Program and system

Abstract

Provided is a program capable of publishing a unique profile, which is created according to an object, in association with the object, without increasing the workload of a user.　This program causes a computer to function as: an object generation means for generating an object, which is arranged in an online space, according to a plurality of setting values selected by a user for setting visual features of the object; a profile generation means for generating a profile of the object by inputting the plurality of setting values to a trained model which has been trained in advance; and a publishing means for publishing in the online space the profile generated by the profile generation means in association with the object generated by the object generation means.

Description

Programs and systems

[0001] The present invention relates to a program and a system.

[0002] Conventionally, there has been known a technique for disclosing the profile of one's own avatar to other avatars in a virtual reality (VR) space (see, for example, Patent Documents 1 and 2). In the VR space, a user can view the profile of another avatar and decide whether or not to become friends with that avatar (so-called friend registration).

[0003] Similarly, in cooperative online games in which multiple avatars cooperate to play, or in competitive online games in which multiple avatars compete against each other, players can view the profiles of other avatars and select an avatar to cooperate or compete with. In this way, the profile of each avatar is becoming increasingly important in VR spaces and online games.

[0004] JP 2018-170013 A JP 2018-106499 A

[0005] However, many users find the task of creating a profile burdensome, and as a result, if a large number of avatars use predefined default profiles, the profiles become useless when selecting avatars to register as friends or to cooperate or compete with.

[0006] The present invention has been made in consideration of the above circumstances, and its purpose is to provide a program that can publish a unique profile created to suit an object in association with the object without increasing the workload of the user.

[0007] In order to solve the above problem, the program of the present invention causes a computer to function as an object generation means that generates an object to be placed in an online space according to multiple setting values ​​selected by a user to set the visual characteristics of the object, a profile generation means that inputs the multiple setting values ​​into a pre-trained model to generate a profile of the object, and a publishing means that associates the profile generated by the profile generation means with the object generated by the object generation means and publishes it in the online space.

[0008] According to the present invention, a unique profile created to suit an object can be made public in association with the object without increasing the workload of the user.

[0009] 1 is a diagram illustrating an overview of a system according to an embodiment of the present invention; FIG. 1 is a conceptual diagram of learning processing by AI; FIG. 2 is a conceptual diagram of generation processing by AI; FIG. 3 is a diagram illustrating a neural network that realizes AI; FIG. 4 is a hardware configuration diagram of a user terminal; FIG. 5 is a functional block diagram of a user terminal; FIG. 6 is an example of an avatar generation screen; FIG. 7 is an example of a priority of setting parameters; FIG. 8 is an example of a histogram of setting values ​​of hairstyle parameters; FIG. 9 is an example of a histogram of setting values ​​of clothing parameters; FIG. 10 is an example of a profile generated by AI; FIG. 11 is an example of a profile after editing; FIG. 12 is an example of learning data; FIG. 13 is another example of an avatar generation screen; FIG. 14 is an example of a priority of setting parameters; FIG. 15 is another example of a histogram of setting values ​​of hairstyle parameters; FIG. 16 is another example of a histogram of setting values ​​of clothing parameters; FIG. 17 is another example of a profile generated by AI; FIG. 18 is another example of a profile after editing; FIG. 19 is another example of learning data; FIG. 20 is an example of a profile editing screen; FIG. 21 is an example of learning data; FIG. 22 is an example of a user selection screen; FIG. 23 is an example of a user details screen.

[0010] A system 1 according to an embodiment will be described below with reference to the drawings. Note that the embodiment of the present invention described below is merely an example of how the present invention can be realized, and the scope of the present invention is not limited to the scope of the described embodiment. Therefore, the present invention can be implemented by adding various modifications to the embodiment.

[0011] [Overview of System 1] FIG. 1 is a diagram showing an overview of system 1 according to this embodiment. As shown in FIG. 1, system 1 mainly includes a game server 10, an AI server 15, and multiple user terminals 20. Note that although three user terminals 20 are shown in FIG. 1, the number of user terminals 20 included in system 1 is not limited to this. The game server 10, the AI ​​server 15, and the user terminals 20 are connected to each other so as to be able to communicate with each other via a communication network 2. Specific examples of communication network 2 are not particularly limited, and may include, for example, the Internet, a mobile communication system (e.g., 4G, 5G, etc.), a wireless network such as Wi-Fi (registered trademark), or a combination thereof.

[0012] As one example, the system 1 realizes a cooperative online game in which users (players) of multiple user terminals 20A, 20B, and 20C cooperate to play. As another example, the system 1 realizes a competitive online game in which users (players) of multiple user terminals 20A, 20B, and 20C compete against each other. As yet another example, the system 1 realizes a virtual space in which users of multiple user terminals 20A, 20B, and 20C communicate via avatars. These systems 1 are already well known, so detailed description thereof will be omitted.

