Information processing system, information processing method, and program

Abstract

To properly assist reactions from a content distributor in a field of content distribution.SOLUTION: A program causes a computer to execute the processes of: managing past content distributed by a distributor, and activity information, for each viewer, related to activities allowed for the viewers who view at least one of the past content and content currently distributed by the distributor; managing setting information related to reactions of the distributor; obtaining multiple actions from one or more viewers who are viewing the content currently distributed by the distributor; and automatically generating reaction candidates that the distributor can take for one or more specific actions out of multiple actions, on the basis of the activity information and the setting information.SELECTED DRAWING: Figure 15

Description

[Technical field]

[0001] The present disclosure relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] A technology is known that allows salespeople to navigate sales talks appropriately according to the situation of the conversation at any given time by dynamically changing what they should say next in business negotiations that are conducted through flexible conversation and proposing changes based on classifications that change dynamically according to the progress of the negotiation and the intentions of the statements made by the salespeople and customers involved at that time. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-009535 Summary of the Invention [Problem to be solved by the invention]

[0004] In the field of content distribution, with the conventional techniques as described above, it is difficult for a distributor to appropriately support reactions to a large number and diverse actions from a large number and diverse audience.

[0005] Therefore, in one aspect, the present disclosure aims to appropriately support reactions from distributors in the field of content distribution. [Means for solving the problem]

[0006] In one aspect, activity information regarding activities that a viewer who views at least one of past content distributed by a distributor and the past content and the content currently being distributed by the distributor can perform is managed for each viewer; Manage settings information regarding the distributor's reactions; obtaining a plurality of actions from one or more viewers viewing content currently being distributed by the distributor; A program is provided that causes a computer to execute a process to automatically generate reaction candidates that can be taken by the distributor in response to one or more specific actions among the plurality of actions based on the activity information and the setting information. Effect of the Invention

[0007] In one aspect, the present disclosure makes it possible to appropriately support reactions from distributors in the field of content distribution. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram of an information distribution system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a schematic diagram illustrating an example of a hardware configuration of a server device. [Diagram 3] FIG. 2 is a schematic diagram illustrating an example of a hardware configuration of a terminal device. [Figure 4A] FIG. 2 is an explanatory diagram of a terminal image viewable through a head mounted display. [Figure 4B] FIG. 11 is an explanatory diagram of a terminal image viewable via a smartphone. [Diagram 5] FIG. 2 is a schematic diagram for explaining an overview of the overall processing of the present embodiment. [Figure 6] FIG. 13 is a diagram showing an example of content being distributed. [Figure 7] 11 is a schematic flowchart showing an overview of a reaction candidate derivation process. [Figure 8] FIG. 11 is an explanatory diagram showing an example of an output screen of reaction candidates. [Figure 9] 1 is an example of a functional block diagram of an information distribution system 1. FIG. [Figure 10] FIG. 2 is an explanatory diagram of information relating to users (viewers). [Figure 11] FIG. 11 is an explanatory diagram of activity information. [Figure 12] FIG. 4 is an explanatory diagram of setting information. [Figure 13] FIG. 13 is an explanatory diagram of the relationship between the amount charged per viewer and the number of comments. [Figure 14] FIG. 13 is an explanatory diagram of achievements. [Figure 15] FIG. 13 is an explanatory diagram of the analysis results of viewer emotions. [Figure 16] FIG. 13 is an explanatory diagram of the results of grouping a set of viewers. [Figure 17] FIG. 11 is an explanatory diagram of an example of a relationship between comments and reaction candidates. [Figure 18] FIG. 11 is an explanatory diagram of another example of the relationship between comments and reaction candidates. [Figure 19] FIG. 11 is an explanatory diagram of yet another example of the relationship between comments and reaction candidates. [Figure 20] FIG. 1 is an explanatory diagram of a method for generating reaction candidates using a large-scale language model. [Figure 21] 1 is a flowchart illustrating an example of the operation of the information distribution system. [Figure 22] 22 is a flowchart relating to comment processing (step S2108) in FIG. 21. [Figure 23] 22 is a flowchart showing the reaction process (step S2112) in FIG. 21. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, each embodiment will be described in detail with reference to the accompanying drawings. Note that in the accompanying drawings, for ease of viewing, only some of the reference symbols may be attached to multiple parts having the same attribute.

[0010] Hereinafter, an embodiment will be described with reference to the drawings.

[0011] An overview of an information distribution system 1 according to an embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a block diagram of the information distribution system 1 according to the present embodiment.

[0012] The information distribution system 1 includes a server device 10 and one or more terminal devices 20. For simplicity, three terminal devices 20 are illustrated in Fig. 1, but the number of terminal devices 20 may be two or more.

[0013] The server device 10 is an information processing system such as a server managed by an operator who provides an information distribution platform. The terminal device 20 is a device used by a user, such as a mobile phone, a smartphone, a tablet terminal, a PC (Personal Computer), a head-mounted display, or a game device. A plurality of terminal devices 20 can be connected to the server device 10 via the network 3, typically in a different manner for each user.

[0014] The terminal device 20 is capable of executing an information distribution application according to this embodiment. The information distribution application may be received by the terminal device 20 from the server device 10 or a predetermined application distribution server via the network 3, or may be stored in advance in a storage device provided in the terminal device 20 or a storage medium such as a memory card readable by the terminal device 20. The server device 10 and the terminal device 20 are communicatively connected via the network 3. For example, the server device 10 and the terminal device 20 cooperate to execute various processes related to information distribution.

[0015] In the information distribution system 1, users may be classified into a distribution side (content distribution side) and a viewer side (content viewing side). The organizer side of one distribution content may be one user or multiple users (i.e., collaboration by multiple distributors). When the users are classified into a distribution side and a viewer side, the terminal device 20 includes a terminal device 20A on the distribution side (content distribution side) and a terminal device 20B on the viewer side (content viewing side). In the following, for the sake of explanation, the terminal device 20A on the distribution side and the terminal device 20B on the viewer side are described as separate terminal devices, but the terminal device 20A on the distribution side may become the terminal device 20B on the viewer side, or vice versa. In the following, when the terminal device 20A and the terminal device 20B are not particularly distinguished from each other, they may be simply referred to as "terminal device 20".

[0016] The terminal devices 20 are connected to each other so as to be able to communicate with each other via the server device 10. In the following, "one terminal device 20 transmits information to another terminal device 20" means "one terminal device 20 transmits information to another terminal device 20 via the server device 10". Similarly, "one terminal device 20 receives information from another terminal device 20" means "one terminal device 20 receives information from another terminal device 20 via the server device 10". However, in a modified example, the terminal devices 20 may be connected to each other so as to be able to communicate with each other without going through the server device 10.

[0017] The network 3 may include a wireless communication network, the Internet, a Virtual Private Network (VPN), a Wide Area Network (WAN), a wired network, or any combination of these.

[0018] 1, the information distribution system 1 includes studio units 30A and 30B. The studio units 30A and 30B are distribution-side devices, similar to the distribution-side terminal device 20A. The studio units 30A and 30B may be arranged in a studio, room, hall, or the like for content production.

[0019] Each studio unit 30 can have the same functions as the terminal device 20A on the distribution side and / or the server device 10. In the following, when the distribution side and the viewing side are distinguished from each other, for the sake of simplicity, a mode in which the terminal device 20A on the distribution side distributes various contents to the terminal device 20B on each viewing side via the server device 10 will be mainly described. However, instead of or in addition to this, the studio units 30A and 30B facing the distributor may have the same functions as the terminal device 20A on the distribution side, thereby distributing various contents to the terminal device 20B on each viewing side via the server device 10. In a modified example, the information distribution system 1 may not include the studio units 30A and 30B.

