Information output device, information output method, and program

Abstract

Efficiently make available consistent information based on information regarding an individual's self - awareness. 【Solution means】The information output device 1 includes: a response acquisition unit 141 that acquires responses to a plurality of questions regarding the user's way of thinking, which are responses by the user; an input information acquisition unit 143 that acquires input information for inputting into a predetermined large - scale language model based on the acquisition result of the response acquisition unit 141; a generated information acquisition unit 145 that acquires generated information generated by inputting the input information into the large - scale language model and that can relate to the user's self - awareness; a self - awareness information acquisition unit 147 that acquires self - awareness information indicating the user's self - awareness based on the generated information; and an output unit 149 that outputs output information based on the self - awareness information.

Description

Technical Field

[0001] This invention relates to an information output device, an information output method, and a program capable of outputting information based on information regarding an individual's self - awareness.

Background Art

[0002] For example, in job - matching scenarios such as personnel transfers, recruitment activities, and job - hunting activities, and in the consideration of individually - applied training programs, it is required to make decisions or provide support while taking into account an individual's characteristics so as to obtain high effectiveness in light of the objectives. Conventionally, various methods for promoting self - analysis and self - awareness have been proposed to clarify and visualize an individual's characteristics. Such methods include, for example, methods of verbalizing an individual's self - analysis and self - awareness through interpersonal sessions or multiple workshops.

[0003] Note that, for example, Patent Document 1 below discloses a configuration of a support system in which the orientation of a learner's learning motivation is determined based on the answers of the learner to be trained, and information is presented based on the orientation.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] By the way, when adopting a method of verbalizing an individual's self - analysis and self - awareness through interpersonal sessions or multiple workshops as described above, there is a problem that it requires a large amount of labor of the relevant parties. In addition, there is a problem that variations may occur in the results depending on the experience and skills of the persons in charge (coaches, advisors, etc.) who are in charge of the interpersonal sessions and workshops.

[0006] The present invention aims to provide an information output device, an information output method, and a program that can efficiently make available consistent information based on information related to an individual's self-awareness.

Means for Solving the Problems

[0007] An information output device according to an aspect of the present invention includes: a response acquisition unit that acquires responses to a plurality of questions regarding a user's way of thinking, which are responses by the user; an input information acquisition unit that acquires input information for inputting to a predetermined large language model based on the acquisition result of the response acquisition unit; a generated information acquisition unit that acquires generated information generated by inputting the input information to the large language model and that can relate to the user's self-awareness; a self-awareness information acquisition unit that acquires self-awareness information indicating the user's self-awareness based on the generated information; and an output unit that outputs output information based on the self-awareness information.

Effects of the Invention

[0008] According to the present invention, it is possible to efficiently make available consistent information based on information related to an individual's self-awareness.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments of an information output device and the like will be described with reference to the drawings.

[0011] FIG. 1 is a diagram showing a schematic configuration of a computer system Z in an embodiment.

[0012] The computer system Z shown in the figure can be regarded as a configuration example of a computer that realizes devices and the like according to the embodiment. The functions of each device and the like according to the embodiment can be realized by the hardware of the computer system Z and the programs executed by it.

[0013] The computer system Z includes, for example, a general computer Z1, an input device Z2 such as a keyboard and a mouse, and a display Z3. The computer Z1 can include, for example, a storage device Z11 (such as an optical disk drive, HDD, SSD, ROM, RAM, etc.) in which programs and data read during its execution are stored, a communication module Z13 (such as a network card, etc.) for communicating with external devices, a control device Z14 such as a CPU, etc., and can be of a general configuration such as a personal computer or a server device, but is not limited thereto.

[0014] The program Z12 that causes the computer system Z to execute various functions may be stored in the storage device Z11. The process by which the program Z12 is stored in the storage device Z11 is not relevant. The program Z12 may be pre-stored in the storage device Z11, or a medium pre-storing the program Z12 may be read by the storage device Z11, or the program Z12 obtained through a network or the like may be temporarily stored in the storage device Z11. The program Z12 may include only instructions that appropriately call functions to obtain a desired result.

[0015] The terms used hereinafter are generally defined as follows. Note that the semantic meanings of these terms should not always be interpreted as shown here, and for example, when individually explained hereinafter, they should be interpreted in consideration of that explanation.

