Viewing attitude estimation system
The viewing attitude estimation system addresses the challenge of determining viewer attention by analyzing operational metrics during video playback, providing an objective assessment of user engagement and improving the effectiveness of corporate training.
Patent Information
- Application Number
- JP2023193391
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-11-14
- Publication Date
- 2025-05-26
AI Technical Summary
There is a need to accurately determine whether viewers are watching video content with proper attention, as lack of concentration can lead to ineffective dissemination of information, particularly in corporate training settings.
A viewing attitude estimation system that acquires a user's operation history during video playback and estimates their viewing attitude based on various operational metrics, such as switching between applications, playback volume adjustments, and key typing sounds.
Enables objective estimation of user viewing attitudes, helping to ensure that video content is consumed with appropriate concentration, thereby enhancing the effectiveness of corporate training and information sharing.
Smart Images

Figure 2025080315000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a technique for estimating viewing attitudes.
Background Art
[0002] In recent years, in the fields of education and business, the distribution of video content and the like to remote users has been rapidly spreading (see, for example, Patent Document 1).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] There is a need to determine whether viewers are watching the distributed video content properly (in other words, attentively). For example, when distributing video content for in-house training to employees, even if an employee is watching the video content using a terminal within the company, if they are watching the video content in a state lacking concentration, such as operating another application while watching the video (in other words, with a non-serious viewing attitude), it is conceivable that the effects assumed by the distributor will not be obtained (so-called "watching while doing other things"). Therefore, it is extremely important to accurately estimate the viewing attitudes of users, particularly for video content related to work shared within organizations such as companies.
[0005] An object of the present invention is to estimate the viewing attitude of video content.
Means for Solving the Problems
[0006] In one aspect, the present invention provides a viewing attitude estimation system having an acquisition means for acquiring a user's operation history during a period when video content is being played on a terminal, and an estimation means for estimating the user's viewing attitude towards the video content based on the operation history acquired by the acquisition means. According to this aspect, it becomes possible to objectively estimate the user's viewing attitude according to the operations performed by the user on the terminal while the video is being played.
[0007] In a preferred aspect, the estimation means estimates the viewing attitude based on operations related to other applications other than the playback application performed within the period. According to this aspect, it is possible to estimate the user's viewing attitude based on operations related to other applications performed during the playback period of the video content.
[0008] In a preferred aspect, the playback application is executed on a browser, and when the estimation means indicates that the focus has moved to other applications executed by the browser a predetermined number of times or more within the period, the estimation means determines that the user is not concentrating on viewing. According to this aspect, it becomes possible to estimate the user's viewing attitude based on the number of times the focus has moved to other applications.
[0009] In a preferred aspect, when the other application that is the operation target is a predetermined application for inputting text information, the estimation means determines that the user is concentrating on viewing. According to this aspect, it is possible to avoid misestimating the viewing attitude caused by the user taking notes while viewing the video.
[0010] In a preferred aspect, the estimation means estimates the viewing attitude based on operations for adjusting the playback volume performed within the period. According to this aspect, it becomes possible to objectively estimate the user's viewing attitude based on operations for adjusting the playback volume performed while the video content is being played.
[0011] In a preferred embodiment, the estimation means determines that the user is not concentrating on viewing when the length of the period during which the playback volume is set to zero is equal to or greater than a predetermined value within the period during which the video is being played. According to the sixth embodiment, it becomes possible to objectively estimate the viewing attitude of the user based on the length of the period during which the playback volume is set to zero.
[0012] In a preferred embodiment, the estimation means determines that the user is not concentrating on viewing when no operation is performed on the playback application even after a predetermined time has elapsed since the end of the playback of the video content. According to this embodiment, it becomes possible to objectively estimate the viewing attitude of a user who has not noticed the end of the video content playback (i.e., is not seriously viewing the video content).
[0013] In a preferred embodiment, the apparatus further includes a microphone, and the estimation means estimates the viewing attitude based on the time when a key typing sound is detected by the microphone during the playback period. According to this embodiment, the viewing attitude of the user is objectively estimated based on the length of the time when a key typing sound is detected during the playback of the video content.
[0014] In a preferred embodiment, the apparatus further includes a notification means for notifying the user of a message corresponding to the viewing attitude estimated by the estimation means during the period. According to this embodiment, it becomes possible to notify the user of a message corresponding to the viewing attitude.
[0015] In another aspect, the present invention provides a program for causing a computer to execute steps of acquiring an operation history of a user during a period in which video content is being played on a terminal, and estimating a viewing attitude of the user with respect to the video content based on the acquired operation history.
