Agent providing system, agent providing method and recording medium

Abstract

The present technology relates to an agent providing system, an agent providing method, and a recording medium that enable a more preferable agent to be provided. An agent providing system is provided, the agent providing system including a control unit that, when a new agent is provided in a network space capable of registering a plurality of agents, provides an agent that is separated from an agent already registered in the network space by a fixed amount or more in terms of appearance or voice. The present technology can be applied to, for example, an agent providing system for providing an agent registered in a network space.

Description

Technical Field

[0001] The present technology relates to an agent providing system, an agent providing method, and a recording medium, and particularly to an agent providing system, an agent providing method, and a recording medium capable of providing a more appropriate agent. Background Art

[0002] In recent years, with the development of information and communication technology, it has become common to provide services in cyberspace. Among such services, there is a service in which an agent used in cyberspace provides various services by registering the agent.

[0003] For example, as technologies related to agents, technologies disclosed in Patent Documents 1 to 3 are known.

[0004] Citation List

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 2005-149481

[0007] Patent Document 2: Japanese Patent Application Laid-Open No. 2000-20888

[0008] Patent Document 3: Japanese Patent Application Laid-Open No. 2002-342049 Summary of the invention

[0009] Problems to be solved by the present invention

[0010] Incidentally, in the case where multiple agents are allowed to be registered in a cyberspace, if there are agents that are similar in appearance and voice, the agents may no longer be recognized. Therefore, in the case where multiple agents are allowed to be registered in a cyberspace, it is necessary to provide a more appropriate agent.

[0011] The present technology is made in view of such circumstances and aims to provide a more appropriate agent.

[0012] Solution to the problem

[0013] An agent providing system according to one aspect of the present technology is an agent providing system including a control unit which, when newly providing an agent to a network space allowing registration of multiple agents, provides an agent that is separated from agents already registered in the network space by a fixed amount or more in appearance or voice.

[0014] An agent providing method according to one aspect of the present technology is an agent providing method including providing, when a new agent is provided to a network space that allows registration of a plurality of agents, an agent that is separated from agents already registered in the network space by a fixed amount or more in appearance or voice by an agent providing system.

[0015] According to one aspect of the present technology, a recording medium is a recording medium having recorded thereon a program for causing a computer to function as a control unit, which, when a new agent is provided to a network space that allows registration of multiple agents, provides an agent that is separated from agents already registered in the network space by a fixed amount or more in appearance or voice.

[0016] In an agent providing system, an agent providing method, and a recording medium according to one aspect of the present technology, when an agent is newly provided to a network space that allows registration of multiple agents, an agent that is separated from agents already registered in the network space by a fixed amount or more in appearance or voice is provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a representative diagram showing the outline of the present technology.

[0018] Figure 2 is a diagram showing an example of a configuration of an agent providing system to which the present technology is applied.

[0019] Figure 3 It is shown Figure 2 FIG. 4 is a diagram showing an example of a configuration of an information terminal in FIG.

[0020] Figure 4 It is shown Figure 2 Figure 4 is an example of a configuration of a server.

[0021] Figure 5 is a diagram showing an example of a method of generating a unique image.

[0022] Figure 6 This is a flowchart illustrating the flow of the proxy provision process.

[0023] Figure 7 : is a flowchart illustrating the flow of a first example of details of the proxy provision process.

[0024] Figure 8 is a flowchart illustrating the flow of a second example of details of the proxy provision process.

[0025] Fig. 9 is a diagram showing a first example of the appearance and voice of a selection agent.

[0026] Fig.10 : is a flowchart illustrating the flow of a third example of the details of the proxy provision processing.

[0027] Fig.11 is a diagram showing a second example of the appearance and voice of the selection agent.

[0028] Fig.12 is a diagram showing a third example of the appearance and voice of a selection agent.

[0029] Fig.13 : is a flowchart illustrating the flow of a first example of details of the designated proxy providing process.

[0030] Fig.14 is a diagram showing a fourth example of the appearance and voice of the selection agent.

[0031] Fig.15 : is a flowchart illustrating the flow of a second example of details of the designated agent providing process.

[0032] Fig.16 is a diagram showing a first example in the case where recognition confirmation of the appearance of a new agent is performed in an interactive manner.

[0033] Fig.17 is a diagram showing a second example in the case where recognition confirmation of the appearance of a new agent is performed in an interactive manner.

[0034] Fig.18 : is a flowchart illustrating the flow of a third example of the details of the designated agent providing process.

[0035] Fig.19 It is a flowchart explaining the flow of the learning process.

[0036] Fig. 20 is a diagram showing a first example of a specific configuration of the agent providing system.

[0037] Fig.21 is a diagram showing a second example of a specific configuration of the agent providing system.

[0038] Fig. 22 is a diagram showing an example of a proposed facial image.

[0039] Fig.23 : is a flowchart illustrating the flow of a fourth example of the details of the proxy provision processing.

[0040] Fig.24 : is a flowchart illustrating the flow of a first example of details of an avatar agent providing process.

[0041] Fig.25 is a flowchart illustrating the flow of a second example of details of the avatar agent providing process.

[0042] Fig.26 is a diagram illustrating an example of a method of generating a voice of an agent.

[0043] Fig. 27 is a diagram showing an example of the configuration of a computer. DETAILED DESCRIPTION

[0044] Hereinafter, embodiments of the present technology will be described with reference to the drawings. Note that the description is given in the following order.

[0045] 1. First Implementation: Basic Configuration

[0046] 2. Second Embodiment: Method of Registration in Private Network Space

[0047] 3. Third embodiment: Method for changing the appearance or voice of the same agent depending on the user

[0048] 4. Fourth embodiment: Method for providing group agent

[0049] 5. Fifth embodiment: Method for generating a new appearance or voice when recognition is unavailable

[0050] 6. Sixth Implementation Method: Registration Method in Public Network Space

[0051] 7. Seventh embodiment: Method for generating agent voice

[0052] 8. Modifications

[0053] 9. Computer configuration

[0054] (Representative picture)

[0055] Figure 1 This is a representative diagram showing the outline of the present technology.

[0056] The agent providing system to which the present technology is applied aims to provide an agent separated by a fixed amount or more from agents already registered in the network space in appearance or voice when an agent is newly provided to a network space that allows registration of a plurality of agents.

[0057] exist Figure 1 In , a user submits a character agent as a new agent to be used in the cyberspace. However, in the cyberspace, agents that look or sound similar to the newly submitted agent (not separated by a fixed amount or more) are already registered.

[0058] Therefore, a user's newly submitted proxy will be rejected by being verified as "rejected" and will not be provided to the network space.

[0059] On the other hand, although not shown, in the case of submitting a new agent that is not similar in appearance or voice to an agent already registered in the cyberspace (separated by a fixed amount or more), the submitted new agent is accepted by being verified as "Accepted" and will be provided to the cyberspace.

[0060] In this way, the agent providing system to which the present technology is applied has a function as an authentication agency that authenticates new agents to be provided in the cyberspace, and can provide agents whose uniqueness of appearance or voice is ensured to the cyberspace.

[0061] <1. First Embodiment>

[0062] (System configuration example)

[0063] Figure 2 An example of the configuration of an agent providing system to which the present technology is applied is shown.

[0064] The agent providing system 1 is constituted by information terminals 10 - 1 to 10 -N (N: an integer equal to or greater than 1) and a server 20 .

[0065] In the agent providing system 1, information terminals 10-1 to 10-N and a 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.

[0066] The information terminal 10 - 1 is an electronic instrument having a predetermined user interface (UI), such as a personal computer, a smartphone, a mobile phone, a tablet terminal, a game machine, or a wearable instrument.

[0067] The information terminal 10 - 1 performs various actions according to the user's operation on a predetermined user interface.