[0013] [Configuration of Game Server 10] The game server 10 is realized by, for example, a general-purpose computer such as a workstation or a personal computer. As one example, the game server 10 that provides an online game synchronizes the game data of each of the multiple user terminals 20. As another example, the game server 10 that provides a virtual space synchronizes the virtual space data of each of the multiple user terminals 20. Hereinafter, the online game and virtual space in which multiple users can participate will be collectively referred to as "online space." In other words, the game server 10 provides the online space to multiple user terminals 20A, 20B, and 20C.

[0014] [Configuration of AI Server 15] The AI ​​server 15 is realized by, for example, a general-purpose computer such as a workstation or a personal computer. The AI ​​server 15 realizes AI (Artificial Intelligence) 16 including a trained model. As an example, the AI ​​server 15 may be equipped with dedicated AI optimized for the online space provided by the game server 10. In this case, the game server 10 and the AI ​​server 15 may be realized by a single piece of hardware. As another example, the AI ​​server 15 may be equipped with general-purpose AI that can be used for various purposes. The configuration of the AI ​​16 is already well known, so a detailed description will be omitted, but it may have the following configuration, for example.

[0015] FIG. 2A is a conceptual diagram of the learning process by the AI ​​16. FIG. 2B is a conceptual diagram of the generation process by the AI ​​16. FIG. 3 is a diagram showing a neural network 17 that realizes the AI ​​16. The AI ​​16 installed in the AI ​​server 15 is a so-called "generation AI" that processes input data and generates output data. The AI ​​16 executes the learning process shown in FIG. 2A and the generation process shown in FIG. 2B. The AI ​​16 also generates output data from input data, for example, using the neural network 17 shown in FIG. 3.

[0016] As shown in FIG. 2A , the AI ​​16 includes a learning model 16a. The learning model 16a refers to the neural network 17 before the learning process is performed. The learning model 16a becomes a trained model 16b using training data including input data and correct answer data. The input data refers to data input to the AI ​​16. The correct answer data refers to data that should be output when the input data is input. By inputting multiple pieces of training data into the learning model 16a, the neural network 17 is optimized as described below, becoming the trained model 16b.

[0017] 2B, the trained model 16b generates and outputs output data by inputting input data to the neural network 17. The input data and output data may be in any format, such as text, image, or audio. The input data and output data may also be in different formats. On the other hand, the format of the correct answer data is the same as the format of the output data.

[0018] 2A may be performed not only on the learning model 16a but also on the trained model 16b. Furthermore, the AI ​​16 does not need to learn using the input data and correct answer data actually used in the present invention, but may learn using general-purpose learning data. Furthermore, the learning process performed by the AI ​​16 is not limited to "supervised learning" in which input data and correct answer data are input, but may be "unsupervised learning" in which correct answer data is not input, or may perform reinforcement learning, transfer learning, or the like.

[0019] As shown in FIG. 3 , the neural network 17 of the learning model 16a or the trained model 16b includes an input layer L1 composed of multiple nodes I1, I2, and I3, an intermediate layer L2 composed of multiple nodes H1, H2, H3, H4, and H5, and an output layer L3 composed of multiple nodes O1, O2, and O3. In the example of FIG. 3 , the number of nodes in the input layer L1 and the output layer L3 is the same, but the number of nodes in the input layer L1 and the output layer L3 may be different. The neural network 17 may also include multiple intermediate layers L2. Furthermore, while FIG. 3 illustrates a fully connected neural network 17 in which multiple nodes in each layer L1, L2, and L3 are connected to all nodes in adjacent layers, the structure of the neural network 17 is not limited to this.

[0020] The learning process is a process of adjusting the weight coefficients and biases of each node so that correct data is output from the output layer L3 when input data is input to the input layer L1. The generation process is a process of generating output data and outputting it from the output layer L3 by processing the input data input to the input layer L1 using weight coefficients and biases that have been adjusted in advance for each node.

[0021] However, the specific example of processing by AI 16 described above is merely an example, and various well-known methods can be adopted by the AI ​​server 15. As another example, AI 16 may have a network structure such as a CNN (Convolutional Neural Network). As yet another example, the network structure may have a configuration such as a LLM (Large Language Model), an RNN (Recurrent Neural Network), or an LSTM (Long Short-Term Memory). In other words, AI 16 may have a network structure other than deep learning.

[0022] In this embodiment, an example will be described in which input data in text format is input to the trained model 16b, and output data in text format is generated. More specifically, the input data in this embodiment is a plurality of setting values ​​selected by a user to set visual or auditory (at least visual) characteristics of an avatar (object). Furthermore, the output data in this embodiment is a profile of the avatar (object) generated in accordance with the plurality of setting values.