Brief Description of the Drawings
[0016]
Figure 1
Figure 2
Figure 3
Embodiments for Carrying Out the Invention
[0017] <A. Embodiment> The following-described embodiments are subject to various technically preferable limitations. However, the embodiments of the present invention are not limited to the forms described below.
[0018] FIG. 1 is a diagram showing a configuration example of the viewing attitude estimation system 1 according to an embodiment of the present invention. The viewing attitude estimation system 1 is an intranet constructed within a company. As shown in FIG. 1, the viewing attitude estimation system 1 includes terminal devices 10(1) to 10(M) and a management server 20. In the example shown in FIG. 1, M is 3, but M may be 2, or M may be a number of 4 or more. The terminal devices 10 and the management server 20 are connected to a LAN 30 such as an intranet laid within the company. The terminal devices 10 and the management server 20 communicate with each other via the LAN 30. Note that the viewing attitude estimation system 1 is not configured within the intranet, and the terminal devices 10 and the management server 20 may be connected via the Internet.
[0019] Each of the terminal devices 10(1) to 10(M) is a personal computer used by an employee of a company in which the viewing attitude estimation system 1 is constructed. Hereinafter, when it is not necessary to distinguish each of the terminal devices 10(1) to 10(M), the terminal devices 10(1) to 10(M) are denoted as the terminal device 10. Although the terminal device 10 in the present embodiment is a personal computer, it may be a mobile terminal such as a smartphone or a tablet terminal. The terminal device 10 is an example of a terminal in the present invention. An employee of a company in which the viewing attitude estimation system 1 is constructed can use his or her own terminal device 10 to create video content related to work and upload it to the management server 20 during working hours. Specific examples of the video content in the present embodiment include videos related to the method of creating sales materials, the explanation of entry and exit procedures, the way to dispose of garbage, or the use method of a copying machine. Further, an application program (so-called browser) for accessing a website and displaying information by inputting a URL or the like is pre-installed in the terminal device 10. In the present embodiment, a playback application for viewing video content is executed on the browser.
[0020] The management server 20 is a computer device for enabling employees other than the employee who created the video content to view the video content uploaded from the terminal device 10, that is, for realizing the sharing of the video content. Further, the management server 20 is a device for estimating the viewing attitude of a user based on the history of the user's operations performed on the terminal device 10 during the playback of the video content. Hereinafter, the management server 20 that prominently shows the features of the present invention will be mainly described.
[0021] FIG. 2 is a block diagram showing a configuration example of the management server 20. As shown in FIG. 2, the management server 20 includes a processing device 210, a communication device 220, a storage device 230, and a bus 240. Each of the processing device 210, the communication device 220, and the storage device 230 is connected to the bus 240. The bus 240 mediates data transfer between the processing device 210 and each of the communication device 220 and the storage device 230.
[0022] The processing device 210 is a computer such as a CPU (Central Processing Unit). By operating according to the program PA stored in the storage device 230, the processing device 210 functions as the control center of the management server 20. The functions realized by the processing device 210 operating according to the program PA will be clarified later.
[0023] The communication device 220 is a communication interface such as a NIC (Network Interface Card), and is connected to the LAN 30 wirelessly or by wire. The communication device 220 receives various communication messages transmitted from the terminal device 10 via the LAN 30, and delivers the received communication messages to the processing device 210. Specific examples of the communication messages transmitted from the terminal device 10 via the LAN 30 include a posting message (hereinafter, a posting request) for posting video content, and a request message (hereinafter, a viewing request) for requesting viewing of the posted video content. The posting request includes content data representing the video content to be posted, a video identifier (for example, a character string representing the name of the video) uniquely indicating the video content, and a posting source identifier (for example, a character string representing the employee number of the poster) representing the user (poster) of the posting source of the video content. The viewing request includes a video identifier related to the video for which viewing is desired.
[0024] The storage device 230 has a non-volatile storage unit configured by, for example, a hard disk or the like, and a volatile storage unit configured by, for example, a RAM (Random Access Memory) or the like. In FIG. 2, the illustration of the non-volatile storage unit and the volatile storage unit is omitted. In the non-volatile storage unit, content data representing the video content posted by the user of the terminal device 10 is stored in association with the video identifier and the posting source identifier. Further, the program PA described above is stored in the non-volatile storage unit in advance. The volatile storage unit is used as a work area when executing the program PA.
[0025] When the processing device 210 powers on the management server 20 (not shown in FIG. 2), it reads the program PA from the non-volatile memory unit into the volatile memory unit. Then, the processing device 210 starts executing the program PA read into the volatile memory unit. The processing device 210 operating according to the program PA functions as the acquisition means 211, the estimation means 212, and the notification means 213 shown in FIG. 2. That is, each of the acquisition means 211, the estimation means 212, and the notification means 213 shown in FIG. 2 is a software module realized by operating the processing device 210 (computer) according to the program PA (software). The functions of each of the acquisition means 211, the estimation means 212, and the notification means 213 are as follows.
