Data processing method and related device

Abstract

The embodiment of the invention discloses a data processing method and a related device, attitude information of a watching object during video watching can be acquired, and an object attitude change mode of the watching object during video watching is analyzed through the attitude information, so that the attention concentration degree of the watching object during video watching can be analyzed, and the user experience is improved. Therefore, the wonderful degree corresponding to the video content can be analyzed from the perspective of the actual watching experience of the watching object, the accuracy and effectiveness of the analysis of the wonderful degree of the video content are improved, and effective video recommendation can be carried out based on the wonderful degree.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method and related devices. Background Art

[0002] Video is one of the main media for people to receive information nowadays. In order to provide viewers with a better video viewing experience, relevant personnel can analyze the excitement of the video content of each video to recommend more exciting videos to viewers.

[0003] In the related art, the analysis method of the degree of excitement is mainly to measure the degree of excitement of the video through data related to the video itself, such as the like rate and the number of views. However, these data are difficult to represent the degree of concentration of the viewers on the video content when watching the video, so it is difficult to measure the degree of excitement of the video content from the perspective of the viewers, and further difficult to recommend video content that the viewers are really interested in. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a data processing method, which can accurately analyze the excitement of video content based on the posture of the viewing object when watching the video.

[0005] The embodiments of the present application disclose the following technical solutions:

[0006] In a first aspect, an embodiment of the present application discloses a data processing method, the method comprising:

[0007] Determining a video to be analyzed, where the video to be analyzed is used to be displayed to a target object;

[0008] Acquire posture information corresponding to a target object in a viewing period of the video to be analyzed, wherein the posture information is used to characterize an object posture of the target object in the viewing period;

[0009] Determine, according to the posture information, posture change information of the object posture of the target object in the viewing period, wherein the posture change information is used to characterize a change manner of the object posture of the target object in the viewing period;

[0010] The excitement level of the video to be analyzed is determined according to the posture change information.

[0011] In a second aspect, an embodiment of the present application discloses a data processing device, the device comprising a first determining unit, a first acquiring unit, a second determining unit and a third determining unit:

[0012] The first determination unit is used to determine a video to be analyzed, and the video to be analyzed is used to be displayed to a target object;

[0013] The first acquisition unit is used to acquire posture information corresponding to the target object in a viewing period of the video to be analyzed, wherein the posture information is used to characterize the object posture of the target object in the viewing period;

[0014] The second determining unit is used to determine, based on the posture information, posture change information of the object posture of the target object in the viewing period, wherein the posture change information is used to characterize a change manner of the object posture of the target object in the viewing period;

[0015] The third determining unit is used to determine the excitement level of the video to be analyzed according to the posture change information.

[0016] In a possible implementation manner, the posture information includes eye image information, the posture change information includes blinking frequency information, and the second determining unit is specifically configured to:

[0017] determining, according to the eye image information, blinking frequency information of the target object in the viewing period, wherein the blinking frequency information is used to identify the blinking frequency of the target object in the viewing period;

[0018] The third determining unit is specifically configured to:

[0019] The excitement level corresponding to the video to be analyzed is determined according to the blinking frequency information, and the excitement level is inversely correlated with the blinking frequency.

[0020] In a possible implementation manner, the second determining unit is specifically configured to:

[0021] Determining, according to the eye image information, the eye closure degree of the target object's eyes corresponding to each moment in the viewing period;

[0022] Determining that the target object has blinked based on a process in which the eye closure degree corresponding to the eye of the target object first increases to a first degree threshold and then decreases to a second degree threshold;

[0023] Based on the number of blinks of the target object in the viewing period, blink frequency information of the target object in the viewing period is determined.

[0024] In a possible implementation, the viewing period includes a plurality of sub-periods of the same duration, the blink frequency information is used to identify the blink frequencies respectively corresponding to the plurality of sub-periods, and the third determining unit is specifically configured to:

[0025] Determine, according to the blink frequency information, a distribution diagram of the blink frequencies corresponding to the multiple sub-periods respectively;

[0026] The degree of excitement corresponding to the video to be analyzed is determined according to the distribution graph. Under the premise that the distribution graph is right-skewed, the degree of excitement is positively correlated with the kurtosis of the distribution graph and is positively correlated with the skewness of the distribution graph.

[0027] In a possible implementation, the posture change information is used to characterize the change amplitude and change frequency of the object posture of the target object in the viewing period, and the wonderfulness is inversely correlated with the change amplitude and inversely correlated with the change frequency.

[0028] In a possible implementation manner, the device further includes a second acquiring unit:

[0029] The second acquisition unit is used to acquire the voice information corresponding to the target object in the viewing period;

[0030] The third determining unit is specifically configured to:

[0031] The wonderfulness level corresponding to the video to be analyzed is determined according to the posture change information and the voice information, and the wonderfulness level is inversely correlated with the number of voices represented by the voice information.

[0032] In a possible implementation manner, the first determining unit is specifically configured to:

[0033] Acquire an initial video, wherein video content of the initial video corresponds to multiple video scenes;

[0034] The initial video is segmented at a time point when a video scene corresponding to the video content of the initial video switches to obtain a plurality of videos, and the video to be analyzed is any one of the plurality of videos.

[0035] In a possible implementation manner, the device further includes a generating unit:

[0036] The generating unit is used to generate a recommended video corresponding to the initial video according to the video to be analyzed based on the fact that the wonderfulness is greater than a preset degree threshold, and the recommended video is used to recommend the initial video.

