Agent providing system, agent providing method, and recording medium

Abstract

The present techniques relate to an agent providing system, an agent providing method, and a recording medium which make it possible to provide a more preferable agent. Provided is an agent providing system comprising a control unit which, when an agent is newly provided in a cyberspace capable of registering a plurality of agents, provides an agent spaced apart from the agents already registered in the cyberspace by a certain amount or more with respect to appearance or voice. The present techniques are applicable to, for example, an agent providing system for providing agents registered in a cyberspace.

Description

Technical Field

[0001] The present technology relates to an agent providing system, an agent providing method, and a recording medium, and more particularly to an agent providing system, an agent providing method, and a recording medium that are capable of providing a more suitable agent.

Background Art

[0002] In recent years, with the advancement of information and communication technology, services that provide a cyber space have become widespread. In this type of service, there are those that provide various services by registering an agent to be used within the cyber space.

[0003] As technologies related to agents, for example, the technologies disclosed in Patent Documents 1 to 3 are known.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0005] By the way, when multiple agents can be registered within the cyber space, if there are agents with similar appearances or voices, there is a risk that the agents cannot be identified. Therefore, when multiple agents can be registered within the cyber space, it is required to provide a more suitable agent.

[0006] This technology has been made in view of such a situation, and aims to provide a more suitable agent.

Means for Solving the Problem

[0007] When a new agent is provided to a cyber space where a plurality of agents can be registered, the agent providing system according to one aspect of the present technology determines whether a new agent is the same as or similar to an already registered agent in terms of appearance or voice based on a value indicating the similarity between the appearance or voice assigned to the agent already registered in the cyber space and the appearance or voice to be assigned to the new agent. A control unit is provided that provides the cyber space with a new agent that has been determined to be neither the same nor similar. When the control unit cannot separate the appearance and voice of a new agent, based on the value indicating the similarity between the agent already registered in the cyber space and the new agent whose appearance and voice cannot be separated, it determines whether the new agent is identical or similar to the already registered agent. If it is determined that the new agent is identical or similar to the already registered agent, it adjusts the appearance and voice assigned to the already registered agent and provides the new agent to the cyber space. It is an agent providing system.

[0008] When a new agent for a specific user is provided to a private cyber space accessible by the specific user, the agent providing system according to one aspect of the present technology determines whether a new agent is the same as or similar to an already registered agent used by the specific user in terms of appearance or voice based on a value indicating the similarity between the appearance or voice assigned to the agent already registered in the private cyber space and used by the specific user and the appearance or voice to be assigned to the new agent. A control unit is provided that provides the private cyber space with a new agent that has been determined to be neither the same nor similar. The control unit checks whether the user can identify the agent already used by the user based on the appearance or voice of the agent newly provided to the user, and provides a new agent with an identifiable appearance or voice according to the check result. It is an agent providing system.

[0010] An agent providing method or a recording medium according to an aspect of the present technology is such that when an agent providing system provides a new agent to a cyber space in which a plurality of agents can be registered, based on a value indicating the degree of similarity between the appearance or voice assigned to an agent already registered in the cyber space and the appearance or voice to be assigned to the new agent, it is determined whether the new agent is identical or similar to the already registered agent in terms of appearance or voice, and the new agent determined not to be identical and not to be similar is provided to the cyber space. When the appearance and voice of a new agent cannot be separated, based on the value indicating the similarity between the agent already registered in the cyber space and the new agent whose appearance and voice cannot be separated, it determines whether the new agent is identical or similar to the already registered agent. If it is determined that the new agent is identical or similar to the already registered agent, it adjusts the appearance and voice assigned to the already registered agent and provides the new agent to the cyber space. An agent providing method including the above, or a computer, when providing a new agent to a cyber space in which a plurality of agents can be registered, based on a value indicating the degree of similarity between the appearance or voice assigned to an agent already registered in the cyber space and the appearance or voice to be assigned to the new agent, determines whether the new agent is identical or similar to the already registered agent in terms of appearance or voice, and provides the new agent determined not to be identical and not to be similar to the cyber space. A control unit that, when the appearance and voice of a new agent cannot be separated, based on the value indicating the similarity between the agent already registered in the cyber space and the new agent whose appearance and voice cannot be separated, determines whether the new agent is identical or similar to the already registered agent. If it is determined that the new agent is identical or similar to the already registered agent, it adjusts the appearance and voice assigned to the already registered agent and provides the new agent to the cyber space. A recording medium recording a program for functioning as a control unit.

Brief Description of Drawings

[0011] [Figure 1] It is a representative diagram showing an overview of the present technology. [Figure 2] It is a diagram showing an example of the configuration of an agent providing system to which the present technology is applied. [Figure 3] It is a diagram showing an example of the configuration of the information terminal in FIG. 2. [Figure 4] It is a diagram showing an example of the configuration of the server in FIG. 2. [Figure 5] It is a diagram showing an example of a method for generating a unique appearance. [Figure 6] It is a flowchart for explaining the flow of agent providing processing. [Figure 7] It is a flowchart for explaining the flow of a first example of the details of agent providing processing. [Figure 8] It is a flowchart for explaining the flow of a second example of agent provision processing. [Figure 9] It is a diagram showing a first example of the selection of the appearance and voice of an agent. [Figure 10] It is a flowchart for explaining the flow of a third example of agent provision processing. [Figure 11] It is a diagram showing a second example of the selection of the appearance and voice of an agent. [Figure 12] It is a diagram showing a third example of the selection of the appearance and voice of an agent. [Figure 13] It is a flowchart for explaining the flow of a first example of specific agent provision processing. [Figure 14] It is a diagram showing a fourth example of the selection of the appearance and voice of an agent. [Figure 15] It is a flowchart for explaining the flow of a second example of specific agent provision processing. [Figure 16] It is a diagram showing a first example when the identification confirmation of the appearance of a new agent is performed in an interactive form. [Figure 17] It is a diagram showing a second example when the identification confirmation of the appearance of a new agent is performed in an interactive form. [Figure 18] It is a flowchart for explaining the flow of a third example of specific agent provision processing. [Figure 19] It is a flowchart for explaining the flow of learning processing. [Figure 20] It is a diagram showing a first example of the specific configuration of an agent provision system. [Figure 21] It is a diagram showing a second example of the specific configuration of an agent provision system. [Figure 22] It is a diagram showing an example of a proposal for a facial appearance. [Figure 23] It is a flowchart for explaining the flow of a fourth example of agent provision processing. [Figure 24] It is a flowchart for explaining the flow of a first example of agent provision processing for an avatar. [Figure 25] This is a flowchart for explaining the process flow of the second example of details of agent providing processing for an avatar. [Figure 26] This is a diagram showing an example of a method for generating an agent's voice. [Figure 27] This is a diagram showing an example of the configuration of a computer.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present technology will be described with reference to the drawings. The description shall be made in the following order.

[0013] 1. First Embodiment: Basic Configuration 2. Second Embodiment: Method of Registering in a Private Cyber Space 3. Third Embodiment: Method of Changing the Appearance or Voice of the Same Agent by a User 4. Fourth Embodiment: Method of Providing a Group Agent 5. Fifth Embodiment: Method of Generating a New Appearance or Voice When Identification is Impossible 6. Sixth Embodiment: Method of Registering in a Public Cyber Space 7. Seventh Embodiment: Method of Generating an Agent's Voice 8. Modification Example 9. Configuration of a Computer

[0014] (Representative Diagram) FIG. 1 is a representative diagram showing the outline of the present technology.

[0015] When newly providing an agent to a cyber space where a plurality of agents can be registered, the agent providing system to which the present technology is applied provides an agent that is separated from the agents already registered in the cyber space by a certain degree or more in terms of appearance or voice.