[0020] In the following, the information distribution system 1 realizes an example of an information processing system, but each element of a specific terminal device 20 (see FIG. 3) may realize an example of an information processing system, or a plurality of terminal devices 20 may cooperate to realize an example of an information processing system. Also, the server device 10 may independently realize an example of an information processing system, or the server device 10 and one or more terminal devices 20 may cooperate to realize an example of an information processing system.

[0021] Fig. 2 is a schematic diagram showing an example of a hardware configuration of the server device 10. Fig. 2 also shows a peripheral device 129 in association with the hardware configuration of the server device 10. The peripheral device 129 is optional, and may be a display or the like.

[0022] The server device 10 includes a CPU (Central Processing Unit) 111, a RAM (Random Access Memory) 112, a ROM (Read Only Memory) 113, an auxiliary storage device 114, a drive device 115, and a communication interface 117, all connected via a bus 119, as well as a wired transceiver unit 125 and a wireless transceiver unit 126 connected to the communication interface 117.

[0023] The auxiliary storage device 114 is, for example, a hard disk drive (HDD) or a solid state drive (SSD), and is a storage device that stores data related to application software and the like.

[0024] The wired transceiver 125 includes a transceiver capable of communicating over a wired network. Peripheral devices 129 are connected to the wired transceiver 125. However, some or all of the peripheral devices 129 may be connected to the bus 119 or may be connected to the wireless transceiver 126.

[0025] The wireless transceiver 126 is a transceiver capable of communicating over a wireless network. The wireless network may include the network 3 described above.

[0026] The server device 10 may be connectable to a recording medium 116. The recording medium 116 stores a predetermined program. The program stored in the recording medium 116 is installed in the auxiliary storage device 114 of the server device 10 via the drive device 115. The installed predetermined program can be executed by the CPU 111 of the server device 10. For example, the recording medium 116 may be a recording medium that records information optically, electrically, or magnetically, such as a CD (Compact Disc)-ROM, a flexible disk, or a magneto-optical disk, or a semiconductor memory that records information electrically, such as a ROM or a flash memory.

[0027] 3 is a schematic diagram showing an example of the hardware configuration of the terminal device 20. In FIG. 3, a peripheral device 260 is illustrated in association with the hardware configuration of the server device 10.

[0028] The terminal device 20 includes a CPU 211, a RAM 212, a ROM 213, an auxiliary storage device 214, a drive device 215, and a communication interface 217 connected by a bus 219, as well as a wired transceiver unit 225 and a wireless transceiver unit 226 connected to the communication interface 217.

[0029] The auxiliary storage device 214 is, for example, an HDD or SSD, and is a storage device that stores data related to application software and the like.

[0030] The wired transceiver 225 includes a transceiver capable of communicating over a wired network. Peripheral devices 260 are connected to the wired transceiver 225. However, some or all of the peripheral devices 260 may be connected to the bus 219 or may be connected to the wireless transceiver 226.

[0031] The wireless transceiver 226 is a transceiver capable of communicating over a wireless network. The wireless network may include the network 3 described above.

[0032] The terminal device 20 may be connectable to a recording medium 216. The recording medium 216 stores a predetermined program. The program stored in the recording medium 216 is installed in the auxiliary storage device 214 of the terminal device 20 via the drive device 215. The installed predetermined program can be executed by the CPU 211 of the terminal device 20. For example, the recording medium 216 may be a recording medium that records information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, or a magneto-optical disk, or a semiconductor memory that records information electrically, such as a ROM or a flash memory.

[0033] The peripheral devices 260 are optional, but in this embodiment, include a display device 2623 and an input device 2624 .

[0034] The display device 2623 includes a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The display device 2623 is capable of displaying various images. The display device 2623 is configured with, for example, a touch panel, and functions as an interface for detecting various user operations. The display device 2623 may be built into a head-mounted display.

[0035] The input device 2624 may include a physical key, or may further include any input interface including a pointing device such as a mouse. The input device 2624 may be capable of accepting non-contact user input such as voice input, gesture input, and gaze input. For gesture input, a sensor (such as an image sensor, an acceleration sensor, or a distance sensor) for detecting various states of the user, a dedicated motion capture device integrating sensor technology and a camera, or a controller such as a joypad may be used. The camera for gaze detection may be disposed in a head-mounted display. As described above, the various states of the user are, for example, the user's orientation, position, movement, or the like. In this case, the user's orientation, position, and movement are concepts that include not only the orientation, position, and movement of a part or the whole of the user's body such as the face or hands, but also the orientation, position, movement, or the like of the user's gaze.

[0036] The viewer can view the distributed content via the terminal device 20B on the viewing side. The distributed content may be content in a virtual space in which an avatar can move around. For example, in the case of a head-mounted display, the terminal device 20B may generate a stereoscopic image for the head-mounted display by generating images G200 and G201 that are viewed by the left and right eyes, respectively, as shown in FIG. 4A. In FIG. 4A, the images G200 and G201 that are viewed by the left and right eyes, respectively, are shown typically. In the following, unless otherwise specified, the content in the virtual space refers to the content represented by the images G200 and G201. For example, the content may be content that involves various movements of an avatar in the virtual space. In this case, the terminal device 20A on the distribution side realizes various movements of the avatar in the virtual space, for example, in response to various operations by the distributor.

[0037] The virtual space described below is a concept including not only a continuous three-dimensional space that is immersive and visible using a head-mounted display or the like, in which a user can move around freely (as in reality) via an avatar, but also a non-immersive space that is visible using a smartphone or the like as shown in Fig. 4B. The non-immersive space that is visible using a smartphone or the like may be a continuous three-dimensional space in which a user can move around freely via an avatar, or may be a two-dimensional discontinuous space.

[0038] Fig. 5 is a schematic diagram for explaining an overview of the overall processing of this embodiment. In Fig. 5, the elements of the viewer, server device 10 (abbreviated as "server" in Fig. 5), database, and distribution user are shown at the top, and the operation of each element during content distribution is shown below. Fig. 6 is a diagram showing an example of content being distributed. Fig. 7 is a schematic flow chart showing an overview of the reaction candidate derivation processing. Fig. 8 is an explanatory diagram showing an example of an output screen for reaction candidates.

[0039] In this embodiment, while a piece of content is being distributed, the viewer freely generates comments via the terminal device 20B (S2100) and transmits them to the server device 10 (S2110). Although only one viewer is shown in FIG. 5, in reality there may be many viewers. Thus, the server device 10 may receive many comments at various times while a piece of content is being distributed. Here, comments are described as an action from a viewer, but the same applies to other actions such as the granting of other billing media from the viewer to the distributor (the act of giving a gift to the distributor).

[0040] When the server device 10 receives (obtains) a comment (step S2200), it outputs the comment to the distributor (and all viewers) and updates the activity information related to the viewer in the database (activity information DB2302) based on the comment (S2210). The activity information may be managed for each viewer. Note that the comment is not limited to a text message, but is a concept including a voice message, a display expressing an emote, a gesture by an avatar, emoji, a stamp, and the like. In this case, reaction candidates can be automatically generated for comments in various forms by a reaction candidate creation process described later. The comment may be output in the content as shown in FIG. 6. In this case, the distributor and all viewers can see the comment. In the example shown in FIG. 6, content including an avatar M2 of the distributor is distributed, and an image G6 (an image of a certain frame) related to the content includes a comment display field G11. In the comment display field G11, comments from each viewer may be displayed (output) sequentially (for example, in the order of reception). Since the number of comments that can be displayed in the comment display field G11 is limited, the comment display field G11 may be updated in such a manner that only the latest predetermined number of comments are always displayed in the comment display field G11.