[0023] [Configuration of User Terminal 20] The user terminal 20 is realized as, for example, an HMD set, a tablet terminal, a smartphone, a feature phone, a laptop computer, a desktop computer, etc. In this embodiment, an example of the user terminal 20 as a tablet terminal will be described as shown in FIG.

[0024] Fig. 4 is a hardware configuration diagram of the user terminal 20. As shown in Fig. 4, the user terminal 20 mainly includes a processor 21, a memory 22, a storage 23, a communication interface 25, a monitor 31, cameras 33 and 34, a microphone 35, a speaker 36, a motion sensor 41, and an operation device 42 (operation unit). Each component of the user terminal 20 is connected to a communication bus 29.

[0025] The processor 21 performs the processes described below by executing a series of instructions included in a terminal program 23P stored in the memory 22 or the storage 23. The processor 21 is realized as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a micro processing unit (MPU), a field-programmable gate array (FPGA), or other device.

[0026] The memory 22 temporarily stores the terminal program 23P and data. The terminal program 23P is loaded from, for example, the storage 23. The data includes data input to the user terminal 20 and data generated by the processor 21. For example, the memory 22 is realized as a RAM (Random Access Memory) or other volatile memory.

[0027] The storage 23 permanently stores the terminal program 23P and data. The storage 23 is realized, for example, as a ROM (Read-Only Memory), a hard disk drive, flash memory, or other non-volatile storage device. The storage 23 may also be realized as a removable storage device such as a memory card. As another example, instead of being built into the user terminal 20, the storage 23 may be connected to the user terminal 20 as an external storage device. With this configuration, for example, in a situation where multiple user terminals 20 are used, such as an amusement facility, it becomes possible to collectively update the terminal program 23P and data.

[0028] The communication interface 25 communicates with other devices (e.g., the game server 10 and the AI ​​server 15) connected to the communication network 2. The communication interface 25 is realized as, for example, a wired communication interface such as a LAN (Local Area Network), or a wireless communication interface such as Wi-Fi (Wireless Fidelity), Bluetooth (registered trademark), or NFC (Near Field Communication).

[0029] 1, the monitor 31 is provided on the surface of a flat housing. The monitor 31 is a display device (display unit) that displays images or videos. The camera 33 is a so-called in-camera that is attached to the surface of the flat housing and captures an image of the face of a user viewing the monitor 31. The camera 34 is a so-called out-camera that is attached to the back surface of the flat housing (the surface opposite the monitor 31) and captures an image of the surroundings.

[0030] The microphone 35 converts the user's speech into an audio signal (electrical signal) and outputs it to the computer 26. The speaker 36 converts the audio signal output from the computer 26 into sound and outputs it to the user. Note that the user terminal 20 may include earphones instead of the speaker 36.

[0031] The motion sensor 41 detects the motion of the housing (for example, rotation around three mutually orthogonal axes). The motion sensor 41 may be realized by, for example, an angular velocity sensor, a geomagnetic sensor, or an acceleration sensor.

[0032] The operation device 42 accepts input (operation) of commands by the user to the user terminal 20. The operation device 42 is, for example, a touch panel that is superimposed on the monitor 31 and accepts various touch operations by the user. In other words, the monitor 31 according to this embodiment is a touch panel display unit. However, the specific hardware configuration of the user terminal 20 is not limited to the above example. As another example, the user terminal 20 may be provided with a controller equipped with buttons, an operation stick, etc. as the operation device 42.

[0033] [Functional Block Diagram of User Terminal 20] Fig. 5 is a functional block diagram of the user terminal 20. As shown in Fig. 5, the terminal program 23P loaded into the memory 22 causes the user terminal 20 (computer) to function as an object generation means 210, a selection means 220, a profile generation means 230, an automatic editing means 240, a learning means 250, a publishing means 260, a user editing means 270, and a feedback means 280.

[0034] 5 mainly illustrates functional blocks for generating and publishing a profile, the user terminal 20 also has functions for realizing processes in the online space (e.g., participation in a game, avatar movements). Also, while FIG. 5 mainly illustrates functional blocks for the user terminal 20A, the user terminals 20B and 20C also have similar functional blocks.

[0035] First, an example of the process of generating an avatar and a profile in the user terminal 20A will be described with reference to Figures 6 to 8C. Figure 6 is an example of an avatar generation screen. Figure 7A is an example of the priority of setting parameters. Figure 7B is an example of a histogram of setting values ​​for hairstyle parameters. Figure 7C is an example of a histogram of setting values ​​for clothing parameters. Figure 8A is an example of a profile generated by the AI ​​16. Figure 8B is an example of a profile after editing. Figure 8C is an example of learning data.

