Device and method

Abstract

A device according to an exemplary embodiment comprises: a question output unit that outputs a question relating to values; an emotion estimation unit that estimates an emotion of a user when answering the question; an additional question output unit that, if the answer and the emotion of the user are inconsistent with each other, outputs, to the user, an additional question relating to the content of the values in the question; and a value determination unit that acquires the user's values on the basis of the answer obtained when the answer and the emotion of the user are not inconsistent with each other.

Description

Apparatus and method

[0001] The present disclosure relates to an apparatus and method for acquiring a user's values.

[0002] Patent Literature 1 discloses a technology related to an information processing system for acquiring values, in which a survey about values ​​is conducted on employees belonging to an organization such as a company, and the employee's values ​​are acquired based on the results of the survey.

[0003] Patent No. 7278011

[0004] Conventionally, there are known methods for acquiring (understanding) a user's values ​​through questionnaires, etc. However, since responses to questionnaires, etc. tend to be biased toward answers that are considered socially good and avoid answers that are considered socially bad, it has been difficult to acquire the respondent's true values.

[0005] The present disclosure aims to provide an apparatus and method that can easily obtain a user's true values.

[0006] A device according to one aspect of the present disclosure includes a question output unit that outputs a question related to values ​​to a user, a feeling estimation unit that estimates the user's feelings when answering the question, an additional question output unit that, when the content of the answer and the user's feelings are inconsistent with each other, outputs additional questions related to the content of the values ​​in the question to the user until the contradiction between the content of the answer and the user's feelings is resolved, and a value determination unit that acquires the user's values ​​based on the content of the answer when the content of the answer and the user's feelings are not inconsistent with each other.

[0007] According to the above device, additional questions are repeatedly asked until there is no contradiction between the answers to the questions and the user's feelings at the time of the answers, so that the user's true values ​​can be obtained.

[0008] According to one aspect of the present disclosure, it is possible to provide an apparatus and method that can easily obtain a user's true values.

[0009] FIG. 1 is a schematic diagram showing the configuration of an example information processing system. FIG. 2 is a diagram for explaining an example of value information. FIG. 3 is a flowchart showing a method for acquiring value information in an example information processing system. FIG. 4 is a schematic diagram for explaining an example of a method for acquiring value information. FIG. 5 is a schematic diagram illustrating a prompt generated by a question output unit. FIG. 6 is a schematic diagram illustrating a prompt generated by a contradiction determination unit. FIG. 7 is a schematic diagram illustrating a prompt generated by an additional question output unit. FIG. 8 is a schematic diagram illustrating a prompt generated by a value determination unit. FIG. 9 is a diagram showing an example of devices constituting an information processing system.

[0010] Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] 1 is a schematic diagram showing the configuration of an example information processing system. The information processing system 1 is a system for acquiring a user's values. The example information processing system 1 includes a user terminal 3 and an information processing device 10. In this information processing system 1, when a user terminal 3 accesses the information processing device 10, questions for acquiring values ​​are output from the information processing device 10 to the user terminal 3 until information corresponding to the user's true values ​​is acquired from the user.

[0012] Values ​​refer to ways of thinking about things or characteristics that reflect those ways of thinking. For example, values ​​may belong to any of interests, consciousness, personality, cognitive biases, and behavioral characteristics. True values ​​can be defined as not superficial thoughts, but internal thoughts that are likely to actually influence an individual's decision-making, etc.

[0013] The user terminal 3 is configured to be able to access the information processing device 10 via a network including a wireless communication network and a fixed communication network. For example, the user terminal 3 may be a desktop PC, a laptop PC, a smartphone, a tablet terminal, a wearable terminal (e.g., a head-mounted display, smart glasses, etc.), etc. The user terminal 3 is equipped with a display for displaying information input from the information processing device 10.

[0014] The information processing device 10 outputs a question for acquiring values ​​to a user (user terminal 3) who has accessed the information processing device 10, and acquires the user's values ​​based on the answer to the question. The information processing device 10, as an example, includes a question output unit 11, a feeling estimation unit 12, a contradiction determination unit 13, an additional question output unit 15, a value determination unit 16, and a value acquisition unit 17.

[0015] The question output unit 11 outputs a question to the user terminal 3 to acquire the user's values. In one example, the question output unit 11 outputs a question to the user regarding values ​​that have not been acquired by the user at the time of the question. For example, the question output unit 11 accesses a value information database 21 in which value information of each user is stored, and searches for values ​​that have not been acquired from the user. The value information database 21 may be connected to the information processing device 10 via a network including a wireless communication network and a fixed communication network.

