screenshot image in the image sequence is determined according to the target set, including: when the target set includes the g-th element of the first time sequence, taking the g-th screenshot image in the image sequence as a non-target screenshot image, wherein g is a positive integer less than or equal to N; when the target set does not include the g-th element in the first time sequence, taking the g-th screenshot image in the image sequence as the target screenshot image.

[0011] Optionally, each target operation includes: calculating the sum of the first element and the second element of the first time series; detecting whether the sum is greater than a preset threshold; if the sum is greater than the preset threshold, deleting the second element and updating the first time series; if the sum is less than or equal to the preset threshold, moving the first element and the second element to the target set and updating the first time series.

[0012] Optionally, the transaction backtracking method based on video streaming also includes: after obtaining the first time sequence updated after the xth target operation, starting the x+1th target operation according to the first time sequence, wherein x is an integer greater than 1 and the xth target operation is not the last target operation.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of an embodiment of the present application, a transaction backtracking device based on video stream is further provided, including: a collection unit, which, with user authorization, collects a screenshot image of the transaction interface and records the collection time each time it detects that the user performs a touch operation in the transaction interface; a first generation unit, which, after detecting that the user ends the transaction through N touch operations, generates an image sequence with the N collected screenshot images, and generates a time sequence with the N collection times corresponding to the N screenshot images, wherein N is an integer greater than 1; a first processing unit, which deletes the target screenshot image in the image sequence according to the time sequence, and uses the image sequence composed of the remaining screenshot images as the target image sequence, wherein the target screenshot image is determined by the collection interval duration of at least two adjacent screenshot images in the image sequence; a second generation unit, which generates a video stream according to the target image sequence; and a second processing unit, which traces back the user's transaction behavior information based on the video stream.

[0014] According to another aspect of an embodiment of the present application, an electronic device is further provided, including: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned transaction backtracking method based on video stream is executed when the program is running.

[0015] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned video stream-based transaction backtracking method.

[0016] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned video stream-based transaction backtracking method when executed by a processor.

[0017] In an embodiment of the present application, first, with the user's authorization, each time the user is detected to perform a touch operation in the transaction interface, a screenshot image of the transaction interface is collected and the collection time is recorded, then after it is detected that the user has completed the transaction through N touch operations, the N collected screenshot images are used to generate an image sequence, and the N collection times corresponding to the N screenshot images are used to generate a time sequence, wherein N is an integer greater than 1, and then the target screenshot image in the image sequence is deleted according to the time sequence, and the image sequence composed of the remaining screenshot images is used as the target image sequence, wherein the target screenshot image is determined by the collection interval duration of at least two adjacent screenshot images in the image sequence, and then a video stream is generated according to the target image sequence, and finally the user's transaction behavior information is traced back based on the video stream.

[0018] As can be seen from the above content, this application ensures that it runs after the user's explicit authorization and respects user privacy and data security. In the process of user interaction with the transaction interface, every touch screen event is monitored and captured in real time. Whenever a touch operation is detected, a screenshot operation is immediately executed to capture the image of the current transaction interface (screenshot image) and record the corresponding acquisition time, ensuring the real-time recording of user behavior and providing a data basis for subsequent video generation and backtracking.

[0019] Secondly, the user's touch operation is continuously monitored until the transaction completion signal is detected. At this time, all the N screenshots collected are used to generate an image sequence in the order of operation. At the same time, the acquisition time corresponding to each screenshot image also forms a time series, where N is the total number of touch operations performed by the user during the transaction process, which must be an integer greater than 1. The combination of image sequence and time series provides the necessary time and space information for subsequent data processing and video synthesis.

[0020] In addition, in order to further optimize the amount of video data, a data filtering operation is introduced. First, the interval between each two adjacent moments in the time series is calculated to form a set of screenshot time differences. Subsequently, these time differences are analyzed by algorithms to identify and filter out high-frequency screenshot data in a short period of time to reduce meaningless repeated images, thereby significantly reducing the size of the video file. After the filtering operation, the retained screenshot images are combined into a target image sequence to prepare selected data for video generation.

[0021] Finally, a continuous and playable video stream is generated using the target image sequence and its corresponding display duration information. This video stream not only contains all the key operations of the user, but also ensures the smoothness and comprehensibility of the video through the previous filtering steps, while greatly compressing the data volume. The generated video stream can be further used to trace back and analyze the user's transaction behavior information, providing an effective supervision and auditing tool for commercial organizations, and also significantly optimizing user experience and data management.

