Information processing device, information processing method, and computer-readable recording medium

Abstract

The present invention provides feedback in a more effective manner to a user.　An information processing device 100 comprises: a feedback generation unit 140 that generates one or a plurality of pieces of feedback on the basis of input data; an agent selection unit 150 that selects an agent, to be used for the feedback, from among a plurality of agents on the basis of an attribute of each piece of feedback; and an output unit 170 that outputs feedback in which the selected agent is used.

Description

Information Processing Apparatus, Information Processing Method, and Computer-Readable Recording Medium Cross-Reference to Related Applications

[0001] This application is based on Japanese Patent Application No. 2024-207213 filed on November 28, 2024, the contents of which are incorporated herein by reference.

[0002] This disclosure relates to an information processing apparatus, an information processing method, and a computer-readable recording medium.

[0003] Conventionally, technologies for evaluating and analyzing inputs from users and providing some feedback have been known. The information processing apparatus described in Patent Document 1 acquires, as teacher expression force information, the expression force of teacher T defined by the context of the words uttered by teacher T and the expression of teacher T at that time, and acquires, as user expression force information, the expression force of user U defined by the context of the words uttered by user U and the expression of user U at that time, and calculates the similarity degree of the expression forces of teacher T and user U based on the points of agreement and differences between the teacher expression force information and the user expression force information. Thereby, the information processing apparatus aims to facilitate effective training for enhancing expression force and improving communication ability.

[0004] Japanese Unexamined Patent Application Publication No. 2022-142158

[0005] However, in the information processing apparatus described in Patent Document 1, although the information itself fed back to the user is personalized for the user, the feedback method is uniform, and it was not possible to provide feedback in a more effective manner for the user.

[0006] Therefore, an object of the present disclosure is to provide feedback in a more effective manner for the user.

[0007] An information processing device according to one aspect of the present disclosure includes a feedback generation unit that generates one or more feedbacks based on input data, an agent selection unit that selects an agent to be used for each feedback from among a plurality of agents based on the attributes of each feedback, and an output unit that outputs feedback using the selected agent.

[0008] This disclosure will enable the provision of feedback to users in a more effective manner.

[0009] This is a diagram illustrating the configuration of an information processing system according to one embodiment. This is a diagram illustrating the configuration of an information processing device according to one embodiment. This is a diagram illustrating the contents of the agent storage unit. This is a diagram illustrating the contents of the user storage unit. This is a diagram illustrating the configuration of a client terminal according to one embodiment. This is a flowchart illustrating the processing in the information processing device according to one embodiment. This is a diagram illustrating an example of the hardware configuration of the information processing device according to one embodiment. This is a diagram illustrating an example of the hardware configuration of a client terminal according to one embodiment.

[0010] Embodiments of the present invention will be described with reference to the attached drawings. The following embodiments are provided to facilitate understanding of the present invention and are not intended to limit its interpretation. Furthermore, the present invention can be modified in various ways without departing from its essence. Those skilled in the art can also adopt embodiments in which each of the elements described below is replaced with equivalent components, and such embodiments are also included within the scope of the present invention.

[0011] (System Configuration) An overview of this disclosure will be described using Figure 1. Figure 1 is a configuration diagram of an information processing system according to one embodiment. The information processing system comprises an information processing device 100 and a plurality of client terminals 200a, 200b, ..., 200n (hereinafter referred to as client terminals 200), and each client terminal 200 is connected to the information processing device 100 so as to be able to communicate with each other via a communication network N. The communication network N may be either a wired communication network or a wireless communication network composed of wired or wireless lines, and may be the Internet or a Local Area Network (LAN).

[0012] The information processing device 100 is a device that receives input data to be evaluated and provides feedback in an effective output manner. Based on the input data received from the client terminal 200, the information processing device 100 can generate one or more feedbacks and output the feedback in different output manners depending on the attributes of the feedback.

[0013] In this embodiment, the information processing device 100 outputs feedback using an agent. The information processing device 100 stores multiple agents, each having different attributes, and can select a different agent according to the attributes of the feedback and the user's preferences, and output feedback using the selected agent. The feedback using the agent is provided via a display device such as the display of the client terminal 200, and the agent's image or conversation may be displayed on the display device. In one embodiment, as feedback using the agent, audio is played back from an audio output device such as a speaker.