[0036] The object generation means 210 displays the avatar generation screen shown in Fig. 6 on the monitor 31. The avatar generation screen is a screen for generating an avatar (character). The avatar generation screen also allows the user of the user terminal 20A to select multiple setting values ​​in order to set the visual (appearance) or auditory (tone of voice) characteristics of the avatar. The process of generating an avatar and profile, focusing on visual characteristics, will be described below.

[0037] An avatar is an example of an object that represents a user and operates in an online space. The avatar may be a three-dimensional (3D) or two-dimensional (2D) representation. The avatar may be identified by data representing visual characteristics (e.g., image data, 3D model data), data representing auditory characteristics (e.g., audio data), or a combination of these.

[0038] As shown in FIG. 6, the avatar creation screen includes an avatar display area A1, a gender selection area A2, an age selection area A3, a setting parameter selection area A4, a candidate icon selection area A5, and a "OK" icon.

[0039] Avatar display area A1 is an area that displays an avatar image (hereinafter referred to as an "avatar image") generated according to the setting values ​​selected by the user through selection areas A2 to A5. That is, the appearance of the avatar image displayed in avatar display area A1 changes as the setting values ​​are changed through selection areas A2 to A5. Furthermore, the displayed avatar image may change (e.g., rotate, shrink, enlarge) through a touch operation (e.g., swipe, pinch in, pinch out) on avatar display area A1.

[0040] The gender selection area A2 is an area for selecting the gender of the avatar. The gender selection area A2 includes a "Male" icon and a "Female" icon as setting value candidates for the gender parameter. The age selection area A3 is an area for selecting the age of the avatar. The age selection area A3 includes a "Child" icon and an "Adult" icon as setting value candidates for the age parameter. However, the age selection area A3 may also include a text box or pull-down menu for inputting the date of birth.

[0041] The setting parameter selection area A4 is an area for selecting setting parameters (outline, hairstyle, skin color, clothing, color). The setting parameter selection area A4 includes an [Outline] tab, a [Hairstyle] tab, a [Skin Color] tab, a [Clothing] tab, and a [Color] tab. The outline indicates the facial outline of the avatar. The hairstyle indicates the hairstyle of the avatar. The skin color indicates the skin color of the avatar. The clothing indicates the clothing worn by the avatar. The color indicates the base color of the avatar (e.g., the color of the hair, clothing, and accessories).

[0042] The candidate icon selection area A5 is an area for selecting a setting value corresponding to the selection parameter selected in the setting parameter selection area A4. As an example, when the "Hairstyle" tab is selected in the setting parameter selection area A4, a plurality of candidate icons representing selectable hairstyle setting values ​​(e.g., short, bun, pigtails, ponytail) are displayed in the setting parameter selection area A4. As another example, when the "Clothing" tab is selected in the setting parameter selection area A4, a plurality of candidate icons representing selectable clothing setting values ​​(e.g., one-piece dress, miniskirt, denim, maid) are displayed in the setting parameter selection area A4.

[0043] 6, gender, age, face shape, hairstyle, skin color, clothing, and color are examples of setting parameters. Also, selectable candidate icons (e.g., a "male" icon or a "female" icon) associated with a setting parameter (e.g., gender) are setting value candidates that represent the visual characteristics of the avatar (object). In other words, a setting parameter represents a group (type) of setting values ​​of the same type.

[0044] However, specific examples of setting parameters are not limited to the above examples. Furthermore, for the setting parameters described above, the selectable setting value candidates are not limited to the above examples. Furthermore, setting parameters are not limited to those that set the visual characteristics of the avatar. For example, a voice tone parameter is an example of a setting parameter that sets the auditory characteristics of the avatar. Examples of setting values ​​for the voice tone parameter include soprano, mezzo-soprano, and alto.

[0045] Note that the avatar itself as a visual feature, items worn by the avatar as a visual feature (for example, costumes, accessories, etc.), and the avatar's voice data as an auditory feature may be acquired through charges, gacha, etc. For example, it may be possible to acquire an avatar that looks different from the default avatar, items worn by characters appearing in manga or anime, voice data of real voice actors, etc.

[0046] Then, object generation means 210 generates avatar data (image data, 3D model data) according to a plurality of setting values ​​selected by the user through selection areas A2 to A5 (for example, gender = female, age = child, face shape = round face, hairstyle = pigtails, skin color = fair skin, clothing = maid, color = white), and displays an avatar image represented by the generated avatar data in avatar display area A1. Furthermore, object generation means 210 finalizes the generated avatar data in response to selection of the [OK] icon.