[0068] For example, in response to a user operation, information terminal 10-1 transmits a request related to proxy to server 20 via network 30. Information terminal 10-1 receives a response related to proxy transmitted from server 20 via network 30. Information terminal 10-1 performs various processes related to proxy based on the received response.

[0069] Each of the information terminals 10-2 to 10-N is configured as an electronic instrument such as a personal computer similar to the information terminal 10-1. Each of the information terminals 10-2 to 10-N can exchange agent-related requests and responses with the server 20 via the network 30 and perform various processes according to the received responses.

[0070] Note that in the following description, in the case where there is no particular need to distinguish between the information terminals 10 - 1 to 10 -N, the information terminals 10 - 1 to 10 -N are simply referred to as information terminals 10 .

[0071] The server 20 is composed of one or more servers. The server 20 executes various processes related to the agent.

[0072] For example, the server 20 receives a request related to an agent sent from the information terminal 10 via the network 30. The server 20 performs various processes related to the agent based on the received request. The server 20 sends a response related to the agent obtained in various processes to the information terminal 10 via the network 30.

[0073] (Configuration example of information terminal)

[0074] Figure 3 Shows Figure 2 An example of the configuration of the information terminal 10 in FIG.

[0075] exist Figure 3 In the embodiment, the information terminal 10 is composed of a control unit 100, an input unit 101, an output unit 102, a storage unit 103 and a communication unit 104.

[0076] The control unit 100 is constituted by a processor such as a central processing unit (CPU), etc. The control unit 100 is a main control device (processing device) that controls the action of each unit and performs various arithmetic processing.

[0077] 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 according to a user operation to the control unit 100. The control unit 100 controls the action of each unit based on the operation data from the input unit 101.

[0078] The output unit 102 is an output device such as a display 131 or a speaker 132. The output unit 102 outputs information according to various kinds of data under the control of the control unit 100.

[0079] The display 131 displays a video based on the video data from the control unit 100. The speaker 132 outputs an audio (sound) based on the audio data from the control unit 100.

[0080] Note that the display 131 may be configured as a touch panel together with an input unit that supplies operation data to the control unit 100 according to a contact position (position of a predetermined point) obtained when a user's finger contacts (touches) the surface of the screen of the display 131 .

[0081] The storage unit 103 is an auxiliary storage device including a semiconductor memory such as a nonvolatile memory or a hard disk drive (HDD). The storage unit 103 stores various kinds of data under the control of the control unit 100. Note that the storage unit 103 may be configured as an internal storage device, or may be an external storage device such as a memory card.

[0082] The communication unit 104 is a communication device including a communication module compatible with 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 under the control of the control unit 100 .

[0083] Furthermore, the control unit 100 includes an agent processing unit 111 , a presentation control unit 112 , and a communication control unit 113 .

[0084] The agent processing unit 111 performs processing related to an agent provided to a cyberspace (processing of registering an agent, processing of operating a registered agent, etc.) according to an operation from a user. Note that the details of the processing related to an agent will be described later.

[0085] 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.

[0086] The communication control unit 113 controls the communication unit 104 to communicate with other devices via the network 30 .

[0087] (Server configuration example)

[0088] Figure 4 Shows Figure 2 An example of the configuration of the server 20 in FIG.

[0089] exist Figure 4 In the embodiment, 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 .

[0090] The control unit 200 is constituted by a processor such as a CPU, etc. The control unit 200 is a main control device (processing device) that controls the action of each unit and performs various arithmetic processing.

[0091] The input unit 201 is an input device such as a mouse, a keyboard, or a physical button. The input unit 201 supplies input data to the control unit 200 according to a user's operation, etc. The control unit 200 controls the action of each unit based on the input data from the input unit 201 .

[0092] The output unit 202 is an output device such as a display or a speaker. The output unit 202 outputs information according to various kinds of data such as video and audio under the control of the control unit 200.

[0093] The storage unit 203 is a large-capacity auxiliary storage device including a semiconductor memory such as a nonvolatile memory and an HDD. The storage unit 203 stores various kinds of data under the control of the control unit 200.

[0094] The communication unit 204 is a communication device including a communication module compatible with wireless communication or wired communication conforming to a predetermined standard. The communication unit 204 communicates with other devices such as the information terminal 10 via the network 30 under the control of the control unit 200 .

[0095] Furthermore, the control unit 200 includes an agent providing unit 211 , a learning unit 212 , and a communication control unit 213 .

[0096] The agent providing unit 211 performs an agent providing process for providing an agent to a network space. Note that the details of the agent providing process will be described later.

[0097] 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 (for example, verifies or predicts) the input information based on the input information and the result of the machine learning.

[0098] The communication control unit 213 controls the communication unit 204 to communicate with other devices via the network 30 .

[0099] The agent providing system 1 is configured as described above. Hereinafter, details of a process performed by the agent providing system 1 will be described.

[0100] (Uniqueness of the agent's appearance or voice)

[0101] Incidentally, in cyberspace, the uniqueness of the appearance (image) of an agent held by a specific user is used as an identifier when viewed from another user. Therefore, this uniqueness of appearance should play an important role in information input and output in cyberspace.

[0102] That is, the appearance of the agent ensures that the information is allowed to be delivered to the user of the agent. In addition, the appearance of the agent is also the basis for the reliability of the information provided by the user of the agent.

[0103] In this way, the uniqueness of the agent's appearance is an important clue to the authenticity of the information and the handover of the information when the agent is provided. Therefore, the uniqueness of the appearance of agents in cyberspace is an important issue.

[0104] In recent years, agents in cyberspace have begun to take on the appearance of characters, etc. Also, in the future, agents or avatars that are users' own virtual selves will likely grow in number to exceed the real world population.

[0105] In this case, unlike humans (users) in the real space, the uniqueness of the agent's appearance becomes more important, for example, including how the image of the agent involving expression elements is variously drawn in the cyberspace. In addition, this similarly applies to the uniqueness of the agent's voice.

[0106] Therefore, the agent providing system 1 is configured to, when newly providing an agent to a network space that allows registration of a plurality of agents, provide an agent that is separated in appearance or voice by a fixed amount or more from agents already registered in the network space.

[0107] Through this configuration, the uniqueness of the appearance or voice of each agent is ensured in the cyberspace. Therefore, a more suitable agent can be provided.

[0108] Specifically, the agent of a specific user can be clearly distinguished from the agents of other users. In addition, for example, even in the case where a specific user switches a plurality of agents to be used according to the purpose, it is possible to prevent errors from occurring, such as confirming tomorrow's schedule with an agent dedicated to music recommendation, because the agents can be clearly distinguished due to the uniqueness of the agent's appearance.

[0109] Here, as a method of generating a unique appearance (image), for example, there are Figure 5 The method shown.

[0110] That is, Figure 5 As shown, if attention is focused on the eyes of the face as a proxy, parameters such as type, size, and relative position in the face can be set. However, if the user freely sets the parameters, there is a possibility that an undesirable image such as the eyes moving out of the face may be generated, and therefore the parameters may be limited to a maximum value, a minimum value, etc.

[0111] More specifically, examples of the eye types include round eyes, round almond eyes, almond eyes, thin almond eyes, droopy eyes, half-open droopy eyes, half-open eyes, Asian eyes, and child / Asian round eyes.

[0112] Such an eye type is prepared in advance as a basic pattern, and the variation of the eye part can be increased by multiplying the eyes of the basic pattern by a size coefficient.

[0113] Similarly, for parts other than eyes, such as mouth and nose, parameters such as type, size, and relative position in the face can be set ( Figure 5 ).

[0114] For example, when generating the face of an agent, the parameters of each part may be randomly selected and set so that a face similar to faces of other agents (relatively similar faces) is not generated.