[0014] An agent is a virtual character that provides feedback to the user, and includes human characters, animal characters, anthropomorphic characters, etc. For example, an agent may be a system or software program that autonomously performs a specific task. Alternatively, so-called AI agents that utilize generative AI such as Large Language Models (LLMs) or Large Action Models (LAMs) may be used as agents.

[0015] The input data from the client terminal 200 can be any data for which feedback is requested. For example, this could include sales data provided by a sales representative to a customer, learning support data provided by an instructor to a learner, or training data conducted by an athlete, but is not limited to these. Furthermore, the input data can be in any format, such as text information, video images, or audio of conversations.

[0016] The attributes of feedback include, but are not limited to, evaluation items and types of feedback. Furthermore, in this embodiment, positive feedback and negative feedback are given as examples of types of feedback.

[0017] The client terminal 200 is a terminal used by a user, and can be a smartphone, tablet, personal computer, etc. Users include sales representatives who input sales data, instructors who input learning support data, and athletes who input training data. The client terminal 200 receives feedback output from the information processing device 100 and provides feedback to the user.

[0018] (Functional Configuration: Information Processing Device) Figure 2 shows the configuration of an information processing device according to one embodiment. In Figure 2, only the necessary functional configuration is shown, assuming a single information processing device 100. However, the information processing device 100 can also be configured as part of a multifunctional distributed system consisting of multiple computer systems.

[0019] The information processing device 100 includes a storage unit 110, a registration unit 120, a receiving unit 130, a feedback generation unit 140, an agent selection unit 150, a voice acquisition unit 160, and an output unit 170. Each of the units shown in Figure 2 can be realized, for example, by using a storage area or by having a processor execute a program stored in the storage area.

[0020] In this embodiment, it is desirable that the memory unit 110 includes an agent memory unit 111, a sound source memory unit 112, a user memory unit 113, an extraction model 114, and a recommended method memory unit 115.

[0021] The agent memory unit 111 stores information about the agent. In one embodiment, it is desirable that the agent memory unit 111 includes the agent ID, category, name, image, gender, relationship, evaluation items, occupation, and characteristics, as shown in Figure 3. The agent ID is information that can uniquely identify the agent. The category stores information indicating one of the following: "1: Person", "2: Animal", or "3: Personification". The name, image, and gender store various information about the agent.

[0022] Relationships are information that indicates the relationship with the user. In one embodiment, relationships store information indicating one of the following: "1: Colleague, classmate", "2: Junior", "3: Senior", "4: Mentor", "5: Expert", "6: Friend", "7: Customer", or "8: Comrade". For example, if the user's data category described later is "1: Sales", it is conceivable that feedback can be output using an agent with relationship "7: Customer". Also, if the user's data category described later is "3: Self-actualization", it is conceivable that feedback can be output using an agent with relationship "8: Comrade", which represents a user with the same goal. Evaluation items are information that indicates the evaluation items for the feedback. In one embodiment, evaluation items store the permitted evaluation items when the evaluation items that the agent can use are restricted. Occupation is information that indicates the occupation of the agent. Traits are information that indicates the traits associated with the agent. In one embodiment, traits store information one or more of the following: "1: Gentle", "2: Energetic", "11: Unreliable", "12: Reliable", "31: Reserved", or "32: Prompt".

[0023] The sound source memory unit 112 stores sound source information corresponding to the agent. In one embodiment, the sound source memory unit 112 stores waveform data for each agent to reproduce the sound for each of the texts included in the feedback. In this embodiment, the sound source memory unit 112 stores multiple waveform data for a single text, corresponding to multiple agents stored in the agent memory unit 111.

[0024] The user memory unit 113 stores user information. In one embodiment, it is desirable that the user memory unit 113 includes user ID, name, age, gender, data category, data field, agent preference, positive feedback preference, and negative feedback preference, as shown in Figure 4. The user ID is information that can uniquely identify the user. Various user information is stored in the name, age, and gender fields.

