Information processing program, information processing method, and information processing device.

Abstract

To provide useful information that can help alleviate a lack of exercise. [Solution] The information processing device 100 stores preference parameters, including exercise load and frequency of exercise, in a storage device. Based on the frequency of the preference parameters and the user's schedule information, it identifies the time at which the user will perform exercise. Based on the exercise load of the preference parameters, the user's basic information, and the time at which the exercise will be performed, it generates recommendations for exercise content. Based on the user's performance of the recommended exercise content, the preference parameters are updated.

Description

Technical Field

[0006] , , , , , , , , , , , , , , ,

[0005] , ,

[0001] The present invention relates to an information processing program and the like.

Background Art

[0002] Lack of exercise is one of the social problems that lead to lifestyle diseases and decreased productivity, and many citizens feel that they lack exercise. Factors that prevent people from exercising include "lack of time" and "too troublesome".

[0003] For example, with respect to the factor of "lack of time", there is a conventional technique for allowing the user to grasp the available exercise time.

[0004] FIG. 16 is a diagram for explaining the prior art. In the prior art, a screen 10a for inputting the user's schedule is displayed on the mobile terminal, and when the input by the user is received, a screen 10b for displaying the free time is displayed based on the input result. When the user selects the exercise to be performed for each free time on the screen 10b, in the prior art, a screen 10c of a lecture video is displayed on the mobile terminal, and the user taps the "completed" button 10d at the end of the exercise.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

[0007] For example, in the conventional technology explained in Figure 16, the available time for exercise and the type of exercise are user-dependent, which can be inconvenient for the user.

[0008] In one aspect, the present invention aims to provide an information processing program, an information processing method, and an information processing device that can provide useful information to alleviate a lack of exercise. [Means for solving the problem]

[0009] In the first proposal, the computer performs the following processes: The computer stores preference parameters, including exercise load and frequency of exercise, in a memory device; identifies the time the user will exercise based on the frequency of the preference parameters and the user's schedule information; generates exercise recommendations based on the exercise load from the preference parameters, the user's basic information, and the exercise time; and updates the preference parameters based on the user's performance of the recommended exercises. [Effects of the Invention]

[0010] We can provide useful information to help people overcome a lack of exercise. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 is a diagram illustrating the reference technology. [Figure 2] Figure 2 is a diagram illustrating the problem of the reference technology. [Figure 3] Figure 3 is a diagram illustrating the processing of the information processing device according to this embodiment. [Figure 4] Figure 4 is (1) for illustrating the process of updating preference parameters. [Figure 5]FIG. 5 is a diagram (2) for explaining the process of updating the preference parameter. [Figure 6] FIG. 6 is a diagram (1) for explaining the process of specifying the execution time. [Figure 7] FIG. 7 is a diagram (2) for explaining the process of specifying the execution time. [Figure 8] FIG. 8 is a diagram for explaining the process of determining the user's state. [Figure 9] FIG. 9 is a diagram (1) for explaining the process of generating a prompt. [Figure 10] FIG. 10 is a diagram (2) for explaining the process of generating a prompt. [Figure 11] FIG. 11 is a functional block diagram showing the configuration of the information processing apparatus according to this embodiment. [Figure 12] FIG. 12 is a flowchart showing the processing procedure of the information processing apparatus according to this embodiment. [Figure 13] FIG. 13 is a diagram (1) showing an example of a recommendation screen. [Figure 14] FIG. 14 is a diagram (2) showing an example of a recommendation screen. [Figure 15] FIG. 15 is a diagram showing an example of the hardware configuration of a computer that realizes the same functions as the information processing apparatus of the embodiment. [Figure 16] FIG. 16 is a diagram for explaining the prior art.

BEST MODE FOR CARRYING OUT THE INVENTION

[0012] Hereinafter, embodiments of the information processing program, information processing method, and information processing apparatus disclosed in the present application will be described in detail based on the drawings. Note that the present invention is not limited by this embodiment.

EXAMPLE

[0013] Before describing this embodiment, the inventor will explain the reference technology that precedes the present invention. Figure 1 is a diagram illustrating the reference technology. For convenience of explanation, the device that implements the reference technology will be referred to as reference device 40.

[0014] Reference device 40 obtains the user's basic information from the terminal device 11 used by the user. This basic information includes gender, age, position, occupation, sleep duration, and perceived challenges.