[0022] It can be seen that through the technical solution of the present application, the purpose of efficiently and accurately recording the user's operation trajectory during the transaction process while ensuring the integrity and clarity of the video backtracking is achieved, thereby achieving the technical effect of high-precision recording and video backtracking of touch operations during the transaction process, and further solving the technical problem in the prior art that due to the presence of a large number of redundant images in the transaction screen recording video, the amount of screen recording video data is too large, resulting in low analysis efficiency of transaction backtracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 A hardware structure block diagram of a computer terminal for implementing a transaction backtracking method based on video stream is shown;

[0025] Figure 2 is a flowchart of an optional video stream-based transaction backtracking method according to an embodiment of the present application;

[0026] Figure 3 It is a structural composition flow chart of an optional transaction backtracking method based on video stream according to an embodiment of the present application;

[0027] Figure 4 is a flowchart of an optional method for generating a retrospective video based on a time series operation trajectory according to an embodiment of the present application;

[0028] Figure 5 It is a flowchart of the steps of sensing, collecting and filtering controls in an optional video stream-based transaction backtracking device according to an embodiment of the present application;

[0029] Figure 6 is a schematic diagram of a transaction backtracking device based on video stream provided according to an embodiment of the present application;

[0030] Figure 7 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] It should also be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are 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 relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0034] According to an embodiment of the present application, a method embodiment of a transaction backtracking method based on video streaming is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] It should be noted that a transaction backtracking system based on video stream can be used as the execution subject of the transaction backtracking method based on video stream in the embodiment of the present application. It is understandable that the transaction backtracking method based on video stream provided in the embodiment of the present application can also be executed by other systems or devices, and the embodiment of the present application does not specifically limit this.

[0036] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a transaction backtracking method based on video stream is shown. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0037] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be fully or partially integrated into any of the other components in the computer terminal 10 (or mobile device). As in the video stream-based transaction backtracking method involved in the embodiments of the present application, the data processing circuit serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the video stream-based transaction backtracking method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned video stream-based transaction backtracking method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0039] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0041] Under the above operating environment, this application provides Figure 2 The transaction backtracking method based on video streaming is shown. Figure 2 FIG. 1 is a flowchart of an optional video stream-based transaction backtracking method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0042] Step S201, with user authorization, every time a touch operation of the user in the transaction interface is detected, a screenshot image of the transaction interface is captured and the capture time is recorded.

[0043] Optionally, the first condition of the transaction backtracking system based on video streaming is to obtain the explicit authorization of the end user. This step strictly complies with data protection and privacy regulations to ensure that the user is aware of and agrees to the monitoring and data collection of his or her touch interaction behavior in the transaction interface.

[0044] Optionally, whenever the video stream-based transaction backtracking system detects that the user performs a touch operation in the transaction interface, the screenshot function is immediately triggered to capture the current state of the transaction interface with high fidelity to form a screenshot image.

[0045] Optionally, a transaction backtracking system based on video streaming accurately records the capture moment of the screenshot image, that is, the exact time point when the event occurred, and saves the timestamp information with millisecond-level accuracy, providing crucial raw data for subsequent event backtracking and behavior analysis, ensuring the complete recording and high-precision playback of the operation trajectory.

[0046] Step S202, after detecting that the user ends the transaction through N touch operations, generating an image sequence from the N captured screenshot images, and generating a time sequence from the N capture moments corresponding to the N screenshot images, where N is an integer greater than 1.

[0047] Optionally, when the transaction backtracking system based on video stream detects that the user has completed the transaction process through a series of N consecutive touch operations, marking the logical end point of the transaction event, the system integrates the N screenshot images previously collected into an ordered image sequence. The construction of the image sequence provides a structured time point image data set for subsequent data processing and video synthesis, where N is defined as an integer greater than 1, ensuring the integrity and richness of the transaction operation sequence.

[0048] Optionally, a full set of screenshot images (i.e., N screenshot images): P1, P2, P3...P(i-1), P(i), P(i+1)...Pn.

[0049] Optionally, the transaction backtracking system based on video stream generates a time series, which contains N precise acquisition moments, corresponding to the capture moments of N screenshot images. Each element of the time series is recorded with millisecond accuracy, providing a high-precision time reference for subsequent analysis. The combination of this time series and image sequence constructs a spatiotemporal coordinate system for transaction behavior, where N is greater than 1, ensuring the detailed record of multi-touch operations and time points, and providing key time clues for the precise backtracking of the system and event reproduction.

[0050] Optionally, a full set of screenshot moments (i.e., N acquisition moments generate a time series): T1, T2, T3...T(i-1), T(i), T(i+1)...Tn.