[0041] Also, the comment may be output to different locations depending on the attribute. For example, in the example shown in Fig. 6, the image G6 (image of a certain frame) related to the content has comments G12 and G109 with other attributes superimposed on it in an area other than the comment display field G11. The comment G109 indicates a request for a collaboration broadcast.

[0042] Also, during the distribution of a piece of content, viewers, like comments, can acquire (purchase, etc.) Super Chat, gifts, tips, tips or similar billing media via terminal device 20B (S2100) and transmit them to server device 10 as a present to the distributor (S2110).

[0043] When the server device 10 receives (obtains) the billing medium (step S2200), it outputs the billing medium and updates the activity information of the viewer in the database (activity information DB2302) based on the billing medium (S2210). In the example shown in Fig. 6, a gift G12A corresponding to the billing medium is superimposed on an image G6 (an image of a certain frame) related to the content. Note that the method of outputting the billing medium is not limited to this and is arbitrary.

[0044] The activity information related to a viewer may be activity information related to content and communication with a distributor, etc. The activity information related to a viewer relates to at least one of the content of the viewer's comments, the frequency of comments posted by the viewer, the history of comments posted, the history of billing media (including total amount, average, etc.), and information that can be derived based on any one or more of these. The activity information may be the value of one or more index parameters calculated based on some or all of these parameters (e.g., the number of comments, the total amount of billing media, etc.). In this case, an index value parameter that can comprehensively judge the viewer's activities can be used.

[0045] The server device 10 performs a reaction candidate derivation process (step S2220) while performing the comment output / storage process in this manner. The reaction candidate derivation process is a process for automatically generating reaction candidates (hereinafter referred to as "reaction candidates") that can be taken by the distributor in response to one or more specific comments among a plurality of comments (actions) from one or more viewers.

[0046] The output form of the reaction is arbitrary, and may be a visual output of a comment or text, an acoustic output of a comment (output of a voice message), a gesture output, or any combination of these. The gesture output may be an output via a display medium such as an avatar. Furthermore, the gesture output may involve only a movement of a part of the body (e.g., a hand or a face), or may involve a movement of the whole body or using other tools, etc. In the following, unless otherwise specified, the output form of the reaction is assumed to be in the form of a comment as an example, and the reaction candidates are also assumed to be in the form of a comment.

[0047] 7, the reaction candidate derivation process reads setting information from the setting information database DB2300 (step S700). When the setting information in the setting information database DB2300 is updated in real time, the setting information may be read from the setting information database DB2300 at high frequency.

[0048] The setting information may be prepared for each broadcaster. In this case, setting information suited to the way of thinking and preferences, which may differ for each broadcaster, can be used. The setting information relates to priorities for various situations. The various situations may include at least one of the contents or situations of the comments and the situations of the viewers. The setting information may be set (customizable) by the broadcaster, or may be automatically updated according to the characteristics of the broadcaster based on artificial intelligence.

[0049] The content or status of the comment may include at least one of whether or not it is a request or question from the viewer, and whether or not the request or question should be answered. The status of the viewer may be whether or not the viewer is a first-time viewer, whether or not the viewer is a regular viewer, whether or not the viewer has been watching for a long period of time or more, whether or not the viewer has not seen the content in a long time, etc., and specific examples will be described later.

[0050] Incidentally, while it is possible for a distributor to react to all of the many comments sent during distribution of one piece of content, it is unrealistic. Therefore, it is more efficient to automatically generate reaction candidates only for one or more specific comments selected according to a specific priority than to automatically generate reaction candidates for all comments.

[0051] Therefore, in this embodiment, the reaction candidate derivation process selects (extracts) one or more specific comments according to the priority order related to the setting information by the distributor (step S702). Note that the extraction process of one or more specific comments may be executed collectively for a predetermined number of comments each time the number of comments are accumulated. Alternatively, it may be executed in a manner that determines whether each comment is a specific comment (a comment for which a reaction candidate is generated) each time the comment is received.

[0052] In this case, regarding the setting information, which of the various situations is to be given the highest priority, which situation should be given priority over which other situations, etc. may be automatically set (for example, suggested based on artificial intelligence). This can reduce the burden on the distributor. Alternatively, which of the various situations is to be given the highest priority, which situation should be given priority over which other situations, etc. may be freely set by the distributor. This can generate appropriate reaction candidates according to various situations according to the priority that may differ for each distributor.

[0053] Here, comments that are not extracted as one or more specific comments are comments for which no reaction candidates are generated. Therefore, no reaction based on the reaction candidates is made to such comments. However, in this case, it can also be interpreted that a reaction such as "ignoring" or "leaving" is made to such comments.

[0054] In another embodiment, one or more specific comments may be extracted after selecting and excluding comments for which the appropriate reaction is "ignore" or "leave alone." In this case, the population from which one or more specific comments are extracted can be reduced, so that one or more specific comments can be efficiently selected (extracted), and the processing load can be reduced.

[0055] Here, in order to maintain order in a place, it may be effective to "ignore" or "leave" comments made by viewers that disrupt the place or make excessively many comments (comment posting frequency). In such a situation, it is useful to prevent such comments from being extracted as one or more specific comments.

[0056] The setting information for each distributor may be updated (changed) at any time by the corresponding distributor. In addition, various conditions related to the setting information may be set for each distributor, and the granularity (fineness) of the various conditions may also be set for each distributor.

[0057] The reaction candidate derivation process automatically generates (derives) reaction candidates for one or more extracted specific comments (step S704). In this case, the reaction candidate derivation process may automatically generate a common reaction candidate for two or more extracted specific comments, or may automatically generate separate reaction candidates for each of the comments. For example, if two or more extracted specific comments have the same or similar content, a common reaction candidate may be automatically generated.

[0058] The method of automatically generating reaction candidates for a particular comment is arbitrary, and the details of the method of automatically generating reaction candidates will be described later.

[0059] When the server device 10 derives the reaction candidates in this way, it transmits the reaction candidates to the terminal device 20A of the corresponding distributor (step S2230). The transmission of the reaction candidates to the terminal device 20A of the distributor may be performed in real time each time a reaction candidate is derived, or may be transmitted all at once after a certain number of reaction candidates are derived.

[0060] When the distributor's terminal device 20A receives the reaction candidates, it presents (displays) the reaction candidates to the distributor by visually (or visually and acoustically) outputting them (step S2400). Fig. 8 shows an example of a user interface suitable for presenting the reaction candidates to the distributor.

[0061] 8, the number of comments, the comment ranking, the total charge, the elapsed time (minutes), the status, the comment, the to-do, and the reaction candidate are associated with each user representing a viewer. In this case, the number of comments, the comment ranking, the total charge, and the elapsed time (minutes) are examples of activity information.

[0062] The number of comments is the number of comments posted by the corresponding viewer, and may be the number of comments posted during the current content distribution, or the total number of comments posted across multiple contents distributed by the same distributor in the past. The comment ranking is a ranking of the number of comments posted. The comment ranking may be a ranking during the current content distribution, or a ranking based on the total number of comments posted across multiple contents distributed by the same distributor in the past. The total charge is the sum of the charges for the corresponding viewer, and may be the total charge for all contents distributed by the same distributor in the past. The charge is an index value of the economic value of the billing medium. The elapsed time (minutes) may be the elapsed time from the time of the most recent comment posting (the elapsed time at the current time). The status is the status of the corresponding viewer. The status may preferably be expressed by an emoji as shown in FIG. 8. In this case, each emoji may be associated with a predetermined status. The commentary is a commentary on the status (or the emoji corresponding to it), and may include an explanation of the status. The to-do indicates the reaction that the distributor should make, such as whether to react. The ToDo may indicate a reaction candidate when a reaction should be made. The ToDo may preferably be expressed by an Emoji as shown in FIG. 8. In this case, each Emoji may be associated with a predetermined ToDo (things to do). The viewers to whom the ToDo Emoji is associated correspond to the viewers who have made one or more specific comments described above. The Reaction candidates are the reaction candidates described above.