[0015] The reference device 40 acquires the user's schedule information 12. For example, the schedule information 12 associates the content of the appointment with the time slot.

[0016] Reference device 40 sets the user's basic information in area 30a of prompt 30 and sets the user's schedule for today in area 30b of prompt 30.

[0017] The reference device 40 inputs the prompt 30 to the LLM (Large Language Models) 20 and outputs the LLM 20's response to the terminal device 11 for display. For example, the LLM's response might be "20 squats".

[0018] For example, in the reference device 40 described in Figure 1, the LLM20 can automatically generate exercise content appropriate for the user. It can also determine exercise content that corresponds to the user's condition and extract times when the user does not have an appointment.

[0019] However, because LLM20 generates answers based on a lot of general knowledge, it is unable to understand user preferences and provide useful information that can help alleviate a lack of exercise.

[0020] Figure 2 is a diagram illustrating the problems with the reference technology. For example, in the reference device 40, on day N, it may suggest to user U1 "20 squats," which is the response (exercise content) from LLM20, and even though the user finds it "troublesome," it may suggest a similar response, "20 sit-ups," on day N+1. While the reference device 40 can change the content of the response, it does not learn user U1's preferences, so it may suggest exercises that user U1 does not want.

[0021] Next, the information processing device according to this embodiment will be described. For example, the information processing device holds parameters of the user's preferences. In the following description, the parameters of the user's preferences will be referred to as "preference parameters." The information processing device recommends exercise content based on the preference parameters and repeatedly performs a process to update the preference parameters according to the user's progress in performing the exercise content. This makes it possible to recommend exercise content that the user prefers.

[0022] Figure 3 is a diagram illustrating the processing of the information processing device according to this embodiment. On day N, the information processing device recommends "20 squats" (exercise content), which is the response (exercise content) from LLM20, to user U1. If the user finds this exercise content "troublesome" and does not perform it, the device updates the preference parameters. Such updates are designed to reduce the exercise load. On day N+1, the information processing device recommends "10 sit-ups" as exercise content based on the updated preference parameters and LLM20. The user is more likely to decide that they can perform "10 sit-ups" if the exercise load is lower compared to day N. In other words, the device can propose recommendations that the user prefers.

[0023] Next, we will explain in more detail the processing of the information processing device according to this embodiment. In the following explanation, the information processing device according to this embodiment will be referred to as "information processing device 100". First, using Figure 4, we will explain how the information processing device 100 updates the preference parameters according to the user's exercise status and how the recommendation content gradually changes.

[0024] Figures 4 and 5 illustrate the process of updating preference parameters. First, let's explain Figure 4. For example, preference parameters 50 include strength training score, aerobic exercise score, stretching score, and frequency score.

[0025] The muscle training score is a score that indicates the exercise load of muscle training. In the following explanation, muscle training will be referred to as "muscle training." Muscle training includes push-ups, sit-ups, back extensions, etc. As the muscle training score increases, the exercise load of muscle training also increases. Graph G1 is a graph that shows the relationship between the muscle training score and the exercise load (time / repetitions). The horizontal axis of graph G1 corresponds to the muscle training score, and the vertical axis corresponds to the exercise load (time / repetitions). For example, the relationship between the muscle training score and the exercise load (time / repetitions) changes as shown by curve L1. When the muscle training score is "0.5", the exercise load is "30 seconds / 20 repetitions". An exercise load of "30 seconds / 20 repetitions" means "performing muscle training for 30 seconds" or "performing muscle training 20 times".

[0026] The aerobic exercise score is a score that indicates the exercise intensity of aerobic exercise. Aerobic exercise includes activities such as walking and jogging. As the aerobic exercise score increases, the exercise intensity of aerobic exercise also increases. A graph showing the relationship between the aerobic exercise score and the exercise intensity of aerobic exercise is omitted.

[0027] The stretch score indicates the exercise load of a stretch. The higher the stretch score, the greater the stretch load. A graph showing the relationship between the stretch score and the exercise load of the stretch is omitted.

[0028] The frequency score is used to determine how often you exercise. A higher frequency score indicates a higher frequency of exercise. A graph illustrating the relationship between the frequency score and exercise frequency is omitted.

