Information presentation system, information presentation method, and program

The system addresses the challenge of differing sports knowledge levels by personalizing content with user-specific information, enhancing unity and enjoyment for all viewers.

JP2024159279APending Publication Date: 2024-11-08NIPPON TELEGRAPH & TELEPHONE CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023075155
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing technologies fail to bridge the knowledge gap between sports enthusiasts and novices during broadcasts, making it difficult for both groups to experience a unified and exciting viewing experience.

Method used

A system that utilizes a database to store user characteristics and knowledge levels, generating personalized knowledge information based on user attributes, and adding it to sports content through subtitles, audio, or visual enhancements.

Benefits of technology

Enhances the viewing experience by allowing all viewers to enjoy sports content with increased unity and enthusiasm, regardless of their knowledge level, by providing tailored information based on individual interests and understanding.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024159279000001_ABST
    Figure 2024159279000001_ABST
Patent Text Reader

Abstract

To enable everyone watching sports to enjoy the content.SOLUTION: An information presentation system according to an embodiment of the present invention includes a database and a server accessible to the database. The database holds, for each user of distributed sports content, the user's characteristics and knowledge information regarding the sports content in association with each other. The server includes a data processing unit and an analysis unit. The data processing unit obtains the user's attributes regarding the sports content. The analysis unit refers to the database on the basis of the attributes and generates knowledge information to be presented to the user.SELECTED DRAWING: Figure 5
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] One aspect of the present invention relates to a technique for enabling effective viewing of live video of sports and the like. [Background technology]

[0002] Video content distributors are constantly developing technologies to improve services for users (viewers). For example, to meet the needs of families watching live sports broadcasts, there is a demand for ingenuity to increase the sense of unity between spectators and to make the experience more exciting.

[0003] By the way, when a person who is knowledgeable about sports and a person who is not knowledgeable about sports watch a game together, it is difficult for them to get excited at the same time and feel a sense of unity. A person who is knowledgeable about sports can instantly understand the situation and get excited, but a person who is not knowledgeable is often left behind. Therefore, it is possible to add live commentary to the watching scene by audio. By using technologies related to generating subtitles and adding audio commentary in sports broadcasts (see Non-Patent Documents 1 and 2), audio and subtitles can be added automatically. In addition, text information can be added using goggles and eye tracking devices used in VR (Virtual Reality) and XR (see Non-Patent Document 3). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2009-302985 A [Non-patent literature]

[0005] [Non-Patent Document 1] “Automatic Generation Technology of Audio Commentary”, [online], GiKen Dayori, NHK Science & Technology Research Laboratories, [Retrieved March 6, 2023], Internet,<URL:https: / / www.nhk.or.jp / strl / publica / giken_dayori / 204 / 4.html> [Non-Patent Document 2] “Decision method for automatic commentary insertion timing for live broadcast programs: Prediction of speech end of live commentary in sports broadcasts”, Ichiki et al., IEICE Technical Report, vol. 118, no. 270,WIT2018-29, pp. 45-50. [Non-Patent Document 3] “Proposal and Evaluation of a Subtitle Placement Method with Less Eye Movement Based on Attention Areas Calculated from Eye-Tracking Data”, Akahori et al., 2015-EC-38, Research Report Entertainment Computing (EC) Summary of the Invention [Problem to be solved by the invention]

[0006] Existing technology only transcribes the content of a sporting event or facts that can be gleaned from the footage. For this reason, people who are not familiar with sports cannot tell what kind of player a player is just from their name, and cannot understand how amazing a technique is just by hearing the name of the technique. There is a demand for technology that can eliminate the boundaries between those who are knowledgeable about sports and those who are not, and allow anyone to enjoy watching sports.