[0063] In the case shown in Figure 8, the streamer can intuitively recognize the viewer's situation and ToDos through Emoji. Emoji, in particular, is different from normal language in that it does not require translation and can be understood by streamers with various native languages ​​(i.e., it can be made into multiple languages), reducing the processing load of translation, etc. This makes it possible to present reaction candidates in a manner that suits the circumstances of streamers who cannot devote much time to selecting reaction candidates, etc.

[0064] The relationship between the various emojis and the corresponding situations may be fixed uniformly, or may be changeable by the distributor. In addition, some of the various emojis may be created independently by the distributor. In this case, the correspondence is easy for the distributor to understand, making it even easier to select reaction candidates.

[0065] Each item shown in FIG. 8 may be set by each distributor. For example, a certain distributor may set to output only the comment ranking, the elapsed time (minutes), the status, and the reaction candidate among the number of comments, the comment ranking, the total charge amount, the elapsed time (minutes), the status, the comment, the ToDo, and the reaction candidate. Also, the number of items may be changed according to the attribute of the terminal device 20A of the distributor. For example, when the terminal device 20A of the distributor is a terminal with a relatively small screen (e.g., a smartphone), the number of items may be less than when the terminal device 20A is a terminal with a relatively large screen (e.g., a desktop personal computer).

[0066] The distributor inputs a reaction instruction via the terminal device 20A (step S2410). The reaction instruction may be generated automatically or in response to a predetermined input from the distributor. The predetermined input is arbitrary, but may be input, for example, via a user interface as shown in FIG. 8. In this case, when an emoji is selected, a reaction instruction may be generated that causes a reaction candidate corresponding to the selected emoji to be output as a reaction. In this case, a reaction instruction that causes a corresponding reaction candidate to be output as a reaction can be generated simply by performing the intuitive operation of selecting an emoji. Note that if it is determined that a reaction is not necessary, the distributor will not input a reaction instruction.

[0067] When the server device 10 receives a reaction instruction in this manner, it outputs (superimposes) a reaction corresponding to the reaction instruction on the distributed content (step S2240). This makes the reaction viewable to viewers (step S2120). In Fig. 6, a comment G13 is shown as an example of a reaction. Note that the reaction is output in a manner that can be viewed by all viewers, but it may also be output in a manner that can be viewed only by the intended viewers.

[0068] In this manner, according to this embodiment, activity information of each viewer is referenced, and one or more specific comments are extracted in a priority order according to the setting information set by the distributor. Then, reaction candidates are generated only for the specific comments extracted, and presented to the distributor. The setting information can be set (customized, etc.) by the distributor, which increases the likelihood that the distributor will be able to react appropriately and efficiently to the desired comment (and therefore the desired viewer). As a result, in the field of content distribution, reactions from distributors can be appropriately supported.

[0069] Note that the various processes of the information distribution system 1 described above with reference to Figures 5 to 8 are executed in real time while the content is being distributed, but some of the processes may be executed offline. For example, a reaction candidate derivation process is preferably executed in real time, but a certain degree of effect can be expected even if it is executed offline. For example, after distribution, a distributor may individually output reactions to specific viewers. The reaction candidate derivation process described above can also be applied to such reactions.

[0070] Next, the information distribution system 1 will be described in further detail with reference to FIG. 9 and subsequent figures.

[0071] FIG. 9 is an example of a functional block diagram of the information distribution system 1. FIG. 10 is an explanatory diagram of information on users (viewers). FIG. 11 is an explanatory diagram of activity information. FIG. 12 is an explanatory diagram of setting information. FIG. 13 is an explanatory diagram of the relationship between the charge amount for each viewer and the number of comments. FIG. 14 is an explanatory diagram of achievements. FIG. 15 is an explanatory diagram of the analysis result of the viewer's emotions. FIG. 16 is an explanatory diagram of the result of grouping a set of viewers. FIG. 17 is an explanatory diagram of an example of the relationship between comments and reaction candidates. FIG. 18 is an explanatory diagram of another example of the relationship between comments and reaction candidates. FIG. 19 is an explanatory diagram of yet another example of the relationship between comments and reaction candidates. FIG. 20 is an explanatory diagram of a method of generating reaction candidates using a large-scale language model. In FIG. 10 (as well as FIG. 12 and the like), "***" indicates a state in which some information is stored, and "..." indicates a state in which the same information is repeatedly stored. In Figs. 17 to 19, a part of the chronological order of comments made during content distribution is shown on the upper side, and examples of corresponding reaction candidates are shown on the lower side.

[0072] Each unit of the information delivery system 1 described below may be realized by the server device 10 alone. In this case, the data output by the reaction candidate generation processing unit 172 and / or the reaction output unit 174 may be received by the terminal device 20A and output to the display device 2623 (see FIG. 3). Alternatively, each unit of the information delivery system 1 described below may be realized by the terminal device 20A alone (i.e., without the server device 10). In this case, some information (activity information related to the content of other distributors) of the activity information storage unit 150 described below and some information (information related to other distributors) of the setting information storage unit 152 may not be stored. Alternatively, each unit of the information delivery system 1 described below may be realized by a combination of the server device 10 and the terminal device 20A. In this case, for example, some or all of the functions of the reaction candidate generation processing unit 172 and / or the reaction output unit 174 may be realized by the terminal device 20A alone.

[0073] The information distribution system 1 includes an activity information memory unit 150, a setting information memory unit 152, an activity information management unit 154, a setting information management unit 156, a distribution content processing unit 160, an action acquisition unit 162, a situation determination unit 164, a sentiment analysis unit 166, an emoji matching processing unit 168, a comment flow analysis unit 170, a reaction candidate generation processing unit 172, and a reaction output unit 174.

[0074] The activity information storage unit 150 and the setting information storage unit 152 can be realized by, for example, the auxiliary storage device 114 shown in FIG. 2 or the auxiliary storage device 214 shown in FIG.

[0075] In addition, each of the sections from the activity information management unit 154, the setting information management unit 156, and the distribution content processing unit 160 to the reaction output unit 174 can be realized by the CPU 111 shown in FIG. 2 or the CPU 211 shown in FIG. 3 executing one or more programs stored in a storage device (e.g., ROM 113, 213, etc.) shown in FIG. 2 or FIG. 3.

[0076] The activity information storage unit 150 stores activity information related to viewers. The activity information is as described above. The activity information may be managed for each distributor. FIG. 10 shows activity information related to one distributor. In this case, the activity information is associated with a user ID together with a user name ("User" in FIG. 10). As shown in FIG. 11, the activity information related to one distributor may be managed for each user name ("User" in FIG. 10). In the example shown in FIG. 11, the activity information includes the number of comments, comment ranking, total charge, and elapsed time (minutes). Each of these parameters is as described above with reference to FIG. 8.

[0077] The activity information storage unit 150 may store activity information related to a distributor (e.g., activity information related to a reaction) in addition to activity information related to a viewer. In this case, the activity information related to a distributor may be used to generate reaction candidates related to the distributor.