[0029] On day N, the information processing device 100 sets the muscle training score, aerobic exercise score, stretching score, and frequency score of the preference parameter 50 to their initial values. For example, the initial value is set to "0.5". Based on the preference parameter 50 on day N, the information processing device 100 generates a recommendation Rn and notifies the user. For example, the recommendation Rn includes "do 20 sit-ups at 10:00" corresponding to muscle training, and "take a 10-minute walk at 12:00" and "stretch for 10 seconds at 16:00" corresponding to aerobic exercise.

[0030] The user notifies the information processing device 100 of the status of their exercise in response to the recommendation Rn. For example, the explanation will describe a case where the user does not perform "20 sit-ups at 10:00" or "a 10-minute walk at 12:00," but instead notifies the information processing device 100 that they performed "10 seconds of stretching at 16:00."

[0031] The information processing device 100 updates the preference parameters 50 based on the implementation status of Recommend Rn as follows: The information processing device 100 updates the muscle training score from "0.5" to "0.4" because the action corresponding to muscle training, "Do 20 sit-ups at 10:00," has not been performed. The information processing device 100 updates the aerobic exercise score from "0.5" to "0.4" because the action corresponding to aerobic exercise, "Take a 10-minute walk at 12:00," has not been performed.

[0032] The information processing device 100 updates the stretch score from "0.5" to "0.6" because the action corresponding to stretching, "stretch for 10 seconds at 16:00," was performed. The information processing device 100 updates the frequency score from "0.5" to "0.4" because more than half of the three exercises included in the recommendation Rn were not performed.

[0033] The updated preference parameter 50, based on the implementation status of the recommendation Rn, will be presented as the preference parameter 50 for day N+1 in the following explanation.

[0034] The information processing device 100 generates a recommendation Rn+1 based on the preference parameters 50 on day N+1 and notifies the user. For example, the recommendation Rn+1 may include "Do 20 squats at 10:00" for strength training, "Take a 10-minute walk at 12:00" for aerobic exercise, and "Stretch for 20 seconds at 16:00" for stretching.

[0035] The user notifies the information processing device 100 of their exercise status in response to recommendation Rn+1. For example, the explanation will describe a case where the user does not perform "20 squats at 10:00" or "a 10-minute walk at 12:00," but instead notifies the information processing device 100 that they performed "20 seconds of stretching at 16:00."

[0036] The information processing device 100 updates the preference parameters 50 based on the implementation status of recommendation Rn+1 as follows: The information processing device 100 updates the strength training score from "0.4" to "0.3" because the action corresponding to strength training, "Do 20 squats at 10:00," has not been performed. The information processing device 100 updates the aerobic exercise score from "0.4" to "0.3" because the action corresponding to aerobic exercise, "Take a 10-minute walk at 12:00," has not been performed.

[0037] The information processing device 100 updates the stretch score from "0.6" to "0.7" because the action corresponding to stretching, "Stretch for 20 seconds at 16:00," was performed. The information processing device 100 updates the frequency score from "0.4" to "0.3" because more than half of the three exercises included in recommendation Rn+1 were not performed.

[0038] The updated preference parameter 50, based on the implementation status of recommendation Rn+1, will be presented as the preference parameter 50 for day N+2 in the following explanation.

[0039] Let's move on to the explanation of Figure 5. The information processing device 100 generates a recommendation Rn+2 based on the preference parameters 50 on day N+2 and notifies the user. For example, the recommendation Rn+2 includes "Do 10 sit-ups at 10:00" for muscle training and "Stretch for 20 seconds at 16:00" for stretching.

[0040] The user notifies the information processing device 100 of the status of their exercise in response to recommendation Rn+2. For example, the explanation will describe a case where the user notifies the information processing device 100 of the status of their exercise, stating that they performed "10 sit-ups at 10:00" and "20 seconds of stretching at 16:00".

[0041] The information processing device 100 updates the preference parameter 50 based on the implementation status of recommendation Rn+2 as follows: The information processing device 100 updates the muscle training score from "0.3" to "0.4" because the action corresponding to muscle training, "Do 10 sit-ups at 10:00," has been performed. The information processing device 100 leaves the aerobic exercise score at "0.3" because recommendation Rn+2 does not include any exercise corresponding to aerobic exercise.