[0007] The present invention has been made in light of the above circumstances, and aims to provide a technique that enables anyone watching a sports match to enjoy the content. [Means for solving the problem]

[0008] An information presentation system according to one aspect of the present invention includes a database and a server accessible to the database. The database holds, for each user of distributed sports content, a user's characteristics and knowledge information regarding the sports content in association with each other. The server includes a data processing unit and an analysis unit. The data processing unit obtains the user's attributes regarding the sports content. The analysis unit refers to the database based on the attributes and generates knowledge information to be presented to the user. Effect of the Invention

[0009] According to one aspect of the present invention, a technique can be provided that allows anyone watching a sports game to enjoy the content. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of an information presentation system according to an embodiment. [Diagram 2] FIG. 2 is a functional block diagram illustrating an example of the server 100 illustrated in FIG. [Diagram 3] FIG. 3 is a diagram showing an example of data held in the characteristic-knowledge database 101. As shown in FIG. [Figure 4] FIG. 4 is a flowchart showing an example of a processing procedure of the server 100 shown in FIG. [Diagram 5] FIG. 5 is a diagram for explaining the flow of data in the information presentation system according to the embodiment. [Figure 6] FIG. 6 is a functional block diagram showing the processing functions of a data processing unit 100B and an analysis unit 100A according to [Modification 1]. [Figure 7] FIG. 7 is a functional block diagram showing the processing functions of a data processing unit 100B and an analysis unit 100A according to [Modification 2]. [Figure 8] FIG. 8 is a functional block diagram showing the processing functions of a data processing unit 100B and an analysis unit 100A according to [Modification 3]. [Figure 9]FIG. 9 is a block diagram showing an example of a hardware configuration of the server 100 according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The following description will be given with a focus on distributed content related to watching sports (referred to as sports content). [One embodiment] Fig. 1 is a diagram showing an example of an information presentation system according to an embodiment. The system shown in Fig. 1 includes a server 100 belonging to a cloud 1, and a characteristic-knowledge database 101. A content distribution server 200 may also be connected to the cloud 1.

[0012] The server 100 can access the characteristic-knowledge database 101 via, for example, a TCP / IP network. The characteristic-knowledge database 101 holds, for each user of sports content (hereinafter abbreviated as content) distributed via the cloud 1, the characteristics of the user and knowledge information about the content in association with each other.

[0013] The goggles 11, smartphone 12, terminal device 13, smart watch 14, microphone 15, and camera 16 as user side devices can communicate with the cloud 1 via, for example, wireless communication links. These devices are sensing devices that acquire data (physical data) that indicates the user's reaction to the content. For example, the goggles 11 can acquire the user's gaze data on the content. The smart watch 14 can acquire vital data such as heart rate. In addition, the camera 16 and microphone 15 can also acquire sensing data such as the reaction during viewing. The acquired sensing data is transmitted to the server 100 via the cloud 1.

[0014] Fig. 2 is a functional block diagram showing an example of the server 100 shown in Fig. 1. The server 100 includes a sensing data processing unit 102, an analysis unit 100A, an output processing unit 105, and a feedback reflection unit 106.

[0015] The sensing data processing unit 102 obtains the user's attributes for the content. For example, sensing data for identifying a gaze area is input to the sensing data processing unit 102. That is, the sensing data processing unit 102 obtains the gaze direction of the user watching the content as sensing data. The gaze direction is output as gaze data directly from the goggles 11 having an eye tracking function, for example. Alternatively, the gaze direction can be obtained by processing image data obtained by the camera 16 to directly extract the user's face direction, or indirectly extracting the face direction from the angle of the head. In addition, the direction in which the user focuses on an object in the content (attention direction) can also be an example of sensing data.

[0016] The analysis unit 100A refers to the characteristic-knowledge database 101 based on the attributes of the user, and generates knowledge information to be presented to the user. The generated knowledge information is output as additional knowledge from the output processing unit 105. The additional knowledge can be said to be additional information aimed at a group of users having similar characteristics.

[0017] A feedback reflecting unit 106 updates the contents of the characteristic-knowledge database 101 in response to the user's reaction to the outputted assigned knowledge. It is expected that the accuracy of the outputted added knowledge can be improved by updating the contents of the characteristic-knowledge database 101. For example, the priority of each item (table column) in the characteristic-knowledge database 101 is assigned as a value, and the priority value is updated by obtaining the good or bad reaction of the user by sensing the user's speech or facial expression when the output is presented or by having the user press an evaluation button.

[0018] The analysis unit 100A includes a user characteristic estimation unit 103 and an assigned knowledge determination unit 104. The user characteristic estimation unit 103 identifies the user's gaze area with respect to the content from the gaze direction, and estimates the user's characteristics based on the result. The assigned knowledge determination unit 104 refers to the characteristic-knowledge database 101 based on the estimated characteristics, determines knowledge suitable for presentation to the user, and generates knowledge information.

