Information processing system

Abstract

We provide information processing systems and other tools that make it easier for users to achieve what they want to do. [Solution] According to one aspect of the present invention, an information processing system is provided which includes a processor, wherein in a first acquisition step, the processor acquires desire information representing what the user wants to do based on input to a user terminal, and in a first presentation step, based on the acquired desire information, contribution information that contributes to the realization of what the user wants to do is presented to the user via the user terminal.

Description

Technical Field

[0006] , , ,

[0005] , , ,

[0001] The present invention relates to an information processing system.

Background Art

[0002] Patent Document 1 discloses a technique for generating schedules for a plurality of training activities based on a selected training category and performance information such as a pace target or a resistance target recorded during the training activity or input by the user in response to a question after the activity.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In addition to the above training activities, there are many things that the user wants to do. What the user wants to do cannot be realized just by thinking, and some action needs to be taken to realize it, but it may be difficult to take such action appropriately.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system or the like that can easily realize what the user wants to do.

Means for Solving the Problems

[0006] According to one aspect of the present invention, there is provided an information processing system including a processor, wherein the processor acquires desire information representing what the user wants to do based on an input to the user terminal in a first acquisition step, and presents contribution information contributing to the realization of what the user wants to do to the user via the user terminal based on the acquired desire information in a first presentation step.

[0007] This configuration makes it easier for users to achieve what they want to do. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the overall configuration of the implementation support system 1. [Figure 2] This figure shows an example of the hardware configuration of the server device 10. [Figure 3] This figure shows an example of the hardware configuration of user terminal 20. [Figure 4] This is an activity diagram showing an example of the implementation support process. [Figure 5] This figure shows an example of the displayed registration screen. [Figure 6] This figure shows an example of instructions for AI module 3. [Figure 7] This figure shows an example of the selection screen that is displayed. [Figure 8] This figure shows an example of the detailed registration screen that is displayed. [Figure 9] This figure shows an example of the continuation of the detailed registration screen. [Figure 10] This figure shows an example of instructions for AI module 3. [Figure 11] This figure shows an example of a to-do list that is displayed. [Figure 12] This figure shows an example of a displayed grandchild task. [Figure 13] This diagram shows an example of a "Things I Want to Do" database. [Figure 14] This figure shows an example of the displayed summary list. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0010] Incidentally, the program for implementing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or it may be provided as a downloadable medium from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as "reference information") is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a pre-trained model that has learned the correlation between input and output in advance, or a large-scale language model that can output a desired result by inputting a prompt.

[0012] Furthermore, in one embodiment, "part" may include, for example, hardware resources implemented by a circuit in a broad sense, and the information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various types of information are handled, and this information can be represented, for example, by the physical values ​​of signal values ​​representing voltage and current, the high or low values ​​of signal values ​​as a set of binary bits composed of 0s or 1s, or by quantum superposition (so-called qubits), and communication and calculations can be performed on a circuit in a broad sense.

[0013] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] <Embodiment> 1. System Configuration Hereinafter, the system configuration according to the embodiment will be described. FIG. 1 is a diagram showing an example of the overall configuration of the realization support system 1. In FIG. 1, each device included in the realization support system 1 and an overview of the users who use these devices are shown. Each overview will be described as needed while referring to other figures.

[0015] The realization support system 1 is an information processing system that provides a realization support service for assisting the realization of what a user wants to do. What the user wants to do may include various things such as a specific activity (e.g., mountain climbing, camping, or driving) that the user performs by moving their body, a specific experience (e.g., visiting a museum, attending a music live, or staying at a hot spring resort), or the achievement of a specific goal (e.g., obtaining a qualification, completing a marathon, or reaching a target weight). What the user wants to do can be anything as long as the user wants to do it, and it may include things that are highly difficult and somewhat difficult to realize. Also, what the user wants to do may be something the user has not experienced or something the user has experienced.

[0016] The implementation support system 1 comprises a communication line 2, a server device 10, and a user terminal 20. The user terminal 20 is an information processing device used by users registered as users of the implementation support system 1. The user terminal 20 may be, for example, a smartphone, a laptop computer, a desktop computer, or a tablet device.

[0017] Communication line 2 is not particularly limited, but for example, it is composed of the Internet network. Communication line 2 may also include a local area network, a mobile communication network, and a VPN (Virtual Private Network). Communication line 2 mediates the exchange of data between devices connected to its own line. In the example in Figure 1, the server device 10 is connected to communication line 2 by wire, and the user terminal 20 is connected wirelessly. Note that the connection of each device to communication line 2 may be wired or wireless.

[0018] The server device 10 is an information processing device that performs implementation support processing to help users achieve what they want to do. The server device 10 is equipped with, for example, an AI module 3 (AI = Artificial Intelligence). The AI ​​module 3 is a module that has been adjusted to realize a predetermined function using AI technology. In the following explanation, for the sake of brevity, we will describe examples of how the AI ​​module 3 realizes various functions, but each function may also be realized using a dedicated AI module.

[0019] The server device 10 performs authentication processing to authenticate users registered as users of the implementation support system 1, and display processing to display images on the user terminal 20. For example, the server device 10 stores authentication information (user ID and password, etc.) for user authentication and authenticates users who enter the authentication information. The server device 10 may also authenticate users using an external authentication service. By authenticating users, the server device 10 can restrict access to data or make data entered by users identifiable by adding identification information. The implementation support system 1 can be used even by users who are not registered as users.