[0042] The information processing device 100 updates the stretch score from "0.7" to "0.8" because the action corresponding to stretching, "Stretch for 20 seconds at 16:00," was performed. The information processing device 100 updates the frequency score from "0.3" to "0.4" because more than half of the two exercises included in recommendation Rn+2 were performed.

[0043] The updated preference parameter 50, based on the implementation status of Recommend Rn+2, is set as the preference parameter 50 on day N+3.

[0044] As explained in Figures 4 and 5, the information processing device 100 updates the preference parameters 50 according to the user's recommendation status, gradually changing the content of the recommendations.

[0045] While Figures 4 and 5 omit detailed explanations, more specifically, the information processing device 100 generates prompts using the user's exercise duration and user status, in addition to the preference parameters 50, and then generates recommendations using LLM. Therefore, the following will sequentially explain the processes by which the information processing device 100 identifies the exercise duration, identifies the user status, and generates prompts.

[0046] First, an example of the process by which the information processing device 100 identifies the exercise time will be explained. Here, the exercise time refers to the time at which the recommendation for exercise is made to the user. Figures 6 and 7 are diagrams illustrating the process of identifying the exercise time. The information processing device 100 obtains a frequency score from the preference parameters 50 explained in Figure 4, and processes the information processing device assuming that the user will perform exercise based on the frequency of the frequency score. The relationship between the frequency score and the frequency is assumed to be predefined. Figure 6 illustrates the process of the information processing device 100 when the frequency is "once every 6 hours", and Figure 7 illustrates the process of the information processing device 100 when the frequency is "once every 2 hours".

[0047] First, let's explain Figure 6. The information processing device 100 uses the user's schedule information 60 to perform the following processing. The schedule information 60 associates time slots with scheduled events. For example, in the schedule information 60, the scheduled event "Regular Meeting" is set for the time slot "8:00~9:00". The scheduled event "Discussion Meeting" is set for the time slot "9:00~10:00". The scheduled event "Lunch Break" is set for the time slot "12:00~13:00". The scheduled event "Meeting" is set for the time slot "14:00~15:00".

[0048] The information processing device 100 refers to the schedule information 60 and extracts the time slots that are not scheduled. In the example shown in Figure 6, the time slots that are not scheduled are "10:00-12:00", "13:00-14:00", and "15:00-20:00".

[0049] Next, the information processing device 100 sets the start time (for example, 8:00) as the start time and sets the implementation time slots at a frequency of "once every 6 hours". For example, the first implementation time slot will be "8:00 to 14:00". The second implementation time slot will be "14:00 to 20:00".

[0050] Next, the information processing device 100 compares the scheduled time slots with the unscheduled time slots and randomly selects an unscheduled time slot from those included in the scheduled time slots. For example, the information processing device 100 selects "10:00-12:00" as an unscheduled time slot included in the scheduled time slot "1st time: 8:00-14:00". The information processing device 100 selects "15:00-20:00" as an unscheduled time slot included in the scheduled time slot "2nd time: 14:00-20:00".

[0051] Next, the information processing device 100 identifies the middle time of the selected time slot as the implementation time. For example, the first implementation time will be "11:00". The second implementation time will be "18:00". The first implementation time "11:00" and the second implementation time "18:00" are implementation times when the user does not have an appointment.

[0052] For example, based on the processing results in Figure 6, the information processing device 100 determines that the first recommendation will be made at "11:00" and the second recommendation will be made at "18:00".

[0053] We will now move on to the explanation of Figure 7. The information processing device 100 performs the following processing using the user's schedule information 60.

[0054] The information processing device 100 refers to the schedule information 60 and extracts the time slots that are not scheduled. In the example shown in Figure 7, the time slots that are not scheduled are "10:00-12:00", "13:00-14:00", and "15:00-20:00".

[0055] Next, the information processing device 100 sets the start time (for example, 8:00) as the start time and sets the implementation time slots at a frequency of "once every two hours". For example, the first implementation time slot will be "8:00 to 10:00". The second implementation time slot will be "10:00 to 12:00". The third implementation time slot will be "12:00 to 14:00". The explanation for the fourth and subsequent implementation time slots is omitted.