[0016] FIG. 2 is a diagram illustrating an example of value information. As shown in FIG. 2, the example of value information includes items indicating values ​​and a user's score for each item. For example, the score is set so that it is higher when the corresponding value is affirmed and lower when the corresponding value is denied. The value information database 21 also stores the meaning of each value listed in the item. The meaning of the value is written in natural language and linked to the corresponding value item. The user's value information is stored in the value information database 21 linked to identification information that identifies the user.

[0017] The question output unit 11 selects a value with a high priority for acquisition from among the values ​​that have not yet been acquired. The priority for acquisition may be set arbitrarily by an administrator or the like. The question output unit 11 acquires the meaning of the selected value from the value information database 21. Then, the question output unit 11 inputs first generation request information including the value item to be acquired and the meaning of the value of the item to the question generation model 22. The first generation request information is a so-called prompt.

[0018] The question generation model 22 generates output data that is a response to input data based on input data transmitted from the information processing device 10. The question generation model 22 may be connected to the information processing device 10 via a network including a wireless communication network and a fixed communication network. The question generation model 22 is a generative artificial intelligence (AI) model that outputs text data corresponding to a prompt generated by the information processing device 10. The generative AI model is a model that, in response to the input of a prompt including input data, generates content according to any one or a combination of instructions, context, question, and output format indicated by the prompt, and outputs the content as output data. The generative AI model may be, for example, an interactive AI model that includes a large language model (LLM) and a user interface (UI) for interaction with a user, enabling text-based or voice-based chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc.

[0019] A prompt is information indicating an instruction or question to a generating AI model. In one example, a prompt may be text data including information indicating an instruction to be executed by the AI ​​model, a task to be executed by the AI ​​model, a background / context to be considered by the AI ​​model (e.g., a role or condition), a question to be answered by the AI ​​model, and an output format of response information from the AI ​​model. Furthermore, input information to be used as the target of an instruction / task to be executed by the AI ​​model may be added to the prompt. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0020] Based on the value items and the meanings of the values ​​of the items, the question output unit 11 generates first generation request information, which is a prompt to be input to the question generation model 22. For example, the question output unit 11 creates the first generation request information by inputting the value items and the meanings of the values ​​of the items into a specified first format for instructing the generation of a question.

[0021] In one example, the first format is composed of a sentence such as, "Please generate a question to ask about the following values. Do you value 'item'? Do you act in a way that values ​​'item'? Note that 'item' means 'meaning'." In this sentence, "item" and "meaning" are defined as variables. The question output unit 11 creates first generation request information by substituting the item of the value to be acquired for "item" in the first format and substituting the meaning of the value for "meaning." The item and meaning of the value may be acquired from the value information database 21.

[0022] The question output unit 11 inputs the created first generation request information to the question generation model 22. The question generation model 22 outputs a response to the input first generation request information (a question for asking about values) to the question output unit 11. The question output unit 11 outputs the question for asking about values ​​generated by the question generation model 22 to the user terminal 3. In the above example of the first format, two questions are generated: one question asking whether the subject values ​​the target, and the other question asking whether the subject is behaving in a way that emphasizes the target values. The question output unit 11 may output one of the two acquired questions to the user terminal 3, and may retain the other as an unoutput question.

[0023] The feeling deduction unit 12 deduces the feeling of the user when answering a question. In one example, the feeling deduction unit 12 may acquire an answer to the question from the user terminal 3 and estimate the feeling of the user when answering. For example, the feeling deduction unit 12 may accept an answer by voice from the user, and in this case, may accept an answer by video of the user including the voice. Furthermore, the feeling deduction unit 12 may accept a video of the user when the user is answering, separately from accepting the answer from the user. For example, the feeling deduction unit 12 may accept an answer by inputting text data such as via chat, and may also accept a video of the user separately from the answer.

[0024] The emotion estimation unit 12 inputs at least one of the user's voice data when the user is answering and video data showing the user's facial expression when the user is answering into the emotion determination model 23, thereby acquiring the user's emotion estimated by the emotion determination model 23. The emotion determination model 23 may be a determination AI model that has learned the relationship between emotion, voice, and facial expression. When at least one of the user's voice and facial expression is input, the emotion determination model 23 outputs a corresponding emotion. For example, the emotion determination model 23 may classify the user's emotion into one of multiple types, such as "positive," "negative," "active," "passive," "anger," and "sadness."

