Program, information processing device, and method

Abstract

To enable presentation of unique personality of a user who is either unable to understand his / her own nature or is not good at expressing himself / herself.SOLUTION: A program to be executed by a computer performs the steps of: accepting input of episodes experienced by a user and numerical information quantifying the degree of predetermined emotions felt by the user during the experiences; storing the accepted episodes and numerical information in a memory; generating a first prompt for a large language model using the stored episodes and numerical information so that the model can generate text regarding the user's strengths; inputting the generated first prompt into the large language model to generate the text regarding the user's strengths; and outputting the text regarding the user's strengths.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present disclosure relates to a program, an information processing device, and a method. [Background technology]

[0002] There is a technology that accepts input of learning or experience information from a user, applies the learning or experience information to a model, determines the user's strengths, and outputs the user's strengths, with the aim of helping the user recognize their own strengths when choosing a second career (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-048877 Summary of the Invention [Problem to be solved by the invention]

[0004] The above technology evaluates a user's strengths for each strength element and outputs the evaluation results. However, the above technology has a problem in that even if the evaluation results are presented to a user who is not good at expressing his or her strengths, the user is unable to express his or her strengths.

[0005] Therefore, the present disclosure provides a technology that enables a user who is not good at expressing his or her own strengths to express the strengths that are unique to that user. [Means for solving the problem]

[0006] The program according to the present disclosure is a program to be executed by a computer having a processor and a memory, and the program causes the processor to execute the following steps: accepting input of an episode experienced by a user and numerical information that quantifies the degree of a predetermined emotion felt by the user when the experience was experienced; storing the accepted episode and the numerical information in the memory; using the episode and the numerical information stored in the memory to generate a first prompt for a large-scale language model to generate text related to the user's strengths; inputting the created first prompt into the large-scale language model to generate text related to the user's strengths; and outputting the text related to the user's strengths. [Effects of the Invention]

[0007] According to the present disclosure, a user who is not good at expressing his or her own strengths can express the strengths that are unique to that user. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing the overall configuration of a system 1. [Figure 2] FIG. 2 is a diagram showing the functional configuration of the information processing device 10. As shown in FIG. [Figure 3] FIG. 3 is a diagram showing the data structure of the user DB 121. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing the data structure of the episode DB 122. As shown in FIG. [Figure 5] FIG. 5 is a diagram showing the functional configuration of the user terminal 20. As shown in FIG. [Figure 6] FIG. 6 is a diagram showing an example of the flow of processing in the system 1. [Figure 7] FIG. 7 is a diagram showing an example of the flow of processing in the system 1. [Figure 8] FIG. 8 is a diagram showing an example of the flow of processing in the system 1. [Figure 9]FIG. 9 is a diagram showing an example of the flow of processing in the system 1. [Figure 10] FIG. 10 is an example of a portal screen displayed on the user terminal 20. As shown in FIG. [Figure 11] FIG. 11 is an example of an input screen displayed on the user terminal 20. As shown in FIG. [Figure 12] FIG. 12 is an example of an advice screen displayed on the user terminal 20. As shown in FIG. [Figure 13] FIG. 13 is an example of a feedback screen displayed on the user terminal 20. As shown in FIG. [Figure 14] FIG. 14 is a diagram showing the functional configuration of the information processing device 10. As shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated description will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0010] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be single-core or multi-core.

[0011] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC)) that performs part or all of the processing.

[0012] In the following explanation, information that produces an output for an input may be described using expressions such as "xxx table," but this information may be data of any structure, or may be a learning model such as a neural network that produces an output for an input. Therefore, an "xxx table" may be referred to as "xxx information."

[0013] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0014] In addition, in the following explanation, processing may be described using the "program" as the subject, but since a program is executed by a processor to perform specified processing while appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may also be the processor (or a device such as a controller that has that processor).

[0015] The program may be installed in a device such as a computer, or may be stored in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Also, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0016] Furthermore, in the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may also be used.

[0017] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference symbols (or common symbols among the reference symbols) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference symbols) of the elements may be used.

[0018] In the following description, the control lines and information lines are those that are considered necessary for the description, and do not necessarily represent all the control lines and information lines in the product. All components may be interconnected.

[0019] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the information processing device 10 and the user terminal 20, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0020] <Summary of this disclosure> In the present disclosure, a user is presented with text about the user's unique strengths based on the user's own experience. The user may be, for example, a job seeker job-hunting or job-changing. This allows the user to express their strengths even if they do not understand their own strengths or have difficulty expressing them during job-hunting or job-changing activities. Expressing a user's strengths, weaknesses, personality, values, etc. is necessary not only in resumes and curriculum vitae during job-hunting or job-changing activities, but also in interviews. In such situations, for example, students, who are job-hunting for the first time, often have difficulty expressing themselves effectively. Users who are not good at expressing themselves in this way may transcribe typical self-expressions or success stories of others. However, even if they do this, human resources personnel may sense a discrepancy between their description and their actual performance, resulting in the user being rejected at the interview, or they may have difficulty after joining the company due to a mismatch in their values ​​and abilities, resulting in a negative impression of the user.

[0021] It is also difficult to understand one's own strengths. In conventional technology, for example, an evaluation value is displayed for each predetermined item, but this often results in multiple users receiving the same results. This means that even if a user tries to understand their own strengths, they cannot understand what makes them different from others or what their unique strengths are. Furthermore, users may not be able to understand their own strengths because they have low self-esteem, do not have time to reflect on themselves, or believe that they have no strengths. In such cases, even if the results displayed are similar to those of other users, it cannot be said that they are able to understand their own strengths.

[0022] Furthermore, if you ask others to help you with this self-understanding, it takes time and is often difficult to communicate effectively, which is a hassle. Also, if you think of yourself as someone who doesn't have much experience, talking about your experiences with others can be a particularly big psychological hurdle, as you may not have the courage or motivation to do so.