[0051] Step S203, deleting the target screenshot images in the image sequence according to the time sequence, and taking the image sequence composed of the remaining screenshot images as the target image sequence.

[0052] Optionally, the transaction backtracking system based on video stream removes redundant target screenshot images in the image sequence according to the interval distribution of the screenshot image acquisition time in the time series. The system determines the changes between images by analyzing the time difference between the acquisition times of consecutive screenshot images, so that the deleted images do not contain substantial operation information.

[0053] Optionally, after filtering, the remaining screenshot images form a refined image sequence containing key operation information, which is formally defined as the target image sequence. The target image sequence not only removes redundancy, retains the dynamic changes of transaction behavior and the key moments of user operations, but also greatly reduces the amount of data and improves the efficiency and resource utilization of video retracing.

[0054] Step S204: generating a video stream according to the target image sequence.

[0055] Optionally, the video stream-based transaction backtracking system efficiently generates a continuous, low-data-volume video stream based on the target image sequence. The process of generating the video stream makes full use of the streamlined image sequence, where each frame of the image represents a key moment of the user's transaction behavior, and the time series analysis has been used to ensure that the images contain substantial change information.

[0056] Optionally, the system accurately connects a series of images seamlessly in chronological order to form a smooth video stream, while significantly compressing the overall data volume of the video through early optimization strategies.

[0057] Step S205, tracing back the user's transaction behavior information based on the video stream.

[0058] Optionally, the transaction backtracking system based on video stream utilizes the generated video stream with low data volume and high information density to accurately backtrack the transaction behavior information of the user.

[0059] Optionally, based on the close association between each frame image and the time series in the video stream, through frame-by-frame analysis of the video stream and synchronous playback of the time reference, the user's operation trajectory in the transaction interface can be reconstructed, including the position of the touch point, the order of operations and the duration of each operation step.

[0060] It can be seen from the contents of steps S201 to S205 that in an embodiment of the present application, first, with the user's authorization, each time the user is detected to perform a touch operation in the transaction interface, a screenshot image of the transaction interface is collected and the collection time is recorded, and then after it is detected that the user has ended the transaction through N touch operations, the N collected screenshot images are used to generate an image sequence, and the N collection times corresponding to the N screenshot images are used to generate a time sequence, wherein N is an integer greater than 1, and then the target screenshot image in the image sequence is deleted according to the time sequence, and the image sequence composed of the remaining screenshot images is used as the target image sequence, wherein the target screenshot image is determined by the collection interval duration of at least two adjacent screenshot images in the image sequence, and then a video stream is generated according to the target image sequence, and finally the user's transaction behavior information is traced back based on the video stream.

[0061] As can be seen from the above content, this application ensures that it runs after the user's explicit authorization and respects user privacy and data security. In the process of user interaction with the transaction interface, every touch screen event is monitored and captured in real time. Whenever a touch operation is detected, a screenshot operation is immediately executed to capture the image of the current transaction interface (screenshot image) and record the corresponding acquisition time, ensuring the real-time recording of user behavior and providing a data basis for subsequent video generation and backtracking.

[0062] Secondly, the user's touch operation is continuously monitored until the transaction completion signal is detected. At this time, all the N screenshots collected are used to generate an image sequence in the order of operation. At the same time, the acquisition time corresponding to each screenshot image also forms a time series, where N is the total number of touch operations performed by the user during the transaction process, which must be an integer greater than 1. The combination of image sequence and time series provides the necessary time and space information for subsequent data processing and video synthesis.

[0063] In addition, in order to further optimize the amount of video data, a data filtering operation is introduced. First, the interval between each two adjacent moments in the time series is calculated to form a set of screenshot time differences. Subsequently, these time differences are analyzed by algorithms to identify and filter out high-frequency screenshot data in a short period of time to reduce meaningless repeated images, thereby significantly reducing the size of the video file. After the filtering operation, the retained screenshot images are combined into a target image sequence to prepare selected data for video generation.

[0064] Finally, a continuous and playable video stream is generated using the target image sequence and its corresponding display duration information. This video stream not only contains all the key operations of the user, but also ensures the smoothness and comprehensibility of the video through the previous filtering steps, while greatly compressing the data volume. The generated video stream can be further used to trace back and analyze the user's transaction behavior information, providing an effective supervision and auditing tool for commercial organizations, and also significantly optimizing user experience and data management.