[0025] The data category is information indicating the category of the input data. In this embodiment, the data category stores information indicating one of the following: "1: Sales", "2: Support", or "3: Self-actualization". The data field is information indicating a field related to the content of the input data. For example, the data field stores information such as "Insurance", "Learning", and "Running". Agent preference is information indicating the user's preference for the agent. In this embodiment, the agent preference stores information indicating one or more attributes of the agent, such as category, gender, relationship, and characteristics.

[0026] While agent preferences store preferences for agents in general, positive feedback preferences and negative feedback preferences store information indicating one or more attributes of the agent, which apply when the feedback type is positive or negative, respectively. For example, in one case, agent preferences might store category "1: Person" and gender "1: Male," positive feedback preferences might store relationship "4: Leader" and trait "12: Reliable," and negative feedback preferences might store relationship "1: Colleague, Classmate" and trait "1: Gentle" and trait "12: Reliable."

[0027] Extraction model 114 is a model that extracts information about behavior change techniques (BCTs) contained in the input data.

[0028] Here, the behavior change technique (BCT) according to this embodiment refers to a method or technique that acts upon (influences) behavior change. For example, according to BCTTv1 (Michie S, Richardson M, Johnston M, et al.: The behavior change technique taxonomy (v1) of 93 hierarchically clustered techniques: building an international consensus for the reporting of behavior change interventions. Ann Behav Med 2013; 46: 81-95.), 93 BCTs in 16 groups are defined. However, the definition of BCT is not limited to BCTTv1, and may be defined in any way as long as it comprehensively covers methods for behavior change.

[0029] The extraction model 114 may be generated by training it using data to which BCT annotation information has been added.

[0030] The recommended method storage unit 115 stores information on BCTs that are recommended to be included in the input data. In one embodiment, it is desirable that the recommended method storage unit 115 includes data categories, data fields, and recommended BCTs. The data categories and data fields are the same information as the data categories and data fields in the user storage unit 113. The recommended BCTs are information indicating BCTs that are recommended to be included in the input data of the target data category and data field.

[0031] The registration unit 120 registers user information. In this embodiment, the registration unit 120 generates a user ID in response to a registration request from the client terminal 200 and registers the information included in the registration request along with the user ID in the user storage unit 113. In this embodiment, the registration request includes, for example, user information such as name, age, gender, data category, data field, agent preference, positive feedback preference, negative feedback preference, etc.

[0032] The receiving unit 130 receives the input data to be evaluated. In this embodiment, the receiving unit 130 receives the user ID and input data from the client terminal 200. As mentioned above, the input data can be any format of data, such as text information, moving images, or audio of conversations.

[0033] The feedback generation unit 140 generates one or more feedbacks based on the input data. In one embodiment, the feedback generation unit 140 determines one or more evaluation items based on the data category and data field of the input data, and generates feedback for each evaluation item. For example, in the case of input data with data category "1: Sales" and data field "Insurance", the feedback generation unit 140 determines "listening skills", "explanatory skills", and "trouble-solving skills" as evaluation items and can generate a total of three feedbacks for each evaluation item. In another example, in the case of input data with data category "Self-realization" and data field "Running", the feedback generation unit 140 determines evaluation items including "training content" and "health status", and can generate a total of two feedbacks for each evaluation item. In this embodiment, the feedback generation unit 140 associates the generated feedback with either positive feedback or negative feedback.

[0034] In one embodiment, the feedback generation unit 140 generates one piece of feedback for one evaluation item, but in another embodiment, the feedback generation unit 140 may generate multiple pieces of feedback for one evaluation item. For example, the feedback generation unit 140 may generate both positive and negative feedback for one evaluation item.

[0035] The agent selection unit 150 selects an agent to be used for feedback. In this embodiment, the agent selection unit 150 selects an agent for each feedback based on the attributes of the feedback and the user's preferences. In this embodiment, the attributes of the feedback include the evaluation items of the feedback and the type of feedback. The evaluation items of the feedback are evaluation items determined by the feedback generation unit 140, and the type of feedback is a type associated by the feedback generation unit 140.

[0036] The voice acquisition unit 160 acquires voice data corresponding to the text included in the feedback. In this embodiment, the voice acquisition unit 160 uses the sound source storage unit 112 to acquire voice data of the agent selected by the agent selection unit 150.