[0023] The technology disclosed herein generates a user's strengths based on the user's experience, thereby expressing the user's unique strengths that the user himself / herself may not have been aware of. This allows the technology disclosed herein to assist users in their job hunts, career changes, and other activities that require self-promotion. Furthermore, the technology disclosed herein automatically extracts a user's strengths based on the user's anecdotes, rather than manually, eliminating the hassle of asking for help. Furthermore, by presenting the user's unique strengths, feedback about the user's strengths is provided to users who believe they have no strengths. This allows the user to become aware of and understand their strengths. Note that while the embodiments of the present disclosure describe an example of generating text related to a user's strengths, the technology can also be applied to generating information other than strengths, such as the user's weaknesses, personality, values, etc.

[0024] <1. Embodiment> <1.1. Overall configuration of System 1> The configuration of a system 1 according to an embodiment of the present disclosure will be described. The system 1 is a system for generating text related to a user's strengths according to the present disclosure.

[0025] 1, the system 1 includes an information processing device 10, a user terminal 20, a server 30, and a network 80. The information processing device 10, the user terminal 20, and the server 30 are connected via the network 80 for communication.

[0026] The information processing device 10 is an information processing device that exhibits a function of generating text relating to a user's strengths. The user terminal 20 is an information processing device operated by a user. The server 30 is an information processing device that functions as a server that receives input to large language models (LLMs) from the information processing device 10 and returns generated results to the information processing device 10. As the large language model, any large language model such as GPT-4 or BERT can be adopted.

[0027] The information processing device 10 is realized by a desktop PC (Personal Computer), a laptop PC, or the like.

[0028] As shown in FIG. 1, the information processing device 10 includes a communication IF 12, an input / output IF 13, a memory 15, and a storage 16.

[0029] The communication IF 12 is an interface for inputting and outputting signals so that the information processing device 10 can communicate with external devices. The input / output IF 13 functions as an interface with an input device for receiving input operations from a user and an output device for presenting information to the user. The input / output IF 13 is used to temporarily store programs and data processed by the programs, and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The memory 15 is a storage device for saving data, such as a flash memory or an HDD (Hard Disc Drive). The storage 16 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0030] The user terminal 20 is realized by a mobile terminal such as a smartphone or tablet compatible with a mobile communication system, a desktop personal computer (PC), a laptop PC, or the like.

[0031] As shown in FIG. 1, the user terminal 20 includes a communication IF 22, an input / output IF 23, a memory 25, and a storage 26.

[0032] The communication IF 22 is an interface for inputting and outputting signals so that the user terminal 20 can communicate with external devices. The input / output IF 23 functions as an interface with an input device for receiving input operations from a user and an output device for presenting information to the user. The input / output IF 23 is used to temporarily store programs and data processed by the programs, and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The memory 25 is a storage device for saving data, such as a flash memory or an HDD (Hard Disc Drive). The storage 26 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0033] <1.2. Functional configuration of information processing device 10> 2 is a diagram showing the functional configuration of the information processing device 10. As shown in FIG. 2, the information processing device 10 functions as a communication unit 101, a storage unit 102, and a control unit 103.

[0034] The communication unit 101 performs processing for communicating with an external device.

[0035] The storage unit 102 stores data and programs to be used.

[0036] Specifically, the storage unit 102 stores a user DB (database) 121, an episode DB 122, and the like.

[0037] The following describes the data structures of the user DB 121 and episode DB 122 stored in the information processing device 10 shown in Figures 3 and 4. Figures 3 and 4 are diagrams showing the data structures of each database.

[0038] The user DB 121 is a database that holds information about users, and includes the following items: "user ID," "name," "affiliation," and "date of birth."

[0039] The item "user ID" is information for identifying a user.

[0040] The item "Name" is the name or first name of the user.

[0041] The item "affiliation" is an organization to which the user belongs. Specifically, the item "affiliation" is a university, company, etc. to which the user belongs.

[0042] The item "Date of Birth" is the user's date of birth.

[0043] The episode DB 122 is a database that holds data related to the user's experiences. The episode DB 122 includes the following items: a "user ID," a "data ID," a "title," an "episode," a "date information," a "numeric information," and a "video."

[0044] The item "user ID" is information for identifying a user.

[0045] The item "data ID" is information for identifying an information set.

[0046] The item "episode" is the content of a subjective episode experienced by the user. Specifically, an episode is text data that describes a specific episode that the user experienced. An episode includes information such as the title, the event that was experienced, and the emotions felt when the experience occurred.

[0047] The item "date information" is the time when the user experienced the episode. Specifically, the date information may be, for example, the year and month, or the year, month, and day, or the age of the user when the episode occurred.

[0048] The item "numerical information" is a numerical representation of the degree of a predetermined emotion felt by the user when experiencing the episode. Specifically, the numerical information is, for example, a happiness level indicating the degree to which the user felt happy when experiencing the episode. In addition to happiness level, the numerical information can also employ degrees related to various emotions, such as interest level and disgust level felt when experiencing the episode. In the present disclosure, an example will be described in which the numerical information is happiness level. It is preferable that the happiness level is a number that is easy for the user to input and can be expressed intuitively. In the present disclosure, an example will be described in which the happiness level is expressed using an integer between -10 and 10. Note that, when employing emotions other than happiness level (interest level, disgust, etc.), integers between -10 and 10 can also be used.

[0049] The item "video" is data of video related to the episode. Specifically, the video is data of moving images or still images.

[0050] The control unit 103 performs functions shown as various modules by the processor of the information processing device 10 performing processing according to a program. The control unit 103 includes a reception control unit 131, a transmission control unit 132, a display unit 133, an input unit 134, a first generation unit 135, a second generation unit 136, etc.

[0051] The reception control unit 131 controls the process in which the information processing device 10 transmits and receives signals to and from external devices in accordance with a communication protocol.

[0052] The transmission control unit 132 controls the process in which the information processing device 10 transmits a signal to an external device in accordance with a communication protocol.

[0053] The display unit 133 displays various screens on the user terminal 20. Specifically, the display unit 133 displays a portal screen on the user terminal 20. The portal screen includes buttons for displaying an input screen, a correction screen, an advice screen, and a feedback screen, which will be described later.

[0054] Furthermore, the display unit 133 displays an input screen on the user terminal 20 for receiving input of an episode experienced by the user, numerical information that quantifies the degree of a predetermined emotion that the user felt when the experience was experienced, and date information when the user experienced the experience. The input screen is displayed, for example, when a button for displaying the input screen is pressed on the portal screen by a user operation.

