Video analysis method and device, equipment and medium

Abstract

The embodiment of the invention relates to a video analysis method and device, equipment and a medium, and the method comprises the steps: responding to a video playback operation, obtaining a target recorded video which is a video obtained by carrying out screen recording on an interface of a running target webpage or a target application program, inputting the target recorded video into a video analysis model, and outputting to obtain a corresponding target video summary and a linkage analysis suggestion, the linkage analysis suggestion being used for guiding other function modules in the recording analysis tool to perform linkage analysis processing, and displaying the target recorded video, the target video summary and the linkage analysis suggestion on a video detail page. By adopting the technical scheme, the time of viewing the video from the beginning by the user is saved, the information acquisition efficiency and the video analysis effect of the recording analysis tool are improved, the linkage path of video analysis and other functions is shortened, the linkage effect is effectively improved, the opportunity of using other functional modules by the user is expanded, and the closed-loop analysis capability of the analysis tool is enhanced.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a video analysis method, device, equipment and medium. Background Art

[0002] In order to optimize and troubleshoot web pages or applications in a targeted manner, recording and analysis tools can currently be used to provide the ability to record, capture, store, and replay web pages or applications, providing a full-process picture of user interaction, which facilitates a more realistic and intuitive understanding of the user experience. However, the video analysis effect of the recording and analysis tool is poor, and because the linkage between different analysis functions is fixed, the linkage path between video analysis and other functions is long, and the linkage effect is poor, which needs to be improved. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a video analysis method, device, equipment and medium.

[0004] The present disclosure provides a video analysis method, the method comprising:

[0005] In response to the video playback operation, a target recorded video is obtained, wherein the target recorded video is a video obtained by recording the interface of a running target webpage or target application;

[0006] Input the target recorded video into the video analysis model, and output a corresponding target video summary and linkage analysis suggestions, wherein the linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing;

[0007] The target recorded video, the target video summary and linkage analysis suggestions are displayed on the video details page.

[0008] The present disclosure also provides a video analysis device, the device comprising:

[0009] A first acquisition module is used to acquire a target recorded video in response to a video playback operation, wherein the target recorded video is a video obtained by recording the interface of a running target webpage or target application;

[0010] An output module, used to input the target recorded video into a video analysis model, and output a corresponding target video summary and linkage analysis suggestions, wherein the linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing;

[0011] The first display module is used to display the target recorded video, the target video summary and linkage analysis suggestions on the video details page.

[0012] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the video analysis method provided in the embodiment of the present disclosure.

[0013] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the video analysis method provided by the embodiment of the present disclosure.

[0014] The technical solution provided by the embodiment of the present disclosure has the following advantages over the prior art: the video analysis solution provided by the embodiment of the present disclosure obtains the target recorded video in response to the video playback operation, wherein the target recorded video is a video obtained by recording the interface of the target web page or target application being run, the target recorded video is input into the video analysis model, and the corresponding target video summary and linkage analysis suggestion are output, wherein the linkage analysis suggestion is used to guide the use of other functional modules in the recording analysis tool for linkage analysis processing, and the target recorded video, target video summary and linkage analysis suggestion are displayed on the video details page. With the above technical solution, the recording analysis tool can generate a corresponding video summary for the screen recording video of the running web page or application, saving the time for users to view the video from the beginning, improving the efficiency of information acquisition and the video analysis effect of the recording analysis tool, and on this basis, corresponding linkage analysis suggestions can also be generated to guide users to use other functional modules in the recording analysis tool for linkage analysis processing, shortening the linkage path between video analysis and other functions, effectively improving the linkage effect, broadening the opportunities for users to use other functional modules, and enhancing the closed-loop analysis capability of the analysis tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0016] Figure 1 A schematic diagram of a flow chart of a video analysis method provided by an embodiment of the present disclosure;

[0017] Figure 2 A flowchart of another video analysis method provided by an embodiment of the present disclosure;

[0018] Figure 3 A schematic diagram of a video details page provided in an embodiment of the present disclosure;

[0019] Figure 4A schematic diagram of an event analysis page provided in an embodiment of the present disclosure;

[0020] Figure 5 A schematic diagram of the structure of a video analysis device provided in an embodiment of the present disclosure;

[0021] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0023] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0024] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0025] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] The existing linkage analysis for recorded videos is as follows: through funnel analysis, the user's behavior flow when using a web page or application can be viewed. When the user enters the "microscope" function, the corresponding screen recording video can be directly played, and some important events can be selected to generate a funnel chart to show the user's behavior path. In addition, the microscope function allows the playback of screen recording videos and can filter out users who have recorded the screen. The query results (i.e., the screen recording list) can be saved to a dashboard, and the corresponding screen recording video can be directly played back on the dashboard.