[0019] FIG. 3 is a diagram showing an example of data stored in the characteristic-knowledge database 101. The characteristic-knowledge database 101 accumulates a list (table) of characteristics for each user and knowledge suitable for presenting to a user having the characteristic. Examples of user characteristics include interests, amount of knowledge, and types of patterns that excite the user. The table can be created for each user with different interests by extracting knowledge that would be useful to have when watching a game in advance, for example, through a user questionnaire. Alternatively, the table may be created by collecting tacit knowledge from commentators or experts on the game.

[0020] As shown in Fig. 3(a), the characteristic-knowledge database 101 can hold a table with columns of [interests] that represent the characteristics of a user and [knowledge] that corresponds to the interests. For example, for a user whose [interest] is [Player A], the knowledge that [Player A] has just returned from injury and is expected to do well] can be associated with the user.

[0021] As shown in Fig. 3(b), the characteristic-knowledge database 101 can hold a table with columns of [amount of knowledge] representing the characteristics of a user and [knowledge] corresponding to the amount of knowledge. For example, a user with little [amount of knowledge] can be associated with the knowledge that [Player A is a former ace who has just returned from injury].

[0022] 3(c), the characteristic-knowledge database 101 can hold a table with columns of [excitement patterns] representing the characteristics of the user and [knowledge] corresponding to the excitement patterns. For example, a user who gets excited about a [comeback] can be associated with the knowledge that [Player B, who will be at bat next, is expected to have a high batting average this season].

[0023] Fig. 4 is a flowchart showing an example of a processing procedure of the server 100 shown in Fig. 1. In step S1, the server 100 acquires a state of the user from sensing data, etc. For example, gaze data acquired by an eye tracking function of the goggles 11 is collected by the server 100.

[0024] In step S2, the server 100 estimates the characteristics of each user based on the acquired data by the user characteristic estimation unit 103. Here, characteristics such as the user's interests and knowledge of the target content are estimated.

[0025] In step S3, the server 100 refers to the characteristic-knowledge database 101, and the assigned knowledge determining unit 104 determines knowledge to be assigned in accordance with the user's characteristics. In step S4, the server 100 creates presentation content data such as text data for subtitles or voice reading data according to the determined knowledge. In step S5, the server 100 generates content to which knowledge is added, for example, by superimposing subtitles on the screen or adding audio to video. Furthermore, in step S6, the server 100 presents the content to which the knowledge has been added to the user.

[0026] Incidentally, examples of the embodiment of adding knowledge to content include the following <Example 1> to <Example 3>. Each will be explained in order.

[0027] <Example 1> In the first embodiment, what the user is looking at is taken as the subject of the user's interest, and knowledge matching the user's interest is given. For example, when the user is watching a certain player, the player's background (background of his / her upbringing, etc.) is displayed near the player. Or, when watching a dribble in a basketball game, impressive points of technique are displayed near the ball. Or, when watching the whole scene, meta information (possession rate, etc.) that allows an overview of the game is displayed.

[0028] The tacit knowledge of the scene and the gaze direction can be collected in advance and stored in the characteristic-knowledge database 101. For example, the network may be crawled in real time using a collection process that is patterned to a certain extent, and the automatically generated data may be registered in the characteristic-knowledge database 101.

[0029] The following description will be given based on the contents of the table in Fig. 3(a). In the first embodiment, the gaze data acquired in step S1 (Fig. 4) is passed to the user characteristic estimation unit 103, and the user's gaze target is estimated. For example, if player A is estimated as the user's gaze target, the characteristic-knowledge database 101 is referenced to determine that knowledge that [Just returned from injury. Expected to do well] is to be imparted. On the other hand, if [heel lift] is estimated as the user's gaze target, the characteristic-knowledge database 101 is referenced to determine that knowledge that [Dribble over the head. Rarely successful] is to be imparted (step S3).

[0030] Next, caption data is created from the obtained knowledge (step S4), and video data with captions added to the vicinity of the user's gaze point is created (step S5). Then, the video data with captions added is displayed on a display or the like (step S6).