[0055] Furthermore, the display unit 133 may display an input screen for inputting the data in an interactive format. Specifically, in this case, the input screen accepts the data input by an interactive system such as a chatbot.

[0056] Furthermore, the display unit 133 displays an edit screen on the user terminal 20 that accepts edits to the input episode, numerical information, and date information. The edit screen is displayed, for example, when a button for displaying the edit screen is pressed on the portal screen by a user operation. The edit screen may use the same user interface as the screen for accepting input.

[0057] Furthermore, the display unit 133 displays an advice screen for asking questions to enrich the user's episodes on the user terminal 20. The advice screen is displayed, for example, when a button for displaying the advice screen is pressed on the portal screen by a user operation.

[0058] Furthermore, the display unit 133 displays a feedback screen that displays text related to the user's strengths on the user terminal 20. The feedback screen is displayed, for example, when a button for displaying the feedback screen is pressed on the portal screen by a user operation.

[0059] The input unit 134 accepts input of an episode experienced by the user, numerical information that quantifies the degree of a specific emotion felt by the user when the user had the experience, and date information when the user had the experience.

[0060] Specifically, the input unit 134 accepts input of an episode, numerical information, and date information by receiving an episode experienced by the user, numerical information, and date information from the user terminal 20. The input unit 134 stores the accepted episode, numerical information, and date information in the episode DB 122.

[0061] Furthermore, the input unit 134 receives any of the corrected episode, numerical information, and date information from the user terminal 20, and stores the corrected episode, numerical information, and date information in the episode DB 122.

[0062] The first generating unit 135 generates text relating to the strengths of the user. Specifically, the first generation unit 135 uses the episodes, numerical information, and date information stored in the episode DB 122 to generate a first prompt for causing the large-scale language model to generate text related to the user's strengths.

[0063] More specifically, when the number of episodes for the user stored in the episode DB 122 is greater than a predetermined threshold, the first generation unit 135 first selects an episode from the episodes stored in the episode DB 122 based on the numerical information and date information. This is to resolve the problem that the capacity of the prompt, such as the number of characters, may be limited in a large-scale language model.

[0064] For example, if the predetermined threshold is determined based on the number of episodes, then any value equal to or less than the number of episodes that can be included in the prompt can be set as the predetermined threshold. Furthermore, if the predetermined threshold is determined based on the total data capacity of the episodes, then any value (units such as bytes or bits) equal to or less than the total data capacity of the episodes that can be included in the prompt can be set as the predetermined threshold. For example, if one character is represented by two bytes and the maximum number of characters that can be included as input data in a prompt is 1,000 characters, then the predetermined threshold can be set to 2,000 bytes.

[0065] The episode is selected according to the following selection rules, for example. - Sort episodes in descending order of absolute value of numerical information -For episodes with the same absolute value of numerical information, sort the episodes by most recent date information. -Select as many episodes as you can fit into the first prompt from the top of the sorted episodes

[0066] Next, if an episode is selected, first generation unit 135 generates a first prompt using the selected episode, numerical information, and date information. If an episode is not selected, first generation unit 135 generates a first prompt using all episodes, numerical information, and date information of the user stored in episode DB 122.

[0067] The first prompt is written as an instruction to the large-scale language model, instructing the large-scale language model to generate text related to the user's strengths, and an input data section which is a set of episode, numerical information, and date information.

[0068] The instruction section contains instructions for causing the large-scale language model to generate text about the user's strengths. For example, the instruction section may contain instructions such as, "As a senior consultant of the service, please verbalize the user's unique strengths based on the content of the life episodes described by the user and provide feedback to the user."

[0069] The instruction section may also include instructions to observe the following generation rules in order to have the large-scale language model generate text related to the user's strengths.

[0070] - Generate text about the user's strengths by focusing on episodes with large absolute values ​​of numerical information among multiple episodes. Generate text about the user's strengths by prioritizing the most recent episode among multiple episodes with date information. Generate user strengths by focusing on episodes that are highly unique and reveal the user's strengths among multiple episodes. These generation rules do not treat all of the user's multiple episodes equally, but rather focus on episodes that will bring out the user's strengths more, causing the large-scale language model to generate text related to the user's strengths. The directive may include any combination of these creation rules, and may include an expression specifying the order of priority of these creation rules.

[0071] The instruction unit may also instruct the large-scale language model to include evidence for the user's strengths in the text regarding the user's strengths, in order to make the user's strengths easier to understand. For example, the instruction unit may include an instruction to include evidence by citing an episode.

[0072] The instructing unit may also instruct the large-scale language model to include multiple (for example, three) strengths in the text regarding the user's strengths, so that the user can more easily understand the user's strengths.

[0073] The input data portion of the first prompt is written, for example, as follows: The data entered in the input data section is a table of episodes in the user's life and the emotions they felt at the time. Numerical information in the input (e.g., happiness) must be defined in the range of -10 to 10 for each episode. The input data section should be in the following format, for example: Example of input data section: | Happiness level | Age | Episode title | Episode text | Emotions at the time | |---|---|---|---|---| | 10 | 15 | Title Sample X | Episode Sample X | Emotion Sample X | (The following is a multi-line episode)

[0074] The first generating unit 135 may be configured to include the user's date of birth acquired from the user DB 121 or the user's age calculated from the date of birth in the input data.

[0075] Then, first generating unit 135 inputs the generated first prompt into the large-scale language model to generate text related to the user's strengths.

[0076] Specifically, the first generation unit 135 transmits the generated first prompt to the server 30, thereby causing the large-scale language model of the server 30 to generate text related to the strengths. Upon receiving the text related to the user's strengths from the server 30, the first generation unit 135 causes the display unit 133 to display the text related to the user's strengths on the user terminal 20.

[0077] The second generation unit 136 generates questions to enrich the episodes. Specifically, the second generation unit 136 uses the episodes, numerical information, and date information stored in the episode DB 122 to generate a second prompt for the large-scale language model to generate a question to enrich the episode.

[0078] More specifically, if the number of episodes for the user stored in the episode DB 122 is greater than a predetermined threshold, the second generation unit 136 first selects an episode from the episodes stored in the episode DB 122 based on numerical information and date information. This is to resolve the problem that the capacity of the prompt, such as the number of characters, may be limited in large-scale language models. The predetermined threshold and the selection of episodes are the same as those of the first generation unit 135.