[0115] At this time, if the same (or similar) combination of parameters as the combination of parameters of the face generated in the past is selected, the parameters are selected again. Then, once a state is reached where there is no face with the same (or similar) combination of parameters, the generation of the agent's face is simply completed.

[0116] Note that the agent can be represented by a two-dimensional (2D) image or a three-dimensional (3D) image. Fig.26 and other figures describe the agent's speech.

[0117] (Overall view of the process)

[0118] Next, we will refer to Figures 6 to 8 The flowchart in describes the overall diagram of the proxy providing process in the first embodiment.

[0119] The agent provides processing through the action of the information terminal 10 (control unit 100 of the information terminal 10) or the server 20 (control unit 200 of the server 20) or the action of the information terminal 10 (control unit 100 of the information terminal 10) and the server 20 (control unit 200 of the server 20) in cooperation with each other.

[0120] That is, the agent providing process is performed by at least one of the control units 100 and 200. In the following description, for simplicity of description, the case where the agent providing process is performed by the control unit 200 will be taken as an example, but the whole or part of the process may be performed by the control unit 100.

[0121] In step S11, the control unit 200 determines whether an agent is newly provided to the network space.

[0122] In the case of affirmative determination ("Yes") in the determination processing of step S11, the process proceeds to step S12. In step S12, the control unit 200 performs an agent providing process.

[0123] In this agent providing process, an agent that is separated in appearance or voice by a fixed amount or more from an agent already registered in the cyberspace (an agent whose uniqueness in appearance or voice is ensured) is provided.

[0124] Note that we will refer to Figure 7 , Figure 8 , Fig.10 and Fig.23 The flowchart in describes the details of the agent provisioning process.

[0125] If the processing in step S12 ends or the determination in step S11 is negative ("No"), Figure 6 The proxy provisioning process ends.

[0126] Here, we will refer to Figure 7 The flowchart in the description is similar to Figure 6 The process in step S12 corresponds to a first example of details of the agent providing process.

[0127] In step S31, the control unit 200 compares the new agent with agents already registered in the network space.

[0128] In step S32, the control unit 200 determines whether the new agent is separated from the agents already registered in the network space by a fixed amount or more in appearance or voice based on the comparison result in the process in step S31.

[0129] As an algorithm for performing the comparison and determination processing, various arithmetic methods may be used, for example, Euclidean distance and threshold determination may be used.

[0130] That is, in the case of appearance (image), each parameter related to face shape, facial parts, body shape, skin color, gender, clothing, hairstyle, etc., for example, when a facial part is taken, each of its size, shape, distance from other parts, brightness and color is used as one of its parameters (one element) to construct a multidimensional vector, and the characteristics of the appearance are represented by the multidimensional vector.

[0131] In addition, in the case of speech (audio), a multidimensional vector is created using not only the frequency characteristics but also each of the prosody (tone of speech), intonation, rhythm, characteristics of the way of speaking, etc. as a parameter (an element), and the characteristics of the speech are represented by the multidimensional vector.

[0132] Then, the Euclidean distance between the two multidimensional vectors is taken, and a comparison and determination process is performed depending on whether the distance is equal to or greater than a predetermined threshold value.

[0133] Here, for example, when the Euclidean distance is equal to or greater than a threshold value, it is determined that there is a fixed amount or more separation in appearance or voice. In this case, the appearance or voice is not similar, and it can also be said to be non-similar. In other words, "separated by a fixed amount or more in appearance or voice" means "non-similar in appearance or voice".

[0134] On the other hand, for example, when the Euclidean distance is less than the threshold value, it is determined that there is no fixed amount or more distance in appearance or voice. In this case, it can be said that there is similarity in appearance or voice. In other words, "there is no fixed amount or more distance in appearance or voice" means "similar in appearance or voice".

[0135] Note that the case of "not being separated by a fixed amount or more in appearance or voice" includes the case of having the same appearance or voice. In addition, in the comparison and determination processing to be described later, similarly to step S32, the Euclidean distance and threshold determination may be used. Here, the case of using the Euclidean distance and threshold determination as the comparison and determination processing has been exemplified, but other known methods may also be used.

[0136] In the case where it is determined in step S32 that the appearance or voice is separated by a fixed amount or more, the process proceeds to step S33. In step S33, the control unit 200 provides a new agent to the network space.

[0137] On the other hand, in the case where it is determined in step S32 that there is no separation by a fixed amount or more in appearance or voice, the processing in step S33 is skipped. In other words, in this case, a new agent will not be provided to the network space.

[0138] If the processing of step S33 ends or the determination in step S32 is negative ("No"), the processing returns to Figure 6 The process of step S12 and subsequent steps is performed.

[0139] As described above, since an agent separated by a fixed amount or more from agents already registered in the cyberspace in appearance or voice is provided as a new agent, the agent providing system 1 can provide an agent whose uniqueness in appearance or voice is ensured.

[0140] Next, we will refer to Figure 8 The flowchart in the description is similar to Figure 6 The process in step S12 corresponds to a second example of details of the agent providing process.

[0141] In step S51, the control unit 200 generates a new agent that is separated from the agents already registered in the network space by a fixed amount or more in appearance or voice.

[0142] In step S52, the control unit 200 provides the generated new agent to the network space.

[0143] When the processing in step S52 ends, the processing returns to Figure 6 and executes the processing in step S12 and subsequent steps.

[0144] As described above, since an agent separated from an agent already registered in the cyberspace by a fixed amount or more in appearance or voice is generated as a new agent, the agent providing system 1 can provide an agent whose uniqueness in appearance or voice is ensured.

[0145] <2. Second Embodiment>

[0146] Incidentally, as a network space in which an agent is registered, there is a private network space accessible by a designated user, a public network space accessible by, for example, an agent application and a plurality of any users, such as a virtual reality (VR) space, etc. Here, a case where an agent separated by a fixed amount or more from the appearance or voice of an agent used by a designated user is provided in a private network space will be described.

[0147] (Example of selecting appearance and voice)

[0148] Fig. 9 is a diagram showing a first example of the appearance and voice of a selection agent.

[0149] exist Fig. 9 , the appearance and voice assigned to each agent are shown, but the agent (the main body of the agent) and the appearance and voice of the agent may be disconnected from each other.

[0150] Specifically, although image #1 and voice #1 are assigned to agent #1 (agent #1) by default according to the position of agent #1 in the order, since the appearance and voice of agent #1 can be disconnected, when agent #1 is provided, agent #1 can be assigned images and voices with other numbers as well as image #1 and voice #1.

[0151] Similarly, for agents #2 to #8, each agent is assigned its own image and voice according to its position in the sequence, but the agent (the main body of the agent) and the appearance and voice of the agent can be disconnected and can be assigned images and voices with other numbers.

[0152] At this time, it is assumed that agent #5 is newly provided while agents #1 and #3 are registered in the private network space as agents used by user A who is a designated user.

[0153] However, avatar #1 and voice #1 according to the default order are assigned to agent #1. Avatar #2 and voice #2 are assigned to agent #3 in order. Avatar #1 and voice #1 and avatar #2 and voice #2 are separated by a fixed amount or more.

[0154] Here, agent #5 to be newly provided for user A may be assigned image #3 and voice #3 that are spaced apart by a fixed amount or more from image #1 and voice #1 of agent #1 and image #2 and voice #2 of agent #3.

[0155] In this way, since the agent (the main body of the agent) and the appearance and voice of the agent can be disconnected, any combination of image and voice can be applied to the agent, and therefore it is not necessary to prepare images and voices according to the number of agents. This allows the image and voice (the number) to be reduced relative to (the number of) agents, and thus the cost when providing agents can be reduced.

