Information output apparatus, information output method, and program

Abstract

To efficiently use consistent information based on information on personal self-recognition.SOLUTION: The information output apparatus 1 includes an answer acquisition unit 141 that acquires an answer from a user to each of a plurality of questions about the user's way of thinking, an input information acquisition unit 143 that acquires input information to be input to a predetermined large scale language model based on an acquisition result of the answer acquisition unit 141, a generated information acquisition unit 145 that acquires generated information generated by inputting the input information to the large scale language model and related 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.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information output device, an information output method, and a program that can output information based on information related to an individual's self-awareness. [Background technology]

[0002] For example, in job matching situations such as personnel transfers, recruitment activities, and job searches, and in considering individually tailored training programs, it is necessary to take into account individual characteristics and make decisions and provide support to ensure that the program is highly effective in light of the objectives. To clarify and visualize individual characteristics, various methods have been proposed to promote self-analysis and self-awareness. Such methods include, for example, verbalizing an individual's self-analysis and self-awareness through interpersonal sessions or multiple workshops.

[0003] For example, Patent Document 1 listed below discloses the configuration of a support system that determines the learning motivation inclination of a trainee based on the trainee's answers and presents information based on the inclination. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2024-048513 Summary of the Invention [Problem to be solved by the invention]

[0005] However, when using the above-mentioned method of verbalizing an individual's self-analysis and self-awareness through in-person sessions or multiple workshops, there is a problem that it requires a lot of man-hours for those involved. Also, there is a problem that the results may vary depending on the experience and skills of the person in charge of the in-person sessions or workshops (coaches, advisors, etc.).

[0006] An object of the present invention is 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 problem]

[0007] An information output device according to one aspect of the present invention is an information output device comprising: an answer acquisition unit that acquires answers from a user to each of a plurality of questions related to the user's way of thinking; an input information acquisition unit that acquires input information to be input into a predetermined large-scale language model based on the results acquired by the answer acquisition unit; a generated information acquisition unit that acquires generated information that is generated by inputting the input information into the large-scale language model and that may relate to the user's self-awareness; a self-awareness information acquisition unit that acquires self-awareness information that indicates 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] The present invention makes available information that is consistent and based on an individual's self-awareness in an efficient manner. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating a schematic configuration of a computer system according to an embodiment. [Figure 2] 1 is a diagram illustrating an overview of an information processing system according to an embodiment of the present invention. [Figure 3] FIG. 1 is a block diagram showing a schematic configuration of an information output device. [Figure 4] 10 is a flowchart illustrating an example of an operation of the information output device. [Figure 5] FIG. 1 is a first diagram illustrating an example of a workpiece in a specific example of this embodiment. [Figure 6] FIG. 2 is a second diagram illustrating an example of a workpiece in a specific example of this embodiment. [Figure 7]10A to 10C are diagrams illustrating an example of a method for inputting specific information in a specific example of the present embodiment. [Figure 8] FIG. 10 is a diagram illustrating an example of output information in a specific example of the present embodiment. DETAILED DESCRIPTION OF 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 according to an embodiment.

[0012] The computer system Z shown in the figure can be regarded as an example of the configuration of a computer that realizes the devices, etc. according to the embodiments. The functions of the devices, etc. according to the embodiments can be realized by the hardware of the computer system Z or 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 or a mouse, and a display Z3. The computer Z1 may have a general configuration such as a personal computer or a server device, which may be configured to include, for example, a storage device Z11 (e.g., an optical disk drive, HDD, SSD, ROM, RAM, etc.) that stores programs and data loaded during execution of the programs, a communication module Z13 (e.g., a network card, etc.) for communicating with external devices, a control device Z14 such as a CPU, etc., but is not limited to this.