[0079] Next, if an episode is selected, second generation unit 136 generates a second prompt using the selected episode, numerical information, and date information. If an episode is not selected, second generation unit 136 generates a second prompt using all episodes, numerical information, and date information of the user stored in episode DB 122.

[0080] The second prompt is written as an instruction to the large-scale language model to generate a question to enrich the episode, and is divided into an instruction section and an input data section which is a set of episode, numerical information, and date information.

[0081] The instruction section contains instructions for causing the large-scale language model to generate questions to enrich the episodes. For example, the instruction section may state, "As a senior consultant of the service, please ask as many questions as possible to dig deeper into the content of the life episodes described by the user themselves, to explore areas that are not fully described."

[0082] The instruction section may also include the following instructions to cause the large-scale language model to generate questions to enrich the episodes: Asking questions that delve deeper into each episode At this time, you may want to use a lot of question marks and ask many questions that will dig deeper into the perspectives that the user has not fully explained.

[0083] The input data portion of the second prompt is written, for example, as follows: The data entered in the input data section is a table of episodes in the user's life and the emotions they felt at the time. Numerical information in the input (e.g., happiness) must be defined in the range of -10 to 10 for each episode. The input data section should be in the following format, for example: Example of input data section: | Happiness level | Age | Episode title | Episode text | Emotions at the time | |---|---|---|---|---| | 10 | 15 | Title Sample Y | Episode Sample Y | Emotion Sample Y | (The following is a multi-line episode)

[0084] The second generating unit 136 may be configured to include the user's date of birth acquired from the user DB 121 or the user's age calculated from the date of birth in the input data.

[0085] Then, second generation unit 136 inputs the generated second prompt into the large-scale language model to generate a question for enriching the episode.

[0086] Specifically, the second generation unit 136 transmits the generated second prompt to the server 30, thereby causing the large-scale language model of the server 30 to generate a question for enriching the episode. Upon receiving the question for enriching the episode from the server 30, the second generation unit 136 causes the display unit 133 to display the question for enriching the episode on the user terminal 20.

[0087] <1.3. Functional Configuration of User Terminal 20> 6 is a diagram showing the functional configuration of the user terminal 20. As shown in FIG.

[0088] The communication unit 201 performs processing for the user terminal 20 to communicate with external devices.

[0089] The storage unit 202 stores data and programs used by the user terminal 20.

[0090] The control unit 203 performs functions shown as various modules by the processor of the user terminal 20 performing processing according to a program. The control unit 203 performs functions as a reception control unit 231, a transmission control unit 232, a reception unit 233, a registration unit 234, a notification unit 235, and a display unit 236.

[0091] The reception control unit 231 controls the processing by which the user terminal 20 transmits and receives signals to and from external devices in accordance with a communication protocol.

[0092] The transmission control unit 232 controls the process in which the user terminal 20 transmits a signal to an external device in accordance with a communication protocol.

[0093] The reception unit 233 receives operations and inputs from the user.

[0094] Specifically, the receiving unit 233 receives operations from the user on the portal screen, the input screen, the correction screen, the advice screen, and the feedback screen. The receiving unit transmits information corresponding to the operations to the information processing device 10.

[0095] The display unit 236 displays information received from the information processing device 10. Specifically, the display unit 236 displays a portal screen, an input screen, a correction screen, an advice screen, and a feedback screen received from the information processing device 10.

[0096] <1.4. System 1 processing flow> Next, the processing flow of the system 1 will be described with reference to FIGS.

[0097] FIG. 6 is a diagram showing an example of the flow of processing for acquiring information such as episodes and numerical information from a user.

[0098] In step S601, the display unit 133 displays a portal screen on the user terminal 20.

[0099] In step S603, the user terminal 20 displays a portal screen to the user and accepts a button press from the user to display an input screen. Upon accepting that the button to display the input screen has been pressed, the user terminal 20 transmits a notification to that effect to the information processing device 10.

[0100] In step S605, the display unit 133 displays an input screen on the user terminal 20.

[0101] In step S607, the user terminal 20 displays an input screen to the user, and transmits to the information processing device 10, through the user's operation, the episode experienced by the user that the user inputs into the input screen, numerical information that quantifies the degree of a specified emotion that the user felt when experiencing the experience, and date information when the user experienced the experience.

[0102] In step S609, the input unit 134 receives from the user terminal 20 an input of an episode experienced by the user, numerical information, and date information.

[0103] In step S611, the input unit 134 stores the received episode, numerical information, and date information in the episode DB 122.

[0104] FIG. 7 is a diagram showing an example of the flow of a process for generating and displaying questions to enrich an episode.

[0105] In step S703, the user terminal 20 displays a portal screen to the user and accepts a button pressed by the user to display an advice screen. Upon accepting that the button to display the advice screen has been pressed, the user terminal 20 transmits a notification to that effect to the information processing device 10.

[0106] In step S705, if the number of episodes for the user stored in episode DB 122 is greater than a predetermined threshold, second generation unit 136 selects an episode from the episodes stored in episode DB 122 based on numerical information and date information.

[0107] In step S707, if an episode is selected, second generation unit 136 generates a second prompt using the selected episode, numerical information, and date information. If an episode is not selected, second generation unit 136 generates a second prompt using all episodes, numerical information, and date information of the user stored in episode DB 122.

[0108] In step S709, the second generation unit 136 transmits the generated second prompt to the server 30, thereby causing the large-scale language model of the server 30 to generate a question for enriching the episode.

[0109] In step S711, the server 30 receives the second prompt.

[0110] In step S713, the server 30 generates a question to enrich the episode by inputting the second prompt into a large-scale language model.

[0111] In step S715, the server 30 transmits a question to the information processing device 10 to enrich the generated episode.

[0112] In step S717, the second generation unit 136 receives, from the server 30, a question for enriching the episode.

[0113] In step S719, the display unit 133 causes the user terminal 20 to display an advice screen including a question for enriching the generated episode.

[0114] FIG. 8 is a diagram showing an example of the flow of processing for accepting corrections to information such as episodes and numerical information from a user.