[0016] In FIG. 1, the user is applying for a character agent as a new agent to be used in Cyber Space. However, in this Cyber Space, an agent that is similar in appearance or voice (not separated by a certain degree or more) to the newly applied agent is already registered.

[0017] Therefore, the new agent applied for by the user is rejected as "Reject" and is not provided to the Cyber Space.

[0018] On the other hand, although not shown in the figure, when a new agent that is not similar in appearance or voice (separated by a certain degree or more) to an agent already registered in the Cyber Space is applied for, the new agent is accepted as "Accept" and is provided to the Cyber Space.

[0019] In this way, the agent providing system applying this technology has a function like an authentication agency that authenticates new agents provided in the Cyber Space, and can provide agents with ensured uniqueness of appearance or voice to the Cyber Space.

[0020] <1. First Embodiment>

[0021] (Example of System Configuration) FIG. 2 shows an example of the configuration of an agent providing system applying this technology.

[0022] The agent providing system 1 is composed of information terminals 10-1 to 10-N (N: an integer of 1 or more) and a server 20.

[0023] In the agent providing system 1, the information terminals 10-1 to 10-N and the server 20 are interconnected via a network 30. The network 30 includes a communication network such as the Internet, an intranet, or a mobile phone network.

[0024] The information terminal 10-1 is an electronic device having a predetermined user interface (UI: User Interface), such as a personal computer, a smartphone, a mobile phone, a tablet terminal, a game machine, or a wearable device.

[0025] The information terminal 10-1 performs various operations according to a user's operation on the predetermined user interface.

[0026] For example, the information terminal 10-1 transmits a request regarding an agent to the server 20 via the network 30 according to a user's operation. The information terminal 10-1 receives a response regarding the agent transmitted from the server 20 via the network 30. The information terminal 10-1 performs various processes regarding the agent based on the received response.

[0027] The information terminals 10-2 to 10-N are each configured as an electronic device such as a personal computer, similar to the information terminal 10-1. Each of the information terminals 10-2 to 10-N can communicate with the server 20 via the network 30 regarding requests and responses regarding the agent, and perform various processes according to the received responses.

[0028] In the following description, when there is no need to particularly distinguish the information terminals 10-1 to 10-N, they are simply referred to as the information terminal 10.

[0029] The server 20 is composed of one or more servers. The server 20 performs various processes regarding the agent.

[0030] For example, the server 20 receives a request regarding the agent transmitted from the information terminal 10 via the network 30. The server 20 performs various processes regarding the agent based on the received request. The server 20 transmits a response regarding the agent obtained by the various processes to the information terminal 10 via the network 30.

[0031] (Configuration example of the information terminal) Figure 3 shows an example of the configuration of the information terminal 10 in FIG. 2.

[0032] In FIG. 3, the information terminal 10 includes a control unit 100, an input unit 101, an output unit 102, a storage unit 103, and a communication unit 104.

[0033] The control unit 100 is composed of a processor such as a CPU (Central Processing Unit). The control unit 100 is a central control device (processing device) that controls the operations of each unit and performs various arithmetic processes.

[0034] The input unit 101 is an input device such as a mouse 121, a keyboard 122, or a physical button. The input unit 101 supplies operation data corresponding to a user's operation to the control unit 100. The control unit 100 controls the operations of each unit based on the operation data from the input unit 101.

[0035] The output unit 102 is an output device such as a display 131 or a speaker 132. The output unit 102 outputs information corresponding to various data according to the control from the control unit 100.

[0036] The display 131 displays an image corresponding to the video data from the control unit 100. The speaker 132 outputs a sound (voice) corresponding to the audio data from the control unit 100.

[0037] Note that the display 131 may be configured as a touch panel together with an input unit that supplies operation data corresponding to the contact position (position of a predetermined point) to the control unit 100 when a user's finger touches the surface of the screen.

[0038] The storage unit 103 is an auxiliary storage device including a semiconductor memory such as a non-volatile memory or an HDD (Hard Disk Drive). The storage unit 103 stores various data according to the control from the control unit 100. Note that the storage unit 103 may be configured as an internal storage or an external storage such as a memory card.

[0039] The communication unit 104 is a communication device including a communication module corresponding to wireless communication or wired communication conforming to a predetermined standard. The communication unit 104 communicates with other devices such as the server 20 via the network 30 according to the control from the control unit 100.

[0040] Also, the control unit 100 includes an agent processing unit 111, a presentation control unit 112, and a communication control unit 113.

[0041] The agent processing unit 111 performs processes related to agents provided in the cyber space (processes such as registering an agent and operating a registered agent) according to the operations from the user. Details of the processes related to agents will be described later.

[0042] The presentation control unit 112 controls the output unit 102 such as the display 131 and the speaker 132 to present various kinds of information.

[0043] The communication control unit 113 controls the communication unit 104 to communicate with other devices via the network 30.

[0044] (Example of server configuration) FIG. 4 shows an example of the configuration of the server 20 in FIG. 2.

[0045] In FIG. 4, the server 20 is composed of a control unit 200, an input unit 201, an output unit 202, a storage unit 203, and a communication unit 204.

[0046] The control unit 200 is composed of a processor such as a CPU. The control unit 200 is a central control device (processing device) that controls the operations of each unit and performs various arithmetic processes.

[0047] The input unit 201 is an input device such as a mouse, a keyboard, and physical buttons. The input unit 201 supplies input data corresponding to the operations of the user to the control unit 200. The control unit 200 controls the operations of each unit based on the input data from the input unit 201.

[0048] The output unit 202 is an output device such as a display or a speaker. The output unit 202 outputs information corresponding to various data such as video and audio according to the control from the control unit 200.

[0049] The storage unit 203 is a large-capacity auxiliary storage device including a semiconductor memory such as a non-volatile memory and an HDD. The storage unit 203 stores various data according to the control from the control unit 200.

[0050] The communication unit 204 is a communication device including a communication module corresponding to wireless communication or wired communication compliant with a predetermined standard. The communication unit 204 communicates with other devices such as the information terminal 10 via the network 30 according to the control from the control unit 200.

[0051] Also, the control unit 200 includes an agent providing unit 211, a learning unit 212, and a communication control unit 213.

[0052] The agent providing unit 211 performs an agent providing process for providing an agent in the cyber space. The details of the agent providing process will be described later.

[0053] The learning unit 212 performs machine learning based on the input information (learning data) and outputs the result of the machine learning. The agent providing unit 211 identifies (judges, predicts, etc.) the input information based on the input information and the result of the machine learning.

[0054] The communication control unit 213 controls the communication unit 204 to communicate with other devices via the network 30.

[0055] The agent providing system 1 is configured as described above. Hereinafter, the details of the process executed by the agent providing system 1 will be described.

[0056] (The individuality of the appearance or voice of the agent) By the way, in the cyber space, the uniqueness of the appearance (physique) of an agent held by a certain user serves as an identifier when viewed by other users. Therefore, when inputting and outputting information in the cyber space, the uniqueness of this appearance will play an important role.

[0057] That is, the appearance of the agent serves as a guarantee that information can be passed to the user. Also, the appearance of the agent is the basis for the reliability of the information received from the user.

[0058] In this way, when providing an agent, the uniqueness of its appearance becomes an important clue in terms of information reliability and information transfer. Therefore, the uniqueness of the appearance of agents in the cyber space is an important issue.

[0059] In recent years, agents in the cyber space have begun to have appearances such as characters. On the other hand, in the future, there is a possibility that agents or avatars as the user's own doppelgangers will increase beyond the population of the real world.

[0060] In such a situation, different from humans (users) in the real space, the uniqueness of the appearance of agents, including whether the appearance of agents with the element of expression can be distinguished in the cyber space, becomes important. The same applies to the uniqueness of the voice of agents.