[0014] Program Z12, which causes computer system Z to execute various functions, may be stored in storage device Z11. The circumstances under which program Z12 is stored in storage device Z11 are not important. Program Z12 may be stored in storage device Z11 in advance, a medium on which program Z12 is pre-stored may be read by storage device Z11, or program Z12 obtained via a network or the like may be temporarily stored in storage device Z11. Program Z12 may include only instructions for appropriately calling functions to obtain desired results.

[0015] The terms used below are generally defined as follows. Note that the meanings of these terms should not always be interpreted as shown here, but should be interpreted in light of the explanations given below, for example.

[0016] A user refers to an individual who uses an information output device. A user may also be referred to as a target or subject of the output information described below. A user may also be referred to as a target of attention in services, etc., realized using this information output device. Users may include a wide range of people who wish to deepen their self-understanding or career development, such as corporate employees, students, and job seekers.

[0017] Questions about the user's way of thinking refer to questions that ask about the user's values, past experiences, future orientation, strengths, weaknesses, etc. Questions can be multiple choice, written, or a combination of both.

[0018] An answer is information that a user enters or selects in response to a question. Answers may be expressed in text, numbers, or other formats.

[0019] A large-scale language model is a deep learning model that can perform natural language processing tasks and is trained from large amounts of text data.

[0020] The input information is information input to the large-scale language model. The input information may be, for example, a prompt, or information to be input to the large-scale language model together with a predetermined prompt. As will be described later, in this embodiment, the input information refers to information necessary to generate generated information related to self-recognition. The input information may be information such as a sentence formatted based on the user's answer, or may be the answer itself.

[0021] The generated information is information output by the large-scale language model based on the input information. In this embodiment, the generated information may be information related to the user's self-awareness. In this embodiment, the generated information may be information that expresses the user's values, strengths, weaknesses, future goals, etc. In this embodiment, the generated information may be candidate information that is a candidate for self-awareness information.

[0022] Self-awareness information is information that indicates a user's self-awareness, and may include, for example, information about the user's values, strengths, weaknesses, future goals, etc. A user's self-awareness may also be referred to as the user's identity, inner guidelines, core, purpose, or mission.

[0023] In this embodiment, the self-recognition information is obtained based on the specific information. The specific information is information corresponding to the candidate information or information that is a character expression entered 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 that is a character expression 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 created" includes creation without being based on the candidate information. For example, 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 newly created by the user. 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 treated as self-recognition information as it is.

[0024] Output information is information that an information output device outputs to a user. The output information may be self-awareness information itself, information including self-awareness information and other information, or recommended information or information including the same. Recommended information refers to information based on the user's self-awareness information, related to themes such as educational methods, job information, and lifestyle. Recommended information may be information that represents matters that are likely to match the user's interests, goals, etc. The output information may be useful, for example, for deepening the user's self-understanding or for use in the user's career development. Note that in this embodiment, job offers (or job searches) are not limited to those related to full-time employment, but may also include those related to part-time or side jobs. Furthermore, job offers are not limited to those related to paid work, but may also include volunteer activities, etc.

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

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

[0027] Formatting is the process of converting a user's response into a format that is easily understood by a large-scale language model. Formatting can include, for example, adjusting context, correcting typos, and removing unnecessary information. Formatting can also be done using existing templates and information based on the response.

[0028] Acquisition may include acquiring input information or acquiring information stored in another device. It may also include acquiring information in a format different from the original information. Acquisition of information may utilize a known so-called machine learning technique. That is, learning information configured to receive a specific type of information as input and output a desired type of information may be constructed using a machine learning technique, and the desired type of information may be acquired by applying input information to the learning information.

[0029] Regarding information, output refers to displaying by a display means, printing by a printing means, transmitting to an external device, recording on a recording medium, transferring the processing results to another device or another program, etc.

[0030] Regarding information reception, this refers to receiving information input from an input device, receiving information transmitted from another device, reading information from a recording medium, and the like.

[0031] In this embodiment, the information output device is configured to obtain self-awareness information indicating the user's self-awareness by using generated information generated using a large-scale language model based on answers to each of a plurality of questions regarding the user's way of thinking.