[0115] In step S803, the user terminal 20 displays a portal screen to the user and accepts a button pressed by the user to display the edit screen. Upon accepting that the button to display the edit screen has been pressed, the user terminal 20 transmits a notification to that effect to the information processing device 10.

[0116] In step S805, the display unit 133 displays the correction screen on the user terminal 20.

[0117] In step S807, the user terminal 20 displays an edit screen to the user, and transmits to the information processing device 10 the episode edited by the user, the numerical information, and the date information that the user inputs on the edit screen through the user's operation.

[0118] In step S809, the input unit 134 receives from the user terminal 20 the input of the episode corrected by the user, the numerical information, and the date information.

[0119] In step S811, the input unit 134 stores the corrected episode, the numerical information, and the date information in the episode DB 122.

[0120] FIG. 9 is a diagram showing an example of the flow of a process for generating and displaying text relating to a user's strengths.

[0121] In step S903, the user terminal 20 displays a portal screen to the user and accepts a button pressed by the user to display a feedback screen. Upon accepting that the button to display the feedback screen has been pressed, the user terminal 20 transmits a notification to that effect to the information processing device 10.

[0122] In step S905, if the number of episodes for the user stored in the episode DB 122 is greater than a predetermined threshold, the first generation unit 135 selects an episode from the episodes stored in the episode DB 122 based on numerical information and date information.

[0123] In step S907, first generation unit 135 generates a first prompt using the selected episode, numerical information, and date information if an episode is selected. Alternatively, if an episode is not selected, first generation unit 135 generates a first prompt using all episodes, numerical information, and date information of the user stored in episode DB 122.

[0124] In step S909, the first generator 135 transmits the generated first prompt to the server 30, thereby causing the large-scale language model of the server 30 to generate text related to the user's strengths.

[0125] In step S911, the server 30 receives the first prompt.

[0126] In step S913, the server 30 generates text about the user's strengths by inputting the first prompt into a large-scale language model.

[0127] In step S915, the server 30 transmits the generated text relating to the user's strengths to the information processing device 10.

[0128] In step S917, the first generating unit 135 receives the text related to the user's strengths from the server 30.

[0129] In step S919, the display unit 133 causes the user terminal 20 to display a feedback screen including text relating to the user's strengths.

[0130] <1.5. Screen Examples> Examples of screens used in the system 1 according to the embodiment of the present disclosure will be described below. Figures 10 to 13 are diagrams illustrating a portal screen, an input screen (editing screen), an advice screen, and a feedback screen.

[0131] FIG. 10 is an example of a portal screen displayed on the user terminal 20. As shown in FIG.

[0132] As shown in FIG. 10, a portal screen 1000 includes a display section 1001, a display section 1002, and buttons 1003 to 1006.

[0133] The display unit 1001 displays a first graph. The first graph is a graph that represents the user's state, chronologically, by the happiness level of each experience of the user. For example, the first graph is a line graph or curve that has the happiness level on the vertical axis and the year on the horizontal axis, passing through the time and happiness level of each episode of the user.

[0134] The display unit 1002 displays the episode for the portion of the first graph selected on the display unit 1001. The display unit 1002 may be configured to display the episodes in chronological order automatically or manually. In the case of manual display, the display unit 1002 may be configured to accept user operations by providing buttons for moving forward and backward, for example, on the screen 1000.

[0135] The button 1003 is a button for displaying an input screen. In response to a user pressing the button 1003 on the user terminal 20, the user terminal 20 transmits to the information processing device 10 that the button 1003 has been pressed. When the button 1003 is pressed, the display unit 133 displays the input screen (screen 1100) shown in FIG. 11 on the user terminal 20.

[0136] The button 1004 is a button for displaying an advice screen. In response to a user pressing the button 1004 on the user terminal 20, the user terminal 20 transmits to the information processing device 10 that the button 1004 has been pressed. When the button 1004 is pressed, the display unit 133 displays an advice screen (screen 1200) shown in FIG. 12 on the user terminal 20. The screen 1000 may display a message instructing the user to press the button 1004 after registering a predetermined number (e.g., 10) or more of episodes. Registering the predetermined number or more of episodes is expected to ensure that the number of episodes included in the second prompt is at least the predetermined number. This is because it is possible to improve the accuracy of questions for enriching the episodes generated by the second generation unit 136. The message may be displayed in the vicinity of the button 1004, or when the user hovers the mouse over the button 1004 or an icon prepared in the vicinity of the button 1004, or the like.

[0137] Button 1005 is a button for displaying a correction screen. In response to a user pressing button 1005 on user terminal 20, user terminal 20 transmits to information processing device 10 that button 1005 has been pressed. When button 1005 is pressed, display unit 133 causes user terminal 20 to display a correction screen (screen 1100) shown in FIG. 11 .

[0138] The button 1006 is a button for displaying a feedback screen. In response to a user pressing the button 1006 on the user terminal 20, the user terminal 20 transmits to the information processing device 10 that the button 1004 has been pressed. When the button 1006 is pressed, the display unit 133 displays the feedback screen (screen 1300) shown in FIG. 13 on the user terminal 20. Note that the screen 1000 may display a message instructing the user to press the button 1006 after registering a predetermined number (e.g., 10) or more of enriched episodes registered by answering the above questions. By registering the predetermined number or more enriched episodes, it is expected that the number of enriched episodes included in the first prompt will be at least the predetermined number. This is because the accuracy of the text regarding the user's strengths generated by the first generation unit 135 can be improved. The message may be displayed in the vicinity of the button 1006, or may be displayed when the mouse is placed over the button 1006 or an icon prepared in the vicinity of the button 1006, or the like.

[0139] FIG. 11 is an example of an input screen displayed on the user terminal 20. As shown in FIG.

[0140] As shown in FIG. 11, a screen 1100 includes a pull-down menu 1101 , a pull-down menu 1102 , an image addition section 1103 , a text box 1104 , a text box 1105 , a text box 1106 , and a button 1107 .

[0141] The pull-down menu 1101 is a pull-down menu for inputting date information of an experience. In the user terminal 20, in response to the user pressing the pull-down menu 1101, a plurality of predetermined date information items are displayed so that the user can select the date information. The displayed date information may be, for example, the Gregorian calendar year, the year and month, the date, and age. The pull-down menu 1101 accepts an operation by the user to specify one or more pieces of displayed date information.