[0047] The selection means 220 selects setting values ​​to be input to the trained model 16b from among the multiple setting values ​​selected through the avatar generation screen. The selection means 220 selects setting values ​​to be input to the trained model 16b, for example, using the priority table shown in FIG. 7A and the setting value histograms shown in FIGS. 7B and 7C. In this embodiment, four setting values ​​are selected from the seven setting values. However, the number of setting values ​​to be selected is not limited to the example described above.

[0048] The priority table shown in FIG. 7A holds an initial priority for each setting parameter. The initial priority indicates a predetermined priority for multiple setting parameters. The smaller the initial priority value, the higher the priority. The priority table is set, for example, by an administrator of the game server 10 and downloaded to the user terminal 20A in advance. In other words, the selection means 220 selects fixed setting values ​​for gender, age, hairstyle, and skin color by following only the priority table shown in FIG. 7A.

[0049] The setting value histograms shown in Figures 7B and 7C are a compilation of setting values ​​previously selected by other users for each setting parameter (e.g., hairstyle, clothing) in the online space provided by the game server 10. The vertical axes of Figures 7B and 7C may represent the number of times selected (frequency) or the selection rate (%). These setting value histograms are compiled, for example, by the game server 10. The selection means 220 then receives the setting value histograms from the game server 10 via the communication IF 25. Note that although Figures 7B and 7C only show setting value histograms for hairstyle parameters and clothing parameters, setting value histograms for other setting parameters may also be referenced.

[0050] The selection means 220 then changes the priority of the setting parameters based on the setting value histogram acquired from the game server 10. As an example, as shown in Fig. 7B, the selection means 220 does not change the priority of the hairstyle parameter because "pigtails" is the second most frequently selected hairstyle parameter. As another example, as shown in Fig. 7C, the selection means 220 changes the priority of the clothing parameter to "1" (highest) because "maid" is the least frequently selected clothing parameter.

[0051] As a result, in the examples of Figures 6 to 7C, the selection means 220 selects gender = female, age = child, clothing = maid, and skin color = fair as the setting values ​​to be input into the trained model 16b. In this way, the selection means 220 may prioritize the setting value that has been selected less frequently by other users from among the multiple setting values. However, the method by which the selection means 220 selects the setting value is not limited to this. As another example, the selection means 220 may randomly select the setting value to be input into the trained model 16b from among the multiple setting values. As yet another example, the selection means 220 may prioritize the setting values ​​indicating the avatar, item, and voice acquired by paying a fee and input them into the trained model 16b over other setting values.

[0052] The profile generation means 230 inputs the settings selected by the selection means 220 (e.g., gender = female, age = child, clothing = maid, skin color = fair skin) into the trained model 16b to generate a profile of the avatar. The profile generation means 230 may also input the name of the avatar determined (input) by the user (e.g., name = Linda) into the trained model 16b. The profile generation means 230 may also input the range of the number of characters in the profile (e.g., 70 to 100 characters) into the trained model 16b.

[0053] For example, when an AI 16 capable of natural language processing is to generate a profile, the profile generation means 230 sends the following text-format input data to the AI ​​server 15 via the communication IF 25: "Please generate a profile of Linda, who is a woman, child, maid, and fair-skinned, in 70 to 100 characters."

[0054] The AI ​​server 15 inputs input data acquired from the user terminal 20A into the input layer L1, processes the data in the intermediate layer L2, and outputs a text-format profile from the output layer L3. The AI ​​server 15 also transmits the generated profile to the user terminal 20A. The profile generation means 230 then receives the profile (output data) shown in FIG. 8A from the AI ​​server 15 via the communication IF 25.

[0055] A profile is text data that introduces an avatar. A profile may include any text information related to the avatar, such as the avatar's preferences, what they want to do in the online space, messages to other users, a backstory (e.g., hometown, educational background, work history), and family composition. A profile is also text that is imagined from multiple settings entered as input data. However, a profile is not limited to text format, and may also be in image format, audio format, or a combination of these. Furthermore, a profile does not have to be true and may be fictional.

[0056] The automatic editing means 240 edits the profile generated by the profile generation means 230. As one example, the automatic editing means 240 may delete predetermined keywords from the profile generated by the profile generation means. As another example, the automatic editing means 240 may replace predetermined keywords in the profile generated by the profile generation means with other words. Examples of keywords include sexual, violent, and discriminatory expressions, setting values ​​included in the input data, and specific personal information (current address, phone number).

[0057] In the example of FIG. 8B, the setting value "fair-skinned maid" is deleted, and the sexual expression "sexy" is replaced with "various." Whether to delete a keyword or replace it with another word may be predetermined, or the AI ​​16 may determine this. Furthermore, the automatic editing means 240 may skip editing if a predetermined keyword is not included in the profile.