[0061] Therefore, in the agent providing system 1, when newly providing an agent to a cyber space where a plurality of agents can be registered, an agent that is separated by a certain degree or more in terms of appearance or voice from the agents already registered in the cyber space is provided.

[0062] As a result, in the cyber space, the uniqueness of the appearance or voice of each agent is ensured. As a result, more suitable agents can be provided.

[0063] Specifically, it is possible to reliably distinguish between the agent of a certain user and the agents of other users. Also, for example, even in a situation where a certain user uses multiple agents according to their respective purposes, it is possible to reliably distinguish the agents based on their unique appearance, thus preventing mistakes such as checking tomorrow's schedule against an agent specialized in music recommendations.

[0064] Here, as a method for generating a unique appearance (appearance), for example, there is a method as shown in FIG. 5.

[0065] That is, as shown in FIG. 5, as parts of the agent's face, if we focus on the eyes, parameters such as the type, size, and relative position on the face can be set. However, if the user freely sets the parameters, there is a risk of generating unexpected appearances such as eyes protruding from the face, so restrictions such as maximum and minimum values can be applied to the parameters.

[0066] More specifically, as types of eyes, there are round eyes, roundish-almond eyes, almond eyes, thin almond eyes, droopy eyes, droopy hooded eyes, hooded eyes, asian eyes, childish / round asian eyes, etc.

[0067] By preparing such types of eyes in advance as basic patterns and multiplying the basic pattern eyes by a size coefficient, the variations of the eye parts can be increased.

[0068] Similarly, for parts other than the eyes such as the mouth and nose, parameters such as the type, size, and relative position on the face can be set (FIG. 5).

[0069] When generating the face of an agent, for example, the parameters of each part can be randomly selected and set so that a face similar to that of other agents (a relatively similar face) is not generated.

[0070] At this time, if the same (or similar) combination of parameters of the face generated in the past is selected, the parameters are selected again. Then, when there is no face with the same (or similar) combination of parameters, the generation of the agent's face may be completed.

[0071] Note that the agent can be represented by a 2D image or a 3D image. Also, the voice of the agent will be described later with reference to FIG. 26 and the like.

[0072] (Overall image of the process) Next, with reference to the flowcharts of FIGS. 6 to 8, the overall image of the agent providing process in the first embodiment will be described.

[0073] This agent providing process is realized by the operation of the information terminal 10 (control unit 100) or the server 20 (control unit 200), or the cooperation of the information terminal 10 (control unit 100) and the server 20 (control unit 200).

[0074] That is, this agent providing process is executed by at least one of the control units 100 and 200. In the following description, for the sake of simplicity of explanation, the case where the agent providing process is executed by the control unit 200 is exemplified, but all or part of the process may be executed by the control unit 100.

[0075] In step S11, the control unit 200 determines whether to newly provide an agent in the cyber space.

[0076] If it is determined to be affirmative ("Yes") in the determination process of step S11, the process proceeds to step S12. In step S12, the control unit 200 executes agent providing processing.

[0077] In this agent providing processing, an agent that is sufficiently different from the agents already registered in the cyber space in terms of appearance or voice (an agent with ensured uniqueness of appearance or voice) is provided.

[0078] Note that the details of the agent providing processing will be described later with reference to the flowcharts of FIGS. 7, 8, 10, and 23.

[0079] When the processing of step S12 ends, or when it is determined to be negative ("No") in the determination process of step S11, the agent providing processing in FIG. 6 ends.

[0080] Here, with reference to the flowchart of FIG. 7, a first example of the details of the agent providing processing corresponding to the processing of step S12 in FIG. 6 will be described.

[0081] In step S31, the control unit 200 compares a new agent with the agents already registered in the cyber space.

[0082] In step S32, the control unit 200 determines, based on the comparison result in the processing of step S31, whether the new agent is sufficiently different from the agents already registered in the cyber space in terms of appearance or voice.

[0083] As an algorithm for executing this comparison and determination processing, various algorithms can be used. For example, Euclidean distance and threshold determination can be used.

[0084] That is, regarding appearance (looks), parameters related to face shape, facial features, body type, skin color, gender, clothing, hairstyle, etc. For example, in terms of facial features, the size, shape, distance between each other, brightness, and color are each regarded as one parameter (one element), and after multi-dimensional vectorization, the features of appearance are expressed as a multi-dimensional vector.

[0085] Also, regarding voice (speech), not only the frequency characteristics but also rhythm (pitch of voice), intonation, rhythm, characteristics of speaking style, etc. are regarded as one parameter (one element) each, and the features of voice are expressed as a multi-dimensional vector.

[0086] Then, by taking the Euclidean distance between two multi-dimensional vectors, comparison and determination processing can be performed based on whether the distance is greater than or equal to a predetermined threshold.

[0087] Here, for example, when the Euclidean distance is greater than or equal to the threshold, it is determined that the appearance or voice is separated by a certain amount or more. In this case, it can be said that the appearance or voice is not similar and is dissimilar. That is, "the appearance or voice is separated by a certain amount or more" means "the appearance or voice is dissimilar".

[0088] On the other hand, for example, when the Euclidean distance is less than the threshold, it is determined that the appearance or voice is not separated by a certain amount or more. In this case, it can be said that the appearance or voice is similar. That is, "the appearance or voice is not separated by a certain amount or more" means "the appearance or voice is similar".

[0089] Note that "the appearance or voice is not separated by a certain amount or more" includes cases where the appearance or voice is the same. Also, in the comparison and determination processing described later, similar to step S32, the Euclidean distance and threshold determination can be used. Here, the case of using the Euclidean distance and threshold determination as the comparison and determination processing is exemplified, but other known methods can also be used.

[0090] In step S32, if it is determined that the appearance or voice is separated by a certain amount or more, the process proceeds to step S33. In step S33, the control unit 200 provides a new agent in the cyber space.

[0091] On the other hand, in step S32, if it is determined that the appearance or voice is not separated by a certain amount or more, the process of step S33 is skipped. That is, in this case, a new agent is not provided in the cyber space.

[0092] When the process of step S33 ends, or when it is determined to be negative ("No") in the determination process of step S32, the process returns to step S12 in FIG. 6, and the subsequent processes are executed.

[0093] In this way, in the agent providing system 1, as a new agent, an agent that is separated by a certain amount or more from the agents already registered in the cyber space in terms of appearance or voice is provided. Therefore, an agent with ensured uniqueness of appearance or voice can be provided.

[0094] Next, with reference to the flowchart of FIG. 8, a second example of the details of the agent providing process corresponding to the process of step S12 in FIG. 6 will be described.

[0095] In step S51, the control unit 200 generates a new agent that is separated by a certain amount or more from the agents already registered in the cyber space in terms of appearance or voice.

[0096] In step S52, the control unit 200 provides the generated new agent in the cyber space.

[0097] When the process of step S52 ends, the process returns to step S12 in FIG. 6, and the subsequent processes are executed.

[0098] In this way, in the agent providing system 1, as a new agent, an agent that is sufficiently different from the agents already registered in the cyber space in terms of appearance or voice is generated, so that an agent with ensured appearance or voice uniqueness can be provided.

[0099] <2. Second Embodiment>

[0100] By the way, as the cyber space where agents are registered, there are a private cyber space accessible by a specific user, such as an agent application, and a public cyber space accessible by any plurality of users, such as a VR (Virtual Reality) space. Here, a case of providing an agent that is sufficiently different from the appearance or voice of the agent used by a specific user in the private cyber space will be described.

[0101] (Example of Selection of Appearance and Voice) FIG. 9 shows a first example of the selection of the appearance and voice of an agent.