[0016] A user refers to an individual who uses an information output device. The user may be referred to as the target person regarding the output information described later, or as the subject. It can be said that the user is the target person attracting attention in services or the like realized using this information output device. The user may include a wide range of people who want to deepen self-understanding or engage in career development, such as employees of a company, students, job seekers, etc.

[0017] A question regarding the user's way of thinking refers to a question that asks about the user's values, past experiences, future orientation, strengths, weaknesses, etc. The question can be composed of a multiple-choice type, a descriptive type, or a combination thereof.

[0018] An answer is information input or selected by the user in response to a question. The answer is expressed in text, numerical value, or other forms.

[0019] A large language model is a deep learning model capable of executing natural language processing tasks and refers to one that has been trained from a large amount of text data.

[0020] Input information refers to the information input to the large language model. The input information may be, for example, an instruction (prompt), or may be information for input to the large language model together with a predetermined instruction. As will be described later, in the present embodiment, the input information refers to the information necessary for generating generation information related to self-awareness. The input information may be information such as a sentence formatted based on the user's answer, or may be the answer itself.

[0021] Generation information refers to the information output by the large language model based on the input information. In the present embodiment, the generation information may be said to be information related to the user's self-awareness. In the present embodiment, the generation information may be information expressing the user's values, strengths, weaknesses, future goals, etc. In the present embodiment, the generation information may be said to be candidate information that is a candidate for self-awareness information.

[0022] Self-awareness information refers to information indicating the user's self-awareness, and may include, for example, information such as the user's values, strengths, weaknesses, future goals, etc. The user's self-awareness may be rephrased as the user's identity, or may be rephrased as the user's internal guidelines, the user's core, the user's purpose, the user's mission.

[0023] In this embodiment, the self-recognition information is obtained based on specific information. The specific information is information corresponding to candidate information or information in the form of character expressions input by the user. When there are two or more pieces of candidate information, the specific information can include information for selecting one or more of the two or more pieces of candidate information or information in the form of character expressions corresponding to one or more of the two or more pieces of candidate information. The specific information may be, for example, information indicating the content selected, modified, or edited by the user regarding the candidate information, or information newly created by the user regarding self-recognition. Here, newly creating means creating without relying on the candidate information. For example, that is to say, the self-recognition information may be obtained by the user selecting, modifying, or editing based on the candidate information which is generated information, or may be obtained by the user newly creating. Since the specific information can more accurately reflect the user's self-recognition, appropriate self-recognition information can be obtained based on the specific information. Note that the generated information may be directly treated as self-recognition information.

[0024] The output information is information output by the information output device to the user. The output information may be the self-recognition information itself, or information including the self-recognition information and other information, or recommendation information or information including the same. The recommendation information refers to information related to themes such as educational methods, job information, and lifestyles based on the user's self-recognition information. The recommendation information can be information representing matters that are likely to match the user's interests, goals, etc. The output information can be, for example, information useful for deepening the user's self-understanding or for use in the user's career development. Note that in this embodiment, job hunting (or seeking employment) is not limited to that related to full-time employees, and may be related to part-time or side jobs. Also, it is not limited to that related to paid work, and may be targeted at volunteer activities, etc.

[0025] Learning information is information that has learned the relationship between the user's self-awareness information and the recommendation information based on it. The learning information is generated or updated by a machine learning model, for example, based on a known method, but is not limited to this.

[0026] User information is information about the user and includes attribute values related to the user's attributes. The user information may include, for example, information other than the user's self-awareness information, such as information related to the user's behavior history and interests. Such user information can be utilized to improve the accuracy of the recommendation information obtained using the self-awareness information. Note that the user information may include self-awareness information and output information based on it. The user information can be handled in association with the user, that is, in association with an identifier that identifies the user.

[0027] The formatting process is a process of processing the user's answer into a form that is easy for the large language model to understand. The formatting process may include, for example, adjusting the context, correcting spelling and grammar errors, deleting unnecessary information, etc. It may also be a process of formatting a sentence using an existing template and information based on the answer.

[0028] Obtaining includes obtaining the input matter and obtaining information stored in other devices. It may also include obtaining information in a format different from the original information based on the original information. Also, for obtaining information, a so-called known machine learning method may be used. That is, learning information configured to take a specific type of information as input and output the type of information to be obtained can be configured using a machine learning method, and the information to be input to the learning information can be applied to obtain the type of information to be output.