[0037] In a third aspect, an embodiment of the present application discloses a computer device, wherein the computer device includes a processor and a memory:

[0038] The memory is used to store a computer program and transmit the computer program to the processor;

[0039] The processor is used to execute the data processing method according to any one of the instructions in the computer program;

[0040] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the data processing method described in any one of the first aspects;

[0041] In a fifth aspect, an embodiment of the present application discloses a computer program product including a computer program, which, when executed on a computer device, enables the computer device to execute the data processing method described in any one of the first aspects.

[0042] It can be seen from the above technical solution that the present application can analyze the wonderfulness of the video content from the perspective of the viewing object. Under normal circumstances, if the video content is more wonderful and has a strong attraction to the viewing object, the viewing object will have a higher degree of concentration when watching the video, and will most likely maintain the same posture. Based on this, when analyzing the wonderfulness, the present application can first determine the video to be analyzed for display to the target object, and then obtain the corresponding posture information of the target object in the viewing period of the video to be analyzed. The posture information can be used to analyze the posture changes of the target object when watching the video to be analyzed, so that the posture change information can be determined based on the posture information. The posture change information is used to characterize the change mode of the object posture of the target object in the viewing period. Thus, based on the posture change information, it can be measured whether the target object has a more concentrated attention when watching the video to be analyzed, and then the wonderfulness of the video to be analyzed can be measured, so that the wonderfulness of the video corresponding to the video can be accurately analyzed from the perspective of the object posture of the viewing object when watching the video, and then the video can be accurately recommended based on the wonderfulness, which helps to improve the video viewing experience of the viewing object. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A schematic diagram of a data processing method in an actual application scenario provided by an embodiment of the present application;

[0045] Figure 2 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0047] Figure 4 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0049] Figure 6 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0050] Figure 7 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0051] Figure 8 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0052] Fig. 9 A structural block diagram of a data processing device provided in an embodiment of the present application;

[0053] Fig.10 A structural diagram of a terminal provided in an embodiment of the present application;

[0054] Fig.11 A structural diagram of a server provided in an embodiment of the present application;

[0055] Fig.12 A schematic diagram of a data processing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The embodiments of the present application are described below in conjunction with the accompanying drawings.

[0057] In related technologies, in order to analyze the quality of video content, relevant personnel can collect objective data such as the like rate, forwarding rate, viewing rate, and completion rate of the video, and measure the quality of the video content based on these objective data.

[0058] However, on the one hand, these data are difficult to reflect the state of the viewers when watching the video, making it difficult to measure the excitement of the video from the perspective of the viewers, resulting in the analyzed excitement being difficult to fit the actual video viewing experience of the viewers. On the other hand, these data are also easy to forge and have low authenticity.

[0059] In order to solve the above technical problems, the present application provides a data processing method, which can obtain the posture information of the viewing object when watching a video, and analyze the way the viewing object's posture changes when watching the video through the posture information, so as to analyze the degree of concentration of the viewing object when watching the video, and then analyze the corresponding excitement of the video content from the perspective of the viewing object's actual viewing experience, thereby improving the accuracy and effectiveness of the analysis of the excitement of the video content, and then making effective video recommendations based on the excitement.

[0060] It is understandable that the method can be applied to a computer device, which is a computer device capable of analyzing the wonderfulness of a video, such as a terminal device or a server. The method can be executed independently by a terminal device or a server, or can be applied to a network scenario in which a terminal device and a server communicate, and is executed in cooperation with a terminal device and a server. Among them, the terminal device can be a mobile phone, a tablet computer, a laptop computer, a desktop computer and other devices. The terminal device can also include a variety of virtual reality devices, such as augmented reality (AR) devices, such as AR glasses, AR screens and other devices, and virtual reality (VR) technology (VR) devices, such as head-mounted VR glasses and other devices. The server can be understood as an application server, or a Web server. In actual deployment, the server can be an independent server, a cluster server, or a cloud server.

[0061] In order to facilitate the understanding of the technical solution provided by the present application, the data processing method provided by the present application will be introduced in detail below in combination with an actual application scenario.

[0062] See also Figure 1 , Figure 1 A schematic diagram of a data processing method in an actual application scenario provided in an embodiment of the present application. In the actual application scenario, the computer device is a server 101 with analysis capabilities.

[0063] The server 101 may first determine the video to be analyzed, and then display the video to be analyzed to the target object through the terminal device on the target object side. During the process of the target object watching the video to be analyzed, the server 101 may obtain posture information, which is used to characterize the object posture of the target object during the viewing period of the video to be analyzed.

[0064] Based on the posture information, the server 101 can determine the posture change information, which is used to characterize the change mode of the posture of the object. Since the change of the posture of the target object when watching the video to be analyzed can characterize the degree of concentration of the target object on the video to be analyzed, and the more concentrated the target object is when watching the video, the more exciting the video content can be. Therefore, the server 101 can determine the excitement of the video to be analyzed based on the change mode of the object posture represented by the posture change information, so that the excitement of the video to be analyzed can be accurately determined from the viewing experience dimension of the viewing object, and then the video can be recommended based on the excitement, so that the viewing object has a better video viewing experience.

[0065] Next, the technical solution provided by this application will be introduced in detail in conjunction with the accompanying drawings.

[0066] See also Figure 2 , Figure 2 A flowchart of a data processing method provided in an embodiment of the present application, the method comprising:

[0067] S201: Determine the video to be analyzed.

[0068] The video to be analyzed may be any video, and the video to be analyzed is used to be displayed to a target object, and the target object may be any viewing object that has video viewing experience, such as a user of a video platform.

[0069] S202: Acquire posture information corresponding to the target object during the viewing period of the video to be analyzed.