[0065] It can be seen that through the technical solution of the present application, the purpose of efficiently and accurately recording the user's operation trajectory during the transaction process while ensuring the integrity and clarity of the video backtracking is achieved, thereby achieving the technical effect of high-precision recording and video backtracking of touch operations during the transaction process, and further solving the technical problem in the prior art that due to the presence of a large number of redundant images in the transaction screen recording video, the amount of screen recording video data is too large, resulting in low analysis efficiency of transaction backtracking.

[0066] In an optional embodiment, after detecting that the user ends the transaction through N touch operations, the transaction backtracking system based on video stream first uses the screenshot image captured when the user performs the jth touch operation as the jth screenshot image in the image sequence, where j is a positive integer less than or equal to N, and then uses the capture moment corresponding to the jth screenshot image as the jth moment in the time series.

[0067] Optionally, when the user performs the jth touch operation, the transaction backtracking system based on the video stream responds immediately and collects the current state of the transaction interface to form a screenshot image, which is then clearly identified and inserted into the image sequence as the jth screenshot image. Through this process, all N touch operations can find corresponding records in the image sequence, where N is defined as an integer greater than 1, representing the total number of touch operations, and j is a positive integer less than or equal to N, ensuring the precise correspondence between the image sequence construction and the touch event.

[0068] Optionally, each time the user performs the jth touch operation and triggers screenshot image capture, the video stream-based transaction backtracking system synchronously records the exact capture time of the operation, and the capture time information is then assigned to the time series as the jth moment.

[0069] Optionally, by closely associating the touch operation moment with the screenshot image acquisition moment, each image not only represents the state of the transaction interface, but also carries the timestamp of its generation moment, thereby constructing an accurate time coordinate system.

[0070] From the above content, it can be seen that the transaction backtracking system based on video streaming constructs an image sequence and time series that are highly consistent with the operation sequence and time attributes by limiting the one-to-one correspondence between N touch operations, N screenshot images in the image sequence, and N acquisition moments in the time series, providing solid data support for the efficient recording and backtracking of transaction behaviors.

[0071] In an optional embodiment, before deleting the target screenshot image in the image sequence according to the time series and taking the image sequence composed of the remaining screenshot images as the target image sequence, the transaction backtracking system based on the video stream first calculates the interval duration between each two adjacent moments in the time series to obtain N-1 interval durations, and then combines the N-1 interval durations and the value 0 to form a first time series, wherein the value 0 is the first element of the first time series, and the kth interval duration among the N-1 interval durations is the k+1th element in the first time series, wherein k is a positive integer less than or equal to N-1, and then determines the target screenshot image in the image sequence according to the first time series.

[0072] Optionally, each pair of adjacent acquisition moments in the user touch operation time series is precisely calculated to obtain the interval length therebetween, and generate N-1 specific values ​​reflecting the time intervals of dynamic changes in the transaction interface.

[0073] Optionally, the screenshot time difference set (i.e., N-1 interval durations): TT1, TT2, TT3, ... TT(i-1), TT(i), ... T(n-1).

[0074] Optionally, the first time series is constructed, starting with the value 0 as the first element of the sequence to represent the absolute time point when the transaction behavior starts. Subsequently, the N-1 interval durations calculated above are inserted into the time series in sequence as the k+1th element, where k is a positive integer less than or equal to N-1. Through this structural reorganization and expansion, the first time series not only fully records the dynamic rhythm of the transaction behavior, but also ensures that the number of elements matches the image sequence, providing a unified time reference for subsequent data processing and video synthesis.

[0075] Optionally, the time difference set of the supplementary screenshots (ie, the first time series) is: TT0, TT1, TT2, TT3 ... TT(i-1), TT(i), TT(i+1) ... T(n-1), in milliseconds.

[0076] Optionally, the transaction backtracking system based on video stream uses the quantitative time information in the first time series to analyze the target screenshot images in the image sequence and identify the differences between the images, thereby treating some images with very small differences as redundant information and eliminating them.

[0077] From the above content, it can be seen that the transaction backtracking system based on video streams recognizes and eliminates repeated or slightly changed target screenshot images in the image sequence through the quantification and sequence construction of time intervals, the structured reorganization and expansion of time series, and the analysis and recognition of target images, thereby achieving the simplification and optimization of image sequences.

[0078] In an optional embodiment, the transaction backtracking system based on video stream first performs multiple target operations on the first time series until the first N-1 elements in the first time series all participate in the target operation, wherein each target operation is used to calculate the sum of the first element and the second element of the first time series, and determines to delete the second element or move the first element and the second element to the target set based on the sum result, then moves the last element in the first time series to the target set, and then determines the target screenshot image in the image sequence based on the target set.