[0142] The pull-down menu 1102 is a pull-down menu for inputting numerical information (for example, happiness levels). In response to the user pressing the pull-down menu 1102 on the user terminal 20, a plurality of predetermined happiness levels (-10 to 10) are displayed so that the user can select from them. The pull-down menu 1102 accepts the user's designation of the displayed happiness levels.

[0143] The image adding unit 1103 realizes a function for the user to add an image related to an experience. Images can be added by a user operation. The image adding unit 1103 may also be configured to add a video.

[0144] A text box 1104 is a text box for inputting the title of an episode relating to the user's experience.

[0145] The text box 1105 is a text box for inputting an episode related to the user's experience. Note that the text box 1105 may be configured to include a text box for inputting facts about the episode and a text box for inputting what the user felt about the episode.

[0146] The text box 1106 is a text box for inputting the emotions felt by the user when experiencing the experience. The emotions here are not numerical information such as happiness levels, but rather sentences in which the user expresses how they specifically felt.

[0147] The button 1107 is a button for transmitting data input into the pull-down menu 1101, the pull-down menu 1102, the image addition section 1103, the text box 1104, the text box 1105, and the text box 1106 to the information processing device 10. In response to the user pressing the button 1107 on the user terminal 20, the user terminal 20 transmits the data to the information processing device 10.

[0148] Furthermore, screen 1100 may be used as a correction screen. When screen 1100 is used as a correction screen, it may be configured so that information stored in episode DB 122 is reflected and displayed in pull-down 1101, pull-down 1102, image addition section 1103, text box 1104, text box 1105, and text box 1106.

[0149] FIG. 12 is an example of an advice screen displayed on the user terminal 20. As shown in FIG.

[0150] As shown in FIG. 12, the screen 1200 includes a display unit 1201, a button 1003, a button 1004, a button 1005, a button 1006, and the like.

[0151] Display unit 1201 displays questions for enhancing the episode generated by second generation unit 136 when button 1004 is pressed. Display unit 1203 is configured to allow the user to copy questions for enhancing the episode so that the user can use the copies.

[0152] FIG. 13 is an example of a feedback screen displayed on the user terminal 20. As shown in FIG.

[0153] As shown in FIG. 13, a screen 1300 includes a display section 1301, a button 1302, and the like.

[0154] Display unit 1301 displays the text about the user's strengths generated by first generation unit 135 when button 1005 is pressed. Display unit 1301 is also configured to allow the user to copy the text about the user's strengths so that the user can use it.

[0155] A button 1302 is used to return to the previous screen.

[0156] <1.6.Summary> As described above, the technology disclosed herein accepts input of an episode experienced by a user and numerical information that quantifies the degree of a predetermined emotion the user felt when experiencing the episode. The technology disclosed herein stores the accepted episode and numerical information in a memory. The technology disclosed herein uses the episode and numerical information stored in the memory to generate a first prompt for a large-scale language model to generate text related to the user's strengths. The technology disclosed herein inputs the created first prompt into the large-scale language model to generate text related to the user's strengths. The technology disclosed herein then outputs the text related to the user's strengths. In this way, the technology disclosed herein can present the unique strengths of a user who does not understand their own strengths or who has difficulty expressing them.

[0157] The technology disclosed herein also uses the episodes stored in memory and numerical information to generate a second prompt for causing a large-scale language model to generate a question for enriching the episode. The technology disclosed herein inputs the generated second prompt into the large-scale language model to generate a question, and presents the generated question to the user. This allows the user to know what kind of episode they should input in order to know their strengths, allowing the user to more clearly understand their strengths.

[0158] Furthermore, when the number of episodes stored in memory is greater than a predetermined threshold, the technology disclosed herein selects an episode based on numerical information and generates a first prompt using the selected episode and the numerical information about the selected episode. This allows the most important episode to the user to be selected based on the numerical information from among the user's multiple episodes, thereby generating text related to the user's unique strengths and allowing the user to more clearly understand their own strengths.

[0159] Furthermore, the technology disclosed herein generates a first prompt that instructs a large-scale language model to generate the user's strengths by focusing on episodes from the selected episodes that are highly unique and that reveal the user's strengths, as well as on numerical information about those episodes. This does not treat all selected episodes equally, but rather focuses on episodes that are highly unique and that reveal the user's strengths, as well as on numerical information about those episodes, causing the large-scale language model to generate text about the user's strengths. This makes it possible to generate text about the user's strengths that is more unique to the user, allowing the user to more clearly understand their own strengths.

[0160] <2. Modifications> Although several embodiments of the present disclosure have been described above, these embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are intended to be included in the scope of the inventions and their equivalents as defined in the claims, as well as in the scope and spirit of the inventions.

[0161] For example, although the large-scale language model is implemented in the external server 30 in the above example, the present invention is not limited to this. The large-scale language model may be stored in the information processing device 10, and questions for enriching text and episodes related to the user's strengths may be generated without external communication.

[0162] Furthermore, in the above embodiment, the second generation unit 136 generates a second prompt in response to a user request, inputs the generated second prompt into a large-scale language model, and generates a question to enrich the episode, but this is not limited to this.

[0163] For example, the second generation unit 136 may be configured to generate a second prompt when a predetermined condition is met, input the generated second prompt into a large-scale language model, and generate a question to enrich the episode.

[0164] The predetermined condition can be any condition that is deemed necessary to enrich the episodes, such as that the amount of text in an episode is less than a predetermined amount, or that the sum of the number of episodes and the amount of text is less than a predetermined amount.

[0165] According to this configuration, when a predetermined condition is satisfied, the second generation unit 136 generates a question for the user to automatically enrich the episode. The display unit 133 displays the generated question on the user terminal 20. In this way, the technology disclosed herein automatically presents the user with a question that enriches the episode when a predetermined condition is satisfied, and thus allows the user to easily add or modify the episode to make it easier to generate text related to their own strengths.

[0166] The technology disclosed herein can also be used for job hunting support and training. Examples of training include mutual understanding training for new employees, team building training, training to improve management skills, and career design training. As described above, the technology disclosed herein can be applied to a communication-mediated environment, and therefore has a high affinity with online job hunting support and training. Below, an example of its use in job hunting support will be described.