[0058] As shown in FIG. 8C , the learning means 250 uses the input data "Please create a profile of Linda, who is female, child, maid, and fair-skinned, in 70 to 100 characters." and inputs the training data, which uses the profile edited by the automatic editing means 240 as correct answer data, into the trained model 16b for further training. That is, the learning means 250 transmits the training data to the AI ​​server 15 via the communication IF 25. The AI ​​server 15 causes the trained model 16b to perform a training process using the training data received from the user terminal 20A.

[0059] The publishing means 260 publishes in the online space the profile generated by the profile generating means 230 or edited by the automatic editing means 240 in association with the avatar generated by the object generating means 210. More specifically, the publishing means 260 associates the avatar data generated by the profile generating means 230 with the profile data generated by the profile generating means 230 or the automatic editing means 240, and transmits the associated data to the game server 10 via the communication IF 25.

[0060] In response to requests from user terminals 20B and 20C, game server 10 transmits the avatar data and profile data received from user terminal 20A to user terminals 20B and 20C. This allows users of user terminals 20B and 20C to perceive the avatar (hereinafter referred to as "avatar A") and profile (hereinafter referred to as "profile A") generated by user terminal 20A through monitor 31 and speaker 36.

[0061] As an example, the users of user terminals 20B and 20C view avatar A that comes into view of their own avatars B and C in the online space. The users of user terminals 20B and 20C also view profile A by selecting avatar A that comes into view. Furthermore, the users of user terminals 20B and 20C view avatar A and profile A through a user selection screen or a user details screen, which will be described later with reference to Figures 13A and 13B.

[0062] Next, an example of the process of generating an avatar and a profile in the user terminal 20B will be described with reference to FIGS. 9 to 11C. FIG. 9 is another example of an avatar generation screen. FIG. 10A is an example of the priority of setting parameters. FIG. 10B is another example of a histogram of setting values ​​for hairstyle parameters. FIG. 10C is another example of a histogram of setting values ​​for clothing parameters. FIG. 11A is another example of a profile generated by the AI ​​16. FIG. 11B is another example of a profile after editing. FIG. 11C is another example of learning data. Note that a detailed description of the commonalities with the examples of FIGS. 6 to 8C will be omitted, and the following description will focus on the differences. The examples of FIGS. 9 to 11C differ from the examples of FIGS. 6 to 8C in the combinations of setting values ​​selected by the user on the avatar generation screen.

[0063] More specifically, the user of user terminal 20B has selected the following settings: gender = male, age = adult, face shape = round, hairstyle = mohawk, skin color = dark, clothing = kamikaze uniform, and color = white. Object generation means 210 generates avatar data in accordance with these settings, and displays an avatar image represented by the generated avatar data in avatar display area A1.

[0064] 10A and 10B, the selection means 220 changes the priority of the hairstyle parameter "mohawk" and the clothing parameter "kamikaze uniform" to "1" because they have the fewest selection counts. Then, in the example of FIGS. 9 to 10C, the selection means 220 selects gender = male, age = adult, hairstyle = mohawk, and clothing = kamikaze uniform as the setting values ​​to be input to the trained model 16b.

[0065] The profile generation means 230 inputs text-format input data "Please generate a profile of Taro, male, adult, with a mohawk and wearing a special attack uniform, in 70 to 100 characters" into the trained model 16b, generating the profile shown in FIG. 11A. The automatic editing means 240 deletes the violent expression "fight" from the profile shown in FIG. 11A and replaces the violent expression "street fight" with "sports." Note that the role of the automatic editing means 240 may be assigned to the trained model 16b. That is, the trained model 16b may have previously learned predetermined keywords (in other words, keywords unsuitable for use in a profile) and generate a profile that does not include those keywords.

[0066] As shown in Figure 11C, the learning means 250 takes as input data "Please create a profile of Taro, male, adult, with a mohawk and wearing a special attack uniform, in 70 to 100 characters." and inputs the learning data, which uses the profile edited by the automatic editing means 240 as correct answer data, into the trained model 16b for further training.

[0067] The publishing means 260 associates the profile (hereinafter referred to as "profile B") generated by the profile generating means 230 or edited by the automatic editing means 240 with the avatar (hereinafter referred to as "avatar B") generated by the object generating means 210 and publishes it in the online space.

[0068] Fig. 12A is an example of a profile editing screen. Fig. 12B is an example of learning data. The user editing means 270 edits the profile generated by the profile generation means 230 or edited by the automatic editing means 240 in accordance with instructions from the user of the user terminal 20A. More specifically, the user editing means 270 displays the profile editing screen shown in Fig. 12A on the monitor 31.

[0069] The profile editing screen includes a profile display area A6, a software keyboard A7, and a "Confirm" icon. The profile display area A6 is an area that displays a profile generated by the profile generation means 230 or edited by the automatic editing means 240. The software keyboard A7 is an area that accepts user operations that instruct editing of the profile displayed in the profile display area A6 (adding, deleting, or correcting characters).