[0102] In FIG. 9, the appearance and voice assigned to each agent are shown, and the agent (its main body), its appearance and voice are separable from each other.

[0103] Specifically, for agent #1 (Agent#1), appearance #1 and voice #1 corresponding to its order are assigned by default, but since its appearance and voice are separable, when providing agent #1, not only appearance #1 and voice #1 but also appearances and voices with other numbers can be assigned.

[0104] Similarly for agents #2 to #8, each agent has its own appearance and voice assigned according to its order, but the agent (its main body), its appearance and voice are separable, and appearances and voices with other numbers can be assigned.

[0105] Assume a case where Agent #5 is newly provided when Agents #1 and #3 are registered as agents used by User A, a specific user, in a private cyber space.

[0106] However, the default appearance #1 and voice #1 are assigned to Agent #1, and a different-order appearance #2 and voice #2 are assigned to Agent #3. Appearance #1 or voice #1 and appearance #2 or voice #2 are separated by a certain distance or more.

[0107] Here, for Agent #5 newly provided for User A, an appearance #3 and voice #3 that are separated by a certain distance or more from appearance #1 or voice #1 of Agent #1 and appearance #2 or voice #2 of Agent #3 can be assigned.

[0108] In this way, since the agent (its main body) and its appearance and voice are separable, any combination of appearance and voice can be applied to the agent, so it is not necessary to prepare appearances and voices for each agent. As a result, the number of appearances and voices for the agents can be reduced, and thus the cost of providing agents can be reduced.

[0109] Note that, for example, when a user uses a plurality of agent applications, the respective private cyber spaces of the plurality of agent applications may be regarded as a single private cyber space, and the appearance or voice of the agents used in that private cyber space may be controlled to be separated by a certain distance or more.

[0110] (Overall image of the process) Next, with reference to the flowchart of FIG. 10, the overall image of the agent provision process in the second embodiment will be described. Note that the agent provision process in FIG. 10 corresponds to the process of step S12 in FIG. 6.

[0111] In step S71, the control unit 200 determines whether to newly provide an agent for a specific user in the private server space.

[0112] If it is determined affirmatively in the determination process of step S71, the process proceeds to step S72. In step S72, the control unit 200 executes specific agent providing processing.

[0113] In this specific agent providing processing, an agent that is already registered in the private server space and is separated from the appearance or voice of the agent already used by the specific user by a certain degree or more (an agent with ensured appearance or voice uniqueness) is provided.

[0114] Note that the details of the specific agent providing processing will be described later with reference to the flowcharts of FIGS. 13, 15, and 18.

[0115] When the processing of step S72 ends or when it is determined negatively in the determination process of step S71, the process returns to the processing of step S12 in FIG. 6, and the subsequent processing is executed.

[0116] As described above, in the agent providing system 1, when newly providing an agent for a specific user in the private server space, an agent that is already registered in the private server space and is separated from the appearance or voice of the agent already used by the specific user by a certain degree or more is provided. Therefore, an agent with ensured appearance or voice uniqueness can be provided within the private server space.

[0117] In this embodiment, it is assumed that the appearance and voice of the agent can be separated. However, when registering well-known characters or characters from famous anime as agents, in principle, their appearance or voice cannot be separated. Therefore, when newly registering an agent whose appearance and voice cannot be separated, if it is similar to an already registered agent whose appearance and voice can be separated, the assignment of the appearance and voice of the already registered agent may be adjusted.

[0118] <3. Third Embodiment>

[0119] Even for the same agent, its appearance (facial features) or voice may differ for each user. Specifically, when User A and User B each use the same music recommendation agent, the appearance (facial features) or voice of the music recommendation agent used by User A and the music recommendation agent used by User B will be different.

[0120] (Example of Selection of Appearance and Voice) FIG. 11 shows a second example of the selection of the appearance and voice of the agent.

[0121] In FIG. 11, similar to FIG. 9 described above, for each of Agents #1 to #8, the appearance and voice corresponding to their order are assigned by default. However, the agent (its main body) is separable from its appearance and voice, and it is possible to assign the appearance and voice of other numbers.

[0122] Here, assume a case where Agents #1 and #2 are already registered as agents used by User A, and User A is provided with Agent #7 for a specific purpose such as a music recommendation agent.

[0123] However, in FIG. 11, for the agent #7 for a specific use, the appearance #7 or voice #7 is assigned by default. Also, the appearance #3, voice #3 and the appearance #7, voice #7 are similar to each other (not separated by more than a certain distance).

[0124] At this time, the appearance or voice of all the agents #1, #2 already owned by user A (appearance #1 or voice #1 and appearance #2 or voice #2) and the appearance #7 or voice #7 of the agent #7 for a specific use are separated by more than a certain distance (not similar). Therefore, in the example of this user A, the agent #7 for a specific use is provided with the appearance #7 or voice #7 as it is.

[0125] On the other hand, assume a case where agents #2, #3 are already registered as agents used by user B, and user B is provided with the agent #7 for a specific use.

[0126] At this time, either the appearance or voice of the agents #2, #3 already owned by user B (appearance #2 or voice #2, appearance #3 or voice #3) and the appearance #7 or voice #7 of the agent #7 for a specific use are not separated by more than a certain distance (similar). Therefore, in the example of this user B, instead of the appearance #7 or voice #7, the agent #7 for a specific use with an appearance #8 or voice #8 different from the appearance #7 or voice #7 is provided.

[0127] Also, FIG. 12 shows a third example of the selection of the appearance and voice of an agent.

[0128] In FIG. 12, when user B is provided with the agent #7 for a specific use while agents #2, #3 are already registered as agents used by user B, the default appearance #7 or voice #7 is similar to the appearance #3 or voice #3. Therefore, for the agent #7 for a specific use, an appearance #9 or voice #9 is assigned instead of the default appearance #7 or voice #7.

[0129] Note that the appearance #9 or voice #9 represents an appearance or voice prepared separately (not shown), but it is also possible to assign appearance #8 or voice #8, etc.

[0130] (Overall image of the process) Next, with reference to the flowchart of FIG. 13, the overall image of the agent provision process in the third embodiment will be described. Note that the specific agent provision process in FIG. 13 corresponds to the process of step S72 in FIG. 10.

[0131] In step S91, the control unit 200 determines whether the appearance or voice of all agents already held by the specific user is separated from the first appearance or the first voice of an agent for a specific purpose, such as a music recommendation agent, by a certain degree or more.

[0132] If it is determined to be affirmative in the determination process of step S91, the process proceeds to step S92. In step S92, the control unit 200 provides an agent for a specific purpose having the first appearance or the first voice for the specific user.

[0133] Specifically, when providing agent #7 for a specific purpose for user A, since the appearance #1 or voice #1, appearance #2 or voice #2 of all agents #1, #2 already held by user A and the appearance #3 or voice #3 of the agent #7 for a specific purpose are separated by a certain degree or more, the agent #7 for a specific purpose is provided as appearance #7 or voice #7 (example of user A in FIG. 11).

[0134] On the other hand, if it is determined to be negative in the determination process of step S91, that is, when the appearance or voice of any of the agents already held by the specific user and the first appearance or the first voice of the agent for a specific purpose are not separated by a certain degree or more (when they are similar), the process proceeds to step S93.

[0135] In step S93, the control unit 200 provides an agent for a specific use with a second appearance or voice different from the first appearance or voice for a specific user.

[0136] Specifically, when providing the agent #7 for a specific use to user B, since the appearance #2 or voice #2 of agent #2 and #3 already owned by user B and the appearance #7 or voice #7 of the agent #7 for a specific use are not separated by a certain distance or more, instead of the appearance #7 or voice #7, an agent #7 for a specific use with an appearance #8 or voice #8 is provided (example of user B in FIG. 11).