[0032] FIG. 2 is a diagram showing an overview of an information processing system 100 according to this 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 via a network or the like. The information output device 1 and the user terminal device 3 can also communicate with each other via a network or the like.

[0034] The external device 2 is configured to be able to output information acquired based on information received from a specific device, for example, by using a large-scale language model 211. The external device 2 is, for example, a general server device, and the large-scale 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 the function can be adopted as the external device 2 or as a substitute for the external device 2.

[0035] The user terminal device 3 is, for example, a general smartphone, tablet terminal, personal computer, etc. The user terminal device 3 is configured to display a screen in a predetermined application (including a web browser) running on the user terminal device 3 based on information transmitted from the information output device 1 and to be able to receive information input by a 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. As shown in FIG.

[0037] The information output device 1 is, for example, a server device, and 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] User information of each user is stored in association with that user in the user information storage unit 111. The process by which the user information is accumulated in the user information storage unit 111 does not matter.

[0040] In this embodiment, the user information storage unit 111 stores, for each user, answers to a plurality of questions regarding the user's way of thinking.

[0041] The learning information storage unit 115 stores learning information. The learning information is configured, for example, using a combination of self-recognition information and recommendation information obtained and applied to multiple users. Note that the learning information may also be configured using user information other than the self-recognition information.

[0042] The receiving 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, etc. The communication unit 13 can transmit and receive information to and from an external device.

[0044] The processing unit 14 controls the operation of each unit of the information output device 1. The processing unit 14 performs various functions by executing programs, etc. In this embodiment, the processing unit 14 has a response acquisition unit 141, an input information acquisition unit 143, a generation information acquisition unit 145, a self-recognition information acquisition unit 147, an output unit 149, and a learning information update unit 151.

[0045] The answer acquisition unit 141 acquires answers from a user to each of a plurality of questions related to the user's way of thinking. The answer acquisition unit 141 acquires, for example, each answer stored in the user information storage unit 111 in association with each user.

[0046] The answer acquiring unit 141 may transmit a plurality of questions to the user terminal device 3 of the user, store the answers that the user gives to the questions using the user terminal device 3 in the user information storage unit 111, and acquire the stored answers. Alternatively, answers that have been collected in advance by various methods and stored in the user information storage unit 111 in association with the user may be acquired.

[0047] The input information acquisition unit 143 acquires input information to be input to a predetermined large-scale language model 211 based on the acquisition result of the answer acquisition unit 141. The input information acquisition unit 143 is configured to acquire input information for obtaining generation information, as described below, using the large-scale language model 211. In this embodiment, the input information acquisition unit 143 may be configured to acquire the input information by performing a formatting process that formats a sentence using answers to each of one or more questions selected in advance from among a plurality of questions. However, this is not limited thereto, and the input information acquisition unit 143 may be configured to acquire the input information using answers to each of any one or more questions from among the plurality of questions. The input information acquisition unit 143 may be configured to acquire the input information using answers to each of all the questions.

[0048] The generated information acquisition unit 145 acquires generated information that may be related to the user's self-awareness, which is generated by inputting input information into the large-scale language model 211. In this 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 this embodiment, generation information acquisition unit 145 is configured to acquire two or more pieces of generation information. Since input information acquisition unit 143 is configured to be able to acquire two or more pieces of generation information, generation information acquisition unit 145 may acquire two or more pieces of generation information. Furthermore, 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 will be described later.

[0050] The self-recognition information acquisition unit 147 acquires self-recognition information indicating the user's self-recognition based on the generated information. The self-recognition information acquisition unit 147 may acquire the generated information acquired by the generated information acquisition unit 145 as the self-recognition information. In this case, when two or more pieces of generated information have been acquired, the self-recognition information acquisition unit 147 may acquire any one or more pieces of generated information as the self-recognition information, or may perform a shaping process or the like on any two or more pieces of generated information to acquire them as the self-recognition information.