[0079] Optionally, the video stream-based transaction backtracking system introduces a cyclic iterative algorithm (ie, multiple target operations) to perform in-depth analysis and structural optimization on the first time series to determine key frames in the image sequence.

[0080] Optionally, the video stream-based transaction backtracking system ensures that the last time interval element in the first time series is unconditionally transferred to the target set. For example, the target set can be ListTT: TT0, TT3...TT(i-1), TT(i+1)...T(n-1).

[0081] Optionally, the transaction backtracking system based on video streams ultimately determines the target screenshot images in the image sequence based on the time interval information in the target set, achieving accurate mapping from time series to image sequences, and ensuring that each frame of the video stream carries key change information of the transaction behavior. At the same time, through early iterative optimization, redundant images are eliminated, the amount of video data is greatly reduced, and the efficiency of information processing and storage is improved.

[0082] From the above content, it can be seen that the transaction backtracking system based on video stream identifies and eliminates redundant image frames in the image sequence through a cyclic iterative process and analysis of time series, thereby retaining key visual information in the transaction process and ensuring high quality and low data volume of the video stream.

[0083] In an optional embodiment, the transaction backtracking system based on video stream first uses the g-th screenshot image in the image sequence as a non-target screenshot image when the target set includes the g-th element of the first time series, where g is a positive integer less than or equal to N, and then uses the g-th screenshot image in the image sequence as a target screenshot image when the target set does not include the g-th element in the first time series.

[0084] Optionally, the video stream-based transaction backtracking system performs precise image sequence screening for the first time series element contained in the target set, i.e., the g-th element (where g is a positive integer less than or equal to N, and N is the total number of touch operations).

[0085] Optionally, if the g-th time interval element already exists in the target set, it indicates that the image change corresponding to the time point has been identified by the system as insignificant, or is highly similar to the previous image. Therefore, the system marks the g-th screenshot image as a non-target screenshot image, that is, it is regarded as redundant information that can be optimized and eliminated. On the contrary, if the g-th element of the first time series is not included in the target set, the system regards the g-th screenshot image in the image sequence as a key dynamic change record, that is, the target screenshot image.

[0086] Optionally, for example, the target set may be ListTT: TT0, TT3, ... TT(i-1), TT(i+1) ... T(n-1). Then the filtered screenshot image set ListP (ie, non-target screenshot images) is: P1, P4, ... P(i), P(i+2) ... P(n). Among them, the process of determining the non-target screenshot image includes: if "TT0" in the target set belongs to the first element in the first time sequence (TT0, TT1, TT2, TT3...TT(i-1), TT(i), TT(i+1)...T(n-1)), then the first screenshot image "P1" in the image sequence (P1, P2, P3...P(i-1), P(i), P(i+1)...P(n)) is determined as a non-target screenshot image; if "TT3" in the target set belongs to the fourth element in the first time sequence (TT0, TT1, TT2, TT3...TT(i-1), TT(i), TT(i+1)...T(n-1)), then the fourth screenshot image "P4" in the image sequence (P1, P2, P3...P(i-1), P(i), P(i+1)...P(n)) is determined as a non-target screenshot image.

[0087] From the above content, it can be seen that when the g-th time interval element exists in the target set of the transaction backtracking system based on video stream, the g-th screenshot image is regarded as a non-target screenshot image and is eliminated; otherwise, the image is regarded as a target screenshot image and retained, thereby achieving the simplification of the image sequence and ensuring the high quality of the images in the video stream and the integrity of the information.

[0088] In an optional embodiment, the transaction backtracking system based on video stream first calculates the sum of the first element and the second element of the first time series, then detects whether the sum is greater than a preset threshold, and then deletes the second element and updates the first time series if the sum is greater than the preset threshold, and finally moves the first element and the second element to the target set and updates the first time series if the sum is less than or equal to the preset threshold.

[0089] Optionally, the first N-1 elements in the first time series are processed one by one by performing the target operation multiple times. Each target operation is to calculate the sum of the first element and the second element of the first time series each time, and when the sum is greater than a preset threshold, delete the second element and update the first time series; when the sum is less than or equal to the preset threshold, move the first element and the second element to the target set, and update the first time series.

[0090] Optionally, there is a calculation example:

[0091] Calculate TTT = TT i+TT (i+1) .

[0092] If TTT<300 (i.e. the preset threshold), filter out TT (i+1) , continue to calculate TTT = TTT + TT i+2 , if TTT<300, filter out TT i+2 , and so on.

[0093] If TTT>=300, then TTT=0+TT i+2 , and so on. n-1 Unconditional reservation.