[0137] When the process of step S92 or S93 ends, the process returns to the process of step S72 in FIG. 10, and the subsequent processes are executed.

[0138] In this way, in the agent providing system 1, when providing an agent for a specific use with the uniqueness of appearance or voice ensured, even for the same agent, its appearance or voice can be changed for each user, so that an agent suitable for the user can be provided.

[0139] <4. Fourth Embodiment>

[0140] In the cyber space, it is also assumed that a group agent is used within a group to which a plurality of users belong. Here, a case of providing a group agent considering appearance (form) or voice in a private cyber space will be described.

[0141] (Example of Selection of Appearance and Voice) FIG. 14 shows a fourth example of the selection of the appearance and voice of an agent.

[0142] In FIG. 14, similar to FIG. 9 and the like described above, each of Agents #1 to #8 has a default appearance and voice assigned according to the order, but the agent (its main body), its appearance and voice are separable, and it is possible to assign the appearance and voice of other numbers.

[0143] Here, two users, User A and User B, belong to the same group in a private cyber space, and each of User A and User B has already registered the agents they use.

[0144] As agents used by User A, Agents #1, #3, #5 (Appearance #1 and Voice #1, Appearance #2 and Voice #2, Appearance #3 and Voice #3) have already been registered. As agents used by User B, Agents #2, #3, #8, #9 (Appearance #1 and Voice #1, Appearance #2 and Voice #2, Appearance #3 and Voice #3, Appearance #4 and Voice #4) have already been registered.

[0145] At this time, assume a case where a group agent #X is provided. When providing this group agent #X, different appearances and voices from all the agents already owned by users A and B in the group are assigned.

[0146] That is, Appearance #5 and Voice #5 are not assigned to Agents #1, #3, #5 used by User A and Agents #2, #3, #8, #9 used by User B, and the appearances and voices of the agents used by User A and B are separated from Appearance #5 and Voice #5 by a certain amount or more. Therefore, Appearance #5 and Voice #5 can be assigned to the group agent #X.

[0147] As a result, when newly providing a group agent for the group to which User A and User B belong in the private cyber space, it is possible to provide a group agent that is separated from the agents already owned by User A and User B by a certain amount or more in terms of appearance or voice.

[0148] (Overall Image of the Process) Next, with reference to the flowchart of FIG. 15, the overall image of the agent providing process in the fourth embodiment will be described. Note that the specific agent providing process in FIG. 15 corresponds to the process of step S72 in FIG. 10.

[0149] In step S111, the control unit 200 determines whether to newly provide an agent for a group in the private server space.

[0150] If it is determined affirmatively in the determination process of step S111, the process proceeds to step S112. In step S112, the control unit 200 provides an agent having an appearance or voice different from all the agents already held by the users in the group.

[0151] Specifically, when providing an agent for a group to which user A and user B belong, an agent for the group having an appearance #5 and a voice #5 different from the appearances and voices of the agents already held by user A (appearance #1 and voice #1, appearance #2 and voice #2, appearance #3 and voice #3) and the appearances and voices of the agents already held by user B (appearance #1 and voice #1, appearance #2 and voice #2, appearance #3 and voice #3, appearance #4 and voice #4) is provided (example in FIG. 14).

[0152] When the process of step S112 ends or when it is determined negatively in the determination process of step S111, the process returns to step S72 in FIG. 10, and the subsequent processes are executed.

[0153] In this way, in the agent providing system 1, when newly providing an agent for a group in the private server space, an agent for the group that is sufficiently separated from the agents already held by the users in the group in terms of appearance or voice can be provided.

[0154] <5. Fifth Embodiment>

[0155] When providing a new agent, the user may be asked whether the appearance (facial features) or voice of the new agent is distinguishable. Depending on the confirmation result, an agent with a distinguishable appearance (facial features) or voice may be provided.

[0156] (First example) Figure 16 shows an example of the interaction between the agent and the user when confirming the distinguishability of the appearance (facial features) of the new agent.

[0157] Agent: "Can you distinguish it from the agents you are related to?" User: "It's okay, I can distinguish it." User: "Sorry, it looks like Agent A." Agent: "What parts look alike?" User: "The area around the mouth looks alike."

[0158] In this first example, during the interaction between the agent and the user, the facial parts of other agents that are considered similar to the facial parts of the new agent are identified. In the agent providing system 1, by obtaining the information regarding "what looks alike", an agent reflecting this information can be presented again.

[0159] For example, in the agent providing system 1, for the new agent and other agents, the parameters of the facial parts considered similar during the interaction are compared, and the relationship of the coefficients is analyzed. Also, in the agent providing system 1, assuming that the user is highly sensitive to the facial parts considered similar, in the appearance of the new agent to be presented (re - presented) thereafter, the difference (parameter difference) of the said parts is made larger.

[0160] More specifically, in the interaction between the agent and the user described above, since it was identified that the mouth part of the new agent resembles that of other agents, when re-presenting the new agent, in particular, the appearance is changed so that the mouth part looks different from that of other agents.

[0161] (Second example) FIG. 17 shows an example of the interaction between the agent and the user when reconfirming the appearance (look) of the new agent.

[0162] Agent: "Can I distinguish?" User: "It's okay, I can distinguish."

[0163] In this second example, when re-presenting a new agent that reflects the interaction between the agent and the user in the first example of FIG. 16 described above, the user conveys that they can distinguish a new agent whose appearance, especially the appearance of the mouth part, has been changed from other agents.

[0164] Thus, when the appearance of the re-presented new agent is separated (not similar) from the appearance of other agents by a certain degree or more, the new agent is determined as the agent to be provided to the user.

[0165] On the other hand, when the appearance of the re-presented new agent is not separated (similar) from the appearance of other agents by a certain degree or more, the presentation of a new agent with a changed appearance is repeated by appropriately changing the parameters for each part, so that a new agent that does not resemble other agents is presented to the user.

[0166] Note that the interaction between the agent and the user shown in FIGS. 16 and 17 can be performed, for example, in a text chat by displaying messages exchanged in real time on the screen of the information terminal 10, or can also be performed by voice using, for example, a voice chat.

[0167] (Overall Image of the Process) Next, with reference to the flowchart of FIG. 18, the overall image of the agent provision process in the fifth embodiment will be described. Note that the specific agent provision process in FIG. 18 corresponds to the process of step S72 in FIG. 10.

[0168] In step S131, the control unit 200 determines whether it is possible to identify the agent that the user is already using based on the appearance or voice of the newly provided agent.

[0169] If it is determined to be affirmative in the determination process of step S131, the process proceeds to step S132. In step S132, the control unit 200 provides a new agent having an identifiable appearance or voice.

[0170] On the other hand, if it is determined to be negative in the determination process of step S131, the process proceeds to step S133. In step S133, the control unit 200 generates an agent having a new appearance or voice different from the unidentifiable appearance or voice.

[0171] When the process of step S133 ends, the process returns to step S131. Then, in the determination process of step S131, it is determined again whether it is possible to identify the agent that the user is already using based on the new appearance or voice, and the loop of steps S133 and S131 is repeated until it is determined to be identifiable (''Yes'' in S131).

[0172] Then, when it is determined that it is identifiable based on the new appearance or voice, the agent having the identifiable new appearance or voice is provided as a new agent.

[0173] Specifically, in the dialogue between the agent and the user, when it is determined that the mouth part of the new agent is similar to that of another agent, in particular, an agent whose appearance is changed so that the mouth part looks different from that of another agent is re-presented. Then, if the appearance of the newly presented agent is not similar to that of another agent, the new agent is provided (examples in FIGS. 16 and 17).