[0029] However, for the above method, the linkage between different analysis functions is fixed, and other functional modules can only be displayed in the process of displaying certain information for further analysis. If other functional modules of the recording analysis tool need to be used, multiple interfaces need to be switched repeatedly, resulting in a long linkage path between video analysis and other functions and a high learning cost.

[0030] In addition, solutions for large-model video summary capabilities are usually based on the summary of conference videos. They need to be translated into text based on the voices of the conference participants, and then the text is summarized and polished to obtain the corresponding video summary. Its essence is a process from text to optimized text, not a process from nothing to something. If the video has no dialogue and the participants only share the desktop, the video summary cannot be performed, and this type of method belongs to pure video content and there is no need to link with other pages.

[0031] In order to solve the above problems, the embodiments of the present disclosure provide a video analysis method, which is introduced below in conjunction with specific embodiments.

[0032] Figure 1 The present invention provides a flow chart of a video analysis method provided in an embodiment of the present invention. The method can be performed by a video analysis device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0033] Step 101: In response to a video playback operation, a target recorded video is obtained, wherein the target recorded video is a video obtained by recording the interface of a running target web page or target application.

[0034] The video analysis method provided in the embodiment of the present disclosure is implemented based on a recording analysis tool.

[0035] The recording and analysis tool can record any operation on the interface of any running web page or any application to obtain a recorded video to reproduce the problems in the web page or application, so as to carry out targeted optimization and troubleshooting. Such as optimization for user experience problems, analysis for user churn problems, troubleshooting for product vulnerabilities, etc. Specifically, the recording and analysis tool is a cloud-based Web screen recording, screenshot, storage, playback and live broadcast tool that is free of installation, high-performance, and has a high lossless compression ratio. The recording and analysis tool can support silent recording, and can carry out targeted troubleshooting and optimization in multiple dimensions such as product usage problems, user interface (UI) or user experience (UX) problems, functional troubleshooting, and user churn behavior analysis of web pages or applications. It supports multi-track content recording including Web interface, user operation, network request, console and error log, and can accurately restore the recorded content during playback.

[0036] Specifically, the optimization of user experience issues in the recording analysis tool is exemplified as follows: by presetting some measurement indicators in the recording analysis tool, such as angry clicks, that is, users continuously click on a small area in a short period of time, such as within 800 milliseconds, the number of clicks on a 30×30px area is greater than or equal to 4 times, which is an angry click. In the actual application scenario, the user clicked a button three times in a row and found no response, and then continued to click twice and found that the button still did not respond, resulting in a poor user experience. Through the recording analysis tool, it is concluded that there is angry click behavior in the corresponding recorded video, indicating that the button is misleading. Therefore, the recording analysis tool can determine that the button design is not reasonable by analyzing this behavior of the user. Furthermore, specific examples of the linkage analysis capabilities of the recording analysis tool are as follows: for example, the recording analysis tool can support querying specified recorded videos through event attributes, user attributes, and user group associations; the recording analysis tool can also be linked to various analysis model charts, that is, the list of users with recorded videos can be previewed preferentially through the microscope, and the recorded video can be directly played back on the current page by clicking on the corresponding recorded video; the recording analysis tool can also be linked to the dashboard, that is, the recorded videos of specified users can be saved on the dashboard.

[0037] The video playback operation refers to the triggering operation of replaying any recorded video recorded in the recording analysis tool. Exemplarily, the video playback operation includes the user's gesture control operation (such as clicking, long pressing, double-clicking, etc.), voice control operation or expression control operation on any recorded video. The present disclosure does not limit the specific form of the video playback operation. The target recorded video refers to one or more recorded videos selected by the video playback operation, and may include the interface changes of the running target web page or target application following the user's interactive operation. Among them, the target web page refers to the web page of any URL in the browser analyzed by the recording analysis tool, and the target application refers to any type of application analyzed by the recording analysis tool, for example, the target application can be a video application.

[0038] The recording and analysis tool obtains a target recorded video by recording the interface of the target web page or target application being run. The target recorded video can be a silent video or a sound video obtained by recording the interface of the target web page or target application being run, such as recording only the user's operation behavior in the target web page or target application to obtain a silent target recorded video, or recording the target web page or target application that is playing audio or video, and the target recorded video may include sound. In actual application scenarios, when a user opens a running web page or application, the recording and analysis tool first records the initial state of the page, including all visible content and layout, and then the recording and analysis tool will continue to monitor and record every rendering change on the page, and record every user operation, such as clicking a button, filling out a form, scrolling the page, etc. At the same time, in order to ensure the accuracy and smoothness of the recorded video playback, each page change and user operation will be timestamped to play back these operations in the correct order, thereby obtaining the target recorded video, so that the target recorded video includes information about page changes and user operations.