[0020] Furthermore, the server device 10 performs display processing, such as generating and sending HTML (Hyper Text Markup Language) files, and displays a web page showing the system screen on the user terminal 20 using a browser or similar function. Alternatively, the user terminal 20 may install an application program to use the implementation support system 1, and the server device 10 may perform display processing, such as generating and sending display data for that application. The server device 10 controls the display on the user terminal 20 by performing these display processing operations.

[0021] 2. Hardware Configuration The hardware configuration according to this embodiment will be described below. Figure 2 shows an example of the hardware configuration of the server device 10. The server device 10 comprises a control unit 11, a storage unit 12, a communication unit 13, and a bus 14. The bus 14 electrically connects each part of the server device 10.

[0022] (Control Unit 11) The control unit 11 has at least one processor. The at least one processor may consist of, for example, a central processing unit (CPU), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), one or more integrated circuits, one or more discrete circuits, or a combination thereof.

[0023] The control unit 11 is a computer that realizes various functions related to the implementation support system 1 by reading predetermined programs stored in the memory unit 12. In other words, information processing by software stored in the memory unit 12 is concretely realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. Note that the control unit 11 is not limited to being a single unit, and may be implemented with multiple control units 11 for each function, or a combination thereof.

[0024] (Storage unit 12) The storage unit 12 stores various types of information as defined above. This can be done, for example, as a storage device such as a solid-state drive (SSD) or hard disk drive (HDD) that stores various programs related to the implementation support system 1 executed by the control unit 11, or as a memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The storage unit 12 stores various programs and variables related to the implementation support system 1 executed by the control unit 11.

[0025] (Communications Section 13) The communication unit 13 is composed of a communication module. The communication module may be a wireless communication module compliant with standards such as IEEE 802.11a / b / g / n / ac / ax, LTE, 5G, 6G, or a wired communication module compliant with standards such as IEEE 802.3. The communication unit 13 is configured to transmit various electrical signals from the server device 10 to external components. The communication unit 13 is also configured to receive various electrical signals from external components to the server device 10. More preferably, the communication unit 13 may have a network communication function, thereby enabling the communication of various information between the server device 10 and external devices via the communication line 2.

[0026] Figure 3 shows an example of the hardware configuration of a user terminal 20. The user terminal 20 comprises a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a bus 26. The bus 26 electrically connects each part of the user terminal 20. The control unit 21, storage unit 22, and communication unit 23 are similar hardware to the control unit 11, storage unit 12, and communication unit 13 shown in Figure 2, although their specifications and models may differ.

[0027] (Input section 24) The input unit 24 has input receiving means such as keys, buttons, touchscreens, and mice, and accepts input from the user. The input unit 24 may also have sound receiving means such as a microphone, and may have a function to collect the user's voice and accept the input of the collected voice.

[0028] (Output section 25) The output unit 25 has display means such as a display and sound emission means such as a speaker, and outputs visual information and auditory information. For example, the output unit 25 displays visual information such as screens, images, icons, and text on a display surface such as a display, in a manner that is visible to the user. The output unit 25 also outputs audible sound such as speech or synthesized sound from the speaker.

[0029] 3. Information Processing The following describes the information processing according to the embodiment. In the following description, the server device 10 and the user terminal 20 are described as the main subjects of each information processing, but these information processing are executed by at least one processor provided in the implementation support system 1, that is, the processor in the control unit of each device. The implementation support system 1 executes the implementation support processing described above.

[0030] Figure 4 is an activity diagram showing an example of the implementation support process. The implementation support process is initiated, for example, when a user launches the "Things I Want to Do" app to find out what they want to do. The "Things I Want to Do" app is an application for using the implementation support services provided by the implementation support system 1. First, the server device 10 generates a registration screen for the user to register what they want to do (Activity A11), and displays the registration screen on the user terminal 20 (Activity A12).

[0031] Figure 5 shows an example of a displayed registration screen. The registration screen G1 shown in Figure 5 displays dialogue display fields C11, C12, C13, and C14, which show dialogue messages in a chat format. The server device 10 generates dialogue messages using the AI ​​module 3. The AI ​​module 3 has a natural language processing model whose accuracy has been improved by machine learning using a large dataset called LLM (Large Language Models), and is adjusted to realize a text generation function that can generate natural-sounding sentences.

[0032] Immediately after displaying the registration screen, the server device 10 instructs the AI ​​module 3 to generate dialogue messages according to a predetermined template. The AI ​​module 3 generates dialogue messages according to the instructions, and the server device 10 displays the generated dialogue messages in the dialogue display area. The dialogue display area where the dialogue messages generated by the AI ​​module 3 are displayed shows an "AI" icon, and the dialogue display area where the dialogue messages entered by the user are displayed shows a "User" icon.

[0033] First, the server device 10 displays the dialogue message "We are here to help you find out what you specifically want to do" in the dialogue display area C11. Next, the server device 10 has the AI ​​module 3 generate a predetermined question (Activity A13), and displays the generated question on the user terminal 20 (Activity A14). In the example in Figure 5, the dialogue display area C12 shows a dialogue message indicating the question "Please tell us your date of birth so we can suggest something that's perfect for you," along with an input field D11 for entering the date of birth.

[0034] The user terminal 20 accepts the input in input field D11 as the user's answer to the displayed question and displays the accepted answer (Activity A15). In the example in Figure 5, the dialogue display field C13 shows a dialogue message indicating the answer "Born in yyyy year mm month". Next, the server device 10 determines whether the question has ended or not (Activity A16), and if the question has not yet ended, it returns to A13 to generate the next question and displays it on the user terminal 20.