[0174] When the process of step S132 ends, the process returns to the process of step S72 in FIG. 10, and the subsequent processes are executed.

[0175] (Learning process) Next, with reference to the flowchart of FIG. 19, the flow of the learning process will be described.

[0176] In step S151, the control unit 200 acquires an answer from the user as to whether the appearance or voice of the newly provided agent is distinguishable.

[0177] In step S152, the control unit 200 learns the characteristics when the user identifies the appearance or voice of the agent using the answer from the user as teacher data. Here, for example, the answers of the user in the dialogue between the agent and the user shown in FIGS. 16 and 17 can be used as teacher data.

[0178] As this learning method, for example, machine learning such as neural networks and deep learning is used.

[0179] A neural network is a model that mimics the human brain nerve circuit and consists of three types of layers: an input layer, an intermediate layer (hidden layer), and an output layer. Deep learning is a model using a neural network with a multi-layer structure, which can repeatedly perform characteristic learning in each layer and learn complex patterns hidden in a large amount of data.

[0180] In addition, problem settings for machine learning include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, inverse reinforcement learning, active learning, transfer learning, etc. In the sixth example, the case of using supervised learning is illustrated. In supervised learning, features are learned based on given labeled training data (teacher data). This makes it possible to derive the labels of unknown data.

[0181] When the process of step S152 ends, the learning process in FIG. 19 ends.

[0182] As described above, in the agent providing system 1, when providing a new agent, the user is confirmed whether the appearance or voice of the new agent is distinguishable, and an agent having a distinguishable appearance or voice is provided according to the confirmation result. Therefore, an agent close to the user's feeling can be provided.

[0183] When generating a new agent, since the results of machine learning can be used, the more user responses used as teacher data are obtained, the more surely an agent having a distinguishable appearance or voice can be generated.

[0184] Here, the description has been centered on the appearance (facial features) in particular. However, regarding the voice as well, the user can be confirmed whether the voice of the new agent is distinguishable, and based on the confirmation result, specific agent providing processes, learning processes, etc. may be performed.

[0185] <6. The Sixth Embodiment>

[0186] Even in the public cyber space, an agent that is sufficiently separated from the appearance or voice of the agent used as an avatar by a specific user can be provided.

[0187] (The First Example) FIG. 20 shows a first example of the specific configuration of the agent providing system 1.

[0188] In FIG. 20, the information terminal 10 and the server 20 exchange various data, and the appearance (image) or voice (data) of the agent is registered. Here, the registration of the appearance (image) of the agent will be mainly described among the registration of the appearance (image) and voice of the agent.

[0189] In the information terminal 10, when the appearance creation tool 151 or the voice creation tool 152 provided as software is executed by the control unit 100, the GUI (Graphical User Interface) of these tools is displayed on the display 131. At this time, the users who operate these tools include the producer (creator) who creates the agent.

[0190] The appearance creation tool 151 is a tool for generating the appearance of the agent. The voice creation tool 152 is a tool for generating the voice of the agent.

[0191] The appearance creation tool 151 includes a paint tool 161. The paint tool 161 is graphic software for drawing an image (such as 2D CG (Computer Graphics)) on a computer mainly using a mouse 121 or the like.

[0192] For example, in the paint tool 161, the drawing software 162 performs processing such as deformation and processing on various objects 163 (for example, facial parts such as eyes, ears, and face shapes), and the appearance of the agent is generated. The paint tool 161 outputs a message including a registration request for the generated appearance of the agent to the communication unit 104, and transmits it to the server 20 via the network 30.

[0193] In the server 20, when the appearance registration program 251 is executed by the control unit 200, the functions of the appearance similarity check unit 261 and the appearance registration unit 271 are realized. Also, in the server 20, a registered appearance database 252 is recorded in the storage unit 203.

[0194] When a message including a registration request is input from the communication unit 204, the appearance similarity check unit 261 refers to the data (appearance data, space ID, etc.) stored in the registered appearance database 252 and checks the similarity of the appearance of the generated agent (the appearance of the request target).

[0195] For example, in the appearance similarity check unit 261, the parameter analysis unit 263 analyzes the parameters of the appearance of the request target (for example, each part such as eyes, ears, face shape, etc.), and the face authentication unit 262 authenticates the appearance of the request target (face) based on the analysis result of the parameters.

[0196] Then, in the appearance similarity check unit 261, based on the authentication result of the appearance (face), the similarity between the appearance of the request target (face) and the appearance (face) already registered in the public cyber space is checked.

[0197] Furthermore, in the appearance similarity check unit 261, for example, when the score value indicating the similarity is equal to or greater than a predetermined threshold value, that is, when they are not similar (when they are separated by a certain amount or more), it is determined that the appearance of the request target can be registered, and the determination result is output to the appearance registration unit 271.

[0198] The appearance registration unit 271 stores the data related to the appearance of the request target in the registered appearance database 252 based on the determination result from the appearance similarity check unit 261.

[0199] In addition, the appearance similarity check unit 261 outputs a message including whether the appearance of the request target can be registered to the communication unit 204, and transmits it to the information terminal 10 via the network 30. As a result, in the information terminal 10, the paint tool 161 presents to the user whether the appearance of the request target can be registered.

[0200] Here, when the appearance similarity check unit 261 cannot register the appearance of the requested target, it transmits a message to that effect to the information terminal 10 via the network 30. Further, instead of (or together with) the message indicating that the appearance of the requested target cannot be registered, a registrable appearance may be proposed from the server 20 side to the information terminal 10 side.

[0201] That is, as shown in FIG. 21, in the appearance similarity check unit 261, when the appearance (face) of the requested target and the already registered appearance (face) are similar (not separated by a certain amount or more), for example, the following processing is performed to propose a registrable appearance.

[0202] That is, in the appearance similarity check unit 261, by adjusting the parameters of the appearance (for example, each part such as eyes, ears, face shape, etc.) of the requested target, a proposed target appearance (face) that is separated from the already registered appearance (face) by a certain amount or more is generated. Then, data regarding the proposed target appearance (face) thus generated is notified to the information terminal 10 and presented to the user.

[0203] Specifically, in FIG. 22, when the appearance of the requested target is placed at the origin in a three-dimensional coordinate system, the horizontal axis (X direction) in the figure is taken as the axis corresponding to the parameter regarding "eyes", and the vertical axis (Y direction) in the figure is taken as the axis corresponding to the parameter regarding "mouth", and the appearance (candidate appearance) when those parameters are adjusted is shown.

[0204] That is, in FIG. 22, two appearances with the eye parameters of the appearance (face) of the requested target adjusted are drawn on the horizontal axis as candidate appearances (faces). Also, in FIG. 22, two appearances with the mouth parameters of the appearance (face) of the requested target adjusted are drawn on the vertical axis as candidate appearances (faces). However, the four candidate appearances (faces) shown here are appearances (faces) that are separated from the already registered appearance (face) by a certain amount or more.

[0205] The appearance similarity check unit 261 can select one or more candidate appearances (faces) from among the four candidate appearances (faces) as the appearance to be proposed and notify the information terminal 10. In this way, even if there is an appearance similar to the appearance of the request target, it is possible to propose an appearance (a registrable appearance) in which the parameters of each part of the appearance of the request target are changed.

[0206] In this way, since the appearance can be registered, using the registered appearance, for example, as an agent (avatar) of a specific user, it is possible to provide an agent (avatar) that is at least visually separated from the agents (avatars) of other users already registered in the public cyber space.

[0207] Note that the agent (avatar) provided in this way is also assumed to be used by a specific user in applications such as chat and social media, and can also be used as an agent as a clone of oneself used in applications such as chat.