[0094] The final result set is: TT0, TT3...TT i-1 TT i+1 ……T n-1 .

[0095] From the above content, it can be seen that the transaction backtracking system based on video stream achieves scientific optimization of image sequences by calculating the sum of time intervals and comparing it with the preset threshold. This process is based on the dynamic analysis of time series. Based on the threshold evaluation, the system performs time series optimization operations according to the judgment results, including the deletion and retention of time interval elements and the transfer of data to the target set, which not only achieves intelligent simplification of image sequences, but also ensures the integrity and accuracy of the data required for video stream generation.

[0096] In an optional embodiment, after obtaining the first time sequence updated after the xth target operation, the video stream-based transaction backtracking system starts the x+1th target operation according to the first time sequence, where x is an integer greater than 1 and the xth target operation is not the last target operation.

[0097] Optionally, when the transaction backtracking system based on video stream completes the xth target operation, an updated first time series is obtained. In order to further improve the quality and data efficiency of the video stream, the system immediately starts the next round, i.e., the x+1th target operation, according to the updated first time series, where x is an integer greater than 1.

[0098] Optionally, the first time series updated after the previous target operation is used as input information for the next target operation.

[0099] From the above content, it can be seen that the transaction backtracking system based on video stream achieves continuous optimization and simplification of the first time series through a cyclic iterative algorithm. Each iteration is based on the result of the previous round of target operation. By recalculating the sum value and comparing it with the threshold, it decides to retain or delete the time interval elements, scientifically adjusts the structure of the first time series, and ensures the high quality and low data volume of the video stream.

[0100] In an optional embodiment, Figure 3 The structural composition flow chart of a transaction backtracking method based on video stream according to an embodiment of the present application is shown, which can more clearly understand the structural composition of the transaction backtracking method based on video stream: the device mainly involves three components, namely, a sensing acquisition unit, a filtering unit (filtering algorithm), and a video synthesis unit. Two types of intermediate data and one type of final data will be generated during the working process, namely, a full screenshot data set, a filtered data set, and a synthesized video data.

[0101] In an optional embodiment, Figure 4 A flow chart of a method for generating a retrospective video based on an operation trajectory of a time series according to an embodiment of the present application is shown, which can more clearly understand the process of the transaction retrospective method based on video stream: first, the touch screen event of the customer is acquired in real time through the perception and acquisition unit and a screenshot is taken, while the time parameters between the events are recorded. Then, after the transaction operation is completed, the filtering unit analyzes the collected data and filters out the high-frequency screenshot data. Then the video synthesis unit synthesizes the filtered data into a video according to the corresponding display time data. Finally, the transaction terminal uploads the synthesized video to the background server for archiving.

[0102] In an optional embodiment, Figure 5 A flowchart of the steps of the perception acquisition and filtering control in a transaction backtracking device based on video stream according to an embodiment of the present application is shown, which can more clearly understand the process of perception acquisition and filtering:

[0103] The caller integrates and activates the transaction backtracking device;

[0104] The sensing and collection unit captures customer touch screen operations in real time and generates the following data:

[0105] Full screenshot collection: P1, P2, P3...P(i-1), P(i), P(i+1)...P(n);

[0106] Full screenshot time collection: T1, T2, T3...T(i-1), T(i), T(i+1)...T(n); the unit is milliseconds;

[0107] The screenshot time difference set is calculated according to TT(i)=Ti-T(i-1). The screenshot time difference set is: TT1, TT2, TT3...TT(i-1), TT(i),...T(n-1); the unit is milliseconds; since the screenshot time difference set is 1 less than the number of screenshot images, TT0 is added for one-to-one matching and the value is 0; the screenshot time difference set is: TT0, TT1, TT2, TT3...TT(i-1), TT(i), TT(i+1)...T(n-1); the unit is milliseconds;

[0108] Calculate TTT=TT(i)+TT(i+1). If TTT<300, filter out TT(i+1), and continue to calculate TTT=TTT+TT(i+2). If TTT<300, filter out TT(i+2), and so on. If TTT>=300, then TTT=0+TT(i+2), and so on. Tn-1 is retained unconditionally. The final result set is, for example: TT0, TT3...TT(i-1), TT(i+1)...T(n-1);

[0109] The image result set that needs to be retained for reverse matching. The format is as follows:

[0110] The filtered screenshot image collection ListP: P1, P4, ...Pi, P(i+2)...P(n); the filtered display result collection ListTT: TT0, TT3...TT(i-1), TT(i+1)...T(n-1);

[0111] The video synthesis unit synthesizes ListP: P1, P4, ...Pi, P(i+2) ...P(n) into a continuous playable video;

[0112] The caller uploads the video to the server for storage;

[0113] According to another aspect of the embodiment of the present application, a transaction backtracking device based on video stream is also provided, wherein: Figure 6 is a schematic diagram of an optional transaction backtracking device based on video stream according to an embodiment of the present application, such as Figure 6 As shown, the transaction backtracking device based on video stream includes: a collection unit 601, a first generation unit 602, a first processing unit 603, a second generation unit 604, and a second processing unit 605.