[0078] The setting information storage unit 152 stores the setting information. The setting information is as described above. The setting information may be managed for each distributor. FIG. 12 shows the setting information for one distributor. In this case, the setting information associates reaction priorities and priorities with each of the various situations. The various situations are as described above. The various situations may be prepared as default settings, or may be customizable by the distributor. For example, situation A may include a situation related to the frequency of reactions from the distributor. For example, when a high priority is set for the frequency of reactions from the distributor, reaction candidates may be generated and presented to the distributor in a manner that allows a reaction for each relatively small number of comments.

[0079] The reaction priority indicates an absolute priority and may be indicated in three stages such as "high", "medium", and "low". The priority level indicates a relative priority and may be indicated in a rank such as first or second.

[0080] Incidentally, regarding the setting information, what circumstances a broadcaster places importance on may differ depending on the broadcaster, but it is also possible to generate recommended setting information for different purposes, for example. For example, recommended setting information may be generated based on artificial intelligence for each purpose, such as increasing the number of subscribers or participants, increasing the total amount charged, increasing the comment frequency (number of comments per unit time), etc., and presented to the broadcaster. At this time, the results of responses to a questionnaire given to the broadcaster may be used. In this case, the broadcaster can create original setting information based on the recommended setting information.

[0081] Here, as shown in FIG. 13, the relationship between the number of comments and the total charge amount may show a specific tendency. For example, in the example shown in FIG. 13, the viewers with the highest number of comments are not necessarily those with the highest total charge amount. Therefore, if the setting information only prioritizes a situation with a large number of comments over a situation with a large total charge amount, an effective increase in the total charge amount may not be realized. Similarly, if the setting information only prioritizes a situation with a large total charge amount over a situation with a large number of comments, an effective increase in the number of comments may not be realized. Therefore, the setting information may be adapted according to the purpose, etc. Also, by adapting the setting information, it is possible to realize distribution that is not dominated by some persistent or heavy chargers, and to prevent so-called spoilers.

[0082] In addition, the situations to be included in the various situations related to the setting information may be definable by the distributor. For example, in FIG. 12, the contents of each of situation A and situation B may be definable by the distributor. Furthermore, a situation that is a request or question from a viewer, or a situation in which a request or question should be answered, may be associated with a relatively high priority by default. In this case, the importance of the request or question may also be determined. Furthermore, a situation as to whether or not a specific keyword is included in a comment may be determined. In this case, the specific keyword related to a situation to which a high priority is assigned may be set by the distributor. The specific keyword may include an emoji, etc.

[0083] The various situations related to the setting information may include the emotional situations of the viewer. In this case, the setting information may be set such that a situation in which negative emotions such as anger predominates is given a higher priority than a situation in which positive emotions such as joy predominate.

[0084] The activity information management unit 154 executes various management processes, such as a storage process for storing activity information in the activity information storage unit 150 and an update process for updating the activity information in the activity information storage unit 150. For example, when the action acquisition unit 162 described later acquires various actions from the viewer, the activity information management unit 154 may update the activity information in the activity information storage unit 150 accordingly. The activity information may be updated in real time, or periodically or irregularly. For example, the activity information may be updated for each piece of content. In this case, it is possible to reduce processing load compared to updating in real time.

[0085] The setting information management unit 156 executes various management processes, such as a storage process for storing setting information in the setting information storage unit 152, and an update process for updating activity information in the setting information storage unit 152. For example, the setting information management unit 156 executes the management process based on an input from a distributor.

[0086] The distribution content processing unit 160 manages the distribution of content by each viewer. The form of content distribution is arbitrary, and may be live distribution. In addition, the distribution may be a distribution in which a human broadcaster appears as is, a distribution using an avatar related to a human broadcaster, a distribution related to a robot (e.g., artificial intelligence), a distribution by collaboration of multiple broadcasters, a viewer participation type distribution, or any combination of these. For example, the first half of the distribution may be a distribution related to a robot broadcaster, and the second half may be a distribution by collaboration of multiple broadcasters. The speaking part of the distribution may be performed by a human broadcaster (or a corresponding avatar), and the reaction (for example, a comment by the broadcaster to the viewer in the comment section) may be performed by a broadcaster of a robot (e.g., artificial intelligence). In addition, in a very long distribution such as a 24-hour distribution, a certain time period (e.g., from 9 p.m. to 11 p.m.) may be performed by a human broadcaster (or a corresponding avatar), and the other time periods may be performed by a broadcaster of a robot (e.g., artificial intelligence). In such diverse modes of distribution, various functions such as the above-mentioned action candidate generation processing unit 172 may be executed not only during the distribution period by a human distributor, but also during the distribution period by a robot (e.g., artificial intelligence) distributor.

[0087] The distribution content processing unit 160 may implement artificial intelligence that supports the distributor and / or artificial intelligence that controls the direction of the program, the camera (e.g., a virtual camera for generating content), sound effects, etc. The distribution content processing unit 160 may reduce the volume and point the camera while the speaker is speaking. In addition, while the speaker is speaking, it may control other sounds (e.g., interruptions such as reading out comments from viewers) to prevent sounds and / or various effects from clashing.

[0088] The action acquisition unit 162 acquires various actions from viewers. The action acquisition unit 162 may function for each piece of content. The various actions are acts that are the subject of reactions from distributors, and may typically be posting of comments, purchasing billable media, etc. Note that the various actions are related to activity information.

[0089] The situation determination unit 164 determines various situations based on the activity information. The situation determination unit 164 may function for each content. The situation determination unit 164 preferably functions in real time during the distribution of the corresponding content, and determines (detects) various situations that may change dynamically. The various situations to be determined may be the same across all contents, but may only correspond to situations described in the setting information of the distributor of the corresponding content. For example, in the case of setting information in which the reaction priority is "high" only for situation A and situation B among situations A to X, the various situations to be determined (detected) may only be situation A and situation B among situations A to X. In this case, by reducing the number of various situations to be determined, it is possible to reduce the number of situations that cannot be processed.

[0090] The situation determination unit 164 may determine, as the content or situation of a comment, whether it is a request or question from a viewer, whether a response should be given to the request or question, whether a specific keyword is included, etc. The content of a comment may be classified based on whether it is favorable, negative, violates public order and morals, is novel, etc.

[0091] The status determination unit 164 may determine, as the status of the viewer, whether or not the viewer is a first-time viewer, whether or not the viewer is making a comment for the first time, whether or not the viewer has made a payment for the first time (providing a payment medium such as a tip to a distributor), whether or not the viewer has not been seen for a long time, etc. Such a determination regarding a comment may be performed for each comment.

[0092] The situation determination unit 164 may determine the emotional situation of the viewer based on the result of the emotion analysis by the emotion analysis unit 166 .

[0093] The status of the viewer to be determined may include at least one of the following: a first status of a viewer who is viewing content distributed by a distributor for the first time; a second status of a viewer who pays a fee equal to or above a predetermined standard; a third status of a viewer who is favorable to the distributor and does not fall under the first or second status; and a fourth status of a viewer who is unfavorable to the distributor or hostile to the distributor. The fee equal to or above the predetermined standard may be based on the above-mentioned charging medium. Whether or not a viewer is favorable to a distributor may be determined based on the content of a comment made by the viewer in response to the distribution of the content by the distributor. Also, whether or not a viewer is unfavorable to a distributor or hostile to the distributor may be determined based on the content of a comment made by the viewer in response to the distribution of the content by the distributor.

[0094] Regarding charges above a predetermined standard, the predetermined standard may be arbitrary and may be adjustable by the distributor as described above. Meanwhile, viewers who have a relatively large total charge are often favorable to the distributor (i.e., often in the third situation), but may also be in the fourth situation. Therefore, the situation of the viewer to be determined may be further subdivided. For example, the fourth situation may be further classified into more detailed situations depending on whether or not it also applies to the second situation. That is, the fourth situation may include two sub-situations: a situation that also applies to the second situation, and a situation that does not also apply to the second situation. This makes it possible to adapt the setting information to various situations.