[0070] The user editing unit 270 edits the profile displayed in the profile display area A6 in accordance with user operations (instructions) via the software keyboard A7. The user editing unit 270 then finalizes the profile edit in response to the selection of the [OK] icon. Note that if the user enters a predetermined keyword (in other words, a keyword that is not suitable for use in the profile), the user editing unit 270 may not reflect the keyword in the profile.

[0071] Then, publishing means 260 publishes the profile edited by user editing means 270 in association with the avatar. Furthermore, as shown in Fig. 12B , learning means 250 inputs learning data including the input data generated by profile generation means 230 and the profile edited by user editing means 270 (correct answer data) into trained model 16b for further learning.

[0072] Next, a process in which a user of the user terminal 20C views avatars A and B and profiles A and B will be described with reference to Figures 13A and 13B. Here, the process of selecting users to play cooperatively in a cooperative online game will be described as an example. Figure 13A is an example of a user selection screen. Figure 13B is an example of a user details screen.

[0073] The user terminal 20C displays the user selection screen shown in FIG. 13A on the monitor 31. The user selection screen displays a list of users who can play cooperatively (e.g., users who are logged in to the online game). The user selection screen displays, for example, an avatar, name, level, and a [Details] icon for each user who can play cooperatively. That is, the user terminal 20C receives the avatars, names, and levels of users who can play cooperatively from the game server 10 and displays them in a list on the user selection screen.

[0074] In response to the selection of the [Details] icon corresponding to, for example, the name = Linda, the user terminal 20C displays the user details screen shown in FIG. 13B on the monitor 31. The user details screen is a screen that displays detailed information about the user selected through the user selection screen. The user details screen includes, for example, the name, level, avatar image, profile, rating, and [Request for Cooperation] icon of the selected user.

[0075] The evaluation items on the user details screen include a [GOOD] icon, a [BAD] icon, the number of times (91) the user has previously given a high rating when the [GOOD] icon was selected, and the number of times (9) the user has previously given a low rating when the [BAD] icon was selected. The [GOOD] icon corresponds to a high rating given by a user who viewed the profile. The [BAD] icon corresponds to a low rating given by a user who viewed the profile. The number of high ratings and the number of low ratings are cumulative values ​​tallied by the game server 10. When the [GOOD] icon or the [BAD] icon is selected, the user terminal 20C notifies the game server 10 of the selected icon. The game server 10 updates the tallied results of the number of high ratings and the number of low ratings, and notifies the user terminal 20A of the updated number of high ratings and the number of low ratings.

[0076] The feedback means 280 receives the updated number of likes and dislikes from the game server 10 via the communication IF 25. The number of likes and dislikes is an example of an evaluation of the profile. Then, the feedback means 280 feeds back the evaluation of the profile to the trained model 16b. The feedback means 280 transmits, for example, the number of likes as a score for the profile to the AI ​​server 15 via the communication IF 25. The trained model 16b re-learns or performs additional training using the number of likes fed back from the feedback means 280. In other words, the trained model 16b becomes more likely to generate a profile similar to a profile with a large number of likes and less likely to generate a profile similar to a profile with a small number of likes.

[0077] The timing and conditions for the feedback means 280 to provide feedback on the evaluation may be, for example, as follows: As one example, the feedback means 280 provides feedback when a predetermined time (e.g., 10 hours) has elapsed since the profile was made public. As another example, the feedback means 280 provides feedback on the condition that the number of likes, the number of dislikes, or the total number of likes and dislikes has reached a predetermined number (e.g., 100). However, the specific method for other users to evaluate a profile is not limited to the above-mentioned example.

[0078] According to the above embodiment, a profile of an avatar is generated in the trained model 16b using multiple setting values ​​selected when generating an avatar as input data. This allows a unique profile generated for an avatar to be associated with the avatar and made public without increasing the workload of the user.

[0079] Furthermore, according to the above embodiment, a unique profile can be generated by selecting setting values ​​to be input to the trained model 16b from among a plurality of setting values. In particular, a more unique profile can be generated by preferentially inputting setting values ​​that are selected less frequently by other users. However, if all setting values ​​are input to the trained model 16b, the selection means 220 can be omitted.

[0080] Furthermore, according to the above embodiment, by editing the profile generated by the trained model 16b, it is possible to prevent a profile including undesirable expressions from being published in the online space. However, if the trained model 16b is trained to exclude undesirable expressions, the automatic editing means 240 can be omitted.

[0081] Furthermore, according to the above embodiment, by enabling users to edit their profiles, it is possible to publish profiles of the users' preferences in the online space. Furthermore, compared to having the users create their profiles from scratch, it is possible to reduce the workload on the users. However, the user editing means 270 can be omitted.