[0156] Note that, for example, in the case where a user uses multiple agent applications, the private network space of each of the multiple agent applications can be regarded as a single private network space, and the appearance or voice of the agent used in the single private network space can be controlled to be separated by a fixed amount or more.

[0157] (Overall view of the process)

[0158] Next, we will refer to Fig.10 The flowchart in describes the overall diagram of the proxy provision processing in the second embodiment. Note that Fig.10 The proxy in provides processing corresponding to Figure 6 The processing in step S12 in .

[0159] In step S71, the control unit 200 determines whether an agent for a designated user is newly provided to the private network space.

[0160] In the case of affirmative determination in the determination processing of step S71, the process proceeds to step S72. In step S72, the control unit 200 executes designated agent providing processing.

[0161] In this designated agent providing process, an agent whose appearance or voice is separated by a fixed amount or more from an agent already registered in a private network space and used by a designated user (an agent whose uniqueness of appearance or voice is ensured) is provided.

[0162] Note that we will refer to Fig.13 , Fig.15 and Fig.18 The flowchart in describes the details of the specified agent providing processing.

[0163] If the processing in step S72 ends or the determination in step S71 is negative, the processing returns to step S73. Figure 6 The process of step S12 and subsequent steps is performed.

[0164] As described above, when an agent for a designated user is newly provided to a private network space, since an agent is provided whose appearance or voice is separated by a fixed amount or more from that of an agent already registered in the private network space and used by the designated user, the agent providing system 1 can provide an agent whose uniqueness in appearance or voice is ensured in the private network space.

[0165] In the present embodiment, it is assumed that the appearance and voice of the agent can be disconnected. However, in the case where a character that has been widely recognized or a well-known animation character is registered as an agent, the appearance or voice of the character cannot be disconnected in principle. Therefore, when such an agent whose appearance and voice cannot be disconnected is newly registered, in the case where such an agent is similar to an already registered agent whose appearance and voice can be disconnected, the allocation of the appearance and voice of the already registered agent can be adjusted.

[0166] <3. Third Embodiment>

[0167] For each user, even the same agent may have a different appearance (image) or voice. Specifically, in the case where user A and user B personally use the same music recommendation agent, the music recommendation agent used by user A and the music recommendation agent used by user B will have different appearance (image) or voice.

[0168] (Example of selecting appearance and voice)

[0169] Fig.11 A second example of selecting an agent's appearance and voice is shown.

[0170] exist Fig.11 In, as mentioned above Fig. 9 As in the example, each of agents #1 to #8 is assigned an image and voice according to its position in the sequence by default, but the agent (the main body of the agent) and the appearance and voice of the agent can be disconnected, and an image and voice with other numbers can be assigned.

[0171] Here, in the case where agents #1 and #2 have already been registered as agents used by user A, a situation is assumed where agent #7 for a specific purpose, such as a music recommendation agent, is provided to user A.

[0172] However, in Fig.11 In the example, by default, avatar #7 or voice #7 is assigned to agent #7 for a given purpose. In addition, avatar #3 and voice #3 are similar to avatar #7 and voice #7, respectively (not separated by a fixed amount or more).

[0173] At this time, the appearance or voice (image #1 or voice #1 and image #2 or voice #2) of all agents #1 and agents #2 already held by user A is separated by a fixed amount or more (dissimilar) from the image #7 or voice #7 of the designated agent #7. Therefore, in this example of user A, the designated agent #7 is provided while maintaining the image #7 or voice #7.

[0174] Meanwhile, in the case where agent #2 and agent #3 have already been registered as agents used by user B, assume a situation where agent #7 for a specific purpose is provided to user B.

[0175] At this time, one of the appearances or voices of agents #2 and #3 already held by user B (image #2 or voice #2 and image #3 or voice #3) is not separated by a fixed amount or more (similar) from image #7 or voice #7 of designated-purpose agent #7. Therefore, in this example of user B, designated-purpose agent #7 is provided that does not have image #7 or voice #7 but has image #8 or voice #8 different from image #7 or voice #7.

[0176] also, Fig.12A third example of selecting an agent's appearance and voice is shown.

[0177] exist Fig.12 In the case where agent #2 and agent #3 have been registered as agents used by user B, when agent #7 for a specific purpose is provided to user B, the default image #7 or voice #7 is similar to image #3 or voice #3. Therefore, instead of the default image #7 or voice #7, image #9 or voice #9 is assigned to agent #7 for a specific purpose.

[0178] Note that avatar #9 or voice #9 indicates an avatar or voice that is prepared separately and not shown, but avatar #8 or voice #8, for example, may also be assigned.

[0179] (Overall view of the process)

[0180] Next, we will refer to Fig.13 The flowchart in describes the overall diagram of the proxy provision processing in the third embodiment. Note that Fig.13 The designated agent in provides processing corresponding to Fig.10 The processing in step S72 in .

[0181] In step S91, the control unit 200 determines whether the appearance or voice of all agents already held by the specified user is separated from the first appearance or first voice of the agent for the specified purpose (eg, music recommendation agent) by a fixed amount or more.

[0182] In the case of affirmative determination in the determination process of step S91, the process proceeds to step S92. In step S92, the control unit 200 provides the designated user with an agent of the designated purpose having the first appearance or the first voice.

[0183] Specifically, when the designated agent #7 is provided to the user A, since the image #1 or voice #1 and image #2 or voice #2 of all agents #1 and agents #2 already held by the user A are separated from the image #3 or voice #3 of the designated agent #7 by a fixed amount or more, the designated agent #7 is provided while maintaining the image #7 or voice #7. Fig.11 Example of user A in ).

[0184] On the other hand, in the case where the determination is negative in the determination processing of step S91, that is, when one of the appearances or voices of the agent already held by the specified user is not separated by a fixed amount or more (similar) from the first appearance or first voice of the agent for the specified purpose, the processing proceeds to step S93.

[0185] In step S93, the control unit 200 provides the designated user with an agent of the designated purpose having a second appearance or a second voice different from the first appearance or the first voice.

[0186] Specifically, when the designated-purpose agent #7 is provided to user B, since one of the image #2 or voice #2 and image #3 or voice #3 of the agents #2 and #3 already held by user B is not separated from the image #7 or voice #7 of the designated-purpose agent #7 by a fixed amount or more, the designated-purpose agent #7 (which does not have image #7 or voice #7 but has image #8 or voice #8) is provided. Fig.11 Example of user B in ).

[0187] When the processing in step S92 or S93 ends, the processing returns to Fig.10 The processing in step S72 in , and the processing in step S72 and subsequent steps are executed.

[0188] As described above, when providing a specific-purpose agent whose uniqueness of appearance or voice is ensured, since it is possible to change the appearance or voice of the agent for each user even for the same agent, the agent providing system 1 can provide an agent suitable for the user.

[0189] <4. Fourth Embodiment>

[0190] In the network space, it is also assumed that a proxy of a group to which a plurality of users belong is used in the group. Here, a case where a group proxy is provided in consideration of appearance (image) or voice in a private network space will be described.

[0191] (Example of selecting appearance and voice)

[0192] Fig.14 A fourth example of selecting an agent's appearance and voice is shown.

[0193] exist Fig.14 In Fig. 9 As in the other figures described above, each of Agents #1 to Agent #8 is assigned an image and voice by default according to its position in the sequence, but the agent (the main body of the agent) and the appearance and voice of the agent can be disconnected, and an image and voice with other numbers can be assigned.

[0194] Here, two users, user A and user B, belong to the same group in a private network space, and each of user A and user B has registered his / her own agent for personal use.

[0195] As agents used by user A, agents #1, #3 and #5 (image #1 and voice #1, image #2 and voice #2, and image #3 and voice #3) have been registered. As agents used by user B, agents #2, #3, #8 and #9 (image #1 and voice #1, image #2 and voice #2, image #3 and voice #3, and image #4 and voice #4) have been registered.