[0114] The acquisition unit 601, with the authorization of the user, acquires a screenshot image of the transaction interface and records the acquisition time each time it detects that the user performs a touch operation in the transaction interface; the first generation unit 602, after detecting that the user ends the transaction through N touch operations, generates an image sequence with the N acquired screenshot images, and generates a time sequence with the N acquisition times corresponding to the N screenshot images, wherein N is an integer greater than 1; the first processing unit 603, deletes the target screenshot image in the image sequence according to the time sequence, and uses the image sequence composed of the remaining screenshot images as the target image sequence, wherein the target screenshot image is determined by the acquisition interval duration of at least two adjacent screenshot images in the image sequence; the second generation unit 604, generates a video stream according to the target image sequence; the second processing unit 605, traces back the user's transaction behavior information based on the video stream.

[0115] Optionally, the transaction backtracking device based on video stream further includes: a third processing unit and a fourth processing unit. The third processing unit is used to use the screenshot image collected when the user performs the jth touch operation as the jth screenshot image in the image sequence, where j is a positive integer less than or equal to N; and the fourth processing unit is used to use the collection time corresponding to the jth screenshot image as the jth time in the time series.

[0116] Optionally, the transaction backtracking device based on video stream further includes: a calculation unit, a fifth processing unit, and a determination unit. The calculation unit is used to calculate the interval duration between each two adjacent moments in the time series to obtain N-1 interval durations; the fifth processing unit is used to combine the N-1 interval durations and the value 0 to form a first time series, wherein the value 0 is the first element of the first time series, and the kth interval duration among the N-1 interval durations is the k+1th element in the first time series, wherein k is a positive integer less than or equal to N-1; the determination unit is used to determine the target screenshot image in the image sequence according to the first time series.

[0117] Optionally, the determination unit includes: a first processing subunit, a second processing subunit and a first determination subunit. The first processing subunit is used to perform multiple target operations on the first time series until the first N-1 elements in the first time series all participate in the target operation, wherein each target operation is used to calculate the sum of the first element and the second element of the first time series, and determine to delete the second element or move the first element and the second element to the target set based on the sum; the second processing subunit is used to move the last element in the first time series to the target set; the first determination subunit is used to determine the target screenshot image in the image sequence based on the target set.

[0118] Optionally, the first determination subunit includes: a first processing module and a second processing module. The first processing module is used to use the g-th screenshot image in the image sequence as a non-target screenshot image when the target set includes the g-th element of the first time series, where g is a positive integer less than or equal to N; and the second processing module is used to use the g-th screenshot image in the image sequence as a target screenshot image when the target set does not include the g-th element in the first time series.

[0119] Optionally, the first processing subunit includes: a first calculation module, a first detection module, a third processing module, and a fourth processing module. The first calculation module is used to calculate the sum of the first element and the second element of the first time series; the first detection module is used to detect whether the sum is greater than a preset threshold; the third processing module is used to delete the second element and update the first time series when the sum is greater than the preset threshold; the fourth processing module is used to move the first element and the second element to the target set and update the first time series when the sum is less than or equal to the preset threshold.

[0120] Optionally, the transaction backtracking device based on video stream also includes: a fifth processing module, which is used to start the x+1th target operation according to the first time sequence updated after obtaining the xth target operation, wherein x is an integer greater than 1 and the xth target operation is not the last target operation.

[0121] An embodiment of the present application may provide an electronic device, Figure 7 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 7 As shown, the electronic device may include: one or more ( Figure 7 Only one is shown) a processor, a memory, a storage controller, and a peripheral interface, wherein the peripheral interface is connected to a radio frequency module, an audio module, and a display.

[0122] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0123] It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 7 The structure of the electronic device is not limited. Figure 7More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 7 Different configurations are shown.

[0124] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0125] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned transaction backtracking method based on video streaming.

[0126] According to another aspect of the present application, a computer program product is also provided, wherein the computer program product includes computer instructions, wherein when the computer instructions are executed, the device where the computer program product is located executes the above-mentioned video stream-based transaction backtracking method.