[0051] In this embodiment, the self-recognition information acquisition unit 147 is configured to output the generation information to the user as candidate information and to output reception information for receiving input of specific information by the user in response to the output of the candidate information. When two or more pieces of generation information are acquired, the self-recognition information acquisition unit 147 outputs two or more pieces of candidate information corresponding to the two or more pieces of generation information, respectively, and reception information to the user terminal device 3. The reception information is, for example, information for displaying a screen on the user terminal device 3 for receiving input of specific information, but is not limited to this. When the candidate information and the reception information are output to the user terminal device 3, the user can input the specific information using the user terminal device 3. That is, the user can input the 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 the self-recognition information based on the specific information. For example, when the specific information is information for selecting one or more pieces of candidate information, the self-recognition information acquisition unit 147 can acquire the selected candidate information as the self-recognition information. Furthermore, when the specific information is information that is 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] Output unit 149 outputs output information based on the self-recognition information. When output unit 149 outputs the self-recognition information itself or information including the self-recognition information and other information as output information, the output self-recognition information of the user can be used.

[0053] In this embodiment, the output unit 149 may output recommended information or information including the recommended information as output information. For example, by outputting recommended information that indicates items that are likely to match the user's interests, goals, etc., the user and related parties can use the information as a reference when making decisions or judgments about various matters related to the user. The output information can be useful information for deepening the user's self-understanding or for use in the user's career development, for example.

[0054] The output unit 149 may be configured to, for example, acquire recommendation information related to 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 output information. The predetermined theme may be, for example, at least one of an educational method applicable to the user, a job applicable to the user, a recruiter who can be matched with the user, and a lifestyle applicable to the user. Here, lifestyle may be understood to refer to, for example, matters related to the user's work-life balance, health management, and fulfillment of hobbies and leisure time. For example, the recommended information may include working hours, suitable volunteer activities, etc.

[0055] In this case, the learning information may be information constructed by a machine learning technique, for example, so that self-recognition information is input and a score used for making recommendations on a predetermined theme is output.

[0056] In this case, the learning information may be correspondence information in which the self-awareness information is associated with a score used for making recommendations on a specific theme, and the correspondence information is configured so that the score can be identified based on the self-awareness information.

[0057] The output of the output information can be, for example, sending it to the user's user terminal device 3, storing it in the storage unit 11 or the like so that it can be analyzed together with the output information of other users or can be viewed by people related to the user, or displaying it on a display device or the like. This makes the output information available to the user or people related to the user.

[0058] 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 output information previously output by the output unit 149 about the user and user information subsequently acquired about the user. Then, the learning information update unit 151 re-learns the learning information based on the acquired information. Re-learning can be performed by a known method. In this way, it becomes possible to output recommendation information with higher accuracy.

[0059] Next, the flow of operations 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 self-recognition information of the user. The processing unit 14 acquires answers to a plurality of questions about the user's way of thinking using the answer acquisition unit 141 (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 answer and transmits the formatted input information to the external device 2 via the communication unit 13 (step S12). Then, the large-scale language model 211 of the external device 2 generates generation information based on the input information and transmits the generation information to the information output device 1.

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

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

[0065] The self-recognition information acquisition unit 147 determines whether the specific information input by the user has been accepted (step S15). When the user inputs the 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 accepted, and proceeds to the next step (YES).

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

[0067] The output unit 149 outputs the 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. This completes the series of processes.

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

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

[0070] In this specific example, a user first accesses the information output device 1 using the user terminal device 3 and performs an individual task of answering questions online. The task is composed of, for example, a first half that requires multiple-choice answers and a second half that requires written answers.

[0071] Fig. 5 is a first diagram illustrating an example of a workpiece in a specific example of this embodiment, and Fig. 6 is a second diagram illustrating an example of a workpiece in a specific example of this embodiment.