[0167] In job hunting support, the user's strengths are generated through the following steps (1) to (3). (1) The user inputs from the user terminal 20 an episode that he or she has experienced and the degree of happiness associated with that experience. (2) The information processing device 10 generates a first prompt and inputs the first prompt into a large-scale language model, thereby generating text related to the user's strengths. (3) Present the user's strengths to the user.

[0168] The user then writes down their strengths in their resume as a way to promote themselves, and trains to be able to explain those strengths in an interview.

[0169] In this way, using the technology of the present disclosure, even if a user is not good at expressing themselves, they can express themselves in the way necessary for job hunting.

[0170] Furthermore, the technology disclosed herein is not limited to use in job hunting support. For example, users continue to gain various experiences after starting work. Therefore, by extracting the user's strengths after adding the episodes the user experienced after starting work, the user can learn about the new strengths he or she has acquired. This allows the user to recognize his or her own growth and discover a new side of himself or herself after starting work. Furthermore, the strengths can also be used for training, self-improvement, and career design.

[0171] Furthermore, in the above embodiment, an example has been described in which happiness level is used as the numerical information, but this is not limited to this. For example, interest level, disgust, etc. can be used as the numerical information. When interest level is used as the numerical information, the level of interest can be expressed as -10 to 10. When disgust level is used as the numerical information, the strength of disgust can be expressed as -10 to 10.

[0172] <Basic computer hardware configuration> 14 is a block diagram showing the basic hardware configuration of a computer 1400. The computer 1400 includes at least a processor 1401, a main memory device 1402, an auxiliary memory device 1403, and a communication IF (interface) 1404. These are electrically connected to each other by a communication bus 1406.

[0173] The processor 1401 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0174] The main memory device 1402 is used to temporarily store programs and data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0175] The auxiliary storage device 1403 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0176] The communication IF 1404 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.

[0177] Note that the computer 1400 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 1400 and interconnecting them via a network. In this way, the computer 1400 is a concept that includes not only a computer 1400 housed in a single housing or case, but also a virtualized computer system.

[0178] <Basic functional configuration of computer 1400> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 11) of the computer 1400. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0179] The functional units of the computer 1400 can also be realized by distributing all or part of the functional units among multiple computers 1400 interconnected via a network. The computer 1400 is a concept that includes not only a single computer 1400 but also a virtualized computer system.

[0180] The control unit is realized by the processor 1401 reading out various programs stored in the auxiliary storage device 1403, expanding them in the main storage device 1402, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0181] The storage unit is realized by a main storage device 1402 and an auxiliary storage device 1403. The storage unit stores data, various programs, and various databases. Furthermore, the processor 1401 can allocate a storage area corresponding to the storage unit in the main storage device 1402 or the auxiliary storage device 1403 in accordance with a program. Furthermore, the control unit can cause the processor 1401 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0182] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Typically, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 1401 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0183] Note that the databases and masters in this disclosure may include any data structure in which information is structurally defined (such as a list, dictionary, associative array, or object). The data structure also includes data that can be considered as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

[0184] The communication unit is realized by the communication IF 1404. The communication unit realizes a function of communicating with other computers 1400 via a network. The communication unit can receive information transmitted from other computers 1400 and input the information to the control unit. The control unit can cause the processor 1401 to execute information processing on the received information in accordance with various programs. Furthermore, the communication unit can transmit information output from the control unit to other computers 1400.

[0185] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.

[0186] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, and Java (registered trademark).

[0187] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or storage medium.

[0188] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0189] Although several embodiments of the present disclosure have been described above, these embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are intended to be included in the scope of the inventions and their equivalents as defined in the claims, as well as in the scope and spirit of the inventions.

[0190] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0191] (Appendix 1) A program to be executed by a computer having a processor and a memory, the program causing the processor to: a step (S609) of accepting input of an episode experienced by the user and numerical information that quantifies the degree of a predetermined emotion felt by the user when the experience was experienced; a step (S611) of storing the received episode and the numerical information in the memory; generating a first prompt for causing a large-scale language model to generate text related to the user's strengths using the episode and the numerical information stored in the memory (S907); a step (S909) of inputting the created first prompt into the large-scale language model to generate text related to the user's strengths; outputting text relating to the user's strengths (S919); A program that executes the following.

[0192] (Appendix 2) generating a second prompt (S707) using the episode stored in the memory to cause the large-scale language model to generate a question to enrich the episode; (S709) inputting the generated second prompt into the large-scale language model to generate the question; a step of outputting the question (S717); a step (S809) of accepting the episode modified by the user's operation; a step (S811) of storing the received modified episode in the memory; Execute In the step of generating the first prompt, the first prompt is generated using the modified episode and the numerical information stored in the memory. (Appendix 1) describes the program.

[0193] (Appendix 3) In the step of generating the second prompt, the second prompt is generated in response to a request from the user or when a predetermined condition is satisfied. (Appendix 2) The program described in.

[0194] (Appendix 4) and generating the second prompt by selecting an episode based on the numerical information when the amount of episodes stored in the memory is greater than the predetermined threshold. The second prompt is generated using the selected episode and the numerical information about the selected episode. A program described in (Appendix 2) or (Appendix 3).

[0195] (Appendix 5) In the step of receiving the input, input of the episode, the numerical information, and date information when the user had the experience is received; In the storing step, the received episode, the numerical information, and the date information are stored in the memory; In the step of generating the first prompt, the first prompt is generated so as to cause the large-scale language model to generate text related to the user's strengths, with emphasis on the episode having the most recent date information about the episode among the episodes stored in the memory. (Appendix 1) describes the program.

[0196] (Appendix 6) and generating the first prompt by selecting an episode based on the numerical information when the amount of the episodes stored in the memory is greater than the predetermined threshold. (Appendix 1) describes the program.

[0197] (Appendix 7) In the step of receiving the input, input of the episode, the numerical information, and date information when the user had the experience is received; In the storing step, the received episode, the numerical information, and the date information are stored in the memory; and generating the first prompt by selecting an episode based on the numerical information and the date information about the episode when the amount of the episodes stored in the memory is greater than the predetermined threshold. (Appendix 6) The program described in.