[0035] In the example in Figure 5, the dialogue display area C14 shows a dialogue message that asks, "Please choose the option that best suits your current feelings from the following choices," along with a list of feelings: "I want to find something I can do easily and quickly," "I want to take on a small challenge," "I want to find a new hobby or skill," "I want to do something I can do alone and focus on," "I want to find something fun to do with someone," "I want to get some exercise and refresh myself," "I want to do something I can enjoy in nature," and "I want to find the next level of challenge from something I've done in the past," as well as selection buttons B11 for choosing one of the options.

[0036] The user terminal 20 accepts input to the selection button B11 at A15 as the user's answer to the displayed question and displays the accepted answer. In the example in Figure 5, the selected feelings are "I want to do a little challenge," "I want to get some exercise and refresh myself," and "I want to do something I can enjoy in nature." Note that the questions asked to the user are not limited to these. For example, the server device 10 may display questions about the user's place of residence, marital status, whether they have children, or the difficulty level of what they want to do.

[0037] Furthermore, the server device 10 may omit questions that have already been answered when the user registered what they wanted to do in the past, or questions that can be estimated from information obtainable from the user terminal 20 (for example, estimating the user's residential area from the location information of the user terminal 20). When the server device 10 determines that all the questions prepared as templates have been answered and the questioning is complete, it then generates candidate information indicating possible things the user wants to do (Activity A21). The server device 10 generates candidate information, for example, by generating a prompt that instructs the AI ​​module 3 to output the candidate information.

[0038] Figure 6 shows an example of instructions for AI Module 3. Figure 6 shows prompt P1 for AI Module 3. Prompt P1 includes the instruction "#Request," which means "Please suggest something you want to do." It also includes conditions such as "#Conditions," which means "Please suggest 10 things you want to do based on user information," "The output should consist of a title and subtitle as a single selection," and "Please rate the difficulty of the desired tasks on a 5-point scale." Furthermore, "#Output Format" shows a JSON-formatted code. These are, for example, the contents of a pre-prepared template.

[0039] Furthermore, prompt P1 displays "#User Information," indicating that "Current Location" is "Tokyo," "Date of Birth" is "yyyy / mm," and "Current Feelings" are "I want to try a small challenge," "I want to get some exercise and refresh myself," and "I want to do something enjoyable in nature." "Current Location" is, for example, a location estimated from the location information of user terminal 20. "Date of Birth" and "Current Feelings" are based on the answers to the questions described in Figure 5.

[0040] When AI Module 3 receives instructions via Prompt P1, it generates and outputs candidate information for desired actions according to those instructions. AI Module 3 is configured to implement a candidate information generation function that, when input such as requests, conditions, user information, and output format as indicated by Prompt P1, generates and outputs candidate information for desired actions that correspond to those conditions, user information, and output format. Specifically, AI Module 3 performs machine learning using training data that takes requests, conditions, user information, and output format as input and candidate information for desired actions as output, and generates a learning model. AI Module 3 then implements the candidate information generation function by using the generated learning model.

[0041] The server device 10 generates candidate information using the generation function realized by the AI ​​module 3 as described above. Next, the server device 10 generates a selection screen for selecting one of the generated candidate information (Activity A22), and displays the generated selection screen on the user terminal 20 (Activity A23).

[0042] Figure 7 shows an example of a displayed selection screen. The selection screen G2 in Figure 7 displays a display field C21 for suggested activities and a registration button B23. Display field C21 shows the text prompting the user to select an activity, "We have prepared a list to help you find something you want to do...", as well as suggested activities such as "Climbing Mt. Fuji", "Skydiving experience", "Beginner camping experience", "Bouldering challenge", and "Horse riding experience", along with a selection button B21 and an add display button B22.

[0043] Each candidate entry includes a title (F21), a subtitle (F22), and a difficulty level (F23) for the activity. The title (F21) is a concise phrase that summarizes the activity. The subtitle (F22) provides a more detailed explanation of the activity. For example, "Climbing Mount Fuji" would include information such as altitude, estimated time required, and main climbing routes. The difficulty level (F23) indicates the level of difficulty in achieving the activity. For instance, "Climbing Mount Fuji" is rated at a relatively high level (4) due to factors such as physical fitness, equipment, weather, and altitude. Similarly, "Skydiving" is rated at level (5) because while beginners are accompanied by an instructor and therefore technically not difficult, it presents a significant psychological hurdle. These levels represent absolute difficulty levels that do not vary depending on individual user circumstances (such as abilities) (however, the values ​​may change due to the randomness of AI output).

[0044] When the additional display button B22 is pressed, previously undisplayed candidate information is shown. The user uses the displayed candidate information as a reference and selects what they want to do by pressing the selection button B21 corresponding to the candidate information they want to do. In the example in Figure 7, "Climbing Mount Fuji" is selected as what the user wants to do. The user terminal 20 accepts the operations on the selection button B21 and the registration button B23 as selection operations (activity A24) and sends selection data indicating the title and subtitle of the selected activity to the server device 10.

[0045] The server device 10 acquires the title and subtitle indicated by the transmitted selection data as desire information that shows what the user wants to do (Activity A25). Next, the server device 10 generates a detailed registration screen based on the acquired desire information (Activity A31) and displays the generated detailed registration screen on the user terminal 20 (Activity A32). The detailed registration screen is a screen for registering the details of what the user wants to do.

[0046] Figure 8 shows an example of the displayed detailed registration screen. The detailed registration screen G3 shown in Figure 8 displays a display field C31 for the title of what you want to do, a display field C32 for the subtitle, a difficulty calculation button B31, a difficulty display field C33, a display field C34 for the degree of desire, an input button B32 for the degree of desire, a save button B33, and a next page button B34. The server device 10 displays the title and subtitle indicated by the acquired candidate information in display fields C31 and C32.