[0196] At this time, assume the case where an agent #X is to be provided for the group. When the agent #X is provided for the group, an image and voice different from those of all agents already held by users A and B in the group are assigned.

[0197] That is, since image #5 and voice #5 are not assigned to agents #1, #3 and #5 used by user A and agents #2, #3, #8 and #9 used by user B, and the image and voice of each agent used by users A and B are separated from image #5 and voice #5 by a fixed amount or more, image #5 and voice #5 can be assigned to agent #X used for the group.

[0198] By this allocation, when an agent for a group to which users A and B belong is newly provided in a private network space, an agent for the group that is separated from agents already held by users A and B by a fixed amount or more in appearance or voice can be provided.

[0199] (Overall view of the process)

[0200] Next, we will refer to Fig.15 The flowchart in describes the overall diagram of the proxy providing process in the fourth embodiment. Note that Fig.15 The designated agent in provides processing corresponding to Fig.10 The processing in step S72 in .

[0201] In step S111 , the control unit 200 determines whether an agent for a group is newly provided to a private network space.

[0202] In the case of affirmative determination 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 the appearance or voice of all agents already held by the users in the group.

[0203] Specifically, when providing an agent for a group to which users A and B belong, an agent for the group having an image #5 and a voice #5 that are different from the image and voice of the agent already held by user A (image #1 and voice #1, image #2 and voice #2, and image #3 and voice #3) and the image and voice of the agent already held by user B (image #1 and voice #1, image #2 and voice #2, image #3 and voice #3, and image #4 and voice #4) is provided. Fig.14 ).

[0204] If the processing in step S112 ends or the determination in step S111 is negative, the processing returns to Fig.10 The process goes to step S72 and executes the processing in step S72 and subsequent steps.

[0205] As described above, when an agent for a group is newly provided into a private network space, the agent providing system 1 can provide an agent for the group that is separated by a fixed amount or more in appearance or voice from agents already held by users in the group.

[0206] <5. Fifth embodiment>

[0207] When a new agent is to be provided, whether the appearance (image) or voice of the new agent is recognizable may be confirmed with the user, so that an agent having a recognizable appearance (image) or voice is provided according to the confirmation result.

[0208] (First example)

[0209] Fig.16 An example of interaction between an agent and a user when performing recognition confirmation of the appearance (image) of a new agent is shown.

[0210] Agent: “Is there a difference between the agent I’m associated with and the one you’re associated with?”

[0211] User: “No problem, you can be distinguished.”

[0212] User: "Sorry, you look like Agent A."

[0213] Agent: “What area looks like?” User: “The mouth area looks like.”

[0214] In the first example, the part of the face of the other agent that is considered to look like the part of the face of the new agent is specified through the interaction between the agent and the user. The agent providing system 1 obtains this information about "what it looks like", so that it can present an agent that reflects the obtained information again.

[0215] For example, in the agent providing system 1, the parameters of the facial part that is considered to look like by interaction are compared between the new agent and the other agents, and the relationship between the coefficients is analyzed. In addition, in the agent providing system 1, assuming that the user's sensitivity to the part of the face that is considered to look like is high, the impossibility (difference in parameters) in the part will become larger in the image of the new agent to be presented (re-presented) thereafter.

[0216] More specifically, since it has been specified in the above-mentioned interaction between the agent and the user that the mouth of the new agent looks like the mouth of another agent, the image is changed so that the mouth does not look like the mouth of another agent, especially when the new agent is re-presented.

[0217] (Second example)

[0218] Fig.17An example of interaction between an agent and a user is shown when reconfirmation of the appearance (image) of a new agent is performed.

[0219] Agent: "Can I be distinguished?"

[0220] User: “No problem, you can be separated.”

[0221] In the second example, when reflecting the above Fig.16 When the new agent in the first example of interaction between the agent and the user was re-presented, the user commented that the new agent could be distinguished from the other agents because the image of the mouth, in particular, had changed.

[0222] In this way, in the case where the image of the re-presented new agent is separated from the images of other agents by a fixed amount or more (does not look like each other), the re-presented new agent is fixed as the agent to be provided to the user.

[0223] On the other hand, in a case where the image of the newly presented agent is not separated from the images of the other agents by a fixed amount or more (looks like), the presentation of the new agent whose image has been changed is repeated by further appropriately changing the parameters of each part, and a new agent that does not look like the user's other agents is to be presented.

[0224] Note that, for example, in addition to text chatting by displaying messages exchanged in real time on the screen of the information terminal 10, Fig.16 and Fig.17 The interaction between the agent and the user shown in may also be performed via audio, for example using voice chat.

[0225] (Overall view of the process)

[0226] Next, we will refer to Fig.18 The flowchart in describes the overall diagram of the proxy provision processing in the fifth embodiment. Note that Fig.18 The designated agent in provides processing corresponding to Fig.10 The processing in step S72 in .

[0227] In step S131, the control unit 200 determines whether an agent that the user has already used can be recognized by the user based on the appearance or voice pair of the newly provided agent.

[0228] In the case of affirmative determination 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 a recognizable appearance or voice.

[0229] On the other hand, in the case of negative determination 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 unrecognizable appearance or voice.

[0230] When the processing in step S133 ends, the processing returns to step S131. Then, in the determination processing of step S131, it is determined again whether the agent that the user has already used can be recognized based on the new appearance or voice, and the loop of steps S133 and S131 is repeated until it is determined that it can be recognized ("Yes" in S131).

[0231] Then, in the case where it is determined that recognition is possible based on the new appearance or voice, an agent having the determined recognizable new appearance or voice is provided as a new agent.

[0232] Specifically, in the case where it has been specified in the interaction between the agent and the user that the mouth of the new agent looks like the mouth of other agents, the agent whose image has been changed so that the mouth in particular does not look like the mouth of other agents is re-presented. Then, in the case where the image of the re-presented new agent does not look like the image of other agents, the re-presented new agent ( Fig.16 and Fig.17 ).

[0233] When the processing in step S132 ends, the processing returns to Fig.10 The processing in step S72 in , and the processing in step S72 and subsequent steps are executed.

[0234] (Learning Process)

[0235] Next, we will refer to Fig.19 The flowchart in describes the flow of the learning process.

[0236] In step S151, the control unit 200 acquires a response from the user as to whether the appearance or voice of the newly provided agent is recognizable.

[0237] In step S152, the control unit 200 learns the characteristics when the user recognizes the appearance or voice of the agent, and uses the answer from the user as the teacher data. Here, for example, Fig.16 and Fig.17 The user's responses in the interaction between the agent and the user shown may be used as teacher data.

[0238] As a method of such learning, for example, a neural network and machine learning such as deep learning are used.

[0239] A neural network is a model that imitates the neural circuits of the human brain and is composed of three types of layers, namely an input layer, an intermediate layer (hidden layer), and an output layer. In addition, deep learning is a model that uses a neural network with a multi-layer structure, and can learn complex patterns underlying a large amount of data by repeating learning unique to each layer.

[0240] In addition, the problem setting of machine learning includes 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, feature quantities are learned based on given labeled learning data (teacher data). This makes it possible to derive labels for unknown data.

[0241] When the processing in step S152 ends, Fig.19 The learning process in is completed.

[0242] As described above, when providing a new agent, since whether the appearance or voice of the new agent is recognizable is confirmed with the user and an agent with a recognizable appearance or voice is provided based on the confirmation result, the agent providing system 1 can provide an agent close to the user's feeling.

[0243] Since the results of machine learning can be used when generating new agents, as more answers from users used as teacher data are obtained, agents with more clearly recognizable appearance or voice can be generated.