[0039] In the disclosed embodiment, the recording analysis tool obtains a target recorded video by recording the interface of a running target web page or target application, and obtains the corresponding target recorded video after receiving a video playback operation from the user for the target recorded video recorded in the recording analysis tool.

[0040] Step 102: Input the target recorded video into the video analysis model, and output the corresponding target video summary and linkage analysis suggestions. The linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing.

[0041] Among them, the video analysis model refers to a model that obtains a video summary and linkage analysis suggestions corresponding to the video by analyzing and summarizing the key content in the video. Specifically, there is no limitation on the type of video analysis model. The video analysis model can be trained based on historical recorded video samples, video summary samples corresponding to historical recorded video samples, and linkage analysis suggestion samples corresponding to historical recorded video samples. The target video summary can be a text formed by summarizing the key content in the video. Specifically, the target video summary can include a content summary of the target recorded video to indicate the key content recorded by the target recorded video. According to the target video summary, the user can understand the core key content of the target recorded video, saving the user the time to view the target recorded video from the beginning, thereby improving the analysis efficiency. The linkage analysis suggestion refers to the analysis of the analysis and processing process of the target recorded video by the recording analysis tool, and the subsequent linkage analysis and processing suggestions with other functional modules in the recording analysis tool are obtained, thereby guiding the user to use other functional modules for linkage analysis and processing.

[0042] In the disclosed embodiment, the recording analysis tool can input the target recorded video into the video analysis model, and the video analysis model performs reasoning analysis on the target recorded video to obtain a video summary corresponding to the target recorded video and a linkage analysis suggestion corresponding to the target recorded video. The user can understand the core content of the target recorded video based on the target video summary, saving the user the time of viewing the target recorded video from the beginning, improving the efficiency of information acquisition, and the user can also understand how to use other functional modules in the recording analysis tool for linkage processing based on the linkage analysis suggestion, shortening the linkage path between video analysis and other functions, effectively improving the linkage effect, expanding the user's opportunity to use other functional modules in the recording analysis tool, and increasing the closed-loop analysis capability of the analysis tool.

[0043] The video analysis model may include a summary sub-model and an analysis sub-model. For example, Figure 2 , is a flow chart of another video analysis method provided by an embodiment of the present disclosure, such as Figure 2 As shown, the above step 102 may include step 201 and step 202, which specifically include:

[0044] Step 201 inputs the target recorded video into the summary sub-model of the video analysis model to obtain a target video summary, wherein the target video summary represents the key content of the target recorded video.

[0045] Among them, the summary sub-model of the video analysis model refers to a model that summarizes the key content in the video and obtains the video summary corresponding to the video. Specifically, there is no limitation on the type of the summary sub-model of the video analysis model. The summary sub-model of the video analysis model can be trained based on historical recorded video samples and video summary samples corresponding to the historical recorded video samples.

[0046] In the disclosed embodiment, after acquiring the target recorded video, the recording analysis tool inputs the target recorded video into the video analysis model, and summarizes the target recorded video through the summary sub-model of the video analysis model to obtain a summary of the target video.

[0047] Step 201 inputs the target recorded video into the analysis sub-model of the video analysis model to obtain linkage analysis suggestions.

[0048] The analysis sub-model of the video analysis model refers to a model that obtains the corresponding linkage analysis suggestions for the video by analyzing the analysis processing process in the video. Specifically, there is no limitation on the type of the analysis sub-model of the video analysis model. The analysis sub-model of the video analysis model can be trained based on historical recorded video samples and the linkage analysis suggestion samples corresponding to the historical recorded video samples. It is specifically used to analyze the recorded video and obtain the corresponding linkage analysis suggestions.

[0049] In the disclosed embodiment, after acquiring the target recorded video, the recording analysis tool inputs the target recorded video into the video analysis model, and the analysis sub-model of the video analysis model analyzes the analysis and processing process in the target recorded video to obtain linkage analysis suggestions.

[0050] In an optional implementation, the linkage analysis suggestion may include at least one of the following: an existing analysis summary corresponding to the target recorded video, a predictive analysis suggestion, and an entry to a predictive linkage function module.

[0051] Among them, the existing analysis summary corresponding to the target recorded video can be a summary of the analysis process manually implemented by the user involved in the target recorded video. For example, in the target recorded video, the user repeatedly switches to view two tables and compares the two tables, then the existing analysis summary corresponding to the target recorded video can be: the user repeatedly switches to view the two tables and compares the differences between the two tables. The existing analysis summary corresponding to the target recorded video can be a statement only for the problems in the target recorded video, such as in an activity, a certain data is low and worthy of further analysis. The existing analysis summary corresponding to the target recorded video can be a summary of the analysis of the increase or decrease in the target recorded video, such as in the target recorded video, by clarifying the range of the object (such as from 20 percent to 35 percent), accordingly, the existing analysis summary corresponding to the target recorded video is the specific increase or decrease of the object, so as to better understand the changes in the object.