[0047] When the calculation button B31 is operated, the server device 10 calculates the difficulty level of the task based on the title and subtitle, for example, and displays the calculated difficulty level in the display field C34. In the example in Figure 8, "Climbing Mount Fuji" is displayed as the title, and as shown in Figure 7, the level is 4. In this case, the level does not change due to user-specific circumstances, so it represents the absolute difficulty level.

[0048] When the user operates the input button B32 to enter a desired level, the server device 10 displays the entered desired level in the display field C34. In the example in Figure 8, it is shown that the desired level is 80% when the maximum value is 100%. The user terminal 20 accepts input into the input field D31 and operations on the calculation button B31 and input button B32 as detailed registration operations to register the details of what the user wants to do (Activity A33). When the save button B33 is operated, the server device 10 stores the detailed information registered by the accepted detailed registration operation in the "Things to Do DB" (Data Base) (Activity A34). The "Things to Do DB" will be explained later. When the next page button B34 is operated, the server device 10 displays the next detailed registration screen.

[0049] Figure 9 shows an example of the continuation of the detailed registration screen. The detailed registration screen G4 shown in Figure 9 displays a button B41 for creating an image to boost the user's motivation (hereinafter referred to as "motivation-boosting image"), a selection button B42, a motivation-boosting image C41, an input field D41 for the planned execution date, a button B43 for creating a to-do list, and a save button B44.

[0050] When the Create button B41 is pressed, the server device 10 inputs the user's request to the AI ​​module 3 and instructs it to generate a motivational image. The AI ​​module 3 is also configured to generate images, and for example, it generates a motivational image based on a prompt that includes a request such as "Generate an image that can be associated with the title according to the conditions," the conditions "Single scene, no human faces, simple composition, brushstrokes should be as invisible as possible," and the title instruction "Mount Fuji." If the Select button B42 is pressed, the server device 10 executes a process to upload the image selected by the user as a motivational image to its own device. In the example in Figure 9, the motivational image C41 generated or uploaded in this way is displayed.

[0051] In input field D41, the user enters the planned execution date, indicating when they intend to carry out what they want to do. The operation of the Create button B41 and Select button B42, as well as the input in input field D41, are accepted as detailed registration operations (Activity A33). When the Save button B44 is operated, the server device 10 stores the motivation-boosting image and the planned execution date in the Things to Do DB (Activity A34).

[0052] When the Create button B43 is pressed, the server device 10 generates a to-do list (Activity A35). The to-do list is a list of things that need to be done in order to achieve what the user wants to do. The server device 10 generates the to-do list, for example, by generating a prompt that instructs the AI ​​module 3 to output the to-do list.

[0053] Figure 10 shows an example of instructions for AI module 3. Figure 10 shows prompt P2 for AI module 3. Prompt P2 includes the instruction, "Create a list of things to do to achieve what you want to do," the thing to do, "Climb Mount Fuji," and the conditions, "List five main tasks," and "List five subtasks for each main task that are necessary to achieve the main tasks." Prompt P2 also includes "#Output language," "#Output format," and "#Output format."

[0054] AI Module 3 generates a to-do list in accordance with instructions given by Prompt P2. AI Module 3 is configured to implement a list generation function that generates a to-do list according to the conditions, output language, output format, and output format input, such as prompt P2. Specifically, AI Module 3 performs machine learning using training data that takes conditions, output language, output format, and output format as input and a to-do list as output, and generates a learning model. AI Module 3 then implements the list generation function using the generated learning model.

[0055] The server device 10 generates a to-do list (Activity A35) using the list generation function of the AI ​​module 3 described above, and displays the generated to-do list on the user terminal 20 (Activity A36).

[0056] Figure 11 shows an example of a displayed to-do list. The list screen G5 in Figure 11 displays the main task area C51, the subtask areas C52-C55, the save button B51, and the add button B52. The main task, "Plan a climb of Mt. Fuji," is displayed in area C51. The subtasks, "Decide on a climbing date," "Book accommodation," "Secure transportation," and "Choose a climbing route," are displayed in areas C52-C55.

[0057] The main task and each subtask display a title such as "Plan a climb of Mt. Fuji" and a subtitle that summarizes the task. When the Add button B52 is pressed, input fields for entering the subtask title and summary appear, and the user can create a new subtask by entering this information. Each subtask displays a Delete button B56, and pressing this button will delete the subtask.

[0058] Furthermore, the display area for each subtask shows the AI ​​generation button B53, the manual generation button B54, and the selected task button B55. When the AI ​​generation button B53 is operated, the server device 10 uses the AI ​​module 3 to generate grandchild tasks (subtasks that are even lower in rank than the subtasks). In the case of the subtask "Decide on a climbing date," the server device 10 generates grandchild tasks such as "Check the weather forecast," "Consider the season and temperature," "Check the congestion status of the destination," and "Adjust the daylight hours and departure time."

[0059] When the manual generation button B54 is operated, the server device 10 generates and displays an input field for a grandchild task. The user can manually enter a grandchild task into the generated input field. When the selection task button B55 is operated, the server device 10 generates a selection-type grandchild task using the AI ​​module 3.

[0060] Figure 12 shows an example of a displayed subtask. The list screen G6 in Figure 12 displays a subtask called "Choose a Hiking Route" in display field C55, subtasks of that subtask in display fields C61-C64, and a save button B51. Display fields C61-C64 show "Yoshida Route," "Subashiri Route," "Gotemba Route," and "Fujinomiya Route" as selectable subtasks. Each of these subtasks contains a radio button, and only one can be selected. In the example in Figure 12, "Subashiri Route" is selected. Each display field also contains a delete button B61, allowing users to delete unnecessary subtasks.