[0244] Note that although the appearance (image) is particularly mainly described here, for voice, it is only necessary to similarly confirm with the user whether the voice of the new agent is recognizable, and perform designated agent providing processing, learning processing, etc. based on the confirmation result.

[0245] <6. Sixth Implementation Method>

[0246] Also in the public network space, an agent may be provided that is separated by a fixed amount or more from the appearance or voice of the agent used as an avatar by a designated user.

[0247] (First example)

[0248] Fig. 20 A first example of a specific configuration of the agent providing system 1 is shown.

[0249] exist Fig. 20 In the information terminal 10 and the server 20 exchange various kinds of data, thereby the appearance (image) or voice (data of the appearance (image) or voice) of the agent is registered. Here, among the registration of the appearance (image) and voice of the agent, the registration of the appearance (image) will be mainly described.

[0250] In the information terminal 10, when the character creation tool 151 or the audio creation tool 152 provided as software is executed by the control unit 100, the graphical user interface (GUI) of these tools is displayed on the display 131. At this time, users who operate these tools include producers (creators) who create agents, etc.

[0251] The image creation tool 151 is a tool for generating an image of an agent. The audio creation tool 152 is a tool for generating a voice of an agent.

[0252] The character creation tool 151 includes a drawing tool 161. The drawing tool 161 is graphics software for drawing an image (two-dimensional computer graphics (CG) or the like) on a computer generally using the mouse 121 or the like.

[0253] For example, in the drawing tool 161, various objects 163 (e.g., parts of the face such as eyes, ears, and face shape) are subjected to processing such as deformation and modification by the drawing software 162, and an image of an agent is generated. The drawing tool 161 outputs a message including a registration request for the generated image of the agent to the communication unit 104 to transmit the message to the server 20 via the network 30.

[0254] In the server 20 , when the control unit 200 executes the image registration program 251 , the functions of the image similarity checking unit 261 and the image registration unit 271 are realized. In addition, in the server 20 , the registered image database 252 is recorded in the storage unit 203 .

[0255] When a message including a registration request is input from communication unit 204, avatar similarity checking unit 261 checks the similarity of the generated agent avatar (avatar of the request target) by referring to data (avatar data, space ID, etc.) stored in registered avatar database 252.

[0256] For example, in the image similarity checking unit 261, the parameter analyzing unit 263 analyzes the parameters of the image of the request target (for example, each part such as eyes, ears and face shape), and the face authentication unit 262 authenticates the image (face) of the request target based on the analysis results of the parameters.

[0257] Then, the image similarity checking unit 261 checks the similarity between the image (face) of the request target and the image (face) already registered in the public network space based on the authentication result of the image (face).

[0258] In addition, for example, in a case where the score value indicating the similarity is equal to or greater than a predetermined threshold, that is, in a case where the images are not similar (in a case where the images are separated by a fixed amount or more), the image similarity checking unit 261 determines the image of the target of the registration request and outputs the determination result to the image registration unit 271.

[0259] The image registration unit 271 saves data on the image of the request target in the registration image database 252 based on the determination result from the image similarity checking unit 261 .

[0260] Furthermore, the image similarity checking unit 261 outputs a message including the registration permission or rejection of the image of the request target to the communication unit 204 to transmit the message to the information terminal 10 via the network 30. By this processing, in the information terminal 10, the registration permission or rejection of the image of the request target is presented to the user through the drawing tool 161.

[0261] Here, in the case where the image of the request target is not allowed to be registered, the image similarity checking unit 261 sends a message indicating this to the information terminal 10 via the network 30. In addition, an image that is allowed to be registered may be proposed from the server 20 side to the information terminal 10 side instead of (or together with) a message that the image of the request target is not allowed to be registered.

[0262] That is to say, Fig.21 As shown, in the case where the image (face) of the request target is similar to an image (face) already registered (in the case where the images are not separated by a fixed amount or more), the image similarity checking unit 261 proposes an image that is allowed to be registered, for example by performing the following processing.

[0263] That is, the image similarity checking unit 261 adjusts the parameters of the image (e.g., each part such as eyes, ears, and face shape) of the requested target to generate an image (face) of the proposed target that is separated from the image (face) that has been registered by a fixed amount or more. Then, the data related to the image (face) of the proposed target generated in this way is notified to the information terminal 10, and the data is presented to the user.

[0264] Specifically, in Fig. 22 In the figure, with the image of the requested target arranged at the origin in a three-dimensional coordinate system (wherein the axis in the horizontal direction (X direction) in the figure is designated as the axis corresponding to the parameters related to the "eyes" and the axis in the vertical direction (Y direction) in the figure is designated as the axis corresponding to the parameters related to the "mouth"), the image (candidate image) when these parameters are adjusted is shown.

[0265] In other words, Fig. 22In the horizontal axis, two images in which the parameters of the eyes of the requested target image (face) are adjusted are drawn as candidate images (faces). Fig. 22 In the figure, two images in which the parameters of the mouth of the image (face) of the requested target are adjusted are drawn on the axis in the vertical direction as candidate images (faces). However, the four candidate images (faces) shown here are assumed to be images (faces) separated by a fixed amount or more from the image (face) that has already been registered.

[0266] The image similarity checking unit 261 can select one or more candidate images (faces) from the four candidate images (faces) as the image of the proposed target, and notify the selected image to the information terminal 10. In this way, even in the case where there is an image similar to the image of the requested target, an image (an image allowed to be registered) in which the parameters of each part of the image of the requested target are changed can be proposed.

[0267] Since an image can be registered in the above manner, the registered image can be used to provide an agent (avatar) that is separated from agents (avatars) of other users who have registered in the public network space by a fixed amount or more at least in appearance as an agent (avatar) of a designated user.

[0268] Note that the agent (avatar) provided in this manner is assumed to be used by a specified user in an application such as chat or social media, and can also be used as an agent as a clone of the specified user himself used in an application such as chat.

[0269] (Overall view of the process)

[0270] Next, we will refer to Figure 23 to Figure 25 The flowchart in describes the overall diagram of the proxy provision processing in the sixth embodiment. Note that Fig.23 The proxy in provides processing corresponding to Figure 6 The processing in step S12 in .

[0271] In step S171, the control unit 200 determines whether an agent is newly provided to the public network space as an avatar of a designated user.

[0272] In the case of affirmative determination in the determination processing of step S171, the process proceeds to step S 172. In step S172, the control unit 200 performs an avatar agent providing process.

[0273] Here, we will refer to Fig.24 The flowchart in the description is similar to Fig.23 The processing in step S172 corresponds to the avatar agent providing a first example of details of the processing.

[0274] In step S191, the control unit 200 provides an agent that is separated by a fixed amount or more in appearance or voice from an agent that is an avatar of other users who have registered in the public network space.

[0275] Specifically, for example, in the case where an image of an agent is generated in the information terminal 10, the server 20 checks the similarity between the generated image and images already registered in the public network space, and in the case where these images are not similar (in the case where these images are separated by a fixed amount or more), registers data on the generated image ( Fig. 20 ).

[0276] By using the image registered in the above-described manner, it is possible to provide an agent (avatar) that is separated from agents (avatars) of other users who have registered in the public network space by a fixed amount or more at least in appearance.

[0277] Next, we will refer to Fig.25 The flowchart in the description is similar to Fig.23 The avatar agent corresponding to the process in step S172 provides a second example of details of the process.

[0278] In step S211 , the control unit 200 presents to the user agent candidates that are separated by a fixed amount or more in appearance or voice from agents that are avatars of other users that have registered in the public space.

[0279] Specifically, in the case where an image of an agent is generated in the information terminal 10, the server 20 checks the similarity between the generated image and images already registered in the public network space, and in the case where these images are similar (in the case where these images are not separated by a fixed amount or more), selects one or more candidate images ( Fig.21 and Fig. 22 ) Proposed image (image that is allowed to be registered).