[0070] It is understandable that when the video content of the video to be analyzed is more exciting, the viewing object's concentration in watching the video to be analyzed is also higher. At this time, the viewing object's object posture changes in the process of watching the video to be analyzed are usually less. For example, when watching the video attentively, the viewing object usually blinks less and the amplitude of the object's head movement is also reduced. Based on this, the computer device can obtain the corresponding posture information of the target object in the viewing period of the video to be analyzed. The posture information is used to characterize the object posture of the target object in the viewing period. The object posture can be used to analyze the concentration of the target object when watching the video to be analyzed, and then the excitement of the video to be analyzed.

[0071] S203: Determine, according to the posture information, posture change information of the object posture of the target object in the viewing period.

[0072] Among them, the posture change information is used to characterize the way in which the object posture of the target object changes during the viewing period. The change method may include multiple dimensions, such as the change amplitude, change frequency, etc., all of which can reflect the concentration of the target object when watching the video to be analyzed.

[0073] S204: Determine the excitement level of the video to be analyzed according to the posture change information.

[0074] Through the posture change information, the computer device can analyze the concentration of the target object when watching the video to be analyzed, and then analyze the corresponding wonderfulness of the video to be analyzed. For example, when the change amplitude of the target object's posture during the viewing period is smaller, it can be said that the target object is more focused when watching the video to be analyzed, and then it can be said that the video to be analyzed has a higher degree of wonderfulness.

[0075] It can be seen from the above technical solution that the present application can analyze the wonderfulness of the video content from the perspective of the viewing object. Under normal circumstances, if the video content is more wonderful and has a strong attraction to the viewing object, the viewing object will have a higher degree of concentration when watching the video, and will most likely maintain the same posture. Based on this, when analyzing the wonderfulness, the present application can first determine the video to be analyzed for display to the target object, and then obtain the corresponding posture information of the target object in the viewing period of the video to be analyzed. The posture information can be used to analyze the posture changes of the target object when watching the video to be analyzed, so that the posture change information can be determined based on the posture information. The posture change information is used to characterize the change mode of the object posture of the target object in the viewing period. Thus, based on the posture change information, it can be measured whether the target object has a more concentrated attention when watching the video to be analyzed, and then the wonderfulness of the video to be analyzed can be measured, so that the wonderfulness of the video corresponding to the video can be accurately analyzed from the perspective of the object posture of the viewing object when watching the video, and then the video can be accurately recommended based on the wonderfulness, which helps to improve the video viewing experience of the viewing object. At the same time, since the excitement level is analyzed based on the actual performance of the viewers when watching the video, it is more difficult to falsify the data, so the data used for analysis is more accurate and real, and the analyzed excitement level is more accurate.

[0076] Next, the details of the technical solution provided in this application will be introduced in detail.

[0077] In the present application, posture information may include multiple types. In one possible implementation, the posture information may include eye image information. The computer device may analyze the excitement of the video to be analyzed by analyzing the blinking behavior of the viewing object.

[0078] Blinking is a biological instinct, but blinking can also be artificially suppressed at certain moments to minimize the loss of visual information during blinking. Because the more important the visual information is to the viewer, the more likely people are to artificially intervene to suppress blinking. Taking children as an example, when children use smartphones to play games, the frequency of eye blinking decreases and the interval between blinks increases. The specific data is: the blinking frequency decreases from 20.8 blinks / minute to 8.9 blinks / minute, the time interval between blinks becomes longer, and the interval between blinks increases from 2.9 seconds to 8.7 seconds. The specific data is as follows: Figure 3 shown. Figure 3 The horizontal axis of the data graph in the figure is different analysis situations, the vertical axis of the left figure is the blink rate (Blink rate), and the vertical axis of the right figure is the blink interval (interblink interval). In the left figure, the blink rate corresponding to contersation is the blink rate of children during conversation. The blink rate at this time is a normal blink rate, and the computer device can determine the blink rate as the baseline blink rate. The blink rate corresponding to Smartphone gaming is the blink rate of children when playing smartphone games. It can be seen from the left figure that the blink rate of children during mobile phone games has dropped significantly; in the right figure, the blink interval corresponding to contersation is the blink interval of children during conversation. The blink rate at this time is a normal blink interval, and the computer device can determine the blink rate as the baseline blink interval. The blink interval corresponding to Smartphone gaming is the blink interval of children when playing smartphone games. It can be seen from the right figure that the blink interval of children during mobile phone games has increased significantly.

[0079] Through analysis, it can be learned that the frequency of blinking by viewers will decrease when they watch content that they think is more important or involved. At the same time, the blinking action occurs synchronously with the plot of the story content. Blinking is usually suppressed during tasks that require visual attention, and when the start and end times of the task are clearly given, blinking tends to occur immediately before or after the task. During the viewing of video stories, blinking is expected to occur at clear interruptions such as scene changes. However, given that the length of the scene is unpredictable, there should also be appropriate blinking timing within the scene to prevent the temporary loss of key visual information. The article also pointed out that when multiple viewers watch the same short video story, spontaneous blinking between viewers is highly synchronized, but there is no clear connection with the scene interruption. That is, the time and frequency of blinking of people participating in the experiment are highly consistent and strongly related to the plot of the story. Synchronous blinking occurs in scenes that require less attention, such as at the end of the action, when the protagonist is not present, during long shots, and during repeated presentations of similar scenes. In contrast, no blink synchronization was observed when subjects watched background videos or listened to stories read aloud. The results suggest that humans have a biological commonality in the timing of blinking, which seeks out certain implicit (instinctively maximal payoff) timings to minimize the chance of missing critical information when watching video-like events.