[0052] Predictive analysis suggestions refer to the next step of analysis and processing suggestions for the content in the recorded video after analyzing the recorded video through the recording analysis tool, that is, the analysis of the existing content of the target recorded video predicts what needs to be done next. If it is inefficient to compare data through tables, it is recommended to view them in groups through event analysis so that users can analyze the target recorded video without watching the target recorded video. Among them, the predictive analysis suggestions can be suggestions that need to be analyzed and processed in conjunction with other functions in the recording analysis tool, and the predictive analysis suggestions can also be suggestions that do not need to be analyzed and processed in conjunction with other functions in the recording analysis tool. For example, if there are some interfaces in the target recorded video without any operation behavior, it is recommended to enable skipping blank segments or smart filtering in the video configuration area to streamline the invalid segments in the target recorded video.

[0053] The prediction linkage function module can be a specific other function module used for subsequent analysis determined according to the prediction analysis suggestions among multiple other function modules in the recording analysis tool. The entrance of the prediction linkage function module refers to the entrance used to trigger entry into the corresponding prediction linkage function module. The entrance can be presented in any form, such as a control, button or other interactive element. In actual applications, if in the recorded video, the user repeatedly switches to view the relevant tables and compares the contents in the tables, then the recorded video is analyzed by the recording analysis tool, and the linkage analysis suggestions are displayed to give the corresponding prediction analysis suggestions, and inform which function module of the recording analysis tool can be used for analysis.

[0054] Figure 3 A schematic diagram of a video details page provided by an embodiment of the present disclosure, such as Figure 3 As shown, it is recommended to view the grouping by event analysis. At this time, the user can click the event analysis control 303 to jump to Figure 4The event analysis page shown is used to analyze the table and improve the analysis efficiency.

[0055] In the disclosed embodiment, the linkage analysis suggestion includes at least one of the existing analysis summary, predictive analysis suggestion and entrance to the predictive linkage functional module corresponding to the target recorded video. In an optional implementation, if the recording analysis tool only analyzes the process manually implemented by the user involved in the target recorded video, the linkage analysis suggestion only includes the existing analysis data corresponding to the target recorded video. In another optional implementation, if the permissions of other functional modules in the recording analysis tool are not yet open, the linkage analysis suggestion includes the existing analysis summary and predictive analysis suggestion corresponding to the target recorded video. In yet another optional implementation, if the permissions of other functional modules in the recording analysis tool are already open, the linkage analysis suggestion includes the existing analysis summary, predictive analysis suggestion and entrance to the predictive linkage functional module corresponding to the target recorded video.

[0056] In an optional implementation, the prediction linkage function module includes at least one of an event analysis module, a distribution analysis module, a retention analysis module, a conversion analysis module, a user grouping module, and an attribution analysis module.

[0057] The event analysis module is one of the most important analysis methods for data analysis. It can analyze the value impact of a certain behavior event on the enterprise. Specifically, the event analysis module supports multi-dimensional analysis of user behavior by building indicators, grouping and filtering, and various visual charts. At the same time, it provides the function of abnormal data analysis in terms of data intelligence insight to discover more impacts caused by data anomalies. Figure 3 As shown in the figure, event analysis can be used to compare the data in the table. The distribution analysis module is to divide some intervals (distribution intervals) according to the calculation results under the overall or a certain dimension (distribution analysis indicator) to view the distribution of the corresponding number of people in each interval. For example, the distribution of the number of people in the three distribution intervals of less than 2 points, 2 to 5 points, and more than 5 points of the user satisfaction index of an application is used to analyze the overall user satisfaction with the application.

[0058] The retention analysis module is a method for analyzing the user's participation or activity level within a specific time period, which helps to understand the user's behavior patterns and retention trends, thereby improving the user experience. For example, if the target recorded video is for the use of an application, the retention analysis module can analyze the user's continued use of the application within a specific time period. The conversion analysis module is mainly used to analyze the user's conversion in the process. Specifically, the entire process is first divided into steps, and then the conversion rate is used to measure the performance of each step. Finally, the problematic links are found through abnormal data indicators, so as to solve the problem and optimize the step, and finally achieve the purpose of improving the overall conversion rate. For example, if the target recorded video is an introduction to a certain object, then through the conversion analysis module, the conversion status such as the viewing status of the introduction, as well as the conversion status of each stage from the beginning to the end can be analyzed. The user grouping module refers to finding and saving users with the same attributes or the same behavior over a period of time. For example, if the target recorded video is a questionnaire for investigating user interests and intentions, the user grouping module can filter out user groups of corresponding interest and intention categories through user grouping, and the attribution analysis module is mainly used to measure the conversion contribution of multiple positions or events to the target event.