[0025] The contradiction determination unit 13 determines whether the content of the user's answer and the user's emotion are inconsistent with each other. A contradiction means that the content of the user's answer and the emotion of the user at the time of the answer are inconsistent. An example of the contradiction determination unit 13 acquires the content of the user's answer. For example, when the user's answer is input to the information processing device 10 by voice or video, the contradiction determination unit 13 may acquire the content of the answer by converting the voice information included in the user's answer into text data. The voice recognition technology for converting the voice information into text data may be an existing technology. When the user's answer is input to the information processing device 10 as text data, the contradiction determination unit 13 may acquire the input text data as the content of the answer as is.

[0026] The contradiction determination unit 13 inputs second generation request information, including the content of the acquired user's answer and the user's emotion acquired by the emotion estimation unit 12, into the contradiction determination model 25 to determine whether the user's answer and the emotion are contradictory. The contradiction determination model 25 may be, for example, a generative AI model, and outputs an answer corresponding to the instruction indicated by the input prompt. The contradiction determination model 25, for example, may have learned whether the relationship between the answer (context) and the emotion is contradictory. This learning may be reinforcement learning. In the example reinforcement learning, for example, a dataset consisting of an answer and an emotion contradicting the answer, and a dataset consisting of an answer and an emotion consistent with the answer, are used to learn the correspondence between the answer and the emotion.

[0027] The contradiction determination unit 13 creates second generation request information based on the user's answer and emotion. For example, the contradiction determination unit 13 creates the second generation request information by inputting the user's answer and emotion into a specified second format for instructing a determination of whether the user's answer and emotion are contradictory. In one example, the second format is configured with a sentence such as "Please determine whether the 'answer' and the 'emotion' are contradictory." In this sentence, the "answer" and the "emotion" are defined as variables.

[0028] The contradiction determination unit 13 substitutes text data indicating the content of the user's answer into "answer" of the second format, and substitutes the user's emotion acquired by the emotion estimation unit 12 into "emotion." The contradiction determination unit 13 inputs the created second generation request information to the contradiction determination model 25. When the second generation request information is input, the contradiction determination model 25 outputs to the contradiction determination unit 13 whether or not there is a contradiction between the user's answer and the emotion. If there is a contradiction between the user's answer and the emotion, the contradiction determination unit 13 outputs the result to the additional question output unit 15. Furthermore, if there is no contradiction between the user's answer and the emotion, the contradiction determination unit 13 outputs the result to the value determination unit 16.

[0029] When the content of the answer and the user's emotion are inconsistent with each other, the additional question output unit 15 outputs to the user terminal 3 additional questions related to the content of the values ​​in the previous question until the contradiction between the content of the answer and the user's emotion is resolved. When the additional question output unit 15 receives a result from the contradiction determination unit 13 indicating that the user's answer to the question and the emotion are inconsistent, the additional question output unit 15 acquires the value item that is the subject of the question and the meaning of the value of the item. The additional question output unit 15 inputs third generation request information including at least the user's answer and the emotion to the question generation model 22. The additional question output unit 15 generates third generation request information based on the value item that is the subject of the question, the meaning of the value of the item, and the determination result by the contradiction determination unit 13.

[0030] For example, the additional question output unit 15 creates third generation request information by inputting the value item being the subject of the question, the meaning of the value of the item, and the determination result by the contradiction determination unit 13 into a specified third format for instructing the generation of an additional question. In one example, the third format is composed of a sentence such as, "The answer to the question about the value 'item' was contradictory, so please generate a question that delves deeper into the contradiction. The answer to the question was 'answer', and the user's emotion at that time was 'emotion'. Note that 'item' means 'meaning'." In this sentence, "item," "meaning," "answer," and "emotion" are defined as variables. The additional question output unit 15 creates third generation request information by substituting the value item being the subject of the question for "item," the meaning of the value for "meaning," the user's answer for "answer," and the user's emotion for "emotion."

[0031] The additional question output unit 15 inputs the created third generation request information to the question generation model 22. The question generation model 22 outputs a response to the input third generation request information to the additional question output unit 15. The additional question output unit 15 outputs an additional question to inquire about the values ​​generated by the question generation model 22 to the user terminal 3.

[0032] When the content of the user's answer and the user's emotion are consistent with each other, the value determination unit 16 determines information indicating the level of the user's value regarding the target item (hereinafter, "score" is used as an example of this information). In one example, the value determination unit 16 acquires text data indicating the content of the user's answer. For example, the value determination unit 16 may acquire the text data used in the determination by the contradiction determination unit 13.