[0080] Based on this, in this implementation, the posture change information may include blink frequency information. When executing step S203, the computer device may execute step S2031 (not shown in the figure). Step S2031 is a possible implementation of step S203, including:

[0081] S2031: Determine the blinking frequency information of the target object during the viewing period according to the eye image information.

[0082] The blinking frequency information is used to identify the blinking frequency of the target object in the viewing period. For example, the number of blinks of the target object in the viewing period can be analyzed based on the eye image information to further analyze the blinking frequency.

[0083] Among them, eye image information can be collected by the original depth camera, and the working principle of the original depth camera is based on 3D structured light technology. 3D structured light is an active vision technology that uses a laser projector to project patterns and captures the images formed after the objects reflect these patterns. By analyzing these images, the three-dimensional depth information of the object can be obtained. The 3D structured light projector projects more than 10,000 invisible light spots onto the face, and these light spots are evenly distributed throughout the facial area. The infrared camera is responsible for capturing the reflection patterns of these light spots and transmitting them to the image processing chip. The image processing chip analyzes these reflection patterns and calculates the position of each light spot on the face. By integrating the position information of these light spots, a three-dimensional depth map of the face can be created. The depth map contains the depth information of the face (unique facial features of different users), and this data can be used for facial feature recognition.

[0084] When executing step S204, the computer device may execute step S2041 (not shown in the figure), which is a possible implementation of step S204, including:

[0085] S2041: Determine the excitement level of the video to be analyzed according to the blink frequency information.

[0086] The excitement level is inversely correlated with the blinking frequency, that is, the lower the blinking frequency of the target object during the viewing period, the higher the concentration of the target object when watching the video to be analyzed, which further indicates that the excitement level of the video to be analyzed is higher.

[0087] For example, the computer device may characterize the degree of excitement of the video to be analyzed by an eye-attracting index, wherein the better the eye-attracting index is, the higher the degree of excitement of the video to be analyzed is. The eye-attracting index is determined based on the blinking frequency identified by the blinking frequency information, and the computer device may preset some blinking frequency thresholds, and determine the eye-attracting index of the video to be analyzed by comparing the blinking frequency information with the blinking frequency thresholds.

[0088] For example, the blinking frequency threshold may include 8 times per minute and 18 times per minute. The computer device may determine the average blinking frequency per minute of the target object based on the blinking frequency information. An average blinking frequency of more than 18 times per minute during the movie-watching process is considered to have a poor eye-catching index (level of excitement), an average blinking frequency of less than 18 times per minute and more than 8 times per minute is considered to have a medium eye-catching index (level of excitement), and an average blinking frequency of less than 8 times per minute is considered to have a good eye-catching index (level of excitement).

[0089] It is understandable that not all changes in the eye image can indicate that the target object has blinked. For example, when the viewing object has poor eyesight, he or she may squint to see more clearly, and the eye image may also change. Based on this, in a possible implementation, in order to further improve the accuracy of the wonderfulness analysis, the computer device can perform a more accurate analysis of the target object's blinking behavior.

[0090] When executing step S2031, the computer device may execute steps S20311-S20313 (not shown in the figure), where steps S20311-S20313 are a possible implementation of step S2031, including:

[0091] S20311: Determine, based on the eye image information, the eye closure degree of the target object's eyes corresponding to each moment in the viewing period.

[0092] This process can be achieved through computer vision processing. By performing computer vision processing on the collected depth data, the user's facial features can be established, including facial contours, eyes, nose, mouth and other feature points. Taking the iPhone as an example, the system library ARKit provides a more abstract way to represent facial expressions, which is called BlendShapes. Blend Shapes is technically a set of dictionaries that store the user's facial expression feature motion factors, which contains a total of 52 sets of feature motion data. ARKit will set the corresponding motion factors in real time according to the user's expression feature values ​​collected by the depth camera. These motion factors can be used to drive 2D or 3D models, which will show expressions consistent with the user in real time. ARKit provides all 52 sets of motion factors in real time, including 7 sets of left eye motion factor data, 7 sets of right eye motion factor data, 27 sets of mouth and chin motion factor data, 10 sets of eyebrow, cheek and nose motion factor data, and 1 set of tongue motion factor data. This application only focuses on eye-related motion factor data.

[0093] Each set of motion factors represents a facial expression feature recognized by ARKit. Each set of motion factors includes a locator representing a specific facial expression and a floating-point value representing the degree of expression. The range of the expression degree value is [0,1], where 0 represents no expression and 1 represents full expression. Taking the mouth as an example, the specific changes in motion factors refer to Fig.12As shown, value is the expression degree value. The larger the value, the greater the probability that the mouth is in an expressive state at this time, and vice versa. The information collected in this application is eye blinking actions, including left eye blinking (ARBlendShapeLocationEyeBlinkLeft) and right eye blinking (ARBlendShapeLocationEyeBlinkRight); the closer the blinking motion factor returned by the system is to the number 1, the greater the degree of eye closure (eyes closed); the closer the blinking motion factor returned by the system is to the number 0, the smaller the degree of eye closure (eyes are open); the computer device monitors the user's facial state 60 times per minute, that is, it returns the user's facial data every 16 to 17 milliseconds. During the children's viewing process, the left and right eye closure degree data values ​​are collected in chronological order. The specific data include: current time point (millisecond level), left eye closure state (floating point data value), and right eye closure state (floating point data value). The data is stored in a dictionary data set with the time point as the key. Collect some data such as Figure 4 Based on this data, Figure 5 The eye closure degree icon shown, where the horizontal axis is time and the vertical axis is the eye closure degree.