[0029] Regarding information, output refers to display by a display means, printing by a printing means, transmission to an external device, recording on a recording medium, delivery of a processing result to another device or another program, etc.

[0030] Receiving information means receiving information input from an input device, receiving information transmitted from another device or the like, reading information from a recording medium, and the like.

[0031] In the present embodiment, the information output device is configured to use the generated information generated using a large language model based on the answers to a plurality of questions regarding the user's way of thinking, and acquire self - recognition information indicating the user's self - recognition.

[0032] FIG. 2 is a diagram showing an overview of the information processing system 100 in the present embodiment.

[0033] The information processing system 100 includes an information output device 1, an external device 2, and a user terminal device 3 that can be used by a user. The information output device 1 and the external device 2 can communicate with each other through a network or the like. Also, the information output device 1 and the user terminal device 3 can communicate with each other through a network or the like.

[0034] The external device 2 is configured to be able to output information acquired based on the received information to a specific device, for example, using a large language model 211. The external device 2 is, for example, a general - purpose server device, and the large language model 211 is stored in its storage unit 21. The configuration of the external device 2 is not limited to this, and various configurations capable of providing its functions can be adopted as the external device 2 or a substitute therefor.

[0035] The user terminal device 3 is, for example, a general - purpose smartphone, tablet terminal, personal computer, or the like. The user terminal device 3 is configured to display a screen based on the information transmitted from the information output device 1 on a predetermined application (including a web browser) that operates thereby, and receive information input by the user. The received information can be transmitted to the information output device 1.

[0036] FIG. 3 is a block diagram showing a schematic configuration of the information output device 1.

[0037] The information output device 1 is, for example, a server device. The information output device 1 includes a storage unit 11, a reception unit 12, a communication unit 13, a processing unit 14, and the like.

[0038] Various types of information are stored in the storage unit 11. The storage unit 11 is configured using, for example, a storage device Z11. The storage unit 11 includes a user information storage unit 111 and a learning information storage unit 115.

[0039] In the user information storage unit 111, user information of individual users is stored in association with those users. The process by which the user information is accumulated in the user information storage unit 111 is not questioned.

[0040] In the present embodiment, in the user information storage unit 111, answers to each of a plurality of questions regarding the way of thinking of the user are stored for each user.

[0041] Learning information is stored in the learning information storage unit 115. The learning information is configured using, for example, a combination of self - recognition information and recommendation information obtained or applied to a plurality of users. Note that the learning information may be further configured using other user information of the self - recognition information.

[0042] The reception unit 12 receives information input to the information output device 1. The received information can be accumulated in the storage unit 11, for example.

[0043] The communication unit 13 is configured using, for example, the above - mentioned communication module or the like. Information can be transmitted and received between the communication unit 13 and an external device.

[0044] The processing unit 14 controls the operations of each part of the information output device 1. The processing unit 14 executes various functions by executing a program or the like. In the present embodiment, the processing unit 14 includes an answer acquisition unit 141, an input information acquisition unit 143, a generated information acquisition unit 145, a self - recognition information acquisition unit 147, an output unit 149, and a learning information update unit 151, and the like.

[0045] The response acquisition unit 141 acquires responses to each of a plurality of questions regarding the user's way of thinking, which are responses by the user. The response acquisition unit 141 acquires each response stored in the user information storage unit 111, for example, in association with each user.

[0046] Note that the response acquisition unit 141 may also transmit a plurality of questions to the user's user terminal device 3, accumulate the content of the responses given by the user to the questions using the user terminal device 3 in the user information storage unit 111, and acquire the accumulated responses. Further, responses collected in various ways in advance and accumulated in the user information storage unit 111 in association with the user may be acquired.

[0047] Based on the acquisition result of the response acquisition unit 141, the input information acquisition unit 143 acquires input information for inputting to a predetermined large language model 211. The input information acquisition unit 143 is configured to acquire input information for obtaining generated information as described later using the large language model 211. In the present embodiment, the input information acquisition unit 143 may be configured to acquire input information by performing formatting processing to format a sentence using the responses to one or more questions selected in advance from among the plurality of questions. Note that the present invention is not limited to this, and the input information acquisition unit 143 may be configured to acquire input information using the responses to any one or more questions among the plurality of questions. It may also be configured to acquire input information using the responses to each of all the questions.