[0059] Step 103: Display the target recorded video, target video summary, and linkage analysis suggestions on the video details page.

[0060] The video details page refers to a page used to display the recorded video and information related to the core content of the recorded video. Specifically, the video details page can be a page displayed when a playback trigger operation for the recorded video is received. When the target recorded video is displayed on the video details page, the interface of the web page or the target application and each subsequent change can be reproduced to display each operation of the user.

[0061] In the disclosed embodiment, the target recorded video, target video summary and linkage analysis suggestions can be displayed in partitions in the video details page, such as displaying the target recorded video on the left side of the video details page, displaying the target video summary and linkage analysis suggestions on the right side of the video details page, displaying the target recorded video on the upper side of the video details page, and displaying the target video summary and linkage analysis suggestions on the lower side of the video details page.

[0062] like Figure 3As shown, the figure shows a video details page, in which a target recorded video is displayed. The target recorded video is displayed in the left area 304 of the video details page, and a target video summary is displayed in the right area 301 of the video details page. For example, the video mainly records the user's implementation of activity B at time A, and records 6 different channel-related data through a table. The optimal channel is selected through comparison for further activities. The right area 302 of the video details page displays linkage analysis suggestions. In addition, when the target recorded video is displayed on the video details page, a heat map can be displayed in the playback screen of the target recorded video to intuitively see which part of the target web page or target application interface is more focused on. The code corresponding to each event in the recorded video can also be displayed in the video details page to troubleshoot where problems occur during the playback of the recorded video, such as problems with the code corresponding to the event or problems with the event's embedding point.

[0063] The video analysis solution provided by the disclosed embodiment obtains the target recorded video in response to the video playback operation, wherein the target recorded video is a video obtained by recording the interface of the target web page or target application being run, the target recorded video is input into the video analysis model, and the corresponding target video summary and linkage analysis suggestion are output, wherein the linkage analysis suggestion is used to guide the use of other functional modules in the recording analysis tool for linkage analysis processing, and the target recorded video, target video summary and linkage analysis suggestion are displayed on the video details page. With the above technical solution, the recording analysis tool can generate a corresponding video summary for the screen recording video of the running web page or application, saving the user the time to view the video from the beginning, improving the information acquisition efficiency and the video analysis effect of the recording analysis tool, on this basis, the recording analysis tool can also generate corresponding linkage analysis suggestions to guide the user to use other functional modules in the recording analysis tool for linkage analysis processing, shortening the linkage path between video analysis and other functions, effectively improving the linkage effect, broadening the user's opportunities to use other functional modules, and enhancing the closed-loop analysis capability of the analysis tool.

[0064] In some embodiments, after displaying the target video summary and linkage analysis suggestions, the video analysis method may further include: responding to a trigger operation on the entry of the predictive linkage function module in the linkage analysis suggestion, obtaining analysis basic information associated with the predictive linkage function module corresponding to the target recorded video, using the predictive linkage function module to analyze and process the analysis basic information, obtain linkage analysis results, and display the linkage analysis results.

[0065] Among them, the triggering operation of the entrance of the prediction linkage function module may include gesture operation (such as click, long press, double click, etc.), voice control operation or expression control operation, etc., on the entrance of the prediction linkage function module in the video details page. The present disclosure does not limit the specific form of the triggering operation of the entrance of the prediction linkage function module. The analysis basic information refers to the original basic information that exists in the recorded video and can be subsequently linked and analyzed based on the prediction linkage function module. The analysis basic information corresponding to different prediction linkage function modules is different. Exemplarily, it is assumed that there is a table in the target recorded video, and 10 data are recorded in the table. The 10 data included in this table are the analysis basic information. The corresponding linkage analysis suggestion will give the corresponding entrance of the prediction linkage function module for processing the above 10 data. After receiving the triggering operation for the entrance of the prediction linkage function module, the above 10 data (that is, the analysis basic information associated with the prediction linkage function module corresponding to the target recorded video) can be displayed on the display interface of the corresponding prediction linkage function module.

[0066] The linkage analysis result refers to the result obtained after linkage analysis processing is performed on the basic analysis information in the recorded video using other functional modules in the recording analysis tool. Specifically, the linkage analysis result is the result obtained after the prediction linkage functional module in the recording analysis tool processes the basic analysis information in the target recorded video that is managed by the prediction linkage functional model. Continuing with the example of a table in the target recorded video that records 10 data, the linkage analysis result is the result obtained by analyzing and processing the above 10 data using the prediction linkage functional module.

[0067] In the disclosed embodiment, after receiving the trigger operation for the entry of the prediction linkage function module in the linkage analysis suggestion, the recording analysis tool obtains the analysis basic information associated with the prediction linkage function module corresponding to the target recorded video from the target recorded video, and then uses the prediction linkage function module to analyze and process the analysis basic information to obtain the linkage analysis result and display it. Specifically, the linkage analysis result can be displayed in the video details page, or on the display page corresponding to the corresponding prediction linkage function module, which is not limited in the disclosed embodiment.