[0033] The value determination unit 16 determines the user's score for values ​​by inputting fourth generation request information including the content of the acquired user's answer into the value determination model 26. The value determination model 26 may be, for example, a generative AI model, and outputs an answer corresponding to the instruction indicated by the input prompt. In one example, the value determination model 26 may have already learned the criteria for determining the value score for the content of the answer. This learning may be reinforcement learning. In one example of reinforcement learning, for example, the score determination criteria are learned by using a dataset consisting of answers and the value scores corresponding to the answers.

[0034] The value determination unit 16 creates fourth generation request information based on the user's answer. For example, the value determination unit 16 creates the fourth generation request information by inputting the user's answer into a specified fourth format for instructing a determination of a value score based on the user's answer. In one example, the fourth format is configured with a sentence such as "Please output the score for the answer 'Answer' to the question for determining the value of 'Item'."

[0035] The value determination unit 16 substitutes text data indicating the content of the user's answer into "Answer" in the fourth format. The value determination unit 16 inputs the created fourth generation request information to the value determination model 26. When the fourth generation request information is input, the value determination model 26 outputs the user's score for the target value to the value determination unit 16.

[0036] The value acquisition unit 17 stores the user's score for the values ​​determined by the value determination unit 16 in the value information database 21. This updates the contents of the value information database 21. The value acquisition unit 17 may also notify the question output unit 11 that the user's values ​​have been acquired. In this case, the question output unit 11 may determine whether or not a question that has not been output is held. If the question output unit 11 holds a question that has not been output, the question output unit 11 outputs the question that has not been output to the user terminal 3.

[0037] FIG. 3 is a flow chart showing a method for acquiring a user's values ​​in an example information processing system. FIG. 4 is a diagram for explaining a method for acquiring values ​​information, showing an example of an image displayed on a user terminal. In FIG. 4, an example of a flow for acquiring values ​​information is shown in the order of (a), (b), and (c). Note that the values ​​planned to be acquired in the example of FIG. 4 are "Family-oriented (attitude)," which means placing importance on family (home), and "Family-oriented (action)," which means placing importance on actual actions related to family. FIGS. 5 to 8 are schematic diagrams illustrating prompts generated by the information processing device 10.

[0038] In the exemplary process of the information processing system 1, first, the question output unit 11 outputs a question to the user terminal 3 to inquire about values ​​(step S1). For example, if the information processing system 1 provides a virtual space to the user, a non-player character (NPC) placed in the virtual space may be controlled to ask a question about values. In the example shown in FIG. 4 , an animal-themed NPC 55 asks an avatar 51 representing the user a question about the value "family-oriented." In step S1, as shown in FIG. 5 , the question output unit 11 outputs a prompt to the question generation model 22 to generate a question about the value "family-oriented." The prompt in FIG. 5 includes an instruction for the value "family-oriented," which reads, "Please generate a question to inquire about the following values." The prompt includes a prototype of a question to inquire about whether the user values ​​values ​​and a prototype of a question to inquire about whether the user is behaving in a way that values ​​values. The prompt also includes a sentence explaining the meaning of the value "family-oriented": "An attitude or behavior that values ​​family ties and relationships and prioritizes the happiness and interests of family over other considerations."

[0039] The question generation model 22 outputs, as responses to the prompt, a question asking whether the user values ​​values ​​and a question asking whether the user acts in a way that values ​​values ​​to the question output unit 11. The question output unit 11 outputs the acquired questions to the user terminal 3. In FIG. 4 , the question asking whether the user values ​​values ​​("Do you value your family?") is displayed as a line spoken by the NPC 55. Note that the event for acquiring values ​​may be started at any timing set by the administrator.

[0040] Next, in the processing in the information processing system 1, a user's answer is acquired (step S2). The user's answer may be acquired, for example, by the feeling deduction unit 12. For example, when the user's answer is input by voice, the user's voice input to the user terminal 3 is output to the feeling deduction unit 12. At this time, the user terminal 3 may output a video of the user answering to the feeling deduction unit 12.

[0041] Next, in the processing in the information processing system, the feeling deduction unit 12 determines the feeling of the user while answering (Step S3). That is, the feeling deduction unit 12 determines the feeling of the user while answering based on at least one of the acquired voice and video of the user.