[0127] The above-mentioned embodiments or examples disclosed in the present application are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection disclosed in the present application. In the absence of contradiction, each step in a certain embodiment or example in the present application can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0128] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0129] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0134] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A transaction backtracking method based on video stream, characterized in that: include: With the authorization of the user, each time a touch operation of the user in the transaction interface is detected, a screenshot image of the transaction interface is captured and the capture time is recorded; After detecting that the user ends the transaction through N touch operations, generating an image sequence from the N captured screenshot images, and generating a time sequence from the N capture moments corresponding to the N screenshot images, where N is an integer greater than 1; Deleting target screenshot images in the image sequence according to the time sequence, and using the image sequence composed of the remaining screenshot images as the target image sequence, wherein the target screenshot image is determined by the acquisition interval length of at least two adjacent screenshot images in the image sequence; Generate a video stream according to the target image sequence; The transaction behavior information of the user is traced back based on the video stream.

2. The transaction backtracking method based on video stream according to claim 1 is characterized in that: After detecting that the user completes the transaction through N touch operations, generating an image sequence from the N captured screenshot images, and generating a time sequence from the N capture moments corresponding to the N screenshot images, including: The screenshot image collected when the user performs the j-th touch operation is used as the j-th screenshot image in the image sequence, where j is a positive integer less than or equal to N; The acquisition moment corresponding to the j-th screenshot image is taken as the j-th moment in the time series.

3. The transaction backtracking method based on video stream according to claim 1 is characterized in that: Before deleting the target screenshot image in the image sequence according to the time sequence and using the image sequence composed of the remaining screenshot images as the target image sequence, the transaction backtracking method based on video stream further includes: Calculate the interval length between each two adjacent moments in the time series to obtain N-1 interval lengths; The N-1 interval durations and the value 0 form a first time series, wherein the value 0 is the first element of the first time series, and the kth interval duration among the N-1 interval durations is the k+1th element in the first time series, wherein k is a positive integer less than or equal to N-1; A target screenshot image in the image sequence is determined according to the first time sequence.

4. The transaction backtracking method based on video stream according to claim 3 is characterized in that: Determining a target screenshot image in the image sequence according to the first time sequence includes: Performing multiple target operations on the first time series until all the first N-1 elements in the first time series participate in the target operation, wherein each target operation is used to calculate the sum of the first element and the second element of the first time series, and determining to delete the second element or move the first element and the second element to the target set according to the sum; Move the last element in the first time series to the target set; A target screenshot image in the image sequence is determined according to the target set.

5. The transaction backtracking method based on video stream according to claim 4 is characterized in that: Determining a target screenshot image in the image sequence according to the target set includes: In a case where the target set includes the g-th element of the first time series, taking the g-th screenshot image in the image sequence as a non-target screenshot image, wherein g is a positive integer less than or equal to N; In a case where the target set does not include the g-th element in the first time series, the g-th screenshot image in the image sequence is used as the target screenshot image.

6. The transaction backtracking method based on video stream according to claim 4 is characterized in that: Each of the target operations includes: Calculate the sum of the first element and the second element of the first time series; Detecting whether the summation result is greater than a preset threshold; When the sum result is greater than the preset threshold, deleting the second element and updating the first time series; When the sum result is less than or equal to the preset threshold, the first element and the second element are moved to the target set, and the first time series is updated.

7. The transaction backtracking method based on video stream according to claim 6 is characterized in that: The transaction backtracking method based on video stream also includes: After obtaining the first time sequence updated after the xth target operation, the x+1th target operation is started according to the first time sequence, wherein x is an integer greater than 1 and the xth target operation is not the last target operation.

8. A transaction backtracking device based on video stream, characterized in that: include: A collection unit, under the authorization of the user, collects a screenshot image of the transaction interface and records the collection time each time it detects that the user performs a touch operation in the transaction interface; A first generating unit, after detecting that the user ends the transaction through N touch operations, generates an image sequence from the N captured screenshot images, and generates a time sequence from the N capture moments corresponding to the N screenshot images, where N is an integer greater than 1; a first processing unit, deleting a target screenshot image in the image sequence according to the time sequence, and using an image sequence composed of the remaining screenshot images as a target image sequence, wherein the target screenshot image is determined by a capture interval duration of at least two adjacent screenshot images in the image sequence; A second generating unit, generating a video stream according to the target image sequence; The second processing unit traces back the transaction behavior information of the user according to the video stream.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the transaction tracing method based on video stream according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the transaction backtracking method based on video stream as described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the transaction backtracking method based on video stream described in any one of claims 1 to 7 are implemented.

Images