[0208] (Overall image of the process) Next, with reference to the flowcharts of FIGS. 23 to 25, the overall image of the agent providing process in the sixth embodiment will be described. Note that the agent providing process in FIG. 23 corresponds to the process of step S12 in FIG. 6.

[0209] In step S171, the control unit 200 determines whether to newly provide an agent as an avatar of a specific user in the public cyber space.

[0210] If it is determined to be affirmative in the determination process of step S171, the process proceeds to step S172. In step S172, the control unit 200 executes the avatar agent providing process.

[0211] Here, referring to the flowchart of FIG. 24, a first example of the details of the avatar agent providing process corresponding to the process of step S172 in FIG. 23 will be described.

[0212] In step S191, the control unit 200 provides an agent that is sufficiently separated from other users' agents registered in the public server space in terms of appearance or voice.

[0213] Specifically, for example, when the appearance of the agent is generated on the information terminal 10, the server 20 checks the similarity between the generated appearance and the appearances already registered in the public server space. If those appearances are not similar (if they are sufficiently separated), the data regarding the generated appearance is registered (the example of FIG. 20).

[0214] By using the appearance registered in this way, it is possible to provide an agent (avatar) that is sufficiently separated from other users' agents (avatars) registered in the public server space, at least in terms of appearance.

[0215] Next, referring to the flowchart of FIG. 25, a second example of the details of the avatar agent providing process corresponding to the process of step S172 in FIG. 23 will be described.

[0216] In step S211, the control unit 200 presents candidates for agents that are sufficiently separated from other users' avatars registered in the public space in terms of appearance or voice to the user.

[0217] Specifically, when the appearance of the agent is generated on the information terminal 10, the server 20 checks the similarity between the generated appearance and the appearances already registered in the public server space. If those appearances are similar (if they are not sufficiently separated), appearances corresponding to one or more candidate appearances (registrable appearances) are proposed (the examples of FIGS. 21 and 22).

[0218] By using the appearance thus proposed, it is possible to present one or more candidates for agents (avatars) that are at least somewhat distinct from the agents (avatars) of other users already registered in the public cyber space, at least in terms of appearance.

[0219] In this way, in the agent providing system 1, when newly providing an agent (avatar) of a specific user to the public cyber space, it is possible to provide an agent that is somewhat distinct from the agents (avatars) of other users already registered in the public cyber space in terms of appearance or voice.

[0220] <7. Seventh Embodiment>

[0221] In the above description, the appearance of the agent has been mainly described. Here, a method for generating the voice of the agent will be described.

[0222] For example, the user can generate the voice of the agent by operating the voice creation tool 152 (FIG. 20) executed on the information terminal 10. The information terminal 10 can register the generated voice by transmitting it to the server 20 via the network 30.

[0223] FIG. 26 shows an example of a method for generating the voice of an agent.

[0224] When voice data obtained by converting text into voice by TTS (Text to Speech) is input as original data, pitch adjustment processing, formant adjustment processing, and other effect processing are sequentially performed on the input voice data to generate the voice of the agent.

[0225] First, in the pitch adjustment processing, processing for adjusting the pitch (pitch) of the voice data is performed to process the voice (S311).

[0226] Next, in the formant adjustment process, a process of adjusting the frequency components that characterize the agent's voice is performed on the voice data, and the voice is processed (S312).

[0227] The formant is a plurality of temporally moving peaks obtained by observing the spectrum of the voice, and is called the first formant frequency, the second formant frequency, the third formant frequency, ··· in ascending order of frequency. Each formant frequency is important for identifying vowels.

[0228] In this formant adjustment process, more complex formant adjustments can be made by performing processing for each formant frequency, etc., to create variations in the voice. That is, here, instead of applying the same adjustment to all vowels, a process different from performing pitch adjustment or formant adjustment on the entire voice, such as emphasizing in the "a" row, is performed.

[0229] Next, in the other effect process, effects and other processes are performed on the voice data, and the voice is processed (S313).

[0230] In this effect process, for example, processes such as adding overtones, inserting noise, or dropping bits are performed. Also, here, processes for processing voices other than the effect process may be performed.

[0231] In this way, by sequentially performing pitch adjustment processing, formant adjustment processing, and other effect processing on the input voice data, it is possible to create a voice that the user can be attached to, rather than a realistic voice emitted by a person, as the agent's voice.

[0232] <8. Modification Example>

[0233] (Other Configuration Examples) In the above description, the case where the agent providing system 1 is composed of the information terminal 10 and the server 20 has been shown. However, for example, other configurations may be used, such as adding other devices or external servers.

[0234] Specifically, the server 20 as one information processing device may be divided into a server that performs processing for providing an agent and a database server that stores data related to the agent, etc., and configured as a plurality of information processing devices. Similarly, the information terminal 10 may be configured not only as one information processing device but also as a plurality of information processing devices.

[0235] Also, in the agent providing system 1, it is arbitrary which device includes the components (control units) constituting each of the information terminal 10 and the server 20. For example, the information terminal 10 may execute a part of the information processing performed by the above-described server 20. Alternatively, using the technology of edge computing, a part of the information processing performed by the above-described server 20 may be executed by an edge server connected to a network (peripheral part of the network) close to the information terminal 10.

[0236] In the present disclosure, a system means a collection of a plurality of components (devices, modules (parts), etc.), and it does not matter whether all the components are in the same housing. Therefore, a plurality of devices housed in separate housings and connected via a network, and one device in which a plurality of modules are housed in one housing are both systems.

[0237] Also, the communication form of each component is arbitrary. In other words, each component may be connected via a network 30 such as the Internet, a communication network such as a mobile phone network, or a local network (LAN (Local Area Network) or WAN (Wide Area Network)). Furthermore, each component may be connected by wire or wirelessly.

[0238] <9. Configuration of Computer>

[0239] The above-described series of processes (for example, the agent providing process in FIG. 6) can be executed by hardware or by software. When the series of processes is executed by software, the programs constituting the software are installed in the computers of the respective devices.

[0240] FIG. 27 is a block diagram showing an example of the hardware configuration of a computer that executes the above-described series of processes by a program.

[0241] In a computer, a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, and a RAM (Random Access Memory) 1003 are interconnected by a bus 1004. An input / output interface 1005 is further connected to the bus 1004. An input unit 1006, an output unit 1007, a storage unit 1008, a communication unit 1009, and a drive 1010 are connected to the input / output interface 1005.

[0242] The input unit 1006 includes a microphone, a keyboard, a mouse, etc. The output unit 1007 includes a speaker, a display, etc. The storage unit 1008 includes a hard disk, a non-volatile memory, etc. The communication unit 1009 includes a network interface, etc. The drive 1010 drives a removable recording medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

[0243] In the computer configured as described above, the CPU 1001 loads and executes the programs recorded in the ROM 1002 and the storage unit 1008 via the input / output interface 1005 and the bus 1004 into the RAM 1003, whereby the above-described series of processes are performed.

[0244] The program executed by the computer (CPU 1001) can be provided by being recorded on a removable recording medium 1011 such as a package medium or the like. Further, the program can be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

[0245] In the computer, the program can be installed in the storage unit 1008 via the input / output interface 1005 by mounting the removable recording medium 1011 on the drive 1010. Further, the program can be received by the communication unit 1009 via a wired or wireless transmission medium and installed in the storage unit 1008. In addition, the program can be installed in advance in the ROM 1002 or the storage unit 1008.

[0246] Here, in this specification, the processing performed by the computer according to the program does not necessarily need to be performed in time series in the order described as a flowchart. That is, the processing performed by the computer according to the program includes processing that is executed in parallel or individually (for example, parallel processing or object-based processing). Further, the program may be processed by one computer (processor) or may be distributedly processed by a plurality of computers.