[0042] Next, in the processing of the information processing system, the contradiction determination unit 13 determines whether the user's answer and the user's emotion are inconsistent (step S4). That is, the contradiction determination unit 13 converts the user's vocal answer into text data using speech recognition technology and acquires text data indicating the content of the user's answer. This text data may be displayed on the user terminal as a speech bubble of an avatar representing the user (see (a) of FIG. 4). The contradiction determination unit 13 determines whether the user's answer and the user's emotion are inconsistent based on the text data indicating the answer and the user's emotion acquired by the emotion estimation unit 12. In step S4, as shown in FIG. 6, the contradiction determination unit 13 generates a prompt asking whether there is a contradiction between the user's answer and the emotion, and outputs this prompt to the contradiction determination model 25. If it is determined that there is no contradiction in step S4, in the processing of the information processing system 1, the value determination unit 16 determines the user's values ​​(step S5).

[0043] If it is determined in step S4 that there is a contradiction, in the processing of the information processing system 1, the additional question output unit 15 outputs an additional question about the value that was the subject of the previous question (step S6). In the example of FIG. 4 , the user's emotion when the user answers "Of course," is "negative," and the contradiction determination model 25 determines that "Of course" and "negative" are contradictory. Therefore, in this example, as shown in FIG. 7 , the additional question output unit 15 generates a prompt for requesting an additional question, and outputs this prompt to the question generation model 22. When the question generation model 22 generates an additional question such as "Is there something that's bothering you?", the additional question output unit 15 outputs the additional question to the user terminal 3. The additional question may be displayed on the user terminal 3 as a speech bubble of the NPC 55.

[0044] When an additional question is output in step S6, the flow from step S2 to step S4 is repeated for the additional question. In the example of FIG. 4 , the user's answer, "My family is important, but I'm not doing the housework," is acquired, and the emotion "sadness" is acquired for this answer. In this case, the contradiction determination model 25 determines that there is no contradiction between the answer and the emotion, and the user's values ​​are determined (step S5). In step S5, a score for "family-oriented (consciousness)" is determined based on the text data, "My family is important, but I'm not doing the housework." That is, the values ​​determination unit 16 generates a prompt for determining the values ​​score from the consistent answer ( FIG. 8 ), and this prompt is output to the values ​​determination model 26. The score determined by the values ​​determination model 26 is acquired by the values ​​acquisition unit 17 and stored in the values ​​information database 21 (step S7).

[0045] Next, in the processing in the information processing system 1, it is determined whether all values ​​scheduled to be acquired have been acquired (step S8). If all values ​​have been acquired, the processing ends. On the other hand, if there are values ​​that have not been acquired, the question output unit 11 outputs a question regarding the unacquired values ​​to the user terminal 3. In the example of FIG. 4 , since the score for “Family-oriented (behavior)” has not been acquired, the question output unit 11 outputs a question asking about “Family-oriented (behavior)” (step S1), and the processing from step S2 onward is executed. In one example, the question “How much housework and childcare do you do?” is output (step S1), and the answer “About an hour a week. I'm busy at work” is acquired (step S2). In this example, the emotion estimation unit 12 estimates “sadness” as the user's emotion (step S3). Then, by determining that there is no contradiction between the answer and the emotion (step S4), the user's score for “Family-oriented (behavior)” is determined based on “About an hour a week. I'm busy at work” (step S5). The calculated scores are acquired by the value acquisition unit 17 and stored in the value information database 21 (step S7). In step S8, when it is confirmed that all values ​​that were scheduled to be acquired have been acquired, the event ends.

[0046] As described above, the information processing device 10 includes a question output unit 11 that outputs questions related to values ​​to the user, a feeling estimation unit 12 that estimates the user's feelings when answering the questions, an additional question output unit 15 that, when the content of the answer and the user's feelings are inconsistent with each other, outputs additional questions related to the content of the values ​​in the questions to the user until the contradiction between the content of the answer and the user's feelings is resolved, and a value determination unit 16 that estimates the user's values ​​based on the content of the answer when the content of the answer and the user's feelings are not inconsistent with each other.

[0047] The device estimates the user's emotions when answering a question, and if the user's emotions contradict the content of the answer, the device can resolve the contradiction by asking additional questions. This makes it possible to obtain answers that reflect the user's underlying thoughts, actions, etc., rather than the user's superficial answers. Therefore, by determining the user's values ​​from such answers, the user's true values ​​can be obtained.