[0031] <Example 2> In the second embodiment, the speed at which the subtitles are read and the time spent looking at the subtitles are regarded as the amount of knowledge, and knowledge that matches the amount of knowledge is provided. For example, if the user stares at a certain word, it is assumed that the user does not understand the meaning of that word, and an explanation related to that word is provided. Alternatively, words that the user has not looked at at all are deemed unnecessary, and the subtitles are turned off. If the user's reading speed is not fast enough, a summary is presented.

[0032] The following description will be given based on the table contents in FIG. 3(b). In the second embodiment, the gaze data acquired in step S1 (FIG. 4) is passed to the user characteristic estimation unit 103, and the speed at which the user follows the subtitles is estimated. For example, for a displayed subtitle saying [Watch out for Player A this season!], the amount of knowledge is estimated using a subtitle following speed of 10 characters / second as a threshold (step S2). For example, if it is estimated that the amount of knowledge is small, it is determined to impart knowledge that [Player A is a former ace who has just returned from injury] by referring to the characteristic-knowledge database 101. On the other hand, if it is estimated that the amount of knowledge is large, it is determined to impart knowledge that [Player A is doing his usual routine and is in top form] by referring to the characteristic-knowledge database 101 (step S3).

[0033] Next, subtitle data is created based on the obtained knowledge, for example, by adding information such as "Player A is a former ace who has just returned from injury" (step S4), and video data is created with subtitles added to the area around the user's gaze (step S5). The video data with the subtitles added is then displayed on a display or the like (step S6).

[0034] <Example 3> In the third embodiment, relevant knowledge is provided before a predicted boom. For example, the boom and its pattern can be predicted in advance using the technology described in reference [1].

[0035] For example, the sensing data processing unit 102 collects in advance personal characteristics about what situations are exciting, and the results are stored in the characteristic-knowledge database 101. Exciting situations can be predicted using data generated in advance in this way. Alternatively, exciting situations may be estimated in real time using biological information such as the degree of attention to each scene measured by gaze measurement.

[0036] The following description will be given based on the contents of the table in Fig. 3(c). In the third embodiment, the user state acquired in step S1 (Fig. 4) is passed to the user characteristic estimation unit 103, and the user's excitement pattern is estimated. For example, if [comeback] is estimated as the excitement pattern, it is determined by referring to the characteristic-knowledge database 101 that the knowledge that [Player B, who will be at bat next, is expected to have a high batting average this season] should be imparted. On the other hand, if [chance] is estimated as the excitement pattern, it is determined by referring to the characteristic-knowledge database 101 that the knowledge that [the next turn at bat will be a continuous turn by players with high batting averages] should be imparted (step S3).

[0037] Next, caption data is created from the obtained knowledge (step S4), and video data with captions added to the vicinity of the user's gaze point is created (step S5). Then, the video data with captions added is displayed on a display or the like (step S6).

[0038] Fig. 5 is a diagram for explaining the flow of data in the information presentation system according to the embodiment. Note that the data processing unit 100B shown in Fig. 5 is a functional block having the same functions as the sensing data processing unit 102 and the output processing unit 105 in Fig. 2.

[0039] 5, the data processing unit 100B acquires sensor data such as the user's video, voice, and IMU from the user side device (FIG. 1) and performs recognition processing of the user sensing results. Data obtained by the processing, such as action recognition, gaze (point of gaze), head direction, and voice recognition, are passed to the analysis unit 100A in the cloud 1 as human sensing results and user action results.

[0040] The analysis unit 100A mainly determines feedback information and knowledge information according to the behavioral results of fans (users). The feedback contents and knowledge assignment (video, audio, tactile, text information, etc.) are fed back to the data processing unit 100B. The data processing unit 100B generates response information for each device and passes it to each device.

[0041] Incidentally, the following [Modification 1] to [Modification 3] can also be given as examples of adding knowledge to content. They will be explained in order.

[0042] [Variation 1] Fig. 6 is a functional block diagram showing the processing functions of a data processing unit 100B and an analysis unit 100A according to [Modification 1]. In Fig. 6, the sensing data processing unit 102 of the data processing unit 100B includes an input processing unit 31, a human recognition processing unit 32, a determination unit 33, a database update unit 34, and a content analysis unit 35. The input processing unit 31 passes data such as the user's facial direction, expression, line of sight, behavior, and voice to the human recognition processing unit 32. In addition, the content analysis unit 35 analyzes the distribution content and passes data such as the game progress (scene context) and timeline to the human recognition processing unit 32.