[0026] The acquisition means 211 acquires the operation history of the user during the period of playing video content by communicating with the terminal device 10 using the communication device 220. In this embodiment, since the playback application for playing video content is executed on the browser of the terminal device 10, the acquisition means 211 acquires the operation history from the browser. Note that the playback application is not limited to a browser application and may be an application program executed on the OS (Operating System) separately from the browser. In this case, the acquisition means 211 acquires the operation history from the OS. In this embodiment, the acquisition means 211 acquires the operation history in real time, but it may also be acquired after the viewing of the video content ends.
[0027] The estimation means 212 estimates the user's viewing attitude towards the video content based on the operation history acquired by the acquisition means 211. In this embodiment, the estimation means 212 calculates an index indicating the user's concentration (for example, a value obtained by subtracting the number of switching times from a predetermined value such as 10) based on the number of times another tab other than the playback application in the browser is opened during the period of playing the video content, and thereby estimates the user's viewing attitude. This index means that the larger the value, the higher the concentration of viewing the video, in other words, the more seriously the video is being viewed.
[0028] When the playback application is not a browser application, the estimation means 212 may estimate the user's viewing attitude based on operations related to applications other than the playback application. For example, when the focus has moved to another application a predetermined number of times (e.g., once) or more during the period of playing video content (i.e., the switching of the right to speak to another application has occurred a predetermined number of times or more) as shown in the operation history, the estimation means 212 may calculate an index indicating the user's concentration based on the number of times of switching the right to speak. In addition, when the other application is a predetermined application for inputting text information, it is estimated that the user is viewing the video content while taking notes, so the estimation means 212 may determine that the user is concentrating on viewing.
[0029] The notification means 213 notifies the user of the above message during the above period by instructing the terminal device 10 to output a message corresponding to the viewing attitude estimated by the estimation means 212. Specific examples of the above message include messages with words prompting the user to concentrate on viewing, such as "Are you concentrating on watching?" Note that the notification means 213 is omitted in the mode of acquiring the operation history after the viewing of the video content ends.
[0030] In addition, every time the processing device 210 operating according to the program PA receives a viewing request using the communication device 220, it executes a viewing attitude estimation method that prominently shows the features of the present invention. FIG. 3 is a flowchart showing the flow of this viewing attitude estimation method. As shown in FIG. 3, this viewing attitude estimation method includes an acquisition process SA110, an estimation process SA120, a first determination process SA130, a notification process SA140, and a second determination process SA150. The contents of each of the acquisition process SA110, the estimation process SA120, the first determination process SA130, the notification process SA140, and the second determination process SA150 are as follows.
[0031] In the acquisition process SA110, the processing device 210 functions as the acquisition means 211, and in the estimation process SA120, the processing device 210 functions as the estimation means 212. In the first determination process SA130, based on the index calculated in the estimation process SA120, it is determined whether the user is concentrating on watching the video content. Specifically, in the first determination process SA130, it is determined whether the above index is equal to or greater than a predetermined threshold value (for example, 5). If the above index is equal to or greater than the predetermined threshold value, the determination result of the first determination process SA130 is "Yes". Conversely, if the above index is less than the predetermined threshold value, the determination result of the first determination process SA130 is "No".
[0032] When the determination result of the first determination process SA130 is "No", the second determination process SA150 is executed after the notification process SA140 is executed. In the notification process SA140, the processing device 210 functions as the notification means 213. When the determination result of the first determination process SA130 is "Yes", the second determination process SA150 is executed without executing the notification process SA140. In the second determination process SA150, the processing device 210 determines whether the playback of the video content has ended by communicating with the terminal device 10. When the playback of the video content has ended (that is, when the determination result of the second determination process SA150 is "Yes"), the processing device 210 ends the execution of this viewing attitude estimation method. On the contrary, when the playback of the video content has not ended (that is, when the determination result of the second determination process SA150 is "No"), the processing device 210 executes the processes after the acquisition process SA110 again.
[0033] As described above, according to this embodiment, it is possible to objectively estimate the viewing attitude of a user watching video content related to work based on the operation history of the user made during the period when the video content is being played.
[0034] <B: Modification Example> The above-described embodiment may be modified as follows. The estimation means 212 may estimate the user's viewing attitude based on an operation of adjusting the playback volume performed during the period of playing the video content. Specifically, the estimation means 212 may determine that the user is not concentrating on viewing when the length of the period during which the playback volume is set to zero (the so-called mute state period) is equal to or greater than a predetermined value within the period during which the video is being played.