[0048] The generated information acquisition unit 145 acquires generated information generated by inputting the input information to the large language model 211 and regarding the user's self - awareness. In the present embodiment, the generated information acquisition unit 145 is configured to output the input information to the external device 2 and acquire the generated information output from the external device 2.

[0049] In addition, in the present embodiment, the generation information acquisition unit 145 is configured to acquire two or more pieces of generation information. Since the input information acquisition unit 143 is configured to be able to acquire two or more pieces of generation information, the generation information acquisition unit 145 may acquire two or more pieces of generation information. Further, the generation information acquisition unit 145 may acquire two or more pieces of generation information by repeating the acquisition of one or more pieces of generation information two or more times. The acquired generation information is used as candidate information as described later.

[0050] The self-recognition information acquisition unit 147 acquires self-recognition information indicating the self-recognition of the user based on the generation information. The self-recognition information acquisition unit 147 may acquire the generation information acquired by the generation information acquisition unit 145 as self-recognition information. In this case, when two or more pieces of generation information are acquired, any one or more pieces of generation information may be acquired as self-recognition information, or a process such as shaping for any two or more pieces of generation information may be performed and then acquired as self-recognition information.

[0051] In this embodiment, the self - recognition information acquisition unit 147 is configured to output the generated information to the user as candidate information and output reception information for receiving the input of specific information by the user in response to the output of the candidate information. When two or more pieces of generated information are acquired, the self - recognition information acquisition unit 147 outputs two or more pieces of candidate information corresponding to each of the two or more pieces of generated information and the reception information to the user terminal device 3. The reception information is, for example, information for causing the user terminal device 3 to display a screen for receiving the input of specific information, but is not limited thereto. When the candidate information and the reception information are output to the user terminal device 3, the user can input specific information using the user terminal device 3. That is, the user can input specific information using the reception information. When the specific information input by the user using the reception information is transmitted to the information output device 1, the self - recognition information acquisition unit 147 acquires self - recognition information based on the specific information. For example, when the specific information is information for selecting one or more of the candidate information, the self - recognition information acquisition unit 147 can acquire the selected candidate information as self - recognition information. Also, when the specific information is information of a character expression newly input by the user, the self - recognition information acquisition unit 147 can acquire the input specific information as self - recognition information.

[0052] The output unit 149 outputs output information based on the self - recognition information. When the output unit 149 outputs the self - recognition information itself or information including the self - recognition information and other information as the output information, the output user's self - recognition information can be used.

[0053] In this embodiment, the output unit 149 may output recommendation information or information including the same as the output information. For example, by outputting recommendation information representing matters highly likely to match the user's interests, goals, etc., the user and those related to the user can refer to it when making decisions or judgments about various matters related to the user. The output information can be, for example, information useful for deepening the user's self - understanding or for use in the user's career development.

[0054] Incidentally, the output unit 149 may be configured to obtain recommendation information regarding a predetermined theme recommended to the user using, for example, self - recognition information and predetermined learning information, and output the obtained recommendation information as output information. The predetermined theme is, for example, at least one of an educational method applicable to the user, a job applicable to the user, a job seeker who can be matched with the user, and a lifestyle applicable to the user. Here, the lifestyle may be regarded as, for example, referring to matters related to the balance between the user's work and private life, health management, hobbies, and enrichment of leisure time. For example, the recommendation information may be working hours, a suitable volunteer activity, etc.

[0055] In this case, the learning information can be information configured by a machine learning method so as to be, for example, information for inputting self - recognition information and information for outputting a score used for recommendations regarding a predetermined theme.

[0056] Incidentally, in this case, correspondence information in which self - recognition information and a score used for recommendations regarding a predetermined theme are associated with each other and configured to be able to specify the score based on the self - recognition information may be used as the learning information.

[0057] The output of the output information can be, for example, transmission to the user's user terminal device 3, storage in a storage unit 11 or the like for making it analyzable in combination with the output information of other users or viewable by the user's relatives, or display on a display device or the like. As a result, the user or their relatives can use the output information.