[0043] The human recognition processing unit 32 extracts data such as user data, action recognition level, content object being viewed, context determination (cheering level), and rhythm synchronization from the passed data, and gives a user trigger to the determination unit 33. The determination unit 33 determines enhancements such as unity and enthusiasm. The results are passed to the database update unit 34, and the characteristic-knowledge database 101 is updated with data such as time, user action results for each scene, and cheering behavior level.

[0044] In addition, the user action result and the cheering behavior level are passed to a user characteristic estimation unit 103 of the analysis unit 100A, and fan attribute information is extracted by processing such as clustering. The fan attribute information is registered in a characteristic-knowledge database 101. Knowledge imparting information candidates read from the characteristic-knowledge database 101 are passed to an imparting knowledge determination unit 104, and the contents to be fed back to an output processing unit 105 are determined.

[0045] The output processing unit 105 includes an output processing unit 42 and an output content generation unit 41. The output content generation unit 41 generates content such as video, audio, and haptics according to the user context based on information (feedback content, knowledge assignment (video, audio, haptic, text information, etc.)) from the assigned knowledge determination unit 104, and passes it to the output processing unit 42. The output processing unit 42 generates custom content such as a screen layout, audio, and haptics according to the user device, and outputs it to the user device.

[0046] 6, each process of the input processing unit 31 and the output processing unit 42 may be performed by a remote user. For example, the input processing unit 31 may analyze a remote user with similar characteristics. Alternatively, conversely, the output processing unit 42 may output data for the remote user.

[0047] [Variation 2] 7 is a functional block diagram showing the processing functions of a data processing unit 100B and an analysis unit 100A according to [Modification 2]. The functional configuration is the same as in FIG. 6, and the parts where the operation is different will be described below.

[0048] In the second modification, information is provided using both the input sensing data and the target sports content. In the second modification, in addition to the sensing data related to the gaze area, reactions and contexts are also input, and information is provided from / to other users in remote locations. The following (Example 1) to (Example 3) are examples of the implementation method.

[0049] (Example 1) Input is sensing data of gaze area and reaction during viewing, and context, and outputs additional information for the user. -Subdivide the information to be provided according to the user's reaction and situation. -In addition to user characteristics, information tailored to the user's reaction and situation at the time promotes understanding and entertains even those with no prior knowledge.

[0050] (Example 2) The system takes sensing data of gaze areas and reactions while viewing as input, and outputs annotated information for all users with similar characteristics. Generate attribution information for all other users with similar characteristics based on the sensing data of only one person. - It will be more entertaining to show the reactions obtained as input to all users or stadiums with similar characteristics.

[0051] (Example 3) Input is sensing data of the gaze areas and reactions of other users with similar characteristics, and outputs additional information for the user. By registering characteristics in advance, attribute information can be generated without sensing the user. - It will be more entertaining to show the stadium and the reactions of other users with similar characteristics along with additional information. [Variation 3] FIG. 8 is a functional block diagram showing the processing functions of a data processing unit 100B and an analysis unit 100A according to [Modification 3].

[0052] In the third modification, information is added using only the target sports content at the time. In other words, sensing data is not necessarily required. Sensing is not performed as an input, and pre-registered user characteristics are used as input to add information according to the progress of the game. Eliminating the need for sensing processing has the advantage of ensuring privacy and security.

[0053] In FIG. 8, the sensing data processing unit 102 includes a fan attribute registration unit 36 ​​for registering fan attributes according to facial expressions, actions, voices, and the like. Variation 3 is an example of adding information using only the target sports content, and uses sensing data acquired in the past, not sensing data acquired in real time. The contents and development of the target sports content are input, and information to be added to the user and other users with similar characteristics is added as output. The output content to the user uses the results of past sensing and feedback that were effective.

[0054] In particular, the output content generating unit 41 may control the volume of the additional information, the color scheme when it is presented, decoration, addition of sound effects, etc., depending on the progress of the match. In this way, it is possible to create a more exciting effect.