[0048] The additional question output unit 15 inputs third generation request information including at least the user's answer and emotion to the question generation model 22, which generates an additional question when the content of the answer and the user's emotion are inconsistent with each other. In this configuration, the third generation request information includes the user's answer and emotion, and therefore a natural additional question that is continuous with the content of the user's answer is generated by the question generation model 22. This prevents the user from feeling unnatural.

[0049] The emotion estimation unit 12 estimates the user's emotion based on at least one of the user's voice and facial expression. This allows for more accurate estimation of the user's emotion than when estimating the emotion based on text information or the like. Note that the emotion estimation unit 12 may estimate the user's emotion based on other biometric information of the user in addition to the voice and facial expression. For example, physiological indicators such as the user's heart rate and pupil changes may be detected by the user terminal 3 or a detection device connected to the user terminal 3.

[0050] The question output unit 11 may output the question to the user as a line of an NPC that is at least visually provided to the user. In this configuration, a question about values ​​can be output to the user in a natural manner, allowing the user to answer the question in a relaxed state.

[0051] Note that, in one exemplary embodiment, an example has been shown in which the information processing device 10 is connected to the value information database 21, the question generation model 22, the emotion determination model 23, the contradiction determination model 25, and the value determination model 26 via a network, but the information processing device 10 may be configured to include some or all of the functions of the value information database 21, the question generation model 22, the emotion determination model 23, the contradiction determination model 25, and the value determination model 26. Also, for example, the functions of the information processing device 10, the question generation model 22, the emotion determination model 23, the contradiction determination model 25, and the value determination model 26 may be implemented in the user terminal 3. In this case, the value information database 21 may be implemented in the user terminal 3, or may be connected to the user terminal 3 via a network.

[0052] Although an example is described in which the question generation model 22, contradiction determination model 25, and value determination model 26 are configured using large-scale language models, the question generation model 22, contradiction determination model 25, and value determination model 26 may also be configured using other AI models.

[0053] As an example of value information, a form showing the degree of a user's values ​​as a score has been given, but the value information may also be information that expresses the degree of a user's values ​​in natural language, such as "high" or "low."

[0054] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0055] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0056] For example, the information processing device 10 according to an embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. Fig. 9 is a diagram illustrating an example of a hardware configuration of the information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0057] In the description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0058] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0059] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, each functional block such as the above-mentioned contradiction determination unit 13 may be realized by the processor 1001.

[0060] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the contradiction determination unit 13 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may also be performed for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0061] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be referred to as a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0062] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0063] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0064] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0065] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0066] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0067] Notification of information is not limited to the aspects / embodiments described in this disclosure, and may be performed using other methods.

[0068] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0069] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0070] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0071] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0072] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0073] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0074] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0075] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0076] In addition, terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

[0077] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0078] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0079] The names used for the above parameters are not limiting in any way, and furthermore, the mathematical formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure.

[0080] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like, all of which are considered to be "determining." "Determining" and "determining" may also include resolving, selecting, choosing, establishing, comparing, and the like, all of which are considered to be "determining." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Also, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0081] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0082] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0083] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0084] The "unit" in the configuration of each of the above devices may be replaced with "means," "circuit," "device," etc.

[0085] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0086] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0087] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0088] 10...information processing device (device), 11...question output unit, 12...emotion estimation unit, 15...additional question output unit, 16...value judgment unit, 22...question generation model

Claims

1. A device comprising: a question output unit that outputs a question related to values ​​to a user; a feeling estimation unit that estimates the feeling of the user when answering the question; an additional question output unit that, when the content of the answer and the feeling of the user are inconsistent with each other, outputs additional questions related to the content of the values ​​in the question to the user until the contradiction between the content of the answer and the feeling of the user is resolved; and a value determination unit that estimates the values ​​of the user based on the content of the answer when the content of the answer and the feeling of the user are not inconsistent with each other.

2. The device described in claim 1, wherein the additional question output unit inputs generation request information including at least the user's answer and emotion to a generation AI model that generates the additional question when the content of the answer and the user's emotion are mutually contradictory.

3. The device according to claim 1, wherein the emotion estimation unit estimates the emotion of the user based on biometric information of the user.

4. The device according to claim 1, wherein the question output unit outputs the question to the user as dialogue of a non-player character that is at least visually presented to the user.

5. A method comprising the steps of: outputting a question related to values ​​to a user; acquiring an answer from the user to the question; acquiring the user's emotion estimated based on the state of the user when providing the answer to the question; and, if the content of the answer and the user's emotion are inconsistent with each other, outputting additional questions related to the values ​​to the user until the inconsistency between the content of the answer and the user's emotion is resolved.

Images