[0094] S20312: Determine that the target object has blinked based on a process in which the eye closure degree corresponding to the target object's eyes first increases to a first degree threshold and then decreases to a second degree threshold.

[0095] The computer device can pre-set a first degree threshold and a second degree threshold. If the eye closure degree increases to the first degree threshold, it can be said that the target object's eye closure degree is relatively high, so it can be judged that the target object is not just squinting, but has closed its eyes. If the eye closure degree decreases to the second degree threshold, it can be judged that the target object's eyes have completed an opening action, and thus it can be judged that the target object has completed a blinking action. This method can effectively avoid misidentifying a squinting action as a blinking action, thereby further improving the accuracy of the wonderfulness analysis.

[0096] For example, in Figure 5In the chart shown, the overall idea of ​​judging the blinking process is: the data value of the closed eye state gradually increases from a smaller data value to a data value close to 1, and then gradually decreases from this data value until it returns to the normal open eye state. Since eye closure is a continuous process, if the eye closure data changes too much (for example, from 0.1 to 0.9 in the next moment), it is considered invalid data; a complete blinking process should be distinguished from the squinting process, which is closing to a certain degree and then opening; the basis for judging blinking is first from the open eye state to the squinting state (the closed data interval is 0.2~0.6), and then from the squinting state to the closed state (0.6~1.0).

[0097] Figure 6 The data of blinking motion factor is counted for about one minute, where the horizontal axis is the data value of blinking closed state, and the horizontal axis is the number of data distribution. For all eye closure state data, the floating point type is converted to a decimal value with one decimal place, and whether the eye closing behavior occurs is measured based on the converted value. From the converted decimals with one place, a maximum of two data are selected, and 0.0 and 0.1. It is inferred that the motion factor of the normal open eye state is 0.1 (the result of rounding down the data) and below, and the corresponding motion factor data is in the range of 0 to 0.2. That is, when the blinking motion factor is less than 0.2, it is determined to be an open eye state, that is, the second degree threshold is 0.2, and when the blinking motion factor is greater than or equal to 0.2, it is determined to be squinting. In addition, based on the observation of a large number of blinking processes, it is concluded that the critical value for distinguishing between squinting and closed eyes is 0.6, that is, 0.6 is the first degree threshold.

[0098] S20313: Determine blink frequency information of the target object in the viewing period based on the number of blinks of the target object in the viewing period.

[0099] In a possible implementation, the computer device may also measure the overall concentration of the target object in the viewing period based on the blinking frequency distribution of the target object in the viewing period. The viewing period includes multiple sub-periods of the same duration, and the blinking frequency information is used to identify the blinking frequencies corresponding to the multiple sub-periods. When executing step S204, the computer device may execute steps S2042-S2043 (not shown in the figure), and steps S2042-S2043 are a possible implementation of step S204, including:

[0100] S2042: Determine, according to the blink frequency information, a distribution diagram of the blink frequencies corresponding to the multiple sub-periods.

[0101] The sub-time periods may be divided into time periods of 30 seconds, 60 seconds, etc., and there is no restriction here.

[0102] S2043: Determine the excitement level of the video to be analyzed according to the distribution graph.

[0103] like Figure 7 As shown in the figure, the skewness is measured relative to the normal distribution. The skewness of the normal distribution is 0, that is, if the data distribution is symmetrical, the skewness is 0. If the skewness is greater than 0, the distribution is biased to the right, that is, the distribution has a long tail on the right; if the skewness is less than 0, the distribution is biased to the left, that is, the distribution has a long tail on the left; the left or right skewness of the data distribution refers to the direction of the value tailing, not the position of the peak. At the same time, the larger the absolute value of the skewness, the more serious the deviation of the distribution.

[0104] like Figure 8 As shown in the figure, Kurtosis is a statistic that studies the steepness or smoothness of data distribution. By measuring the kurtosis coefficient, it is determined whether the data is flat or steep relative to the normal distribution. For example, the kurtosis of the normal distribution is 0, the kurtosis of the uniform distribution is -1.2 (flat), and the kurtosis of the exponential distribution is 6 (steep). When the kurtosis is ≈0, the distribution follows the normal distribution; when the kurtosis is >0, the distribution is steep; when the kurtosis is <0, the distribution is flat.

[0105] On the premise that the distribution graph is right-skewed, that is, there are more time periods with lower blinking frequency, the excitement level is positively correlated with the kurtosis of the distribution graph, and is positively correlated with the skewness of the distribution graph, that is, the higher the kurtosis, the more time periods with lower blinking frequency, and thus it can be explained that the target object is more focused when watching the video, and the corresponding excitement level of the video to be analyzed is higher; the greater the skewness of the distribution graph, the lower the blinking frequency corresponding to more time periods, and thus it can be explained that the target object is more focused when watching the video, and the corresponding excitement level of the video to be analyzed is higher.

[0106] In addition to analyzing by blinking, the computer device can also analyze in combination with other object postures. In one possible implementation, the posture change information is used to characterize the change amplitude and change frequency of the object posture of the target object in the viewing period, and the wonderfulness is inversely correlated with the change amplitude and inversely correlated with the change frequency. That is, the smaller the change amplitude and the lower the change frequency, the higher the concentration of the target object in the viewing period, so it can be judged that the wonderfulness of the video to be analyzed is higher. Among them, the object posture can include head posture, body posture, etc., which are not limited here.

[0107] In addition to judging by the object's posture, the computer device may also judge in combination with the voice information of the target object. In a possible implementation, the computer device may obtain the voice information corresponding to the target object in the viewing period. When executing step S204, the computer device may execute step S2044 (not shown in the figure). Step S2044 is a possible implementation of step S204, including:

[0108] S2044: Determine the excitement level of the video to be analyzed according to the posture change information and the voice information.