[0037] The output unit 170 outputs feedback using an agent. In this embodiment, the output unit 170 outputs feedback that applies information about the agent selected by the agent selection unit 150, and audio data acquired by the audio acquisition unit 160. The output unit 170 acquires information about the target agent from the agent storage unit 111, applies the acquired information to the feedback, and outputs the feedback and audio data. In one embodiment, the output unit 170 may output agent information in addition to the feedback. For example, the output unit 170 may output text, images, or audio data indicating that the agent's occupation is a doctor.

[0038] (Functional configuration: Client terminal)

[0039] Figure 5 shows the configuration of a client terminal according to one embodiment. The client terminal 200 includes a storage unit 210, a registration request unit 220, a transmission unit 230, and a playback unit 240. Each of the units shown in Figure 5 can be realized, for example, by using a storage area or by having a processor execute a program stored in the storage area.

[0040] The registration request unit 220 sends a registration request of the user. In the present embodiment, the registration request unit 220 sends a registration request including name, age, gender, data category, data field, agent preference, positive feedback preference, negative feedback preference, etc. to the information processing apparatus 100.

[0041] The transmission unit 230 transmits input data to be evaluated. In the present embodiment, the transmission unit 230 transmits a user ID and input data to the information processing apparatus 100. As described above, the input data can be data in any format such as text information, moving image, voice of conversation, etc.

[0042] The playback unit 240 receives feedback as a response to the input data and plays back the received feedback. In the present embodiment, the playback unit 240 plays back the feedback on the display device and the audio output device of the client terminal 200.

[0043] (Operation) Referring to FIG. 6, the processing in the information processing apparatus 100 according to an embodiment will be described in detail. In the present embodiment, it is assumed that various data are stored in the storage unit 110 before the processing in FIG. 6 is started.

[0044] (Example 1) In this example, an example in which a user A whose occupation is insurance sales transmits input data from the client terminal 200 will be described. As shown in FIG. 4, in the user storage unit 113, for the agent preference of the user A, the category "1: Person" and the gender "1: Male" are stored, for the positive feedback preference, the relationship "4: Leader" and the characteristic "12: Reliable" are stored, and for the negative feedback preference, the relationship "1: Colleague, classmate" and the characteristics "1: Gentle" and "12: Reliable" are stored.

[0045] In step S101, the reception unit 130 of the information processing apparatus 100 receives input data to be evaluated. Here, it is assumed that the reception unit 130 has received the user ID "0001" and the input data from the client terminal 200.

[0046] In step S102, the feedback generation unit 140 of the information processing apparatus 100 determines evaluation items for the input data. In the present embodiment, the feedback generation unit 140 refers to the user storage unit 113 based on the user ID, and determines one or more evaluation items based on the data category of the input data and the data field of the input data. Here, it is assumed that the feedback generation unit 140 determines "hearing ability", "explanatory ability", and "trouble handling ability" as evaluation items based on the data category "1: Sales" and the data field "Insurance".

[0047] In step S103, the feedback generation unit 140 generates feedback for each evaluation item. In the present embodiment, the feedback generation unit 140 associates the generated feedback with either positive feedback or negative feedback. Here, it is assumed that the feedback generation unit 140 generates positive feedback for the evaluation items "hearing ability" and "trouble handling ability", and generates negative feedback for the evaluation item "explanatory ability".

[0048] In one embodiment, the feedback generation unit 140 may input the input data into the extraction model 114 to extract information on the BCT included in the input data. When the information on the BCT included in the input data is extracted, the feedback generation unit 140 may generate feedback including the extracted information on the BCT.

[0049] Also, in one embodiment, the feedback generation unit 140 may refer to the recommended method storage unit 115 based on the data category of the input data and the data field of the input data, and acquire information on the BCT that is recommended to be included in the input data. When the information on the BCT that is recommended to be included in the input data is acquired, the feedback generation unit 140 may generate feedback including the acquired information on the BCT. Note that when the information on the BCT included in the input data is also extracted, the feedback generation unit 140 may generate feedback including the difference between the information on the BCT included in the input data and the information on the BCT that is recommended to be included in the input data.