[0095] When determining various situations such as the viewer's situation, the situation determination unit 164 may apply an evaluation function to the activity information to evaluate the achievement of each viewer. The achievement may be evaluated based on whether or not a certain requirement is satisfied. FIG. 14 shows a method of evaluating achievements using an API (Application Programming Interface) server and a database or model called a UserLTV model. For example, when determining whether or not a viewer has made a comment, a query to that effect (illustrated as "Query" in the figure) is given to the API server. The API server refers to the UserLTV model and outputs a response to the query (for example, two values, True / False). The UserLTV model may store information (comments from each viewer) such as those stored in the above-mentioned activity information storage unit 150. In this case, the situation determination unit 164 can be realized by the API server. By using the API server, the processing load of the server device 10 can be reduced.

[0096] The emotion analysis unit 166 analyzes the emotions of each viewer at multiple points during the distribution of the content. The emotion analysis unit 166 may function for each piece of content. The emotions may include anger, expectation, disgust, fear, joy, sadness, surprise, trust, and the like. FIG. 15 shows an example of an emotion analysis result in a time series. Such an emotion analysis result may be used to generate reaction candidates, as described below. In other embodiments, each emotion such as anger may be further subdivided and analyzed, or its cause (factor) may be analyzed. Such an analysis result may also be effectively used to generate reaction candidates.

[0097] The emotion analysis unit 166 may analyze the comments of the viewers and classify the viewers into a plurality of groups. The function of the emotion analysis unit 166 may be realized by artificial intelligence. The grouping method is arbitrary, and for example, a k-means clustering algorithm may be used. For example, in political content, viewers may be classified into right-wing, left-wing, and the like. FIG. 16 shows an example in which viewers are classified into two groups. Such a classification result may be used to generate reaction candidates, as described later. Note that the number of groups to be classified is not limited to two, and may be three or more. By using the emotion analysis result to extract one or more specific comments and to determine various situations, processing in accordance with the emotions of the viewers can be realized. For example, it is possible to prevent the generation of reaction candidates that may encourage anger in a situation in which anger is the main emotion.

[0098] The emoji association processing unit 168 outputs various situations in association with emojis in a manner that can be viewed by the distributor. The various situations are based on the determination results by the situation determination unit 164. The manner in which the various situations are output in association with emojis and the effect thereof may be as described above with reference to FIG. 8.

[0099] The comment flow analysis unit 170 analyzes the flow of comments from viewers based on the time series of each comment during the distribution of the content. The comment flow analysis unit 170 analyzes the flow of comments (flow of conversation through comments, etc.) during the distribution of the content. The comment flow may include current topics, etc., which may change dynamically. The analysis of the flow may be performed based on keyword extraction, etc. Such analysis results may be used to generate reaction candidates, as described below.

[0100] The reaction candidate generation processing unit 172 generates reaction candidates. The reaction candidates are as described above. As described above, the reaction candidate generation processing unit 172 may generate reaction candidates based on the setting information and the activity information.

[0101] For example, in the case of setting information that prioritizes situations in which reactions are made relatively frequently, reaction candidates may be generated for each comment, as shown in Fig. 17. Also, in the case of setting information that prioritizes the first situation over the above-mentioned second situation, reaction candidates may be generated by prioritizing comments related to viewers in the first situation over comments related to viewers in the second situation, as shown in Fig. 18.

[0102] In this embodiment, the reaction candidate generation processing unit 172 includes a first processing unit 1721 and a second processing unit 1722.

[0103] The first processing unit 1721 generates the same reaction candidates for two or more specific viewers having a predetermined relationship. The predetermined relationship is arbitrary, and may be the same situation or a common situation. For example, two or more viewers in the above-mentioned second situation may be two or more specific viewers having a predetermined relationship. Alternatively, the predetermined relationship may be a relationship in which part or all of the activity information is the same or similar. For example, the predetermined relationship may be the same situation or a common situation, and the elapsed time (minutes) is equal to or greater than a predetermined time.

[0104] The second processing unit 1722 generates different reaction candidates for each of two or more specific viewers having a predetermined relationship. The second processing unit 1722 may function in a different time period from the first processing unit 1721 described above. That is, there are multiple operation modes, and the multiple operation modes include a first mode in which the first processing unit 1721 functions and a second mode in which the second processing unit 1722 functions. In this case, the distributor can selectively realize a desired mode from among the multiple operation modes including these modes. For example, when the distributor has time to spare, the second mode is selected, and when the distributor is busy, the first mode is selected, and the multiple modes can be used appropriately. The mode may be selected automatically according to the distributor's situation.

[0105] In this embodiment, reaction candidates may be generated based on the above-mentioned emotion analysis results. In this case, reaction candidates that correspond to changes in the viewer's emotions can be generated. As a result, even in a distribution event in which the viewer's emotions may change, such as that shown in FIG. 15, it is possible to realize a variety of communication by adding emphasis, controlling the viewer's emotions, or sympathizing with the viewer's emotions. For example, during a time period when disgust is dominant, it may be possible to reduce the viewer's disgust by generating reaction candidates that eliminate the viewer's disgust.

[0106] In addition, in this embodiment, the reaction candidate generation processing unit 172 may generate reaction candidates further based on the analysis result of the comment flow. In this case, reaction candidates that match the comment flow can be generated. As a result, it is possible to promote smooth communication. For example, if the comment flow is "Request for one more song (encore)", a reaction candidate "We'll play one more song!" that matches the comment flow may be generated as shown in FIG. 19. This makes it possible to generate reaction candidates that match the flow formed by the broadcast and the viewer comments, and effectively enhance the sense of unity between the broadcaster and the viewer.

[0107] Here, the method for automatically generating reaction candidates is arbitrary, but may be a method that utilizes artificial intelligence.

[0108] For example, the reaction candidate generation processing unit 172 may generate reaction candidates using generative artificial intelligence based on large language models (LLMs) or the like. In this case, the method of automatically generating reaction candidates may include an automatic generation process of a prompt to obtain reaction candidates. A large language model may be prepared (constructed) for each broadcaster, and in this case, various settings (for example, setting of a persona) may be possible by the broadcaster. Three examples of prompts are shown in FIG. 20. In this case, a prompt or its base may be generated for each emoji associated with a situation. The form of the prompt is arbitrary, but may be a form including examples as shown in FIG. 20. Emojis represent various situations as described above. Therefore, broadcasters can intuitively check prompts according to various situations by relying on emojis. In the case of a prompt base, the broadcaster can complete a desired prompt by inputting or modifying a part of it.

[0109] In this case, the reaction candidate generation processing unit 172 may change the Prompt or its base according to various situations. Also, reaction candidates may be automatically generated according to various situations using templates. In this case, it is possible to generate (present) a variety of reaction candidates while reducing the burden on the distributor.

[0110] In addition, the reaction candidate generation processing unit 172 may generate two or more reaction candidates for one specific comment. In this case, the distributor can select one or more desired reaction candidates from the two or more reaction candidates. In this case, the two or more reaction candidates may be comments that convey substantially different contents, or may convey substantially the same contents but in different forms. In the latter case, for example, one reaction candidate may be a comment, while another reaction candidate may be a gesture that conveys the same contents as the comment. In this case, the possibility of generating the distributor's desired reaction candidate is increased, and an increase in the processing load due to redoing (for example, regenerating reaction candidates based on instructions from the distributor) can be prevented.