[0061] The user terminal 20 accepts button operations and input into input fields as editing operations for the to-do list (Activity A41), and sends operation data indicating the content of the editing operations to the server device 10. The server device 10 acquires the content of the editing operations indicated by the transmitted operation data as editing information (Activity A42), and regenerates the to-do list based on the acquired editing information (Activity A43). The server device 10 displays the regenerated to-do list on the user terminal 20 (Activity A44).

[0062] As the user repeatedly performs editing operations, actions A41 to A44 are repeated, and the to-do list is edited. When the to-do list is complete, the user operates the save button B51 shown in Figure 11 or Figure 12. When the save button B51 is operated, the user terminal 20 accepts it as a save operation (activity A45), and the server device 10 stores the list information representing the to-do list in the To-Do DB (activity A46).

[0063] Figure 13 shows an example of a "Things to Do" database. The "Things to Do" database shown in Figure 13 stores both "things to do" information and "things to do" information. The "things to do" information includes the username, title, subtitle, summary, difficulty level, level of desire, motivational image, and planned execution date. The "things to do" information includes the main task, subtasks, and sub-tasks. As described above, the "things to do" information and "things to do" information are stored in the "Things to Do" database, registering the user's "things to do." As shown in Figure 13, a single user can register multiple "things to do."

[0064] The server device 10 displays a list of registered "things to do" and displays the "things to do" information and "things to do" information for the "things to do" selected from the list. The server device 10 may also update the "things to do" database based on user input. For example, if a user inputs information such as checking completed tasks, task-related information obtained by executing the tasks (for example, a link to accommodation, a map showing the travel route by car, and a webpage explaining the climbing route in the case of climbing Mt. Fuji), and result information showing the results of executing the "things to do" (such as photos of the location), the server device 10 stores this input information in the "things to do" database as progress information indicating the progress of the "things to do". By referring to the stored progress information, the user can manage the progress towards completing the "things to do".

[0065] As described above, the server device 10 functions as an example of a first acquisition unit that acquires desire information representing what the user wants to do based on input to the user terminal 20. The server device 10 acquires desire information at A25 shown in Figure 4. The input of "date of birth" into input field D11 and the selection operation of the current mood using selection button B11 shown in Figure 5 are both examples of input to the user terminal 20, and through these inputs, desire information indicating the title and subtitle of the desired activity, "climbing Mount Fuji," is acquired in the example in Figure 7.

[0066] Furthermore, the server device 10 functions as an example of a first presentation unit that presents contribution information that contributes to the realization of what the user wants to do, based on the acquired desire information, to the user via the user terminal 20. In Figure 4, at A35 and A36, the server device 10 presents contribution information to the user via the user terminal 20 by displaying a to-do list, which is an example of contribution information, on the user terminal 20. The to-do list encourages concrete actions by showing what the user needs to do to realize what they want to do, thereby contributing to the realization of what the user wants to do. With this configuration, it is possible to make it easier for the user to realize what they want to do compared to when contribution information is not presented.

[0067] Contributing information includes a to-do list that outlines the steps needed to accomplish a desired activity. Figures 11 and 12 show examples of to-do lists presented to users. For example, if the desired activity is "climbing Mount Fuji," inexperienced climbers or those who have only climbed it on a tour may not easily come up with the necessary steps. However, by providing a to-do list as contributing information, even these individuals can more easily begin their desired activity compared to when a to-do list is not provided.

[0068] Here, the server device 10 functions as an example of a display unit that displays additional images for adding tasks to the user terminal 20. The AI ​​generation button B53, manual generation button B54, and selected task button B55 shown in Figure 11 are all examples of additional images for adding tasks, known as grandchild tasks. When an additional image is operated, the server device 10 (an example of the first display unit) performs additional processing to add tasks and presents a to-do list that includes the added tasks.

[0069] For example, when the selected task button B55 is operated, the server device 10 presents a to-do list that includes the sub-task shown in Figure 12 as an added task. In this configuration, the to-do list can be expanded as needed, such as when the user feels that there are other things that need to be done.

[0070] Furthermore, the contributing information includes information indicating the difficulty level of the activity. In the example in Figure 7, the user is presented with information indicating the difficulty level F23 of the activity, such as level 4 for climbing Mount Fuji and level 5 for skydiving. This configuration allows users to prepare themselves mentally before starting an activity, such as whether they should approach it casually or with determination.

[0071] Furthermore, contributing information includes information that represents the image of what one wants to do. Motivation-boosting image C41 shown in Figure 9 is a pictogram-like image of Mount Fuji, representing the desired activity of "climbing Mount Fuji," and is an example of information that represents the image of what one wants to do. Note that the information that represents the image of what one wants to do is not limited to images; it may also be text, audio, or a combination thereof. In any case, compared to cases where information that represents the image of what one wants to do is not included in the contributing information, the motivation to achieve what one wants to do can be strengthened.

[0072] Furthermore, the server device 10 functions as an example of a second acquisition unit that acquires relevant information about the user. This relevant information is, for example, the user's answers to the questions shown in Figure 5. In the example in Figure 5, the server device 10 functions as an example of a display unit that displays questions to the user. Next, the server device 10 (an example of a second acquisition unit) acquires the answers to the displayed questions as relevant information. In the example in Figure 5, the server device 10 acquires answers such as "Born in yyyy year, mm month" and "I want to try a little challenge" as relevant information.