[0058] Note that in this embodiment, the learning information may be updated by a method such as re-learning. In this case, for example, the learning information update unit 151 acquires the output information output by the output unit 149 for the user in the past and the user information obtained regarding the user thereafter. Then, the learning information update unit 151 executes re-learning of the learning information based on the acquired information. The re-learning can be performed by a known method. By doing so, it becomes possible to output recommendation information with higher accuracy.

[0059] Next, the operation flow of the information output device 1 will be described.

[0060] FIG. 4 is a flowchart showing an example of the operation of the information output device 1.

[0061] The information output device 1 starts acquiring the user's self-recognition information. The processing unit 14 uses the answer acquisition unit 141 to acquire answers to a plurality of questions regarding the user's way of thinking (step S11). The acquired answers are stored in the user information storage unit 111.

[0062] Next, the input information acquisition unit 143 formats the input information based on the answers and transmits the formatted input information to the external device 2 by the communication unit 13 (step S12). Then, the large language model 211 of the external device 2 generates generated information based on the input information and transmits the generated information to the information output device 1.

[0063] The generated information acquisition unit 145 acquires the generated information transmitted from the external device 2 (step S13).

[0064] The self-recognition information acquisition unit 147 transmits candidate information and reception information to the user terminal device 3 in order to receive the input of specific information by the user (step S14).

[0065] The self - recognition information acquisition unit 147 determines whether specific information input by the user has been received (step S15). When the user inputs specific information using the user terminal device 3, the specific information is transmitted to the information output device 1. Then, the self - recognition information acquisition unit 147 determines that the specific information has been received and proceeds to the next step (YES).

[0066] The self - recognition information acquisition unit 147 acquires self - recognition information based on the specific information (step S16).

[0067] The output unit 149 outputs output information based on the self - recognition information (step S17). The output unit 149 transmits the output information to the user terminal device 3, for example. Then, a series of processes is completed.

[0068] By outputting the output information based on the self - recognition information in this way, information regarding the user's self - recognition becomes available.

[0069] Next, a specific example of this embodiment will be described. In this example, for example, a method by which a user obtains output information based on self - recognition information through online personal work will be described.

[0070] In the specific example, the user first accesses the information output device 1 using the user terminal device 3 and performs personal work of answering questions online. The work is composed of, for example, a first half that requests a selective answer and a second half that requests a descriptive answer.

[0071] FIG. 5 is a first diagram for explaining an example of the work in the specific example of this embodiment. FIG. 6 is a second diagram for explaining an example of the work in the specific example of this embodiment.

[0072] In the first half of the work, for example, users are required to engage with questions such as "Self - evaluation" (S51) regarding self - evaluation, "Life cycle" (S52) regarding the evaluation of one's past life, and "SDGs" (S53) regarding the areas of social issues one is interested in. Specifically, they are as follows, for example.

[0073] Regarding self - evaluation, self - score on the top 5 notable qualities required for recruitment from a corporate perspective. Users input scores for items such as communication skills and initiative, for example.

[0074] Regarding the life cycle, divide life into 8 areas regarding one's current and future self, and self - score the ideal and the reality. The areas can be divided into, for example, work and career, physical environment, play and leisure, learning and self - improvement, human relationships, family and partner, health, money and economy, etc. Users input the current score regarding the level of fulfillment and satisfaction and the ideal score for each area.

[0075] Regarding SDGs, seek the selection of SDGs that one is interested in or concerned about. Users select up to 4 SDG items, for example.

[0076] In the second half of the work, for example, users are required to engage with questions such as "Past experiences" (S54) regarding past experiences, "Will Can Must" (S55) regarding future goals, etc., and "Factor analysis" (S56) regarding the factors related to happiness. Specifically, they are as follows, for example.

[0077] Regarding past experiences, users look back on past impressive events and confirm their desires at that time. Users describe their past experiences. Also, users describe or input, for example, their desires for themselves and for others at that time. Multiple responses are allowed.

[0078] Regarding Will, Can, and Must, confirm your goals, strengths, and requirements from the present to the future. The user describes what they want to do, what they are good at, and what is required of them. For example, for what they want to do, they may describe it separately at the daily level, life level, and life level.

[0079] Regarding factor analysis, for example, confirm each factor such as the first factor (self-actualization and growth factor; let's try it factor), the second factor (connection and gratitude factor; thank you factor), the third factor (positive and optimistic factor; it'll work out factor), and the fourth factor (independence and authenticity factor; as you are factor). The user describes in their own way what matters are included in each factor.