[0109] It is understandable that when the viewing object is concentrating on watching the video, he or she usually does not engage in behaviors such as chatting and talking that involve generating voice information, so the amount of voice information is relatively small. Based on this, the computer device can combine the voice information to determine whether the viewing object is concentrating on watching the video to be analyzed, and the wonderfulness is inversely correlated with the number of voices represented by the voice information, that is, the fewer the number of voices emitted by the target object during the viewing period, the more focused the target object is when watching the video to be analyzed, and thus the higher the wonderfulness of the video to be analyzed.

[0110] In a possible implementation, when executing step S201, the computer device may execute steps S2011-S2012 (not shown in the figure), where steps S2011-S2012 are a possible implementation of step S201, including:

[0111] S2011: Acquire the initial video.

[0112] The video content of the initial video corresponds to multiple video scenes, and the initial video can be any video.

[0113] S2012: Segment the initial video at a time point when a video scene corresponding to the video content of the initial video switches to obtain a plurality of videos.

[0114] Generally, when a subject watches a video of the same scene, the degree of concentration on the video is relatively uniform, so the computer device can segment the video based on the video scene, obtain multiple videos for analysis, and accurately measure the change in the degree of concentration of the target subject, and then accurately analyze the degree of excitement corresponding to each video part of the initial video. The video to be analyzed is any one of the multiple videos.

[0115] Among them, the detection of scene switching can be achieved by manually extracting features, such as calculating the color histogram similarity of adjacent frames, or directly calculating the frame difference, or using the change degree feature VH (viewport Height) of the high-frequency sub-band coefficients of each frame in the video scene to detect scene switching, wherein the calculation of the high-frequency sub-band coefficients requires the use of algorithms such as three-dimensional wavelet transform. These technologies will calculate a feature value and then compare it with the threshold. If it is greater than the threshold or less than the threshold, it is determined to be a switching frame. There are also some adaptive threshold algorithms based on the above technology, such as a video scene change detection method based on an adaptive threshold, in which the sliding window size and the preset threshold need to be set manually.

[0116] The scene switching detection technology may also adopt a detection algorithm based on the pixel domain or a detection algorithm based on the compression domain. Setting corresponding scene switching thresholds according to different scenes may improve the speed and accuracy of scene switching detection, which is not limited here.

[0117] In addition, in a possible implementation, in order to make video recommendations more effective, the computer device can select a video portion with a higher degree of excitement to generate a recommended video for video recommendation. The computer device can analyze the degrees of excitement corresponding to the multiple videos in the above manner, and based on the fact that the degree of excitement is greater than a preset degree threshold, that is, the degree of excitement corresponding to the video to be analyzed is greater than the preset degree threshold, it means that the video to be analyzed has a higher degree of excitement, and the video content corresponding to this part of the video is more attractive. At this time, the computer device can generate a recommended video corresponding to the initial video based on the video to be analyzed, and the recommended video is used to recommend the initial video, so that the recommended video can effectively attract the viewing object, thereby increasing the viewing object's willingness to watch the initial video, and achieving the recommendation of the initial video.

[0118] Based on the data processing method provided in the above embodiment, the present application also provides a data processing device, see Fig. 9 , Fig. 9 This is a structural block diagram of a data processing device provided in an embodiment of the present application. The device 900 includes a first determining unit 901, a first acquiring unit 902, a second determining unit 903, and a third determining unit 904:

[0119] The first determining unit 901 is used to determine a video to be analyzed, and the video to be analyzed is used to be displayed to a target object;

[0120] The first acquisition unit 902 is used to acquire the posture information corresponding to the target object in the viewing period of the video to be analyzed, wherein the posture information is used to represent the object posture of the target object in the viewing period;

[0121] The second determining unit 903 is used to determine, according to the posture information, posture change information of the object posture of the target object in the viewing period, wherein the posture change information is used to characterize a change manner of the object posture of the target object in the viewing period;

[0122] The third determining unit 904 is configured to determine the excitement level of the video to be analyzed according to the posture change information.

[0123] In a possible implementation, the posture information includes eye image information, the posture change information includes blink frequency information, and the second determining unit 903 is specifically configured to:

[0124] determining, according to the eye image information, blinking frequency information of the target object in the viewing period, wherein the blinking frequency information is used to identify the blinking frequency of the target object in the viewing period;

[0125] The third determining unit 904 is specifically configured to:

[0126] The excitement level corresponding to the video to be analyzed is determined according to the blinking frequency information, and the excitement level is inversely correlated with the blinking frequency.

[0127] In a possible implementation manner, the second determining unit 903 is specifically configured to:

[0128] Determining, according to the eye image information, the eye closure degree of the target object's eyes corresponding to each moment in the viewing period;

[0129] Determining that the target object has blinked based on a process in which the eye closure degree corresponding to the eye of the target object first increases to a first degree threshold and then decreases to a second degree threshold;

[0130] Based on the number of blinks of the target object in the viewing period, blink frequency information of the target object in the viewing period is determined.

[0131] In a possible implementation, the viewing period includes multiple sub-periods of the same duration, the blink frequency information is used to identify the blink frequencies corresponding to the multiple sub-periods, and the third determining unit 904 is specifically configured to:

[0132] Determine, according to the blink frequency information, a distribution diagram of the blink frequencies corresponding to the multiple sub-periods respectively;

[0133] The degree of excitement corresponding to the video to be analyzed is determined according to the distribution graph. Under the premise that the distribution graph is right-skewed, the degree of excitement is positively correlated with the kurtosis of the distribution graph and is positively correlated with the skewness of the distribution graph.