[0073] Next, the server device 10 functions as an example of a second presentation unit that presents candidate information that can be used as desired information based on the acquired related information. In the example in Figure 7, the server device 10 presents candidate information such as "climbing Mount Fuji" and "skydiving experience" to the user via the user terminal 20 based on the acquired response. The server device 10 (an example of a first acquisition unit) then acquires information that represents the selected candidate from the presented candidate information as something the user wants to do, as desired information. In the example in Figure 7, the server device 10 acquires desired information that includes the title "climbing Mount Fuji".

[0074] In this way, by using relevant information about the user, it is possible to present suggested activities that match the user's characteristics or circumstances as indicated by the relevant information. For example, in the example in Figure 5, based on the relevant information "I want to do a little challenge," "I want to get some exercise and refresh myself," and "I want to do something I can enjoy in nature," suggested activities such as mountain climbing, skydiving, camping, bouldering, and horseback riding, which are of average or above difficulty and are performed outdoors, are presented as suggested activities. In addition, since the user's "date of birth" reveals their age, it is possible to present activities that match the user's age. With this approach, it is possible to make it easier for users to find something they want to do compared to not presenting suggested activities based on relevant information.

[0075] Furthermore, by using the answers to questions as related information, candidate information can be presented even without pre-registered information. Note that the questions asked to the user are not limited to those mentioned above. For example, questions may be asked about the user's current location, date of birth (including the date), gender, interests, hobbies, skills, past experiences, lifestyle, whether they prefer outdoor or indoor activities, whether they prefer working alone or in a group, or whether they prefer creative or non-creative activities.

[0076] Furthermore, the server device 10 may, for example, display a question to the user regarding the difficulty level of what they want to do. In this case, the user can choose a lower difficulty level if they want to take it easy, or a higher difficulty level if they want to put in some effort. The server device 10 may also display a question to the user regarding the location (prefecture, etc.) where they want to perform what they want to do. In this case, the user can answer the question according to their mood, such as whether they want to do it easily in a nearby location or go to a distant place for a change of pace, or they can answer with a place they particularly want to go.

[0077] In short, you can ask any question that has the potential to connect to what the user wants to do. However, asking too many questions can, while it may allow you to present candidate information that suits the user's preferences, it may also increase the likelihood of presenting information the user already knows or narrowing down the user's options, so it may be better to ask fewer questions.

[0078] Furthermore, the server device 10 may use information about the user (for example, profile information such as date of birth, gender, and hobbies) that was registered when the user registration was performed in the implementation support system 1 as related user information. In addition, the server device 10 may, for example, export the user's activity history from a schedule management application used by the user and obtain and use it as related user information, or similarly export the user's browsing history from a browser used by the user and obtain and use it as related user information.

[0079] <Variation: Sharing with other users> Users may be able to share the things they want to do with other users. For example, the server device 10 reads each user's things they want to do and things they need to do from the things they want to do DB, generates a summary (e.g., title, subtitle, and difficulty level), and displays a list of these summaries on the user terminal 20.

[0080] Figure 14 shows an example of a displayed summary list. The list screen G7 in Figure 14 displays summaries C71, C72, and C73, indicating tasks to be done, such as "Climbing Mount Fuji." Each summary includes a motivational image, planned execution date, title, subtitle, difficulty level, level of desire, and progress. The "progress" shows the percentage of completed tasks relative to the total number of tasks on the to-do list. These summaries can be displayed in order of registration, by planned date, or by level of desire.

[0081] When any summary is selected, the server device 10 displays detailed information about the selected task (such as task information, progress information, etc., that is not included in the summary). In this configuration, users can refer to what other users want to do. If the summary or detailed information contains the user's personal information, the server device 10 may exclude that personal information when displaying the summary and detailed information.

[0082] <Variation: Copy of what you want to do> The server device 10 may perform a process that allows users who see what other users want to do and want to try it themselves to register that thing as their own. For example, the server device 10 may display a registration button associated with each user's summary or detailed information. When a registration button is pressed, the server device 10 displays the registration screen, which is a copy of the information about the thing to do included in the summary or detailed information associated with that registration button.

[0083] The server device 10 registers what the user wants to do based on the user's editing and registration operations on the displayed registration screen. With this configuration, compared to the case where copying is not possible, the user can easily register what other users want to do as their own.

[0084] Furthermore, the server device 10 may allow users to set items that cannot be copied when copying the desired task information and the task information. For example, the server device 10 may display a screen on the user terminal 20 for setting whether each item can be copied, and then display a registration screen that shows only the information that can be copied, excluding the information that is set as uncopyable (e.g., desired level, scheduled execution date, or sub-tasks, etc.). This configuration makes it possible to prevent others from easily using information that the user does not want others to use.

[0085] <Variation: To-do list> In the embodiment, a three-tiered to-do list including a main task, subtasks, and grandchild tasks was described, but the to-do list is not limited to this; it may have one or two tiers, or four or more tiers. The number of task tiers may be predetermined depending on what you want to do, or it may be increased or decreased by user interaction. Furthermore, the method for creating the to-do list is not limited to the method described above.

[0086] For example, if the server device 10 (an example of the first display unit) has acquired first wish information and second wish information as wish information, it may present a to-do list that includes the things that the user wants to do as indicated by the second wish information, as things that need to be done in order to do what the user wants to do as indicated by the first wish information. For example, suppose first wish information containing the title "climb Mount Fuji" and second wish information containing the title "see the sunrise" have been acquired.