[0198] (Appendix 8) In the step of generating the first prompt, the first prompt is generated by focusing on an episode that is highly unique and in which the strengths of the user can be found, among the plurality of episodes stored in the memory, and instructing the large-scale language model to generate the strengths of the user. (Appendix 6) The program described in.

[0199] (Appendix 9) An information processing device comprising a processor and a memory, wherein the processor: a step (S609) of accepting input of an episode experienced by the user and numerical information that quantifies the degree of a predetermined emotion felt by the user when the experience was experienced; a step (S611) of storing the received episode and the numerical information in the memory; generating a first prompt for causing a large-scale language model to generate text related to the user's strengths using the episode and the numerical information stored in the memory (S907); a step (S909) of inputting the created first prompt into the large-scale language model to generate text related to the user's strengths; outputting text relating to the user's strengths (S919); An information processing device that executes the above.

[0200] (Appendix 10) 1. A computer-implemented method comprising a processor and a memory, the processor: a step (S609) of accepting input of an episode experienced by the user and numerical information that quantifies the degree of a predetermined emotion felt by the user when the experience was experienced; a step (S611) of storing the received episode and the numerical information in the memory; generating a first prompt for causing a large-scale language model to generate text related to the user's strengths using the episode and the numerical information stored in the memory (S907); a step (S909) of inputting the created first prompt into the large-scale language model to generate text related to the user's strengths; outputting text relating to the user's strengths (S919); How to do it. [Explanation of symbols]

[0201] 1 System, 10 Information Processing Device, 12 Communication IF, 13 Input / Output IF, 15 Memory, 16 Storage, 20 User Terminal, 22 Communication IF, 23 Input / Output IF, 25 Memory, 26 Storage, 30 Server, 80 Network, 101 Communication Unit, 102 Memory Unit, 103 Control Unit, 121 User DB, 122 Episode DB, 131 Reception Control Unit, 132 Transmission Control Unit, 133 Display Unit, 134 Input Unit, 135 First Generation Unit, 136 Second Generation Unit, 143 Image Addition Unit, 201 Communication Unit, 202 Memory Unit, 203 Control Unit, 231 Reception Control Unit, 232 Transmission Control Unit, 233 Reception Unit, 234 Registration Unit, 235 Notification Unit, 236 Display Unit, 1000 Screen, 1001 Display Unit, 1002 Display Unit, 1003 Button, 1004 button, 1005 button, 1006 button, 1100 screen, 1101 pull-down, 1102 pull-down, 1103 image addition section, 1104 text box, 1105 text box, 1106 text box, 1107 button, 1200 screen, 1201 display section, 1203 display section, 1300 screen, 1301 display section, 1302 button, 1400 computer, 1401 processor, 1402 main memory device, 1403 auxiliary memory device, 1404 communication IF, 1406 communication bus.

Claims

1. A program to be executed by a computer having a processor and a memory, the program causing the processor to: a step of receiving an input of an episode experienced by a user and numerical information that quantifies the degree of a predetermined emotion felt by the user when the user experienced the episode; storing the received episode and the numerical information in the memory; generating a first prompt using the episode stored in the memory and the numerical information to cause a large-scale language model to generate text related to the user's strengths; inputting the created first prompt into the large-scale language model to generate text about the user's strengths; outputting text about the user's strengths; A program that executes the following.

2. using the episode stored in the memory to generate a second prompt for the large-scale language model to generate a question to enrich the episode; inputting the generated second prompt into the large-scale language model to generate the question; outputting the question; accepting the episode modified by the user's operation; storing the received modified episode in the memory; Execute In the step of generating the first prompt, the first prompt is generated using the modified episode and the numerical information stored in the memory. The program according to claim 1.

3. In the step of generating the second prompt, the second prompt is generated in response to a request from the user or when a predetermined condition is satisfied. The program according to claim 2.

4. and generating the second prompt by selecting an episode based on the numerical information when the amount of the episodes stored in the memory is greater than a predetermined threshold. The second prompt is generated using the selected episode and the numerical information about the selected episode. The program according to claim 2.

5. In the step of receiving the input, input of the episode, the numerical information, and date information when the user had the experience is received; In the storing step, the received episode, the numerical information, and the date information are stored in the memory; In the step of generating the first prompt, the first prompt is generated so as to cause the large-scale language model to generate text related to the user's strengths, with emphasis on the episode having the most recent date information about the episode among the episodes stored in the memory. The program according to claim 1.

6. and generating the first prompt by selecting an episode based on the numerical information when the amount of the episodes stored in the memory is greater than a predetermined threshold. The first prompt is generated using the selected episode and the numerical information about the selected episode. The program according to claim 1.

7. In the step of receiving the input, input of the episode, the numerical information, and date information when the user had the experience is received; In the storing step, the received episode, the numerical information, and the date information are stored in the memory; and generating the first prompt by selecting an episode based on the numerical information and the date information about the episode when the amount of the episodes stored in the memory is greater than the predetermined threshold. The program according to claim 6.

8. In the step of generating the first prompt, the first prompt is generated by focusing on an episode that is highly unique and in which the user's strengths can be found, and on the numerical information about the episode, from among the selected episodes, and instructing the large-scale language model to generate the user's strengths. The program according to claim 6.

9. An information processing device comprising a processor and a memory, wherein the processor: receiving an input of an episode experienced by a user and numerical information that quantifies the degree of a predetermined emotion felt by the user when experiencing the episode; storing the received episode and the numerical information in the memory; generating a first prompt using the episode stored in the memory and the numerical information to cause a large-scale language model to generate text related to the user's strengths; inputting the created first prompt into the large-scale language model to generate text about the user's strengths; outputting text about the user's strengths; An information processing device that executes the above.

10. 1. A computer-implemented method comprising a processor and a memory, the processor: a step of receiving an input of an episode experienced by a user and numerical information that quantifies the degree of a predetermined emotion felt by the user when the user experienced the episode; storing the received episode and the numerical information in the memory; generating a first prompt using the episode stored in the memory and the numerical information to cause a large-scale language model to generate text related to the user's strengths; inputting the created first prompt into the large-scale language model to generate text about the user's strengths; outputting text about the user's strengths; How to do it.

Images