[0111] Furthermore, when generating reaction candidates for an action, the reaction candidate generation processing unit 172 may take into consideration not only the content of the action but also the form of the action. For example, reaction candidates for an action may be generated in different forms when the action is a comment and when the action is a gesture (a gesture that conveys substantially the same content as the comment). In this case, for example, when the action is a comment, a reaction candidate in the form of a comment may be generated, whereas when the action is a gesture, a reaction candidate in the form of a gesture may be generated. This makes it possible to diversify the forms of reaction candidates according to the form of the action from the viewer, and to change the impact that a reaction can have on the viewer, which results in activation of comments from the viewer (and excitement in the broadcast that accompanies this).

[0112] It should be noted that an image or sound effect indicating that reaction candidates are being generated by the reaction candidate generation processing unit 172 may be output. This may also be true during the analysis of emotions and the analysis of the comment flow.

[0113] Incidentally, in cases of collaborative distribution by multiple distributors or viewer participation type distribution, it may be difficult to determine who a comment such as a question from a viewer is directed to. For example, in the case of a distribution by collaboration between distributors A and B, if a viewer mentions @A, a reaction candidate may be generated as a comment (or request) directed to A. On the other hand, if there is no clear mention, it is unclear whether the comment is directed to distributor A or distributor B (which one is allowed to speak), and a situation may arise where both parties speak at the same time.

[0114] Therefore, a method such as the evaluation function described above may be used to check the responses to distributors A and B (for example, activity information related to reactions). In this case, it may be assumed that distributor A, who has not generated any particular reaction from past history, etc., will not respond, and that other distributors B (distributors who can be expected to generate some kind of reaction) will respond, and reaction candidates may be generated. Alternatively, when each reaction candidate is generated, the emotion analysis unit 166 may perform emotion analysis on the reaction candidates, and negative comments (low joy values) may be activated as reactions first. Also, when such a judgment is difficult, comments with short text length among the reaction candidates may be activated (output) as reactions first.

[0115] In addition, the function of the reaction candidate generation processing unit 172 may be switched on / off in response to an instruction from a distributor and / or automatically by artificial intelligence or the like. For example, the function may be switched on when the number of comments from viewers per unit time exceeds a threshold value or when the distributor is taking a break. Such conditions for switching on / off may also be set for each distributor. This makes it possible to prevent a situation in which reaction candidates are automatically generated uniformly, and by turning off the function of the reaction candidate generation processing unit 172, the processing load can be reduced. When the function of the reaction candidate generation processing unit 172 is turned off, the functions for acquiring various parameters used to generate reaction candidates (such as the action acquisition unit 162, the situation determination unit 164, and the emotion analysis unit 166) may be stopped in conjunction with the switching off of the function. In this case, the processing load can also be reduced.

[0116] The reaction output unit 174 outputs reaction candidates as reactions from the distributor automatically or in response to a predetermined input from the distributor. For example, the reaction output mode may have an automatic mode and a manual mode. In the automatic mode, the reaction output unit 174 outputs the reaction candidates generated by the reaction candidate generation processing unit 172 as reactions as they are. In the manual mode, when one or more reaction candidates are selected by the distributor from among the reaction candidates generated by the reaction candidate generation processing unit 172, the reaction output unit 174 may generate a reaction instruction for outputting the selected reaction candidates. In addition, in the manual mode, the reaction output unit 174 may generate a reaction instruction for outputting the reaction candidates after the distributor corrects (edits, etc.) the reaction candidates generated by the reaction candidate generation processing unit 172.

[0117] In this embodiment, some or all of the functions of the reaction output unit 174 may be realized by artificial intelligence. In addition, among the functions of the reaction output unit 174, the function of automatically outputting reaction candidates as reactions from the distributor may be made switchable on / off in response to an instruction from the distributor and / or automatically by artificial intelligence, etc. For example, the function may be turned on when the number of comments from viewers per unit time exceeds a threshold value or when the distributor is taking a break, etc. Such on / off switching conditions may also be set for each distributor. This makes it possible to prevent reactions from being automatically output in a situation that the distributor wants to manage, or to prevent a long period of time in which no reactions are output at all due to a situation in which the distributor is busy.

[0118] Next, an example of the operation of the information distribution system 1 will be described with reference to FIGS.

[0119] 21 to 23 are flow charts that generally show an example of the operation of the information distribution system 1. Fig. 21 may be executed at predetermined intervals during content distribution by one distributor.

[0120] In step S2100, the information distribution system 1 acquires comments from viewers. Each time a comment from a viewer is received, it may be stored in a predetermined storage area as a comment waiting to be processed, by an interrupt process separate from the process of Fig. 21. In this case, in step S2100, the comments waiting to be processed may be read out one by one or all at once from the predetermined storage area.

[0121] In step S2102, the information distribution system 1 updates the activity information related to the corresponding viewer on the basis of the comment acquired in step S2100 for the content being distributed.

[0122] In step S2104, the information distribution system 1 outputs the comment acquired in step S2100 to the content being distributed (for example, see the comment display field G11 in FIG. 6).

[0123] In step S2106, the information distribution system 1 assigns a comment processing order to the comments acquired in step S2100. The comment processing order indicates the order in which the comments are processed (described later). Note that the comment processing order is assigned numbers starting from 1 in chronological order of reception.

[0124] In step S2108, the information distribution system 1 executes comment processing for the k-th comment in the comment processing order. Note that the initial value of k is 1. A specific example of comment processing will be described later with reference to FIG.

[0125] In step S2110, the information distribution system 1 increments the variable k by "1".

[0126] In step S2112, the information distribution system 1 executes a reaction process. A specific example of the reaction process will be described later with reference to FIG.

[0127] 21, as an example, comments are processed one by one, but multiple comments may be processed in parallel using a multi-core or the like. Also, depending on the processing load (for example, the number of comments to be processed), processing such as thinning out the comments to be processed may be performed. This makes it possible to reduce the processing load while still being able to execute comment processing (step S2108) even when the number of comments per unit time is extremely large.

[0128] FIG. 22 is a flowchart relating to the comment processing (step S2108) of FIG.

[0129] In step S2200, the information distribution system 1 reads out activity information related to the poster of the k-th comment (hereinafter, also simply referred to as the "comment poster"). The activity information may be read out from the activity information storage unit 150 described above.

[0130] In step S2202, the information distribution system 1 determines the status of the comment poster based on the activity information read in step S2200. The determination of the status of the comment poster may be a determination of whether the status corresponds to the first status, the second status, or the like described above.

[0131] In step S2204, the information distribution system 1 determines the content or status of the k-th comment. The content or status of the comment is as described above.

[0132] In step S2206, the information distribution system 1 performs sentiment analysis and comment flow analysis. These analyses are as described above in relation to the sentiment analysis unit 166 and the comment flow analysis unit 170. The comment flow is analyzed including the k-th comment and the comments before it. Alternatively, it may be determined whether the k-th comment follows the comment flow that is being analyzed based on the comments before it. The sentiment analysis and comment flow analysis do not need to be performed for each comment, and may be performed for multiple comments or periodically. In this case, the sentiment analysis and comment flow analysis can be performed while reducing the processing load.

[0133] In step S2208, the information distribution system 1 compares the determination and analysis results from steps S2202 to S2206 with the setting information related to the distributor. By such comparison, it can be determined whether the determination and analysis results from steps S2202 to S2206 are a high priority situation based on the setting information.

[0134] In step S2210, the information distribution system 1 judges whether or not it is necessary to generate reaction candidates for the k-th comment. For example, if the result of the comparison in step S2208 shows that the judgment and analysis results from steps S2202 to S2206 indicate a high priority situation based on the setting information, it is judged that reaction candidates for the k-th comment should be generated. If the judgment result is "YES", the process proceeds to step S2212, otherwise the process ends. In the latter case, no reaction candidates are generated for the k-th comment.