[0072] In the first half of the work, users are asked to complete questions such as "Self-Evaluation" (S51), which asks about self-evaluation, "The Circle of Life" (S52), which asks about evaluations of their lives so far, and "SDGs" (S53), which asks about areas of social issues that interest them.

[0073] For self-evaluation, users will rate themselves based on the top five qualities that companies look for in a candidate. Users will input scores for items such as communication skills and initiative.

[0074] The Wheel of Life involves dividing one's life into eight areas, present and future, and rating one's ideal and reality. Areas include, for example, work and career, physical environment, play and leisure, learning and self-development, relationships, family and partner, health, money and finances, etc. For each area, users input their current score and their ideal score in terms of fulfillment and satisfaction.

[0075] Regarding the SDGs, users are asked to select the SDGs they are interested in. For example, users can select up to four SDGs.

[0076] In the latter half of the work, the user is asked to answer questions about past experiences (S54), questions about future goals (S55), and questions about factors related to happiness (S56), such as "Past Experiences."

[0077] For past experiences, users look back on memorable events from the past and identify their desires at the time. The user describes the past experience. The user also describes or inputs, for example, the desires they had for themselves and for others at the time. Multiple answers are permitted.

[0078] The Will Can Must section confirms current and future goals, strengths, and expectations. Users write about what they want to do, what they are good at, and what is expected of them. For example, when describing what they want to do, they can write about it separately for daily life, daily living, and life.

[0079] For factor analysis, for example, each of the following factors is confirmed: Factor 1 (self-actualization and growth factor; let's try factor), Factor 2 (connection and gratitude factor; thank you factor), Factor 3 (positivity and optimism factor; it will all work out factor), and Factor 4 (independence and being yourself factor; just being yourself factor). Users are asked to describe in their own words what items they see in each factor.

[0080] When the user has completed these individual 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 input information based on the answers to the large-scale language model 211. The input information may be, for example, a sentence into which the answer content is appropriately inserted, but is not limited to this. Such a sentence is generated according to, for example, a template sentence, but the input information itself may also be generated using the large-scale language model 211 or the like.

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

[0082] FIG. 7 is a diagram illustrating an example of a method for inputting specific information in a specific example of this embodiment.

[0083] The input of specific information can be accepted, for example, on a 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 that corresponds to the self-recognition information that the user considers to be the self-recognition information in an input field 422. That is, in this example, the user can input the 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, a display area 423 of candidate information based on the answer is displayed on the screen (S62). Note that the candidate information may be acquired and displayed in advance or at a predetermined timing, regardless of the timing of the operation of the display button 412, or the input information may be output to the large-scale language model 211 when the display button 412 is operated, thereby displaying the candidate information.

[0085] For example, multiple examples of self-recognition information candidates are displayed together with the reason why the candidates are displayed. The user can input specific information by referring to the displayed candidates. In the example shown in the figure, by selecting a candidate to use for inputting specific information, the selected candidate can be transcribed as specific information into the input field 422 (S62 to S63). This allows the user to 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. As described above, various types of output information can be output, but in this example, information on a training program recommended for a user who is, for example, an employee, is output as output information.

[0087] FIG. 8 is a diagram illustrating an example of output information in a specific example of this embodiment.

[0088] The output information is displayed on the output information display screen 441 of the user terminal device 3. The output information includes, for example, the self-awareness information acquired about the user as described above and recommendation information about the content of a training program obtained based on the self-awareness information. In this way, the recommendation information recommended for the user based on the self-awareness information is displayed, allowing the user and related parties to learn information about training programs that are expected to be highly effective when applied to the user. In this example, the recommendation information also includes reasons for the recommendation. The recommendation reasons may be displayed based on, for example, predetermined example sentences, or may display content output by the large-scale language model 211 using the self-awareness information and the recommendation information. Displaying the recommendation reasons is expected to provide a high level of satisfaction to the user and related parties.