[0068] Taking the prediction linkage function module as an event analysis module as an example, when the user clicks Figure 3 After the event analysis control 303 in Figure 3 The video details page shown jumps to Figure 4 The event analysis page shown is as follows Figure 4As shown, the name of the analysis basic information associated with the event module corresponding to the target recorded video, that is, Table C and Table D, is displayed in area 401, and the linkage analysis results for Table C and Table D are displayed in the form of a chart in area 402. In addition, the user can also set the analysis conditions for Table C and Table D, such as the setting of attribute values. After the analysis conditions are set, the linkage analysis results for Table C and Table D are updated and displayed in the form of a chart in area 402.

[0069] In some embodiments, multiple events corresponding to the target recorded video may also be displayed in the video details page according to event type.

[0070] Among them, an event refers to an important behavior or state change that occurs at a specific time and environment. An event can be a digital description of user behavior obtained by analyzing the interface of a web page or target application recorded in a recorded video using a recording analysis tool, or a digital description from a problem perspective. For example, in a certain application, a user performs a series of user behaviors such as clicking and previewing on a certain interface. Accordingly, clicks and previews are the corresponding events in the recorded video. Event type is the result of classifying different events according to the characteristics of the event. Specifically, the event type can classify each event in the recorded video according to the user's operation behavior or the problems involved, and divide each event in the recorded video into multiple event types. For example, according to the user's operation behavior, the time type can include clicks, inputs, scrolls, etc. This classification method can better reflect the specific behavior patterns of users when using pages or applications.

[0071] like Figure 3 As shown, the recording analysis tool displays the events in the target recorded video according to the event type, such as click, input, and browse in area 306. Specifically, by analyzing the user's click behavior, it is possible to understand which functions in the page are frequently used, or which controls are invalid controls.

[0072] In the disclosed embodiment, multiple events corresponding to the target recorded video can be displayed according to the event type in the video details page, so as to more intuitively distinguish the events of different event types in the target recorded video. Specifically, multiple events corresponding to the target recorded video can be displayed below the linkage analysis suggestion, so as to facilitate viewing of each event corresponding to the target recorded video, such as Figure 3 As shown, events in the target recorded video are displayed in an area (ie, area 306 ) below area 302 according to event types.

[0073] Furthermore, the recording analysis tool may determine a corresponding event identifier according to the event type of each event, and display multiple events and the event identifier corresponding to each event.

[0074] In the embodiments of the present disclosure, an event identifier refers to a label used to uniquely identify and distinguish a specific event. Specifically, a corresponding event identifier is assigned to each event by defining an event type, so that the event type of the corresponding event can be determined by the event identifier. For example, by displaying multiple events and the event identifiers corresponding to each event, the events are associated with the corresponding event identifiers, thereby improving the efficiency of viewing each event.

[0075] In order to better distinguish different types of events, in an optional implementation, different event types may correspond to different event identifiers, and the event identifiers are represented by target graphics with a filled color.

[0076] The target graphic can refer to any graphic used to identify an event, such as a circle, triangle, square, etc. In order to more intuitively distinguish different types of events, target graphics with filled colors can be used to represent events corresponding to different event types. Figure 3 , Figure 3 The circle in the middle right area corresponds to the target graphic. By setting the color of the circle, you can distinguish the events corresponding to different event types without checking the specific event names.

[0077] In order to facilitate the viewing of events of a specific event type, in an optional implementation, at least two events with the same event identifier among multiple events can be combined to obtain an event group, and a corresponding event progress bar can be constructed at the time point of the target recording video according to the at least two events included in each event group, and multiple event progress bars corresponding to the multiple event groups can be displayed, wherein the number of event groups is multiple.

[0078] Among them, an event group refers to a collection of events of the same event type. For example, if there are 20 click events in the target recorded video, the recording analysis tool can construct the 20 click events in the target recorded video into an event group. The event progress bar refers to a visual element used to display the progress of events. In order to better display the position of each event in the event group in the target recorded video, the recording analysis tool can construct a corresponding event progress bar for each event included in the event group at the time point of the target recorded video. The length of the event progress bar can be the same as the length of the progress bar of the target recorded video, and the length of the event progress bar can also be proportional to the progress bar of the target video.

[0079] Continue to refer Figure 3, under the playback screen of the target recorded video, there are displayed an event progress bar corresponding to the click event group, an event progress bar corresponding to the input event group, and an event progress bar corresponding to the browse event group. Taking the click event group as an example, specifically, the progress bar of the click event group is synchronized with the progress bar of the target recorded video, and the time point of the corresponding click event in the target recorded video is displayed in the progress bar of the click event group.