[0056] Next, the information processing device 100 compares the scheduled time slots with the unscheduled time slots and randomly selects an unscheduled time slot from those included in the scheduled time slots. For example, the information processing device 100 sets "1st time: None" because there are no unscheduled time slots included in the scheduled time slot "1st time: 8:00~10:00". The information processing device 100 selects "10:00~12:00" as the unscheduled time slot included in the scheduled time slot "2nd time: 10:00~12:00". The information processing device 100 selects "13:00~14:00" as the unscheduled time slot included in the scheduled time slot "3rd time: 13:00~14:00". The explanation of the processing for the 4th time and beyond is omitted.

[0057] Here, since there are no time slots without scheduled activities within the implementation period "First session: 8:00~10:00", the information processing device 100 performs the following process. Based on the schedule information 60, the information processing device 100 randomly selects a scheduled activity (regular meeting, discussion) from among the scheduled activities (regular meetings, discussion meetings) included in "First session: 8:00~10:00". Here, we will explain assuming that the information processing device 100 has selected the scheduled activity "Regular meeting (8:00~9:00)".

[0058] The information processing device 100 identifies a predetermined time (for example, 10 minutes before) before the end time of the selected scheduled event, "Regular Meeting (8:00-9:00)," as the time for the first implementation. For example, the information processing device 100 sets the time for the first implementation as "8:50." This first implementation time includes the user's scheduled time.

[0059] On the other hand, the information processing device 100 identifies the middle time of the selected time slot for the second and third implementation sessions as the implementation time. For example, the second implementation time would be "11:00," and the third implementation time would be "13:30." These second and third implementation times do not include the user's scheduled time.

[0060] For example, based on the processing results in Figure 7, the information processing device 100 determines that the first recommendation will be made at "8:50", the second recommendation at "11:00", and the third recommendation at "11:00".

[0061] Next, the process by which the information processing device 100 determines the user's status will be described. Figure 8 is a diagram illustrating the process of determining the user's status. The information processing device 100 displays a screen 70 containing the question "What is your usual average sleep time?" on the display unit in advance and accepts input of the user's average sleep time. The information processing device 100 stores the average sleep time information in the storage unit 140.

[0062] When in use, the information processing device 100 displays screens 70a, 70b, and 70c on its display unit. Screen 70a is a screen that includes the question "How long did you sleep last night?". The information processing device 100 uses screen 70a to receive the user's sleep time. If the received sleep time is greater than or equal to the average sleep time stored in the memory unit 140, the information processing device 100 determines the user's status as "long sleep time". On the other hand, if the received sleep time is less than the average sleep time stored in the memory unit 140, the information processing device 100 determines the user's status as "short sleep time".

[0063] Screen 70b is a screen that includes the question, "How anxious are you about your workload?". The information processing device 100 uses screen 70b to receive a numerical value related to the user's anxiety level. For example, if the numerical value related to anxiety is above a threshold (for example, 4), the information processing device 100 determines that the user's state is "high anxiety." On the other hand, if the numerical value related to anxiety is below a threshold (for example, 4), the information processing device 100 determines that the user's state is "low anxiety."

[0064] Screen 70c is a screen that includes the question "Where is your workplace today?". The information processing device 100 uses this screen 70c to receive the workplace information. For example, if the workplace is "home", the information processing device 100 determines the user's information to be "at home". On the other hand, if the workplace is not "home", the information processing device 100 determines the user's information to be "not at home".

[0065] The information processing device 100 determines the user's status by executing the process shown in Figure 8. For example, the user's status includes whether they have slept a long or short amount of time, whether they feel anxious or not, and whether they are at home or not. The information processing device 100 may also determine the status of other users.

[0066] Next, an example of the process by which the information processing device 100 generates prompts will be explained. The information processing device 100 switches prompts depending on whether the execution time, as explained in Figures 6 and 7, includes scheduled execution time. First, Figure 9 will be used to explain the prompt when the execution time does not include scheduled execution time, and then Figure 10 will be used to explain the prompt when the execution time includes scheduled execution time. The information processing device 100 obtains the user's basic information in advance. This basic information includes the user's age, gender, occupation, and position.

[0067] Figure 9 is a diagram (1) illustrating the process of generating prompts. For example, the information processing device 100 generates prompts for generating recommendations for strength training, aerobic exercise, and stretching. Here, we will explain the prompt for generating recommendations for strength training.