[0055] (Hardware configuration) 9 is a block diagram showing an example of a hardware configuration of a server 100 according to an embodiment. The server 100 includes a processor 110 such as a CPU (Central Processing Unit), and a storage unit having a program storage section 111 and a data storage section 112, and an input / output interface (hereinafter, the interface will be abbreviated as I / F) section 113 are connected to the processor 110 via a bus 114. In other words, the server 100 is a computer having a processor and a storage section.

[0056] The input / output I / F unit 113 has a communication interface function and communicates with the cloud 1 via a signal cable or a network.

[0057] The program storage unit 111 is configured by combining, for example, a non-volatile memory such as a solid state drive (SSD) as a storage medium that can be written / read at any time, and a non-volatile memory such as a read only memory (ROM), and stores application programs required for executing various control processes according to an embodiment, in addition to an operating system (OS), etc. Hereinafter, the OS and each application program will be collectively referred to as a program.

[0058] The data storage unit 112 is, for example, a combination of a non-volatile memory such as an SSD, which is writable / readable at any time, and a volatile memory such as a RAM (Random Access Memory), as a storage medium.

[0059] The processor 110 includes an analysis unit 110A having the functional blocks of Fig. 2 and / or a data processing unit 100B of Fig. 5 as processing functions necessary to implement one embodiment. These functional blocks are all realized by causing the processor 110 to execute an application program stored in the program storage unit 111. Some or all of these functional blocks may be realized using hardware such as an LSI (Large Scale Integration) or an ASIC (Application Specific Integrated Circuit).

[0060] As described above, in the embodiment, a database (characteristics-knowledge database 101) is constructed to hold data for increasing the sense of unity and enthusiasm according to the user's attributes and knowledge level. Then, knowledge appropriate for each user is assigned to the content based on the user's characteristics such as interests and knowledge based on gaze measurement by sensing or the like. This makes it possible to provide an environment that increases the sense of unity and enthusiasm when watching sports according to the user's knowledge and attributes level. In addition, by providing user feedback to the system, the database is dynamically updated according to whether the knowledge assignment was successful or not. This makes it possible to improve the accuracy of the assigned knowledge.

[0061] This allows sports fans to feel a greater sense of unity, enthusiasm, and realism while watching, and also allows users who are not familiar with sports to better understand and enjoy sports.

[0062] Among existing technologies, there is a technology that recommends new videos to users by acquiring videos that match the user's interests, which change from moment to moment. This technology detects the user's interests and attention level and dynamically changes the display, but it only switches the content itself and cannot add information to the content to improve its value. There is also a technology that automatically positions subtitles in the direction of the user's gaze. However, it did not take into consideration reflecting the interest characteristics of each user.

[0063] In addition, because the attributes and knowledge levels of supporters and users are unknown and sensing is not possible, it is unclear what information would be valuable to present. This type of information is the tacit knowledge of club management and editors, and has not been modeled. In addition, while technology is known for adding subtitles to support the hearing impaired, technology to support those who are not familiar with the subject is still unknown.

[0064] In response to this, in the embodiment, user characteristics such as interests and knowledge are acquired, and knowledge that enhances the sense of unity and enthusiasm is imparted according to the user's attributes and knowledge level. This makes it possible to provide an environment that enhances the sense of unity and enthusiasm when watching sports. For example, by applying the technology of the embodiment to watching sports, fans who are knowledgeable about sports can watch with a greater sense of unity, enthusiasm, and realism, and users who are not familiar with sports can understand and enjoy sports better. As a result, according to the embodiment, everyone who watches can enjoy the content, regardless of their attributes or knowledge level.

[0065] The present invention is not limited to the above embodiment. For example, the assigned data may be output as characters on a display medium, or may be an easier-to-understand animation or sound. Visual information may be displayed not only on a display, but also on the goggles 11 or AR glasses (goggles) of each user. In addition, the content of interest of each user can be estimated based on gaze data, or can be estimated by referring to interests in other content. For example, a user who often watches quick movements in basketball is assigned knowledge about players and techniques with quick movements in soccer. Furthermore, the subject of interest can be estimated not only from the gaze but also from biological information (vital data) such as heart rate and sweat rate.