[0247] Note that the embodiments of the present technology are not limited to the above-described embodiments, and various modifications are possible without departing from the gist of the present technology.

[0248] Further, the present technology can have the following configuration.

[0249] (1) When newly providing an agent to a cyber space in which a plurality of agents can be registered, a control unit that provides an agent that is separated from the agents already registered in the cyber space by a certain degree or more in terms of appearance or voice is provided. Agent providing system. (2) The control unit determines that a new agent is sufficiently different from the agents already registered in the cyber space in terms of appearance or voice, and provides the agent thus determined. The agent providing system according to (1) above. (3) The control unit newly generates an agent that is sufficiently different from the agents already registered in the cyber space in terms of appearance or voice, and provides the generated agent. The agent providing system according to (1) or (2) above. (4) The control unit when newly providing an agent for a specific user to a private cyber space accessible by the specific user, provides an agent that is already registered in the private cyber space and is sufficiently different from the appearance or voice of the agent used by the specific user. The agent providing system according to (1) above. (5) An agent for a specific purpose has a first appearance or a first voice, The control unit when providing the agent for the specific purpose to a first user, if the first appearance or the first voice is not sufficiently different from either the appearance or the voice of the agents already held by the first user, provides the agent for the specific purpose having a second appearance or a second voice different from the first appearance or the first voice; when providing the agent for the specific purpose to a second user, if the first appearance or the first voice is sufficiently different from the appearance or the voice of all the agents already held by the second user, provides the agent for the specific purpose with the first appearance or the first voice. The agent providing system according to (4) above. (6) When providing an agent for a group consisting of a first user and a second user, the control unit provides an agent having an appearance or voice different from all the agents already possessed by the first user and the second user. The agent providing system according to (4) above. (7) The control unit Checks whether the user can identify the agent already used by the user based on the appearance or voice of the agent newly provided to the user, And provides a new agent with an identifiable appearance or voice to the user according to the check result. The agent providing system according to any one of (4) to (6) above. (8) When the user answers that it is impossible to identify the agent already used by the user based on the appearance or voice of the agent newly provided to the user, the control unit generates an agent having a new appearance or voice different from the unidentifiable appearance or voice. The agent providing system according to (7) above. (9) The control unit Learns the characteristics when the user identifies the appearance or voice of the agent according to the answer of the user, And generates an agent having a new appearance or voice according to the characteristics. The agent providing system according to (8) above. (10) The control unit When newly providing an agent as an avatar of a specific user to a public server space accessible by multiple users, Provides an agent whose appearance or voice is separated by a certain degree or more from the agents of other users already registered in the public server space as avatars. The agent providing system according to (1) above. (11) The control unit When newly providing an agent as an avatar of a specific user in a public server space accessible by multiple users, present candidates for agents that are separated by a certain degree or more from agents that are already registered as avatars of other users in the public server space, in terms of appearance or voice, to the user. The agent providing system according to (10) above. (12) When the agent providing system provides a new agent in a server space where multiple agents can be registered, provide an agent that is separated by a certain degree or more from the agents already registered in that server space, in terms of appearance or voice. Agent providing method. (13) A computer When providing a new agent in a server space where multiple agents can be registered, provide an agent that is separated by a certain degree or more from the agents already registered in that server space, in terms of appearance or voice. A recording medium on which a program for functioning as a control unit is recorded.

Explanation of Signs

[0250] 1 Agent providing system, 10, 10-1 to 10-N Information terminals, 20 Server, 30 Network, 100 Control unit, 101 Input unit, 102 Output unit, 103 Memory unit, 104 Communication unit, 111 Agent processing unit, 112 Presentation control unit, 113 Communication control unit, 121 Mouse, 122 Keyboard, 131 Display, 132 Speaker, 151 Appearance creation tool, 152 Voice creation tool, 161 Painting tool, 162 Drawing software, 163 Object, 200 Control unit, 201 Input unit, 202 Output unit, 203 Memory unit, 204 Communication unit, 211 Agent providing unit, 212 Learning unit, 213 Communication control unit, 251 Appearance registration program, 252 Registered appearance database, 261 Appearance similarity check unit, 262 Face authentication unit, 263 Parameter analysis unit, 271 Appearance registration unit, 1001 CPU, 1011 Removable recording medium

Claims

1. When a new agent is provided to a cyber space where multiple agents can be registered, based on a value indicating the similarity between the appearance or voice assigned to an agent already registered in the cyber space and the appearance or voice to be assigned to the new agent, it is determined whether the new agent is identical or similar to the already registered agent in terms of appearance or voice. The new agent determined to be neither identical nor similar is provided to the cyber space. It includes a control unit. The control unit When the appearance and voice of a new agent cannot be separated, based on a value indicating the similarity between an agent already registered in the cyber space and the new agent whose appearance and voice cannot be separated, it is determined whether the new agent is identical or similar to the already registered agent. When it is determined that the new agent is identical or similar to the already registered agent, the appearance and voice assigned to the already registered agent are adjusted, and the new agent is provided to the cyber space. An agent providing system.

2. When a new agent for a specific user is provided to a private cyber space accessible by the specific user, Based on a value indicating the similarity between the appearance or voice assigned to an agent already registered in the private cyber space and used by the specific user and the appearance or voice to be assigned to the new agent, it is determined whether the new agent is identical or similar to the already registered agent in terms of appearance or voice. The new agent determined to be neither identical nor similar is provided to the private cyber space. It includes a control unit. The control unit Confirms whether the user can identify the agent already used by the user based on the appearance or voice of the agent newly provided to the user. According to the confirmation result, a new agent with an identifiable appearance or voice is provided. An agent providing system.

3. When the user answers that they cannot identify an agent based on the appearance or voice of a newly provided agent, the control unit generates an agent with a new appearance or voice that is different from the appearance or voice that the user could not identify, for an agent that the user is already using. The agent providing system according to claim 2.

4. The control unit uses the user's response as to whether the appearance or voice of a newly provided agent is identifiable as teacher data, and performs learning to determine whether the user can identify the appearance or voice of the newly provided agent. Using the result of the learning, identify an agent with a new appearance or voice that the user can identify. The agent providing system according to claim 3.

5. When the agent providing system provides a new agent to a cyber space where a plurality of agents can be registered, based on a value indicating the similarity between the appearance or voice assigned to an agent already registered in the cyber space and the appearance or voice assigned to the new agent, determine whether the new agent is the same as or similar to the already registered agent in terms of appearance or voice; provide the newly determined non-identical and non-similar agent to the cyber space; when the appearance and voice of the new agent cannot be separated, based on a value indicating the similarity between the already registered agent in the cyber space and the new agent whose appearance and voice cannot be separated, determine whether the new agent is the same as or similar to the already registered agent; when it is determined that the new agent is the same as or similar to the already registered agent, adjust the appearance and voice assigned to the already registered agent, and provide the new agent to the cyber space An agent providing method including the above.

6. A computer When a new agent is provided to a cyber space in which a plurality of agents can be registered, based on a value indicating the degree of similarity between the appearance or voice assigned to an agent already registered in the cyber space and the appearance or voice to be assigned to the new agent, the new agent determines whether it is identical or similar to the already registered agent in terms of appearance or voice, and provides the new agent determined not to be identical and not to be similar to the already registered agent to the cyber space. A control unit, when the appearance and voice of the new agent cannot be separated, based on a value indicating the degree of similarity between the new agent whose appearance and voice cannot be separated and an agent already registered in the cyber space, determines whether the new agent is identical or similar to the already registered agent, and when the new agent is determined to be identical or similar to the already registered agent, adjusts the appearance and voice assigned to the already registered agent and provides the new agent to the cyber space. A recording medium recording a program for functioning as the control unit.

Images