[0082] Furthermore, according to the above embodiment, by re-learning the trained model 16b using the profile edited by the automatic editing means 240 and the user editing means 270 as correct answer data, it is possible to generate a profile that is more unique, does not include undesirable expressions, and matches the user's preferences. However, when using a general-purpose AI 16 that does not disclose the input interface for training data, the training means 250 can be omitted.

[0083] Furthermore, according to the above embodiment, by aggregating the evaluations of other users who have viewed the profile published in the online space and feeding them back to the trained model 16b, it is possible to generate a profile that is more suitable for the online space. However, if a general-purpose AI 16 that does not publish a feedback input interface is used, the feedback means 280 can be omitted.

[0084] [Other Embodiments] Specific examples of objects are not limited to avatars, but may include characters such as animals, monsters, and robots, equipment (e.g., weapons, armor, and accessories), vehicles (e.g., automobiles, ships, aircraft, and spaceships), and buildings (e.g., houses and castles). Specific examples of setting parameters vary depending on the type of object. For example, setting parameters corresponding to a house object include the shape of the roof, the material of the walls, the shape of the windows, and the layout of the room.

[0085] Furthermore, the program according to the present invention is not limited to a single program, but may be a collection of multiple programs. Furthermore, the program according to the present invention is not limited to being executed by a single device, but may be executed by multiple devices in a shared manner. Furthermore, the division of roles among the game server 10, the AI ​​server 15, and the user terminal 20 is not limited to the above-described example. That is, part of the processing of the game server 10 may be executed by the AI ​​server 15 or the user terminal 20, part of the processing of the AI ​​server 15 may be executed by the game server 10 or the user terminal 20, or part of the processing of the user terminal 20 may be executed by the game server 10 or the AI ​​server 15.

[0086] Furthermore, some or all of the means implemented by the program can be implemented by hardware such as an integrated circuit. Furthermore, the program may be provided in a form recorded on a non-transitory recording medium that can be read by a computer. Examples of recording media include hard disks, SD cards, DVDs, and servers on the Internet.

[0087] 1...system, 2...communication network, 10...game server, 15...AI server, 16...learning model, 16a...learning model, 16b...trained model, 17...neural network, 20...user terminal, 21...processor, 22...memory, 23...storage, 23P...terminal program, 25...communication interface, 26...computer, 29...communication bus, 31...monitor, 33...camera, 34...camera, 35...microphone, 36...speaker, 41...motion sensor, 42...operation device, 210...object generation means, 220...selection means, 230...profile generation means, 240...automatic editing means, 250...learning means, 260...publication means, 270...user editing means, 280...feedback means

Claims

1. A program that causes a computer to function as: object generation means that generates an object to be placed in an online space in accordance with a plurality of setting values ​​selected by a user to set the visual characteristics of the object; profile generation means that inputs the plurality of setting values ​​into a trained model that has been trained in advance to generate a profile of the object; and publishing means that associates the profile generated by the profile generation means with the object generated by the object generation means and publishes it in the online space.

2. A program according to claim 1, wherein the computer is caused to function as an automatic editing means for editing the profile generated by the profile generating means, and the publishing means publishes the profile edited by the automatic editing means.

3. A program according to claim 2, wherein the automatic editing means deletes predetermined keywords from the profile generated by the profile generating means.

4. A program as claimed in claim 2, which causes the computer to function as a learning means for inputting learning data, which has a plurality of said setting values ​​as input data and has the profile edited by said automatic editing means as correct answer data, into said trained model for further training.

5. A program according to claim 1, which causes the computer to function as a selection means for selecting one of the plurality of setting values ​​to be input to the trained model.

6. A program according to claim 5, wherein the selection means selects, from among the plurality of setting values, the setting value that has been selected less frequently by other users, with priority.

7. A program as claimed in claim 1, which causes the computer to function as: a user editing means for editing the profile generated by the profile generating means in accordance with instructions from a user; and a learning means for inputting learning data, which has as input data the plurality of setting values ​​and the profile edited by the user editing means as correct answer data, into the trained model for further learning.

8. A program according to claim 1, which causes the computer to function as a feedback means for obtaining evaluations of the profile from other users who have viewed the profile published by the publishing means, and feeding the evaluations back to the trained model.

9. A system comprising: an object generation means for generating an object in accordance with a plurality of setting values ​​selected by a user to set the visual characteristics of the object to be placed in an online space; a profile generation means for inputting the plurality of setting values ​​into a trained model that has been trained in advance to generate a profile of the object; and a publishing means for publishing in the online space the profile generated by the profile generation means in association with the object generated by the object generation means.

Images