[0035] Even if a predetermined time has elapsed since the end of the playback of the video content and no operation is performed on the playback application, the estimation means 212 may determine that the user is not concentrating on viewing. Also, when the terminal device 10 has a microphone, the acquisition means 211 acquires, from the terminal device 10, information representing the sound picked up by the microphone during the period of playing the video content as operation information, and the estimation means may estimate the viewing attitude based on the time when the key typing sound is detected during the above period.
[0036] The estimation process of the viewing attitude may be executed after the completion of the playback of one video content, or may be executed at any time during the playback. In this case, for example, this estimation process is performed using the user's operation information, etc. within an arbitrary period (for example, up to ** minutes from the start of the video) within the playback period of one video content. That is, when estimating the viewing attitude of one video content, it is not necessary to use information such as the user's operation history during the entire playback period of the one video content, and only information such as the operation history collected during a part of the playback period may be used. Also, the estimation process of the viewing attitude may be executed multiple times when a predetermined period (for example, for each preset scene) has elapsed since the start of the playback of one video content. In this case, the viewing attitude regarding the one video content may be calculated based on the results of the estimation process in each period.
[0037] Each of the acquisition means 211, the estimation means 212, and the notification means 213 in the above embodiment was a software module. However, any one, any two, or all of the acquisition means 211, the estimation means 212, and the notification means 213 may be hardware modules such as electronic circuits. Also, in the above embodiment, each of the acquisition means 211, the estimation means 212, and the notification means 213 was provided in one management server, but they may be provided in a distributed manner in a plurality of servers or other information processing devices. In short, in the information processing system according to the present invention, in one or more information processing devices, a step of acquiring a user's operation history during a period when video content is being played, and a step of estimating the user's viewing attitude towards the video content based on the acquired operation history may be executed.
[0038] The program PA may be manufactured or provided alone. As a specific provision mode of the program PA, a mode of writing the program PA to a computer-readable recording medium such as a flash ROM and distributing it, or a mode of distributing it by downloading via an electric communication line such as the Internet can be considered. By operating a computer according to the program PA provided by any of these modes, the computer can be made to function as the acquisition means 211, the estimation means 212, and the notification means 213.
Explanation of Signs
[0039] 1... Viewing attitude estimation system, 10... Terminal device, 20... Management server, 210... Processing device, 211... Acquisition means, 212... Estimation means, 213... Notification means, 220... Communication device, 230... Storage device, 240... Bus, 30... LAN.
Claims
1. An acquisition means for acquiring an operation history of a terminal by a user during a period in which video content is being played, An estimation means for estimating the viewing attitude of the user with respect to the video content based on the operation history acquired by the acquisition means, A viewing attitude estimation system having the above.
2. The estimation means estimates the viewing attitude based on operations related to applications other than the playback application for playing the video content, which are performed within the period. The viewing attitude estimation system according to Claim 1.
3. The playback application is executed on a browser, When the focus has moved to other applications executed by the browser a predetermined number of times or more in the operation history within the period, the estimation means determines that the user is not concentrating on viewing. The viewing attitude estimation system according to Claim 2.
4. When the other application that is the operation target is a predetermined application for inputting text information, it is determined that the user is concentrating on viewing. The viewing attitude estimation system according to Claim 2.
5. The estimation means estimates the viewing attitude based on operations for adjusting the playback volume, which are performed within the period. The viewing attitude estimation system according to Claim 1.
6. When the length of the period during which the playback volume is set to zero within the period is equal to or greater than a predetermined value, the estimation means determines that the user is not concentrating on viewing. The viewing attitude estimation system according to Claim 5.
7. When no operation on the playback application for playing the video content is detected even after a predetermined time has elapsed since the end of playback of the video content, the estimation means determines that the user is not concentrating on viewing. The viewing attitude estimation system according to Claim 1.
8. Further comprising a microphone, The estimation means estimates the viewing attitude based on the time when a key typing sound is detected by the microphone during the period of playing the video content. The viewing attitude estimation system according to Claim 1.
9. Further having a notification means for notifying the user of a message corresponding to the viewing attitude estimated by the estimation means during the period. The viewing attitude estimation system according to Claim 1.
10. On a computer, An acquisition step of acquiring an operation history of a terminal by a user during a period in which video content is being played, a step of estimating the viewing attitude of the user towards the video content based on the acquired operation history, and a program for causing the above to be executed.
Citation Information
Patent Citations
Learning system, automatic video generation method and program
JP6866411B2