[0280] By using the image proposed in the above-described manner, one or more agent (avatar) candidates that are separated from agents (avatars) of other users already registered in the public network space by a fixed amount or more at least in appearance can be presented.

[0281] As described above, when newly providing an agent (avatar) of a designated user to a public network space, the agent providing system 1 can provide an agent that is separated from agents (avatars) of other users already registered in the public network space by a fixed amount or more in appearance or voice.

[0282] <7. Seventh Implementation Method>

[0283] In the above description, the appearance (image) of the agent has been mainly described, but here, a method of generating a voice of the agent will be described.

[0284] For example, the user can operate the audio creation tool 152 ( Fig. 20 ) to generate the voice of the agent. The information terminal 10 can register the voice of the agent by sending the generated voice to the server 20 via the network 30.

[0285] Fig.26 An example of a method of generating a voice for an agent is shown.

[0286] When audio data obtained by converting text into audio through text to speech (TTS) is input as raw data, pitch adjustment processing, formant adjustment processing, and other effect processing are sequentially performed on the input audio data, and the voice of the agent is generated.

[0287] First, in the pitch adjustment process, a process of adjusting the pitch (pitch) of audio data is performed, and the audio is modified (S311).

[0288] Next, in the formant adjustment process, a process of adjusting the frequency components characterizing the voice of the agent is performed on the audio data, and the audio is modified (S312).

[0289] The formants represent a plurality of peaks moving with time obtained by observing the spectrum of audio, and are sequentially referred to as the first formant frequency, the second formant frequency, the third formant frequency, etc. from the lowest frequency. Each formant frequency is important in vowel recognition.

[0290] In this formant adjustment processing, for example, more complex formant adjustment is performed by performing processing on each formant frequency, so that audio changes can be formed. That is, here, the same adjustment is not applied to all vowels, but a process different from the process of performing pitch adjustment and formant adjustment on the entire sound is performed, such as emphasizing the characteristics of "the sound in the column of vowel a".

[0291] Next, in other effect processing, processing such as effects is performed on the audio data, and the audio is modified (S313).

[0292] In these effect processing, for example, processing of placing harmonics, inserting noise or reducing bits is performed. In addition, here, processing for modifying audio other than effect processing can be performed.

[0293] In this way, by sequentially performing pitch adjustment processing, formant adjustment processing, and other effect processing on input audio data, for example, speech that can be emotionally accepted by the user rather than real speech uttered by a person can be developed as the voice of the agent.

[0294] <8. Modifications>

[0295] <Other configuration examples>

[0296] In the above description, there has been indicated a case where the agent providing system 1 is constituted by the information terminal 10 and the server 20. However, for example, other configurations such as a configuration to which other devices or an external server are added may be used.

[0297] Specifically, the server 20 as an information processing device can be configured as a plurality of information processing devices by being divided into a server that performs processing for providing an agent, a database server that stores data about the agent, etc. Similarly, the information terminal 10 can be composed not only of one information processing device but also of a plurality of information processing devices.

[0298] In addition, in the agent providing system 1, which device includes the constituent elements (control unit) of each device constituting the information terminal 10 and the server 20 is arbitrary. For example, the information terminal 10 can perform a part of the processing for information processing performed by the above-mentioned server 20. Alternatively, using edge computing technology, an edge server connected to a network (a peripheral part of the network) close to the information terminal 10 can perform a part of the processing for information processing performed by the above-mentioned server 20.

[0299] In the present disclosure, a system refers to a collection of multiple constituent elements (e.g., devices and modules (constituent members)), and whether all the constituent elements are arranged in the same housing is not considered important. Therefore, multiple devices housed in different housings to be connected to each other via a network and one device in which multiple modules are housed in one housing are both considered to be systems.

[0300] In addition, it is also arbitrary what communication form each component has. In different aspects, in addition to a communication network such as the Internet or a mobile phone network, each component can also be connected via a local network (local area network (LAN) or wide area network (WAN)) as the network 30. In addition, each component can be connected by wire or wirelessly.

[0301] <9. Computer Configuration>

[0302] A series of the above treatments (e.g. Figure 6The agent providing processing in the process, etc.) can be executed by hardware or software. In the case where a series of processes are executed by software, the program constituting the software is installed in the computer of each device.

[0303] Fig. 27 : is a block diagram showing an example of the hardware configuration of a computer that executes the series of processes described above using a program.

[0304] In the computer, a central processing unit (CPU) 1001, a read only memory (ROM) 1002, and a random access memory (RAM) 1003 are interconnected via a bus 1004. In addition, an input / output interface 1005 is 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.

[0305] 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 nonvolatile 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.

[0306] In the computer configured as described above, for example, the above-described series of processes is performed so that the CPU 1001 loads the program recorded in the ROM 1002 or the storage unit 1008 into the RAM 1003 via the input / output interface 1005 and the bus 1004 to execute.

[0307] For example, the program executed by the computer (CPU 1001) can be provided by being recorded in the removable recording medium 1011 serving as a package medium, etc. Furthermore, the program can be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

[0308] In the computer, the program can be installed to the storage unit 1008 via the input / output interface 1005 by installing the removable recording medium 1011 in the drive 1010. In addition, when the program is received through the communication unit 1009, the program can be installed to the storage unit 1008 via a wired or wireless transmission medium. Alternatively, the program may be pre-installed to the ROM 1002 or the storage unit 1008.

[0309] Here, in this specification, the processing performed by the computer according to the program does not necessarily have to be performed in chronological order in the order described in the flowchart. That is, the processing performed by the computer according to the program includes processing performed in parallel or individually (for example, parallel processing or processing by an object). In addition, the program can be processed by a single computer (processor) or distributed by multiple computers.

[0310] Furthermore, the embodiment according to the present technology is not limited to the above-described embodiment, and various changes may be made without departing from the scope of the present technology.

[0311] Furthermore, the present technology can also be configured as described below. (1)

[0313] An agent providing system, comprising:

[0314] A control unit that, when newly providing an agent to a network space that allows registration of a plurality of agents, provides an agent that is spaced apart in appearance or voice by a fixed amount or more from agents already registered in the network space. (2)

[0316] The agent providing system according to (1) above, wherein:

[0317] The control unit:

[0318] determining that the new agent is separated in appearance or voice by a fixed amount or more from agents already registered in the network space; and

[0319] Provide such identified agent. (3)

[0321] The agent providing system according to (1) or (2) above, wherein:

[0322] The control unit:

[0323] newly generating an agent that is separated in appearance or voice by a fixed amount or more from an agent already registered in the network space; and

[0324] Provide the generated proxy. (4)

[0326] The agent providing system according to (1) above, wherein:

[0327] The control unit:

[0328] When a proxy for a designated user is newly provided to a private network space accessible to the designated user,

[0329] An agent is provided which is separated by a fixed amount or more from the appearance or voice of an agent which has been registered in the private network space and used by the designated user. (5)

[0331] The agent providing system according to (4) above, wherein:

[0332] The designated agent has a first appearance or a first voice, and

[0333] The control unit:

[0334] When providing the agent for the designated purpose to a first user, when the first appearance or the first voice is not separated by a fixed amount or more from the appearance or voice of an agent already held by the first user, providing an agent for the designated purpose having a second appearance or a second voice different from the first appearance or the first voice; and

[0335] When providing the agent for the designated purpose to the second user, when the first appearance or the first voice is separated from the appearance or voice of all agents already held by the second user by a fixed amount or more, the agent for the designated purpose is provided while maintaining the first appearance or the first voice. (6)

[0337] The agent providing system according to (4) above, wherein:

[0338] When providing an agent used by a group consisting of a first user and a second user, the control unit provides an agent having an appearance or voice different from the appearance or voice of all agents already held by the first user and the second user. (7)