[0089] As described above, according to this embodiment, the information output device 1 can be used to efficiently acquire and make available information about an individual's self-awareness based on the user's answers and input content. Compared to conventional methods that require repeated in-person sessions or workshops, self-awareness information can be acquired and corresponding information can be output in a short time. Furthermore, compared to conventional methods, the number of situations in which manual evaluation or advice is required can be reduced, making it possible to identify consistent self-awareness information. Ultimately, self-awareness information based on the user's identification information can be obtained, and it is expected that self-awareness information that is highly suited to the user's characteristics can be made available.

[0090] The processing in this embodiment may be realized by the following program. The program is executed on the computer of the information output device 1 and causes the computer to function as an answer acquisition unit that acquires answers from a user to each of a plurality of questions related to the user's way of thinking, an input information acquisition unit that acquires input information to be input into a predetermined large-scale language model based on the results acquired by the answer acquisition unit, a generated information acquisition unit that acquires generated information that is generated by inputting the input information into the large-scale language model and that may relate to the user's self-awareness, a self-awareness information acquisition unit that acquires self-awareness information that indicates the user's self-awareness based on the generated information, and an output unit that outputs output information based on the self-awareness information.

[0091] In the above embodiments, each component can be configured with dedicated hardware or can be realized by software. In the case of software, it is realized by executing a program, and each component functions when a CPU executes the program recorded on a recording medium such as a hard disk or semiconductor memory. The program can be executed by accessing a storage unit or recording medium, or can be executed by downloading it from a server or reading it from a recording medium such as an optical disk. The program can also be used as a program product, and can be executed by a single or multiple computers, performing centralized or distributed processing.

[0092] Each process or function can be realized by centralized processing in a single device (system) or distributed processing in multiple devices. In this case, the entire system consisting of multiple devices performing distributed processing can be recognized as a single "device." Also, two or more components present in one device can be physically realized on a single medium.

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

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

[0095] The above embodiment can be expressed as follows.

[0096] An information output device having a first configuration aspect is an information output device comprising: an answer acquisition unit that acquires answers from a user to each of a plurality of questions regarding the user's way of thinking; an input information acquisition unit that acquires input information to be input into a predetermined large-scale language model based on the results acquired by the answer acquisition unit; a generated information acquisition unit that acquires generated information that is generated by inputting the input information into the large-scale language model and that may relate to the user's self-awareness; a self-awareness information acquisition unit that acquires self-awareness information that indicates 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] In addition, in the information output device of this second configuration, compared to the first configuration, the self-recognition information acquisition unit is configured to output the generated information to the user as candidate information and to output reception information for accepting input of specific information by the user in accordance with the output of the candidate information, and the information output device acquires self-recognition information based on the specific information input by the user using the reception information.

[0098] Furthermore, the information output device of this third configuration aspect is an information output device in which, compared to the second configuration aspect, the generated information acquisition unit is configured to acquire two or more pieces of generated information, the self-recognition 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 for selecting one or more of the two or more candidate pieces of information or information that is a character expression corresponding to one or more of the two or more candidate pieces of information.

[0099] Furthermore, the information output device of this fourth configuration aspect is an information output device in which, compared to the second configuration aspect, the specific information is information corresponding to candidate information or information that is a character expression input by the user.

[0100] Furthermore, the information output device of this fifth configuration aspect is an information output device in which, compared to the first configuration aspect, the input information acquisition unit is configured to perform a formatting process to format a sentence using answers to each of one or more questions selected in advance from among a plurality of questions.

[0101] Furthermore, in the information output device of this sixth configuration aspect, compared to the first configuration aspect, the output unit is configured to obtain recommendation information regarding a specified theme to be recommended to the user using self-awareness information and specified learning information, and output the obtained recommendation information as output information, and the specified theme is at least one of an educational method applicable to the user, a job applicable to the user, an employer that can be matched with the user, and a lifestyle applicable to the user.