[0134] In a possible implementation, the posture change information is used to characterize the change amplitude and change frequency of the object posture of the target object in the viewing period, and the wonderfulness is inversely correlated with the change amplitude and inversely correlated with the change frequency.

[0135] In a possible implementation manner, the device further includes a second acquiring unit:

[0136] The second acquisition unit is used to acquire the voice information corresponding to the target object in the viewing period;

[0137] The third determining unit 904 is specifically configured to:

[0138] The wonderfulness level corresponding to the video to be analyzed is determined according to the posture change information and the voice information, and the wonderfulness level is inversely correlated with the number of voices represented by the voice information.

[0139] In a possible implementation manner, the first determining unit 901 is specifically configured to:

[0140] Acquire an initial video, wherein video content of the initial video corresponds to multiple video scenes;

[0141] The initial video is segmented at a time point when a video scene corresponding to the video content of the initial video switches to obtain a plurality of videos, and the video to be analyzed is any one of the plurality of videos.

[0142] In a possible implementation manner, the device further includes a generating unit:

[0143] The generating unit is used to generate a recommended video corresponding to the initial video according to the video to be analyzed based on the fact that the wonderfulness is greater than a preset degree threshold, and the recommended video is used to recommend the initial video.

[0144] The present application also provides a computer device, see Fig.10 As shown, the computer device may be a terminal device, and a mobile phone is taken as an example:

[0145] Fig.10 FIG. 1 is a block diagram showing a partial structure of a mobile phone related to a terminal device provided in an embodiment of the present application. Fig.10The mobile phone includes: a radio frequency (RF) circuit 710, a memory 720, an input unit 730, a display unit 740, a sensor 750, an audio circuit 760, a wireless fidelity (WiFi) module 770, a processor 780, and a power supply 790. Those skilled in the art will understand that Fig.10 The mobile phone structure shown in the figure does not constitute a limitation on the mobile phone, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0146] Combine the following Fig.10 A detailed introduction to the various components of the mobile phone:

[0147] The RF circuit 710 can be used for receiving and sending signals during the process of sending and receiving information or making calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 780 for processing; in addition, the designed uplink data is sent to the base station. Usually, the RF circuit 710 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, referred to as LNA), a duplexer, etc. In addition, the RF circuit 710 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to the Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0148] The memory 720 can be used to store software programs and modules. The processor 780 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 720. The memory 720 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 720 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0149] The input unit 730 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 730 may include a touch panel 731 and other input devices 732. The touch panel 731, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 731 or near the touch panel 731 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 731 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 780, and can receive and execute commands sent by the processor 780. In addition, the touch panel 731 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 731, the input unit 730 may further include other input devices 732. Specifically, the other input devices 732 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0150] The display unit 740 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 740 may include a display panel 741. Optionally, the display panel 741 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), etc. Further, the touch panel 731 may cover the display panel 741. When the touch panel 731 detects a touch operation on or near it, it is transmitted to the processor 780 to determine the type of touch event. Subsequently, the processor 780 provides a corresponding visual output on the display panel 741 according to the type of touch event. Although in Fig.10 In the embodiment, the touch panel 731 and the display panel 741 are used as two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 731 and the display panel 741 can be integrated to realize the input and output functions of the mobile phone.

[0151] The mobile phone may also include at least one sensor 750, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 741 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 741 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0152] The audio circuit 760, the speaker 761, and the microphone 762 can provide an audio interface between the user and the mobile phone. The audio circuit 760 can transmit the received audio data to the speaker 761 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 762 converts the collected sound signal into an electrical signal, which is received by the audio circuit 760 and converted into audio data, and then the audio data is output to the processor 780 for processing, and then sent to another mobile phone through the RF circuit 710, or the audio data is output to the memory 720 for further processing.

[0153] WiFi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages and access streaming media through the WiFi module 770. It provides users with wireless broadband Internet access. Fig.10A WiFi module 770 is shown, but it is understandable that it is not an essential component of the mobile phone and can be omitted as needed without changing the essence of the invention.

[0154] The processor 780 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 720, and calling data stored in the memory 720, it executes various functions of the mobile phone and processes data, thereby performing overall detection of the mobile phone. Optionally, the processor 780 may include one or more processing units; preferably, the processor 780 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 780.

[0155] The mobile phone also includes a power supply 790 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 780 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions.

[0156] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0157] In this embodiment, the processor 780 included in the terminal device also has the following functions:

[0158] Determining a video to be analyzed, where the video to be analyzed is used to be displayed to a target object;

[0159] Acquire posture information corresponding to a target object in a viewing period of the video to be analyzed, wherein the posture information is used to characterize an object posture of the target object in the viewing period;

[0160] Determine, according to the posture information, posture change information of the object posture of the target object in the viewing period, wherein the posture change information is used to characterize a change manner of the object posture of the target object in the viewing period;

[0161] The excitement level of the video to be analyzed is determined according to the posture change information.

[0162] The present application also provides a server. Fig.11 As shown, Fig.11The structural diagram of the server 800 provided in the embodiment of the present application, the server 800 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 822 (for example, one or more processors) and a memory 832, and one or more storage media 830 (for example, one or more mass storage devices) storing application programs 842 or data 844. Among them, the memory 832 and the storage medium 830 can be temporary storage or permanent storage. The program stored in the storage medium 830 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 822 can be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium 830 on the server 800.

[0163] The server 800 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input and output interfaces 858, and / or one or more operating systems 841, such as Windows Server 2000. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM etc.