[0050] In step S104, the agent selection unit 150 of the information processing device 100 selects an agent to be used for feedback. In this embodiment, the agent selection unit 150 selects an agent for each type of feedback based on the attributes of the feedback and the user's preferences. In this embodiment, the agent selection unit 150 selects an agent to be used for positive feedback and an agent to be used for negative feedback based on the evaluation items and types.

[0051] Here, the agent selection unit 150 selects agents to be used for positive feedback and agents to be used for negative feedback based on user A's agent preferences, positive feedback preferences, and negative feedback preferences. The agent selection unit 150 selects agent X, which matches category "1: Person", gender "1: Male", relationship "4: Leader", and trait "12: Reliable", as the agent to be used for positive feedback, and selects agent Y, which matches category "1: Person", gender "1: Male", relationship "1: Colleague, classmate", trait "1: Gentle", and trait "12: Reliable", as the agent to be used for negative feedback.

[0052] In step S105, the voice acquisition unit 160 of the information processing device 100 acquires voice data corresponding to the text included in the feedback. In this embodiment, the voice acquisition unit 160 uses the sound source storage unit 112 to acquire voice data of the agent selected by the agent selection unit 150. Here, the voice acquisition unit 160 acquires voice data of agent X for the evaluation items "listening ability" and "troubleshooting ability," and acquires voice data of agent Y for the evaluation item "explanatory ability."

[0053] In step S106, the output unit 170 of the information processing device 100 outputs feedback using an agent. In this embodiment, the output unit 170 obtains information about the target agent from the agent storage unit 111, applies the obtained information to the feedback, and outputs the feedback and audio data. Here, the output unit 170 applies the information of agent X to the feedback for the evaluation items "listening ability" and "troubleshooting ability," and applies the information of agent Y to the feedback for the evaluation item "explanatory ability," and outputs the feedback and the audio data obtained in step S105.

[0054] In one embodiment, the user's output type preferences may be stored in the user storage unit 113, and the output unit 170 may output data according to the user's output type preferences.

[0055] (Example 2) This example describes a case in which user C, whose goal is running as a self-actualization objective, transmits input data from the client terminal 200. As shown in Figure 4, the user memory unit 113 stores user C's agent preferences as category "1: person" and gender "2: female", positive feedback preferences as relationship "4: mentor" and trait "12: reliable", and negative feedback preferences as relationship "6: friend" and trait "32: clear".

[0056] In step S101, the receiving unit 130 receives the input data to be evaluated. Here, it is assumed that the receiving unit 130 has received the user ID "0100" and the input data from the client terminal 200.

[0057] In step S102, the feedback generation unit 140 determines the evaluation items for the input data. Here, the feedback generation unit 140 determines "training content" and "health status" as evaluation items based on the data category "3: Self-actualization" and the data field "running".

[0058] In step S103, the feedback generation unit 140 generates feedback for each evaluation item. Here, the feedback generation unit 140 generates positive and negative feedback for the evaluation item "training content" and generates negative feedback for the evaluation item "health status".

[0059] In step S104, the agent selection unit 150 selects an agent to be used for feedback. In this embodiment, since a record of relationship "5: expert" is registered in the agent memory unit 111 for the evaluation item "health status", the agent selection unit 150 selects agent Z as the agent to be used for feedback for the evaluation item "health status".

[0060] Furthermore, regarding the evaluation item "training content," the agent selection unit 150 selects agent P, which matches category "1: person," gender "2: female," relationship "4: instructor," and characteristic "12: reliable," as the agent to be used for positive feedback, based on user B's agent preferences, positive feedback preferences, and negative feedback preferences. It also selects agent Q, which matches category "1: person," gender "2: female," relationship "6: friend," and characteristic "32: clear," as the agent to be used for negative feedback.

[0061] In step S105, the voice acquisition unit 160 acquires voice data corresponding to the text included in the feedback. In this embodiment, the voice acquisition unit 160 uses the sound source storage unit 112 to acquire voice data of the agent selected by the agent selection unit 150. Here, the voice acquisition unit 160 acquires voice data of agent Z for the evaluation item "health status," and acquires voice data of agent P for positive feedback and voice data of agent Q for negative feedback for the evaluation item "training content."