[0102] Furthermore, the information output device of this seventh configuration aspect is an information output device in which, compared to the sixth configuration aspect, the learning information is at least one of information constructed using a machine learning technique so that self-awareness information is input and a score to be used for recommendations on a specified theme is output, and correspondence information in which the self-awareness information and the score are associated with each other.

[0103] In addition, the information output device of this eighth configuration aspect is an information output device that, compared to the sixth configuration aspect, is equipped with a learning information update unit that acquires output information previously output by the output unit about a user and user information subsequently obtained about the user, and performs a process of updating the learning information based on the acquired information. [Explanation of symbols]

[0104] 1. Information output device 2 External device 11 Storage area 12 Reception 13 Communications Department 14 Processing section 21 Storage area 100 Information Processing Systems 111 User information 115 Learning information storage unit 141 Answer acquisition part 143 Input information acquisition unit 145 Generation information acquisition unit 147 Self-awareness information acquisition unit 149 Output Section 151 Learning Information Update Department 211 Large-scale Language Models

Claims

1. an answer acquisition unit that acquires answers from a user to each of a plurality of questions related to the user's way of thinking; an input information acquisition unit that acquires input information to be input to a predetermined large-scale 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-scale language model, the generated information being related to the user's self-awareness; a self-recognition information acquisition unit that acquires self-recognition information indicating the user's self-recognition based on the generated information; an output unit that outputs output information based on the self-recognition information.

2. The self-recognition information acquisition unit the generation information is output to the user as candidate information, and reception information for receiving input of specific information by the user is output in response to the output of the candidate information, The information output device according to claim 1 , wherein the self-recognition information is acquired based on the specific information input by the user using the reception information.

3. the generation information acquisition unit acquires two or more pieces of generation information; the self-recognition information acquisition unit is configured to output two or more pieces of candidate information corresponding to the two or more pieces of generated information, respectively; The information output device according to claim 2 , wherein 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.

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

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

6. the output unit is configured to acquire recommendation information relating to a predetermined theme to be recommended to the user using the self-recognition information and predetermined learning information, and to output the acquired recommendation information as the output information; The information output device according to claim 1, wherein the predetermined theme is at least one of an educational method applicable to the user, a job applicable to the user, an employer that can be matched with the user, and a lifestyle applicable to the user.

7. The information output device of claim 6, wherein the learning information is at least one of information constructed using a machine learning technique to input the self-awareness information and output a score to be used for recommendations regarding the specified theme, and correspondence information in which the self-awareness information and the score are associated with each other.

8. The information output device of claim 6, further comprising a learning information update unit that acquires output information previously output by the output unit about the user and user information subsequently obtained about the user, and performs a process of updating the learning information based on the acquired information.

9. An information output method executed by an information output device including an answer acquisition unit, an input information acquisition unit, a generated information acquisition unit, a self-recognition information acquisition unit, and an output unit, an answer acquisition step in which the answer acquisition unit acquires answers from a user to each of a plurality of questions related to the user's way of thinking; an input information acquisition step in which the input information acquisition unit acquires input information to be input to a predetermined large-scale language model based on the result acquired in the answer acquisition step; a generated information acquisition step in which the generated information acquisition unit acquires generated information generated by inputting the input information into the large-scale language model, the generated information possibly relating to the self-awareness of the user; a self-recognition information acquisition step in which the self-recognition information acquisition unit acquires self-recognition information indicating the self-recognition of the user based on the generated information; an output step in which the output unit outputs output information based on the self-recognition information.

10. Computer, an answer acquisition unit that acquires answers from a user to each of a plurality of questions related to the user's way of thinking; an input information acquisition unit that acquires input information to be input to a predetermined large-scale 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-scale language model, the generated information being related to the user's self-awareness; a self-recognition information acquisition unit that acquires self-recognition information indicating the user's self-recognition based on the generated information; and an output unit that outputs output information based on the self-recognition information.

Images