[0080] In order to intuitively view the time point at which the event included in the corresponding event group is located in the event progress bar, in an optional implementation, the event progress bar is filled with an event identifier at the time point at which the event included in the corresponding event group is located, wherein the identifier filled at the time point is used to identify the position at which the corresponding event in the event group occurs.

[0081] Specifically, an event identifier refers to a label used to uniquely identify and distinguish a specific event. The event identifier filled in at the time point where the event occurs can be the same as the event identifier of the corresponding event, or it can be different from the event identifier of the corresponding event.

[0082] Furthermore, in order to quickly reproduce the corresponding event from the target recorded video, in an optional implementation, in response to a selection operation of a target event among multiple events, the playback progress of the target recorded video is switched from the current frame to a target frame corresponding to the target event.

[0083] The selection operation refers to a trigger operation for selecting any event in the target recorded video, and the selection operation includes a user's gesture operation (such as click, long press, double click, etc.) on any event, a voice control operation, or an expression control operation, etc. The present disclosure does not limit the specific form of the selection operation, and the target frame refers to a video frame in the target recorded video corresponding to the target event.

[0084] Continue to refer Figure 3 , taking the target event as a click event as an example, Figure 3 As shown, the time point when the click event occurs is 00:12 seconds. Accordingly, the video frame corresponding to the click event is the video frame corresponding to the 12th second in the target recorded video. That is, after receiving the user's selection operation for the click event, the recording analysis tool can switch the current frame of the target recorded video playback to the 12th second to improve the viewing efficiency. In actual application scenarios, for example, if an abnormality occurs at the position corresponding to event A, the user can directly jump the playback progress of the target recorded video to the abnormal position corresponding to event A through the selection operation of event A, thereby improving the viewing efficiency of the abnormality.

[0085] In the disclosed embodiment, after receiving a selection operation for a target event among multiple events, the recording analysis tool switches the playback progress of the target recorded video from the current frame to the target frame corresponding to the target event, thereby being able to quickly reproduce the corresponding event from the target video and improving the efficiency of information acquisition.

[0086] Figure 5 The structure diagram of a video analysis device provided by an embodiment of the present disclosure is shown in FIG. 1 , which can be implemented by software and / or hardware and can generally be integrated into an electronic device. Figure 5 As shown, including:

[0087] A first acquisition module 501 is used to acquire a target recorded video in response to a video playback operation, wherein the target recorded video is a video obtained by recording the interface of a running target web page or target application;

[0088] Output module 502, used for inputting the target recorded video into the video analysis model, and outputting the corresponding target video summary and linkage analysis suggestions, wherein the linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing;

[0089] The first display module 503 is used to display the target recorded video, the target video summary and linkage analysis suggestions on the video details page.

[0090] The video analysis model includes a summary sub-model and an analysis sub-model, and the output module 502 includes:

[0091] A first input submodule, configured to input the target recorded video into the summary submodel of the video analysis model to obtain the target video summary, wherein the target video summary represents the key content of the target recorded video;

[0092] The second input submodule is used to input the target recorded video into the analysis submodel of the video analysis model to obtain the linkage analysis suggestion.

[0093] In an optional implementation, the linkage analysis suggestion includes at least one of the following: an existing analysis summary corresponding to the target recorded video, a predictive analysis suggestion, and an entry to a predictive linkage function module.

[0094] In an optional implementation, the prediction linkage function module includes at least one of the following: an event analysis module, a distribution analysis module, a retention analysis module, a conversion analysis module, a user grouping module, and an attribution analysis module.

[0095] In an optional implementation, the device further includes:

[0096] A second acquisition module, configured to, in response to a triggering operation on an entry of a prediction linkage function module in the linkage analysis suggestion, acquire analysis basic information associated with the prediction linkage function module corresponding to the target recorded video;

[0097] The processing module is used to use the prediction linkage function module to analyze and process the analysis basic information, obtain the linkage analysis result, and display the linkage analysis result.

[0098] In an optional implementation, the device further includes:

[0099] The second display module is used to display multiple events corresponding to the target recorded video according to event types on the video details page.

[0100] In an optional implementation, the second display module includes:

[0101] A determination submodule, used to determine a corresponding event identifier according to the event type of each of the events;

[0102] The display submodule is used to display the multiple events and the event identifiers corresponding to the events.

[0103] In an optional implementation manner, different event types correspond to different event identifiers, and the event identifiers are represented by target graphics with a filled color.

[0104] In an optional implementation, the device further includes:

[0105] a combining module, configured to combine at least two events with the same event identifier among the multiple events to obtain an event group, wherein the number of the event groups is multiple;

[0106] A construction module, configured to construct a corresponding event progress bar at a time point of the target recording video according to at least two events included in each event group;

[0107] The third display module is used to display multiple event progress bars corresponding to the multiple event groups.