[0087] In that case, the server device 10 displays, for example, the list screen G5 shown in Figure 11 as a registration screen for what to do based on the first wish information. Then, when the add button B52 is operated, the server device 10 displays the options for the subtask to be added, and includes the second wish information, "Watch the sunrise," among the options. When the option "Watch the sunrise" is selected, the server device 10 generates and displays a subtask titled "Watch the sunrise."

[0088] The first and second desire information also includes combinations where the second desire information is a process for achieving the first desire information, such as "I want to travel around the world" and "I want to see the starry sky in the Namibian desert," or "I want to get a girlfriend" and "I want to lose weight." In any case, in this manner, it is possible to include what you want to do among the things you need to do.

[0089] Note that the method of adding the second desire information is not limited to this. For example, the server device 10 may display a summary list of things to do as shown in Figure 14, copy the displayed summary as a summary of the second desire information, and paste it into the to-do list of the first desire information, thereby adding the second desire information to the to-do list. Alternatively, if the summary list and the to-do list can be displayed simultaneously, the second desire information may be added to the to-do list of the first desire information by dragging and dropping. The server device 10 may also display a list of things to do in a select box and add the selected things to do as the second desire information to the to-do list of the first desire information.

[0090] Furthermore, the first and second wish information must have a certain degree of correlation. The server device 10 may determine whether or not to add the second wish information when it is added. For example, the server device 10 calculates a correlation score between the first and second wish information, and determines that it can be added if the calculated score is above a threshold. The correlation score can be calculated using well-known techniques such as co-occurrence analysis (analysis based on the frequency of two items appearing together) or Bayesian estimation.

[0091] Furthermore, if the calculated score is below a threshold, the server device 10 may, instead of immediately rejecting the addition, display a confirmation message such as "It seems unrelated, but do you really want to add it?" and decide whether or not to add it based on the user's actions. In either case, a more appropriate to-do list can be generated compared to when no decision is made regarding the addition or no comments are displayed.

[0092] <Variation example: Information showing an image of what you want to do> As described above, "information that shows an image of what you want to do," such as motivational images, may be images, text, audio, or a combination thereof, but the method of generating them is not limited to the method described above. For example, the server device 10 displays a keyword input field on the user terminal 20. The server device 10 then generates motivational images that are related to what the user wants to do, as well as the keywords entered in the input field.

[0093] Specifically, the server device 10 inputs the acquired desire information and the entered keywords into the AI ​​module 3, and generates a motivational image based on the prompt, "with the aim of increasing motivation to do what you want to do, and generating an image that evokes the entered keywords." With this configuration, information that is closer to the user's image can be generated as a motivational image, etc., compared to when keywords are not used.

[0094] Furthermore, the server device 10 may present multiple motivational images, etc., and register the one selected by the user as information about what they want to do. The server device 10 may also generate motivational images, etc., based on the aforementioned related information about the user. For example, the server device 10 inputs the answer to a question as related information into the AI ​​module 3 and generates a motivational image based on the prompt, "Generate an image that aims to increase the motivation to do what you want to do and that is appropriate to the user's characteristics or circumstances as indicated by the input related information." With this configuration, information that is more appropriate to the user's characteristics or circumstances can be generated as motivational images, etc., compared to when no related information is input.

[0095] <Variation: Difficulty level of what you want to do> In the example above, the difficulty level of the desired task included in the contribution information was an absolute difficulty level that was the same regardless of the user. However, it could also be a relative difficulty level that differs depending on the user. In that case, the server device 10 can calculate the relative difficulty level by inputting relevant information about the user into the AI ​​module 3. This relevant information could include, for example, information indicating age, gender, qualifications held, and past experience. With this configuration, it is possible to present contribution information that is closer to the difficulty level perceived by each individual user.

[0096] <Variation: Desired Information> In the example above, the desire information, which indicates what the user wants to do, was selected from the presented candidate information, but it is not limited to this. The server device 10 may also acquire a string indicating what the user wants to do (for example, a title and summary) as desire information. Alternatively, the server device 10 may acquire a selection from the summary list of things to do shown in Figure 14 as desire information. In short, any method is acceptable for acquiring desire information, as long as it provides information indicating what the user wants to do.

[0097] <Variation: Candidate Information> The suggested information presented to the user is not limited to the above. For example, the server device 10 may present the user with things they have done in the past as suggested information. In this case, the user can easily register things they would like to do again as things they want to do. The server device 10 may also present popular things that other users want to do, that is, things that other users (including all users, including the user themselves) have registered as things they want to do, in descending order of the number of registrations. In this case, things that many users are interested in can be registered as things they want to do. The server device 10 may also present things with a high repeat rate, that is, things that the same user has registered many times, as suggested information, in descending order of the number of times. In this case, things whose attractiveness has been verified by the user can be registered as things they want to do.

[0098] <Example of variation: Variations in configuration> The configuration shown in Figure 1, etc. (overall configuration, hardware configuration, and functional configuration, etc.) is just an example, and other configurations can be used as long as they do not cause inconvenience in implementation. For example, the server device 10 may be distributed across two or more devices, or it may be provided in the form of SaaS (Software as a Service) or a cloud computing system. Also, the information processing performed by the server device 10 and the user terminal 20 may be performed collectively by a device that integrates them. Furthermore, the processing performed by the server device 10 may be performed by the user terminal 20, or the processing performed by the user terminal 20 may be performed by the server device 10.