[0080] When the user finishes working on these personal tasks, the user's answers to the questions are stored in the storage unit 11. The information output device 1 performs formatting processing using the answers at a predetermined timing and transmits the input information based on the answers to the large language model 211. The input information is, for example, a text with the answer content appropriately incorporated, but is not limited to this. Such a text is generated according to a template text, for example, but the input information itself may be generated using a large language model 211 or the like.

[0081] When the information output device 1 acquires the generated information output by the large language model 211, the candidate information can be sent to the user terminal device 3. The user uses the user terminal device 3 to input specific information for acquiring self-awareness information while appropriately using the candidate information.

[0082] FIG. 7 is a diagram for explaining an example of a method for inputting specific information in a specific example of the present embodiment.

[0083] The reception of the specific information can be performed, for example, on the specific information input screen 411 displayed on the user terminal device 3 (S61). On the specific information input screen 411, for example, the user can input specific information corresponding to the self-recognition information that the user thinks in the input field 422. That is, in this example, the user can input self-recognition information without using candidate information.

[0084] The specific information input screen 411 is provided with, for example, a display button 412 for displaying candidate information. When the user operates the display button 412, the display area 423 of the candidate information based on the answer is displayed on the screen (S62). Note that regardless of the operation timing of the display button 412, the candidate information may be acquired and displayed in advance or at a predetermined timing, or the candidate information may be displayed by outputting the input information to the large language model 211 by operating the display button 412.

[0085] For example, a plurality of examples of self-recognition information candidates and the reasons why the candidates are displayed are displayed together. The user can input specific information with reference to the displayed candidates. In the example shown in the figure, by selecting a candidate to be used for inputting specific information, the selected candidate can be transferred to the input field 422 as specific information (from S62 to S63). Thereby, the user can easily input specific information based on the selected candidate information.

[0086] When the specific information is input, the information output device 1 acquires self-recognition information based on the specific information and outputs output information. The output information can be output in various modes as described above. In this example, for example, information on a training program recommended for a user who is an employee is output as the output information.

[0087] FIG. 8 is a diagram for explaining an example of output information in a specific example of the present embodiment.

[0088] On the output information display screen 441 of the user terminal device 3, the output information is displayed. The output information includes, for example, the self-recognition information obtained about the user as described above, and the recommendation information regarding the content of the training program obtained based on the self-recognition information. In this way, since the recommendation information recommended for the user based on the self-recognition information is displayed, the user and their related parties can know the information about the training program that can be expected to be highly effective when applied to the user. In this example, the reasons for recommendation and the like are included according to the recommendation information. The reasons for recommendation may be displayed, for example, based on a predetermined set of phrases, or may be displayed, for example, as the content output by the large language model 211 using the self-recognition information and the recommendation information. By displaying the reasons for recommendation, it is expected that the user and their related parties can be made to have a high level of acceptance.

[0089] As described above, according to this embodiment, by using the information output device 1, it is possible to efficiently obtain and make available the information regarding an individual's self-recognition according to the user's answers and input content. Compared with the case of repeatedly holding face-to-face sessions or workshops as in the prior art, it is possible to obtain self-recognition information and output corresponding information in a short time. Also, compared with the prior art, the number of scenes where manual evaluation, advice, etc. are performed can be reduced, so that consistent identification of self-recognition information can be performed. Finally, since self-recognition information based on the specific information by the user can be obtained, it is expected that self-recognition information highly adapted to the characteristics of the user can be made available.

[0090] The processing in this embodiment may be realized by a program as follows. The program is executed by the computer of the information output device 1, and the computer is made to function as a response acquisition unit that acquires responses to a plurality of questions regarding the user's way of thinking, which are responses by the user; an input information acquisition unit that acquires input information for inputting into a predetermined large language model based on the acquisition result of the response acquisition unit; a generation information acquisition unit that acquires generation information generated by inputting the input information into the large language model and that may relate to the user's self-awareness; a self-awareness information acquisition unit that acquires self-awareness information indicating the user's self-awareness based on the generation information; and an output unit that outputs output information based on the self-awareness information.