[0108] In an optional implementation, the event progress bar is filled with event identifiers at positions corresponding to the time points of the events included in the event group.

[0109] In an optional implementation, the device further includes:

[0110] The switching module is used to switch the playback progress of the target recorded video from the current frame to the target frame corresponding to the target event in response to the selection operation of the target event among the multiple events.

[0111] The video analysis device provided in the embodiments of the present disclosure can execute the video analysis method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0112] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which implements the video analysis method provided by any embodiment of the present disclosure when executed by a processor.

[0113] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0114] The following specific reference Figure 6 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The electronic device 600 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0115] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0116] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0117] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the video analysis method of the embodiment of the present disclosure are performed.

[0118] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0119] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0120] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0121] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a target recorded video in response to a video playback operation, wherein the target recorded video is a video obtained by recording the interface of a running target web page or target application; inputs the target recorded video into a video analysis model, and outputs a corresponding target video summary and linkage analysis suggestions, wherein the linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing; and displays the target recorded video, the target video summary and the linkage analysis suggestions on a video details page.

[0122] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0123] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0124] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0125] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0126] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0128] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0129] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0130] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A video analysis method, characterized in that: include: In response to the video playback operation, a target recorded video is obtained, wherein the target recorded video is a video obtained by recording the interface of a running target webpage or target application; Input the target recorded video into the video analysis model, and output a corresponding target video summary and linkage analysis suggestions, wherein the linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing; The target recorded video, the target video summary and linkage analysis suggestions are displayed on the video details page.

2. The method according to claim 1, characterized in that The video analysis model includes a summary sub-model and an analysis sub-model. The target recorded video is input into the video analysis model, and the corresponding target video summary and linkage analysis suggestions are output, including: Inputting the target recorded video into the summary sub-model of the video analysis model to obtain the target video summary, wherein the target video summary represents the key content of the target recorded video; The target recorded video is input into the analysis sub-model of the video analysis model to obtain the linkage analysis suggestion.

3. The method according to claim 1 or 2, characterized in that: The linkage analysis suggestion includes at least one of the following: an existing analysis summary corresponding to the target recorded video, a predictive analysis suggestion, and an entry to a predictive linkage function module.

4. The method according to claim 3, characterized in that The prediction linkage function module includes at least one of the following: an event analysis module, a distribution analysis module, a retention analysis module, a conversion analysis module, a user grouping module, and an attribution analysis module.

5. The method according to claim 1, characterized in that After displaying the target video summary and linkage analysis suggestions, the method further includes: In response to a triggering operation on an entry of a prediction linkage function module in the linkage analysis suggestion, obtaining analysis basic information associated with the prediction linkage function module corresponding to the target recorded video; The prediction linkage function module is used to analyze and process the analysis basic information to obtain linkage analysis results, and the linkage analysis results are displayed.

6. The method according to claim 1, characterized in that The method further comprises: On the video details page, multiple events corresponding to the target recorded video are displayed according to event types.

7. The method according to claim 6, characterized in that On the video details page, multiple events corresponding to the target recorded video are displayed according to event type, including: Determine a corresponding event identifier according to the event type of each of the events; The multiple events and event identifiers corresponding to the events are displayed.

8. The method according to claim 7, characterized in that Different event types correspond to different event identifiers, and the event identifiers are represented by target graphics with a filled color.

9. The method according to claim 6, characterized in that After determining the corresponding event identifier according to the event type of each event, the method further includes: Combining at least two events with the same event identifier among the multiple events to obtain an event group, wherein the number of the event groups is multiple; Constructing a corresponding event progress bar at the time point of the target recording video according to at least two events included in each event group; A plurality of event progress bars corresponding to the plurality of event groups are displayed.

10. The method according to claim 9, characterized in that The event progress bar is filled with event identifiers at the positions of the time points of the events included in the corresponding event group.

11. The method according to claim 6, characterized in that The method further comprises: In response to a selection operation of a target event among the multiple events, the playback progress of the target recorded video is switched from a current frame to a target frame corresponding to the target event.

12. A video analysis device, characterized in that: include: A first acquisition module is used to acquire a target recorded video in response to a video playback operation, wherein the target recorded video is a video obtained by recording the interface of a running target webpage or target application; An output module, used to input the target recorded video into a video analysis model, and output a corresponding target video summary and linkage analysis suggestions, wherein the linkage analysis suggestions are used to guide the use of other functional modules in the recording analysis tool to perform linkage analysis processing; The first display module is used to display the target recorded video, the target video summary and linkage analysis suggestions on the video details page.

13. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the video analysis method described in any one of claims 1-11 above.

14. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the video analysis method described in any one of claims 1 to 11.

Images