[0340] The agent providing system according to any one of (4) to (6) above, wherein:

[0341] The control unit:

[0342] confirming whether the user can recognize an agent that the user has already used based on the appearance or voice of an agent newly provided to the user; and

[0343] A new agent having a recognizable appearance or voice is provided to the user according to a result of the confirmation. (8)

[0345] The agent providing system according to (7) above, wherein:

[0346] When the user replies that the agent that the user has already used cannot be recognized 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 unrecognizable appearance or voice. (9)

[0348] The agent providing system according to (8) above, wherein:

[0349] The control unit:

[0350] Based on the answer from the user, learning the characteristics when the user recognizes the appearance or voice of the agent; and

[0351] An agent with a new appearance or voice is generated according to the characteristics. (10)

[0353] The agent providing system according to (1) above, wherein:

[0354] The control unit:

[0355] When a proxy is newly provided as an avatar of a designated user to a public network space accessible to multiple users,

[0356] An agent is provided which is separated in appearance or voice by a fixed amount or more from agents which are avatars of other users already registered in the public network space. (11)

[0358] The agent providing system according to (10) above, wherein:

[0359] The control unit:

[0360] When a proxy is newly provided as an avatar of the designated user to the public network space accessible to the plurality of users,

[0361] Agent candidates that are separated by a fixed amount or more in appearance or voice from agents that are avatars of other users that have been registered in the public network space are presented to the user. (12)

[0363] An agent providing method, comprising:

[0364] When an agent is newly provided to a network space that allows registration of a plurality of agents, an agent that is separated in appearance or voice by a fixed amount or more from agents already registered in the network space is provided by the agent providing system. (13)

[0366] A recording medium recording a program for causing a computer to function as a control unit, the control unit:

[0367] When an agent is newly provided to a network space that allows registration of a plurality of agents, an agent that is separated in appearance or voice by a fixed amount or more from agents already registered in the network space is provided.

[0368] Reference numerals list

[0369] 1 Agent provision system

[0370] 10. 10-1 to 10-N Information Terminal

[0371] 20 Servers

[0372] 30 Network

[0373] 100 Control Unit

[0374] 101 Input Unit

[0375] 102 Output Unit

[0376] 103 Storage Unit

[0377] 104 Communication Unit

[0378] 111 Proxy Processing Unit

[0379] 112 Presentation Control Unit

[0380] 113 Communication control unit

[0381] 121 Mouse

[0382] 122 Keyboard

[0383] 131 Display

[0384] 132 Speakers

[0385] 151 Image Creation Tools

[0386] 152 Audio Creation Tools

[0387] 161 Drawing Tools

[0388] 162 Drawing Software

[0389] 163 objects

[0390] 200 Control Unit

[0391] 201 Input unit

[0392] 202 Output unit

[0393] 203 Storage Unit

[0394] 204 Communication Unit

[0395] 211 Agent Provides Unit

[0396] 212 study units

[0397] 213 Communication control unit

[0398] 251 Image Registration Procedure

[0399] 252 Registration Image Database

[0400] 261 Image Similarity Check Unit

[0401] 262 Facial Authentication Unit

[0402] 263 Parameter Analysis Unit

[0403] 271 Image Registration Unit

[0404] 1001 CPU

[0405] 1011 Removable recording media

Claims

1. An agent providing system, comprising: a control unit that, when newly providing an agent to a network space that allows registration of a plurality of agents, provides an agent that is separated in appearance or voice by a fixed amount or more from agents already registered in the network space, The control unit: when a new agent for a designated user is provided to a private network space accessible to the designated user, providing an agent that is separated in appearance or voice by a fixed amount or more from an agent that has been registered in the private network space and used by the designated user, wherein the agent having the first appearance or the first voice is a designated agent, and The control unit: When providing the agent for the designated purpose to the first user, when the first appearance or the first voice is not separated from the appearance or voice of the agent already held by the designated user by a fixed amount or more, providing an agent having a second appearance or a second voice different from the first appearance or the first voice, and When providing the agent for the designated purpose to the second user, the agent having the first appearance or the first voice is provided when the first appearance or the first voice is separated by a fixed amount or more from the appearance or voice of all agents already held by the designated user.

2. The agent providing system according to claim 1, wherein: The control unit: determining that the new agent is separated in appearance or voice by a fixed amount or more from agents already registered in the network space; and Provide such identified agent.

3. The agent providing system according to claim 1, wherein: The control unit: newly generating an agent that is separated in appearance or voice by a fixed amount or more from an agent already registered in the network space; and Provide the generated proxy.

4. The agent providing system according to claim 1, wherein: When providing an agent used by a group consisting of a first user and a second user, the control unit provides an agent having an appearance or voice different from the appearance or voice of all agents already held by the first user and the second user.

5. The agent providing system according to claim 1, wherein: The control unit: confirming whether the user can recognize the agent that the user has already used based on the appearance or voice of the agent newly provided to the user; as well as A new agent having a recognizable appearance or voice is provided to the user according to a result of the confirmation.

6. The agent providing system according to claim 5, wherein: When the user replies that the agent that the user has already used cannot be recognized 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 unrecognizable appearance or voice.

7. The agent providing system according to claim 6, wherein: The control unit: Based on the answer from the user, learning the characteristics when the user recognizes the appearance or voice of the agent; and An agent with a new appearance or voice is generated according to the characteristics.

8. The agent providing system according to claim 1, wherein: The control unit: When a proxy is newly provided as an avatar of a designated user to a public network space accessible to multiple users, An agent is provided which is separated in appearance or voice by a fixed amount or more from agents which are avatars of other users already registered in the public network space.

9. The agent providing system according to claim 8, wherein: The control unit: When a proxy is newly provided as an avatar of the designated user to the public network space accessible to the plurality of users, Agent candidates that are separated by a fixed amount or more in appearance or voice from agents that are avatars of other users that have been registered in the public network space are presented to the user.

10. An agent providing method, comprising: When a new agent is provided to a network space that allows registration of a plurality of agents, an agent providing system provides an agent that is separated from agents already registered in the network space by a fixed amount or more in appearance or voice, When a proxy for a designated user is newly provided to a private network space accessible to the designated user, providing an agent that is separated in appearance or voice by a fixed amount or more from an agent that has been registered in the private network space and used by the designated user, The agent having the first appearance or the first voice is a designated agent, When providing the agent for the designated purpose to the first user, when the first appearance or the first voice is not separated from the appearance or voice of the agent already held by the designated user by a fixed amount or more, providing an agent having a second appearance or a second voice different from the first appearance or the first voice, and When providing the agent for the designated purpose to the second user, the agent having the first appearance or the first voice is provided when the first appearance or the first voice is separated by a fixed amount or more from the appearance or voice of all agents already held by the designated user.

11. A recording medium recording a program for causing a computer to function as a control unit, the control unit: When an agent is newly provided to a network space that allows registration of a plurality of agents, an agent that is separated in appearance or voice by a fixed amount or more from agents already registered in the network space is provided, in, The control unit: when a proxy for a designated user is newly provided to a private network space accessible to the designated user, providing an agent that is separated in appearance or voice by a fixed amount or more from an agent that has been registered in the private network space and used by the designated user, wherein the agent having the first appearance or the first voice is a designated agent, and The control unit: When providing the agent for the designated purpose to the first user, when the first appearance or the first voice is not separated from the appearance or voice of the agent already held by the designated user by a fixed amount or more, providing an agent having a second appearance or a second voice different from the first appearance or the first voice, and When providing the agent for the designated purpose to the second user, the agent having the first appearance or the first voice is provided when the first appearance or the first voice is separated by a fixed amount or more from the appearance or voice of all agents already held by the designated user.

Images