[0091] In the above embodiment, each component may be configured by dedicated hardware or may be realized by software. In the case of software, it is realized by executing a program, and each component functions when the CPU executes a program recorded on a recording medium such as a hard disk or a semiconductor memory. The program may be executed while accessing a storage unit or a recording medium, and may also be executed by being downloaded from a server or read from a recording medium such as an optical disk. Further, this program may be used as a program product, and is executed by one or more computers, and centralized processing or distributed processing is performed.

[0092] Each process and function can be realized by being centrally processed by a single device (system) or being distributedly processed by a plurality of devices. In this case, it is possible to recognize the entire system composed of a plurality of devices performing distributed processing as one "device". Also, two or more components existing in one device can also be realized physically by one medium.

[0093] Note that the present invention is not limited to the above embodiments, and various modifications are possible, and those are also included in the scope of the present invention. For example, some of the components and functions in the above-described embodiments may be omitted.

[0094] The above large language model does not have to be provided by an external device. The storage location of the large language model is not limited to the above. For example, it may be stored inside the information output device, and the input information to the large language model and the acquisition of the generated information may be appropriately performed by the processing unit.

[0095] Note that the above embodiments can be expressed as follows.

[0096] The information output device according to the first configuration aspect includes a response acquisition unit that acquires responses from a user for each of a plurality of questions regarding the user's way of thinking, an input information acquisition unit that acquires input information for inputting to a predetermined large language model based on the acquisition result of the response acquisition unit, a generated information acquisition unit that acquires generated information generated by inputting the input information to the large language model and that can relate to the user's self-awareness, a self-awareness information acquisition unit that acquires self-awareness information indicating the user's self-awareness based on the generated information, and an output unit that outputs output information based on the self-awareness information.

[0097] Further, in the information output device according to the second configuration aspect, with respect to the first configuration aspect, the self-awareness information acquisition unit is configured to output the generated information to the user as candidate information and output reception information for receiving input of specific information by the user in response to the output of the candidate information, and acquire self-awareness information based on the specific information input by the user using the reception information.

[0098] Further, in the information output device according to the third configuration aspect, with respect to the second configuration aspect, the generated information acquisition unit acquires two or more pieces of generated information, the self-awareness information acquisition unit is configured to output two or more pieces of candidate information corresponding to each of the two or more pieces of generated information, and the specific information includes information that is information for selecting one or more of the two or more pieces of candidate information or information that is a character expression corresponding to one or more of the two or more pieces of candidate information.

[0099] Further, the information output device according to the fourth configuration aspect is an information output device in which, with respect to the second configuration aspect, the specific information is information that is information corresponding to the candidate information or information in the character expression input by the user.

[0100] Further, the information output device according to the fifth configuration aspect is an information output device in which, with respect to the first configuration aspect, the input information acquisition unit is configured to perform a shaping process of shaping a sentence using answers to one or more questions selected in advance from a plurality of questions.

[0101] Further, the information output device according to the sixth configuration aspect is an information output device in which, with respect to the first configuration aspect, the output unit acquires recommendation information regarding a predetermined theme recommended to the user using the self - recognition information and predetermined learning information, and is configured to output the acquired recommendation information as output information, and the predetermined theme is at least one of an educational method applicable to the user, a job applicable to the user, a job seeker matchable with the user, and a lifestyle applicable to the user.

[0102] Further, the information output device according to the seventh configuration aspect is an information output device in which, with respect to the sixth configuration aspect, the learning information is at least one of information configured by a machine learning method to be information for inputting self - recognition information and outputting a score used for recommendation regarding a predetermined theme, and correspondence information in which the self - recognition information and the score are associated.

[0103] Further, the information output device according to the eighth configuration aspect is an information output device in which, with respect to the sixth configuration aspect, the learning information update unit is provided, which acquires the output information output by the output unit regarding the user in the past and the user information obtained regarding the user thereafter, and executes a process of updating the learning information based on the acquired information.