[0062] In step S106, the output unit 170 outputs feedback using the agent. Here, the output unit 170 applies the information of agent Z to the feedback for the evaluation item "health status," the information of agent P to the positive feedback for the evaluation item "training content," and the information of agent Q to the negative feedback for the evaluation item "training content," and outputs the feedback and the voice data acquired in step S105. In addition, for the feedback for the evaluation item "health status," the output unit 170 outputs information indicating that the agent's occupation is a doctor, in addition to the feedback.

[0063] (Hardware Configuration: Information Processing Device) Next, an example of the hardware configuration of the information processing device 100 will be described with reference to Figure 7. As shown in Figure 7, the information processing device 100 includes, for example, a processor 101, memory 102, storage device 103, input I / F unit 104, data I / F unit 105, communication I / F unit 106, and display device 107.

[0064] The processor 101 is a control unit that controls various processes in the information processing device 100 by executing a program stored in the memory 102.

[0065] Memory 102 is a storage medium such as RAM (Random Access Memory). Memory 102 temporarily stores the program code of the program executed by the processor 101, as well as data required during program execution.

[0066] The storage device 103 is a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 103 stores the operating system and various programs for realizing the above configurations.

[0067] The input interface unit 104 is a device for receiving input from the user. The input interface unit 104 may be, for example, a keyboard, mouse, touch panel, various sensors, or a wearable device. The input interface unit 104 may be connected to the information processing device 100 via an interface such as USB (Universal Serial Bus).

[0068] The data I / F unit 105 is a device for inputting data from outside the information processing device 100. The data I / F unit 105 is, for example, a drive device for reading data stored on various storage media. The data I / F unit 105 may be provided outside the information processing device 100. If the data I / F unit 105 is provided outside the information processing device 100, it is connected to the information processing device 100 via an interface such as USB.

[0069] The communication interface unit 106 is a device for performing data communication with an external device of the information processing device 100 via a network such as the Internet, either by wire or wireless connection. The communication interface unit 106 may be located outside the information processing device 100. If the communication interface unit 106 is located outside the information processing device 100, it is connected to the information processing device 100 via an interface such as USB.

[0070] The display device 107 is a device for displaying various types of information. The display device 107 may be, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, or a display for a wearable device. The display device 107 may be provided outside the information processing device 100. If the display device 107 is provided outside the information processing device 100, it is connected to the information processing device 100, for example, via a display cable. Also, if a touch panel is used as the input I / F unit 104, the display device 107 may be configured to be integrated with the input I / F unit 104.

[0071] (Hardware Configuration: Client Terminal) Next, an example of the hardware configuration of the client terminal 200 will be described with reference to Figure 8. As shown in Figure 8, the client terminal 200 includes, for example, a processor 201, memory 202, storage device 203, input I / F unit 204, data I / F unit 205, communication I / F unit 206, display device 207, and audio output device 208.

[0072] Note that the processor 201, memory 202, storage device 203, input I / F unit 204, data I / F unit 205, communication I / F unit 206, and display device 207 have the same configuration as the processor 101, memory 102, storage device 103, input I / F unit 104, data I / F unit 105, communication I / F unit 106, and display device 107, respectively, so a detailed explanation is omitted.

[0073] The audio output device 208 is a device for outputting sound. The audio output device 208 is, for example, a speaker. The audio output device 208 may be located outside the client terminal 200. If the audio output device 208 is located outside the client terminal 200, it is connected to the client terminal 200 via, for example, a speaker cable.

[0074] As described above, according to this embodiment, the information processing device 100 selects an agent to be used for the feedback from among a plurality of agents based on the attributes of the feedback, and outputs feedback using the selected agent, thereby providing feedback in a manner that is more effective for the user, taking into account the attributes of the feedback.

[0075] For example, the information processing device 100 can select an expert in an evaluation item as a feedback agent based on an evaluation item, which is an example of the attributes of the feedback, or it can select different agents depending on whether the feedback is positive or negative, based on the type, which is another example of the attributes of the feedback. By providing feedback in an output format that corresponds to the attributes of the feedback, the information processing device 100 can help the user receive feedback more effectively.