[0099] Furthermore, the server device 10 may perform the processing that the AI ​​module 3 previously performed, or the AI ​​module 3 may perform the processing that the server device 10 previously performed. If the server device 10 does not use the AI ​​module 3, it may, for example, use a table containing pre-defined processing rules as reference information and execute the processing in a rule-based manner. On the other hand, if the AI ​​module 3 is used, the processing can be executed using a learning model generated by having the AI ​​module 3 perform machine learning using training data that takes the data used for processing as input and the processing results as output.

[0100] In short, as long as the necessary information processing is performed throughout the implementation support system 1, the devices that perform that information processing can be configured in any way.

[0101] The output destination for information or data (hereinafter referred to as "information, etc.") may be other devices, displays, storage units (including built-in and external storage units), email addresses, or accounts in other systems. Acquisition of information, etc. includes not only acquiring information, etc. transmitted from other devices, but also acquiring information, etc. generated by the device itself.

[0102] The embodiments described above were information processing devices such as a server device 10 and a user terminal 20, or an information processing system such as an implementation support system 1 equipped with such information processing devices, but they may also be information processing methods. The information processing method comprises the same steps as those performed by the information processing system. Furthermore, the embodiments described above may also be programs. The programs cause a computer to perform the same steps as those performed by the information processing system.

[0103] <Note> Furthermore, they may be provided in the following embodiments.

[0104] (1) An information processing system comprising a processor, wherein in a first acquisition step, the processor acquires desire information representing what the user wants to do based on input to a user terminal, and in a first presentation step, based on the acquired desire information, contribution information that contributes to the realization of what the user wants to do is presented to the user via the user terminal.

[0105] This configuration makes it easier for users to achieve what they want to do.

[0106] (2) An information processing system as described in (1) above, wherein the contributing information includes a to-do list that lists the things that need to be done in order to do what you want to do.

[0107] This approach makes it easier to get started on what you want to do.

[0108] (3) An information processing system as described in (2) above, wherein the processor, in the display step, displays an additional image for adding the tasks to be done on the user terminal, and in the first presentation step, when the additional image is manipulated, performs additional processing for adding the tasks to be done and presents the to-do list including the added tasks.

[0109] In this configuration, the to-do list can be expanded as needed.

[0110] (4) An information processing system as described in (2) or (3) above, wherein in the first presentation step, if the processor has acquired first desire information and second desire information as desire information, it presents a list of things to do as the to-do list, which includes the things that the second desire information wants to do as things that the first desire information wants to do.

[0111] In this manner, it is possible to include what you want to do among the things you need to do.

[0112] (5) An information processing system described in any one of (1) to (4) above, wherein the contributing information includes information representing the difficulty level of what the user wants to do.

[0113] This approach allows one to prepare oneself mentally when starting something one wants to do.

[0114] (6) An information processing system described in any one of (1) to (5) above, wherein the contributing information includes information that shows an image of what you want to do.

[0115] In this manner, the motivation to achieve what one wants to do can be strengthened.

[0116] (7) An information processing system according to any one of (1) to (6) above, wherein the processor acquires relevant information relating to the user in the second acquisition step, presents candidate information that is a candidate for the desired information based on the acquired relevant information in the second presentation step, and acquires information representing the desired thing as the selected candidate from the candidates indicated by the presented candidate information in the first acquisition step.

[0117] This approach makes it easier to find what you want to do.

[0118] (8) An information processing system as described in (7) above, wherein the processor displays a question to the user in the display step, and acquires the answer to the displayed question as related information in the second acquisition step.

[0119] This configuration allows for the presentation of candidate information even without prior registration of information. Of course, this is not always the case. Furthermore, the embodiments and modifications described above may be implemented in any combination.

[0120] Finally, various embodiments of the present invention have been described, but these are presented as examples only and are not intended to limit the scope of the invention. Novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. Embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0121] 1: Implementation support system 2: Communication lines 3: AI Module 10: Server device 11: Control Unit 20: User terminal 21: Control Unit

Claims

1. An information processing system equipped with a processor, The aforementioned processor, In the first acquisition step, desire information representing what the user wants to do is acquired based on input to the user terminal. In the first presentation step, based on the acquired desire information, contribution information that contributes to the realization of the desired action is presented to the user via the user terminal. Information processing system.

2. In the information processing system described in claim 1, The aforementioned contributing information includes a to-do list that outlines the things that need to be done in order to accomplish the aforementioned desired action. Information processing system.

3. In the information processing system described in claim 2, The aforementioned processor, In the display step, an additional image is displayed on the user terminal to indicate the addition of the tasks to be performed. In the first presentation step, if the additional image is manipulated, additional processing is performed to add the tasks to be done, and the to-do list including the added tasks is presented. Information processing system.

4. In the information processing system described in claim 2, The aforementioned processor, In the first presentation step, if first desire information and second desire information are obtained as desire information, a list of things to do, including what the second desire information indicates, is presented as the to-do list, as things that need to be done in order to do what the first desire information indicates. Information processing system.

5. In the information processing system described in claim 1, The aforementioned contribution information includes information representing the difficulty level of what you want to do. Information processing system.

6. In the information processing system described in claim 1, The aforementioned contributing information includes information that shows an image of what you want to do. Information processing system.

7. In the information processing system described in claim 1, The aforementioned processor, In the second acquisition step, relevant information about the user is acquired. In the second presentation step, candidate information that is a candidate for the desired information is presented based on the acquired related information. In the first acquisition step, information representing the desired action, which is selected from the candidates indicated by the presented candidate information, is acquired as the desired action information. Information processing system.

8. In the information processing system described in claim 7, The aforementioned processor, In the display step, the question for the user is displayed, In the second acquisition step, the answers to the displayed questions are acquired as related information. Information processing system.

Images