Explanation of Reference Numerals

[0104] 1 Information output device 2 External device 11 Storage unit 12 Reception section 13 Communication section 14 Processing section 21 Storage section 100 Information processing system 111 User information 115 Learning information storage section 141 Answer acquisition section 143 Input information acquisition section 145 Generated information acquisition section 147 Self - recognition information acquisition section 149 Output section 151 Learning information update section 211 Large language model

Claims

1. An answer acquisition unit that acquires answers to a plurality of questions regarding the user's way of thinking, which are answers given by the user; An input information acquisition unit that acquires input information for inputting into a predetermined large language model based on the acquisition result of the answer acquisition unit; A generated information acquisition unit that acquires generated information generated by inputting the input information into the large language model and that may relate to the user's self-awareness; A self-awareness information acquisition unit that acquires self-awareness information indicating the user's self-awareness based on the generated information; An output unit that outputs output information based on the self-awareness information, wherein the self-awareness information acquisition unit is configured to output the generated information as candidate information to the user and output reception information for receiving input of specific information by the user in response to the output of the candidate information, acquire the self-awareness information based on the specific information input by the user using the reception information, furthermore, the generated information acquisition unit acquires two or more pieces of the generated information, the self-awareness information acquisition unit is configured to output two or more pieces of candidate information corresponding to each of the two or more pieces of the generated information, and the specific information includes information for selecting one or more of the two or more pieces of candidate information or information that is a character expression corresponding to one or more of the two or more pieces of candidate information. An information output device.

2. The information output device according to claim 1, wherein the specific information is information that is information corresponding to the candidate information or information that is a character expression input by the user.

3. The information output device according to claim 1, wherein the input information acquisition unit is configured to perform formatting processing for formatting a sentence using answers to one or more questions selected in advance from the plurality of questions.

4. The output unit is configured to acquire recommendation information regarding a predetermined theme to be recommended to the user using the self-awareness information and predetermined learning information, and output the acquired recommendation information as the output information, wherein the predetermined theme is at least one of an educational method applicable to the user, a job applicable to the user, a job seeker who can be matched with the user, and a lifestyle applicable to the user. The information output device according to claim 1.

5. A learning information update unit that acquires output information output by the output unit for the user in the past and user information obtained for the user thereafter, and executes a process of updating the learning information based on the acquired information. The information output device according to claim 4.

6. An information output method executed by an information output device including a response acquisition unit, an input information acquisition unit, a generated information acquisition unit, a self-recognition information acquisition unit, and an output unit, A response acquisition step in which the response acquisition unit acquires responses to each of a plurality of questions regarding the user's way of thinking, which are responses by the user, An input information acquisition step in which the input information acquisition unit acquires input information for inputting to a predetermined large language model based on the acquisition result of the response acquisition step, A generated information acquisition step in which the generated information acquisition unit acquires generated information generated by inputting the input information to the large language model and related to the user's self-recognition, A self-recognition information acquisition step in which the self-recognition information acquisition unit acquires self-recognition information indicating the user's self-recognition based on the generated information, An output step in which the output unit outputs output information based on the self-recognition information, The self-recognition information acquisition step includes: Outputting the generated information as candidate information to the user and outputting reception information for receiving input of specific information by the user in response to the output of the candidate information, Acquiring the self-recognition information based on the specific information input by the user using the reception information, Furthermore, in the generated information acquisition step, two or more pieces of the generated information are acquired, In the self-recognition information acquisition step, two or more pieces of candidate information corresponding to each of the two or more pieces of the generated information are output, The specific information includes information for selecting one or more of the two or more pieces of candidate information or information that is a character expression corresponding to one or more of the two or more pieces of candidate information. Information output method.

7. A computer, A response acquisition unit that acquires responses to each of a plurality of questions regarding the user's way of thinking, which are responses by the user, An input information acquisition unit that acquires input information for inputting to a predetermined large language model based on the acquisition result of the response acquisition unit, A generated information acquisition unit that acquires generated information generated by inputting the input information into the large language model and that can relate to the user's self-awareness; A self-awareness information acquisition unit that acquires self-awareness information indicating the user's self-awareness based on the generated information; An output unit that outputs output information based on the self-awareness information, and functions as such; The self-awareness information acquisition unit: Outputs the generated information as candidate information to the user and outputs reception information for receiving input of specific information by the user in response to the output of the candidate information; Acquires the self-awareness information based on the specific information input by the user using the reception information; Furthermore, the generated information acquisition unit acquires two or more pieces of the generated information; The self-awareness information acquisition unit outputs two or more pieces of candidate information corresponding to each of the two or more pieces of the generated information; The specific information includes information for selecting one or more of the two or more pieces of candidate information or information that is a character expression corresponding to one or more of the two or more pieces of candidate information. A program.

Images