[0076] Furthermore, the information processing device 100 can make the feedback received by the user more credible by outputting information indicating the agent's occupation in addition to the feedback itself.

[0077] Furthermore, the information processing device 100 can provide feedback in a more effective manner for the user by selecting an agent based on user preference information in addition to the attributes of the feedback. By enabling fine-tuned agent selection that combines the attributes of the feedback and user preference information, the information processing device 100 can provide optimal feedback to users with diverse sensibilities.

[0078] Furthermore, the information processing device 100 can provide feedback in a more effective manner for the user by outputting feedback that includes at least one of images, sounds, and text based on the user's preference information for output types. For example, the effectiveness of the feedback can be further improved by setting an output type that leaves a stronger impression on the user.

[0079] Furthermore, the information processing device 100 can extract behavioral change methods contained in the input data and generate feedback regarding the extracted behavioral change methods, thereby providing the user with feedback analyzed based on behavioral science theory.

[0080] Furthermore, the information processing device 100 can provide the user with effective feedback based on behavioral science theory by generating feedback regarding behavioral change methods that are recommended to be included in the input data.

[0081] Furthermore, the information processing device 100 can provide the user with effective feedback based on behavioral science theory, while reflecting the user's current situation, by generating feedback regarding the difference between the behavioral change methods included in the input data and the behavioral change methods that are recommended to be included in the input data.

[0082] 100 Information processing device, 101 Processor, 102 Memory, 103 Storage device, 104 Input I / F unit, 105 Data I / F unit, 106 Communication I / F unit, 107 Display device, 110 Storage unit, 111 Agent storage unit, 112 Sound source storage unit, 113 User storage unit, 114 Extraction model, 115 Recommended method storage unit, 120 Registration unit, 130 Receiving unit, 140 Feedback generation unit, 150 Agent selection unit, 160 Voice acquisition unit, 170 Output unit, 200 Client terminal, 201 Processor, 202 Memory, 203 Storage device, 204 Input I / F unit, 205 Data I / F unit, 206 Communication I / F unit, 207 Display device, 208 Voice output device, 210 Storage unit, 220 Registration request unit, 230 Transmission unit, 240 Regeneration unit, N network

Claims

1. An information processing device comprising: a feedback generation unit that generates one or more feedbacks based on input data; an agent selection unit that selects an agent to be used for a feedback from among multiple agents based on the attributes of each feedback; and an output unit that outputs feedback using the selected agent.

2. The information processing apparatus according to claim 1, wherein the output unit outputs information of the selected agent in addition to the feedback.

3. The information processing apparatus according to claim 1, further comprising a receiving unit that receives the input data and information identifying a user, wherein the agent selection unit selects an agent from among the plurality of agents based on the user's preference information.

4. The information processing apparatus according to claim 1, wherein the attributes of the feedback include evaluation items for the feedback and / or information indicating whether the feedback is positive or negative.

5. The information processing apparatus according to claim 1, wherein the output unit outputs feedback including at least one of images, sound, and text.

6. The information processing apparatus according to claim 1, wherein the feedback generation unit extracts a first behavioral modification method included in the input data and generates feedback relating to the first behavioral modification method.

7. The information processing apparatus according to claim 1, further comprising a recommendation method storage unit that stores a second behavioral modification method which is recommended to be included in the input data, wherein the feedback generation unit generates feedback relating to the second behavioral modification method.

8. The information processing apparatus according to claim 6, further comprising a recommended method storage unit that stores a second behavior modification method which is recommended to be included in the input data, wherein the feedback generation unit generates feedback relating to the difference between the first behavior modification method and the second behavior modification method.

9. A method comprising: a computer generating one or more feedbacks based on input data; selecting an agent to be used for each feedback from among several agents based on the attributes of each feedback; and outputting the feedback using the selected agent.

10. A computer-readable recording medium that records a program causing a computer to perform the following processes: generating one or more feedbacks based on input data; selecting an agent from among multiple agents to be used for each feedback based on the attributes of that feedback; and outputting the feedback using the selected agent.

Images