[0135] In step S2212, the information distribution system 1 generates reaction candidates for the k-th comment (reaction process). The method of generating reaction candidates is as described above.

[0136] In step S2214, the information distribution system 1 outputs reaction candidates for the k-th comment. The method of outputting reaction candidates is as described above with reference to FIG.

[0137] FIG. 23 is a flowchart relating to the reaction process (step S2112) of FIG.

[0138] In step S2300, the information distribution system 1 determines whether a reaction instruction from the distributor has been generated. If multiple reaction candidates are presented, the reaction instruction may include information indicating which reaction candidate the instruction is for. The details of the reaction instruction are as described above.

[0139] In step S2302, the information distribution system 1 outputs a corresponding reaction in response to the reaction instruction in step S2300. The reaction is output in the manner described above (see, for example, comment G13 in FIG. 6).

[0140] In step S2304, the information distribution system 1 updates the reaction waiting queue by deleting the reaction output in step S2302 from the reaction waiting queue. The reaction waiting queue is a queue in which reactions that can be output, which will be described later, wait. Note that a reaction in the reaction waiting queue may be deleted when a predetermined condition is met, even if it is not to be output. The predetermined condition is arbitrary, but may be met, for example, when a predetermined upper limit time has elapsed, or when the number of reactions in the reaction waiting queue exceeds a predetermined upper limit. In this case, the predetermined condition time or the predetermined upper limit number may be set for each distributor.

[0141] Although each embodiment has been described in detail above, the present invention is not limited to a specific embodiment, and various modifications and changes are possible within the scope of the claims. In addition, it is also possible to combine all or a plurality of the components of the above-described embodiments.

[0142] For example, in the above-described embodiment, different meanings may be given to emojis that can be used in various ways as described above, based on differences in display manner such as color and size. For example, emojis that represent various situations may represent priority according to color and size. For example, a red color may represent high priority. Similarly, a large size may represent high priority. Alternatively, a high priority may be represented by blinking or the like. This allows the distributor to visually grasp the level of priority, etc., and efficiently make the necessary reactions. [Explanation of symbols]

[0143] 1 Information distribution system 3. Network 10. Server device 20 Terminal Equipment 20A Terminal Equipment 20B Terminal Equipment 30 Studio Units 30A Studio Unit 30B Studio Unit 150 Activity information storage section 152 Setting information storage unit 154 Activity Information Management Department (1st Management Department) 156 Setting information management department (second management department) 160 Distribution content processing unit 162 Action Acquisition Unit (Acquisition Unit) 164 Situation Judgment Section 166 Emotion Analysis Department 168 Emoji matching processing unit 170 Comment flow analysis section 172 Reaction candidate generation processing unit (reaction candidate generation unit) 1721 First Processing Section 1722 Second Processing Section 174 Reaction Output Section

Claims

1. managing, for each viewer, activity information relating to activities that a viewer who views at least one of past content distributed by a distributor and the past content and the content currently being distributed by the distributor can perform; Manage settings information regarding the distributor's reactions; obtaining a plurality of actions from one or more viewers viewing content currently being distributed by the distributor; A program that causes a computer to execute a process that automatically generates reaction candidates that can be taken by the distributor in response to one or more specific actions among the multiple actions based on the activity information and the setting information.

2. The program according to claim 1 , wherein the setting information relates to priorities for various situations.

3. The program according to claim 2 , wherein the various situations include at least one of the contents or situation of an action and a situation of a viewer.

4. The program of claim 3 , wherein the content or status of the action includes at least one of whether or not it is a request or question from a viewer, whether or not the request or question should be answered, and whether or not a specific keyword is included.

5. The program of claim 3, wherein the viewer's status includes at least one of a first status of a viewer watching content distributed by the distributor for the first time, a second status of a viewer providing visual support or economic support above a predetermined standard through super chat, gifts, tips, tips or the like, a third status of a viewer who is favorable to the distributor and does not fall under the first status or the second status, and a fourth status of a viewer who is unfavorable to the distributor or hostile to the distributor.

6. The program according to claim 5 , wherein the fourth situation is further classified into smaller situations depending on whether or not the fourth situation also applies to the second situation.

7. The program according to claim 5 , further causing a computer to execute a process of determining the various situations based on the activity information.

8. The program of claim 7, wherein the activity information relates to at least one of the frequency of comment posting, the history of posted comments, the content of posted comments, the history of visual support or financial support, and information that can be derived based on any one or more of these.

9. The program according to claim 7 , wherein the process of determining the various situations includes applying an evaluation function to the activity information to evaluate an achievement of each viewer.

10. 8. The program according to claim 7, further causing a computer to execute a process of outputting the various situations in association with Emoji in a manner that can be viewed by the distributor.

11. The program according to claim 7 , wherein the process of generating reaction candidates includes a first process of generating the same reaction candidates for two or more specific viewers having a predetermined relationship.

12. The program according to claim 11 , wherein the process of generating reaction candidates selectively includes the first process and a second process of generating different reaction candidates for each of two or more specific viewers having the specified relationship.

13. The program according to claim 1 , wherein the setting information relates to a frequency of reactions from the distributor.

14. The program according to claim 1 , further comprising a step of: analyzing, by a computer, the emotions of a viewer at a plurality of points during the distribution of the content.

15. The program according to claim 14 , further causing a computer to execute a process of generating reaction candidates from the distributor based on the emotion analysis result.

16. The program according to claim 1 , further comprising a step of: analyzing a flow of comments from viewers based on a time series of each comment during distribution of said content.

17. The program according to claim 16, further causing a computer to execute a process of generating reaction candidates from the distributor based on the analysis results of the comments.

18. The program of claim 1 , wherein the process of generating reaction candidates includes generating input for a generative artificial intelligence based on the activity information, and providing the input to the generative artificial intelligence to obtain the reaction candidates or a base for the reaction candidates.

19. The program according to claim 1 , further causing a computer to execute a process of outputting the generated reaction candidates as reactions from the distributor automatically or in response to a predetermined input from the distributor.

20. 20. The program according to claim 19, wherein the reaction from the distributor includes at least one of a visual output of a comment or text, an audio output of a comment, and a gesture output.

21. The program according to claim 1 , wherein the broadcast includes at least one of a broadcast using an avatar of a human broadcaster, a broadcast by a robot broadcaster, a broadcast by collaboration between multiple broadcasters, and a broadcast in which viewers can participate.

22. The program of claim 1 , wherein the action includes at least one of a visual output of the comment and an audio output of the comment.

23. managing, for each viewer, activity information relating to activities that a viewer who views at least one of past content distributed by a distributor and the past content and the content currently being distributed by the distributor can perform; Manage settings information regarding the distributor's reactions; obtaining a plurality of actions from one or more viewers viewing content currently being distributed by the distributor; An information processing method executed by a computer, comprising automatically generating candidate reactions that can be taken by the distributor in response to one or more specific actions among the plurality of actions based on the activity information and the setting information.

24. a first management unit that manages, for each viewer, activity information regarding activities that a viewer who views at least one of past content distributed by a distributor and the past content and the content currently being distributed by the distributor can perform; A second management unit that manages setting information related to reactions of the distributor; an acquisition unit that acquires a plurality of actions from one or more viewers who are viewing the content currently being distributed by the distributor; An information processing system including a reaction candidate generation unit that automatically generates reaction candidates that can be taken by the distributor in response to one or more specific actions among the plurality of actions based on the activity information and the setting information.

Images