[0164] The steps performed by the server in the above embodiment can be based on Fig.11 The server structure shown.

[0165] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program, wherein the computer program is used to execute any one of the data processing methods described in the aforementioned embodiments.

[0166] An embodiment of the present application further provides a computer program product including a computer program, which, when executed on a computer device, enables the computer device to execute the data processing method described in any one of the above embodiments.

[0167] It is understandable that in the specific implementation of the present application, related data such as user information (such as eye image information) is involved. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0168] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the above-mentioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the above-mentioned storage medium can be at least one of the following media: read-only memory (English: read-only memory, abbreviated: ROM), RAM, magnetic disk or optical disk, etc. Various media that can store program codes.

[0169] It should be noted that each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, in which the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0170] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data processing method, characterized in that: The method comprises: Determining a video to be analyzed, where the video to be analyzed is used to be displayed to a target object; Acquire posture information corresponding to a target object in a viewing period of the video to be analyzed, wherein the posture information is used to characterize an object posture of the target object in the viewing period; Determine, according to the posture information, posture change information of the object posture of the target object in the viewing period, wherein the posture change information is used to characterize a change manner of the object posture of the target object in the viewing period; The excitement level of the video to be analyzed is determined according to the posture change information.

2. The method according to claim 1, characterized in that The posture information includes eye image information, the posture change information includes blink frequency information, and determining the posture change information of the object posture of the target object in the viewing period according to the posture information includes: determining, according to the eye image information, blinking frequency information of the target object in the viewing period, wherein the blinking frequency information is used to identify the blinking frequency of the target object in the viewing period; The determining the excitement level of the video to be analyzed according to the posture change information includes: The excitement level corresponding to the video to be analyzed is determined according to the blinking frequency information, and the excitement level is inversely correlated with the blinking frequency.

3. The method according to claim 2, characterized in that The step of determining the blinking frequency information of the target object in the viewing period according to the eye image information includes: Determining, according to the eye image information, the eye closure degree of the target object's eyes corresponding to each moment in the viewing period; Determining that the target object has blinked based on a process in which the eye closure degree corresponding to the eye of the target object first increases to a first degree threshold and then decreases to a second degree threshold; Based on the number of blinks of the target object in the viewing period, blink frequency information of the target object in the viewing period is determined.

4. The method according to claim 3, characterized in that The viewing period includes a plurality of sub-periods of the same duration, the blink frequency information is used to identify the blink frequencies corresponding to the plurality of sub-periods, and determining the excitement level corresponding to the to-be-analyzed video according to the blink frequency information includes: Determine, according to the blink frequency information, a distribution diagram of the blink frequencies corresponding to the multiple sub-periods respectively; The degree of excitement corresponding to the video to be analyzed is determined according to the distribution graph. Under the premise that the distribution graph is right-skewed, the degree of excitement is positively correlated with the kurtosis of the distribution graph and is positively correlated with the skewness of the distribution graph.

5. The method according to claim 1, characterized in that The posture change information is used to characterize the change amplitude and change frequency of the object posture of the target object in the viewing period, and the wonderfulness is inversely correlated with the change amplitude and inversely correlated with the change frequency.

6. The method according to claim 1, characterized in that The method further comprises: Acquire the voice information corresponding to the target object in the viewing period; The determining the excitement level of the video to be analyzed according to the posture change information includes: The wonderfulness level corresponding to the video to be analyzed is determined according to the posture change information and the voice information, and the wonderfulness level is inversely correlated with the number of voices represented by the voice information.

7. The method according to claim 1, characterized in that The step of determining the video to be analyzed includes: Acquire an initial video, wherein video content of the initial video corresponds to multiple video scenes; The initial video is segmented at a time point when a video scene corresponding to the video content of the initial video switches to obtain a plurality of videos, and the video to be analyzed is any one of the plurality of videos.

8. The method according to claim 7, characterized in that The method further comprises: Based on the fact that the wonderfulness is greater than a preset threshold, a recommended video corresponding to the initial video is generated according to the video to be analyzed, and the recommended video is used to recommend the initial video.

9. A data processing device, characterized in that: The device comprises a first determining unit, a first acquiring unit, a second determining unit and a third determining unit: The first determination unit is used to determine a video to be analyzed, and the video to be analyzed is used to be displayed to a target object; The first acquisition unit is used to acquire posture information corresponding to the target object in a viewing period of the video to be analyzed, wherein the posture information is used to characterize the object posture of the target object in the viewing period; The second determining unit is used to determine, based on the posture information, posture change information of the object posture of the target object in the viewing period, wherein the posture change information is used to characterize a change manner of the object posture of the target object in the viewing period; The third determination unit is used to determine the excitement level of the video to be analyzed according to the posture change information.

10. The device according to claim 9, characterized in that The posture information includes eye image information, the posture change information includes blink frequency information, and the second determining unit is specifically used for: determining, according to the eye image information, blinking frequency information of the target object in the viewing period, wherein the blinking frequency information is used to identify the blinking frequency of the target object in the viewing period; The third determining unit is specifically configured to: The excitement level corresponding to the video to be analyzed is determined according to the blinking frequency information, and the excitement level is inversely correlated with the blinking frequency.

11. An electronic device, characterized in that: The computer device comprises a processor and a memory: The memory is used to store a computer program and transmit the computer program to the processor; The processor is used to execute the data processing method according to any one of claims 1 to 8 according to the instructions in the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the data processing method according to any one of claims 1 to 8.

13. A computer program product comprising a computer program, which, when executed on a computer device, enables the computer device to execute the data processing method according to any one of claims 1 to 8.

Images