[0066] In addition to creating a database of information to be provided when an event occurs according to knowledge and attributes, a method of presenting the information to be provided may also be created in a database. In other words, a database of the optimal means of presenting information according to the environment and situation may be created. Furthermore, the target of user sensing is not limited to individuals; information on similar communities of sports fans may also be utilized. Variations in the information and content that can be fed back include the status of others, players, and staff, sports content scenes, and player performance "STATS" information.

[0067] As an example of varying the feedback content according to attributes and context, the feedback content may be determined by referring to a historical database of accumulated fluctuations in excitement, unity, and enthusiasm, or the feedback content may be determined according to the attributes of the user watching (such as age or place of residence).

[0068] The sensing location (when sensing is OFF) can be set regardless of whether it is a remote location or a stadium. If the remote location is a home, sensing may be OFF, so in that case, information can be added using results from other venues or locations with similar attributes.

[0069] The output method according to the context and the update of data by acquiring reactions provide feedback (displayed on the screen) that enhances the sense of unity, enthusiasm, realism, etc. Furthermore, the feedback content may be determined using data stored in cloud 1.

[0070] The embodiments of the present invention have been described with reference to Examples 1 to 3 and Modifications 1 to 3. The above description is merely an example of the present invention in every respect. It goes without saying that various improvements and modifications can be made without departing from the scope of the present invention. In other words, specific configurations according to the embodiments may be appropriately adopted when implementing the present invention.

[0071] In short, this invention is not limited to the above-mentioned embodiment as it is, and in the implementation stage, the components can be modified and embodied without departing from the gist of the invention. In addition, various inventions can be formed by appropriately combining multiple components disclosed in the above-mentioned embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, components from different embodiments may be appropriately combined.

[0072] (References) References[1] Fujimoto et al., "Situation estimation model from a small number of live tweets and sports spectator support," Proceedings of the 13th Forum on Data Engineering and Information Management, 2021. [Explanation of symbols]

[0073] 1. Cloud 11. Goggles 12. Smartphone 13...Terminal equipment 14. Smartwatch 15…Mike 16…Camera 31...Input processing unit 32...Human recognition processing section 33…Judgment section 34…Database Update Division 35…Content Analysis Department 36…Fan Attributes Registration Section 41...Output content generation unit 42...Output processing unit 100…Server 100A…Analysis department 100B...Data processing unit 101…Characteristics – Knowledge Database 102...Sensing data processing unit 103...User characteristic estimation unit 104…Added knowledge determination unit 105...Output processing unit 106…Feedback reflection section 110…Processor 110A…Analysis department 111…Program memory section 112...Data storage unit 113... Input / Output I / F section 114…Bus 200...Content distribution server.

Claims

1. a database for storing, for each user of a sports content to be distributed, a user's characteristics and knowledge information regarding the sports content in association with each other; A server capable of accessing the database, The server, A data processing unit that obtains an attribute of the user with respect to the sports content; and an analysis unit that refers to the database based on the attribute and generates knowledge information to be presented to the user.

2. The data processing unit includes: a sensing data processing unit that acquires a gaze direction of the user with respect to the sports content; a user characteristic estimation unit that identifies a gaze area of ​​the user with respect to the sports content from the gaze direction and estimates characteristics of the user based on the result of the identification; The information presentation system according to claim 1 , further comprising: an additional knowledge determination unit that generates the knowledge information by referring to the database based on the estimated characteristics.

3. The information presentation system according to claim 1 , wherein the server further comprises a feedback reflection unit that updates the contents of the database in response to the user's reaction to the generated knowledge information.

4. A remote control method executed by a computer that can access a database that holds, for each user of distributed sports content, characteristics of the user and knowledge information about the sports content in association with each other, the database comprising: obtaining an attribute of the user for the sports content; and generating knowledge information to be presented to the user by referring to the database based on the attribute.

5. a processor of a computer that can access a database that holds, for each user of distributed sports content, characteristics of the user and knowledge information about the sports content in association with each other; A data processing unit that obtains an attribute of the user with respect to the sports content; a program that functions as an analysis unit that references the database based on the attribute and generates knowledge information to be presented to the user;

Citation Information

Patent Citations

  • Video recommendation method, video recommending apparatus, video recommendation program and computer-readable recording medium with the program stored

    JP2009302985A