[0068] The information processing device 100 sets the execution time in area 80a of prompt 80. The information processing device 100 sets "muscle training" in {category} in area 80b of prompt 80. The information processing device 100 sets the basic information age, gender, occupation, and position in {age}, {gender}, {job}, and {position} in area 80c of prompt 80, respectively. The information processing device 100 sets the user's status in {issue} in area 80d. The information processing device 100 sets the value corresponding to the muscle training score of the preference parameter in {parameter} in area 80e.

[0069] The information processing device 100 inputs prompts 80 with values ​​set in each area 80a to 80e to the LLM, thereby generating recommendations for muscle training when the scheduled time is not included. Since these recommendations are generated from prompts related to muscle training, the information processing device 100 can identify the correspondence between the recommendations and the muscle training, as well as the relationship between the implementation status of the recommendations and the muscle training.

[0070] The information processing device 100 generates prompts for aerobic exercise and stretching in the same way as for strength training, and inputs them into the LLM to generate recommendations for aerobic exercise and recommendations for stretching, assuming that the scheduled time is not included.

[0071] Figure 10 is a diagram (2) illustrating the process of generating prompts. For example, the information processing device 100 generates prompts for generating recommendations for strength training, aerobic exercise, and stretching. Here, we will explain the prompt for generating recommendations for strength training.

[0072] The information processing device 100 sets the implementation time and schedule (such as the regular meeting explained in Figure 7) in area 90a of prompt 90. The information processing device 100 sets "muscle training" in {category} in area 90b of prompt 90. The information processing device 100 sets the basic information age, gender, occupation, and position in {age}, {gender}, {job}, and {position} in area 90c of prompt 90, respectively. The information processing device 100 sets the user's status in {issue} in area 90d. The information processing device 100 sets the value corresponding to the muscle training score of the preference parameter in {parameter} in area 90e.

[0073] The information processing device 100 generates recommendations for muscle training, including scheduled workouts, by inputting prompts 90 with values ​​set in each of the areas 90a to 90e into the LLM.

[0074] The information processing device 100 generates prompts for aerobic exercise and stretching in the same way as for strength training, and inputs them into the LLM to generate recommendations for aerobic exercise and recommendations for stretching, assuming that the scheduled time is not included.

[0075] Next, an example of the configuration of the information processing device 100 that performs the above-described processing will be explained. Figure 11 is a functional block diagram showing the configuration of the information processing device according to this embodiment. As shown in Figure 11, the information processing device 100 has a communication unit 110, an input unit 120, a display unit 130, a timer 135, a storage unit 140, and a control unit 150.

[0076] The communication unit 110 performs data communication with external devices via the network. The communication unit 110 is implemented using a NIC (Network Interface Card) or the like.

[0077] The input unit 120 is an input device that inputs various types of information into the information processing device 100. The input unit 120 is compatible with keyboards, mice, touch panels, etc. The user operates the input unit 120 to input various types of information. For example, the user inputs basic information, inputs for each screen 70, 70a to 70c as explained in Figure 8, and inputs the implementation status of recommendations.

[0078] The display unit 130 is a display device that displays information output from the control unit 150. The display unit 130 is compatible with liquid crystal displays, organic EL (Electro-Luminescence) displays, touch panels, etc. For example, the display unit 130 displays the screens 70, 70a to 70c described in Figure 8, recommendation information, etc.

[0079] Timer 135 outputs the current time information to control unit 150.

[0080] The memory unit 140 contains preference parameters 50, schedule information 60, basic information 141, and status information 142. The memory unit 140 is a memory or the like.

[0081] The preference parameters 50 include strength training score, aerobic exercise score, stretching score, frequency score, etc. Further explanation of the preference parameters 50 is the same as the explanation of the preference parameters 50 given in Figures 4 and 5. For example, the initial value of each score of the preference parameters 50 is set to 0.5.

[0082] Schedule information 60 is information that associates time slots with the user's schedule. Further explanation of schedule information 60 is the same as the explanation of schedule information 60 given in Figures 6 and 7.

[0083] Basic information 141 is the user's basic information, including the user's age, gender, occupation, and position. For example, basic information 141 is entered from the input unit 120, etc.

[0084] Status information 142 is information obtained as a result of the process that determines the user's state as described in Figure 8. For example, status information 142 includes whether the user has slept a long or short amount of time, whether their level of anxiety is high or low, whether they are at home or not, etc.

[0085] The control unit 150 includes an acquisition unit 151, an execution time specification unit 152, a state determination unit 153, a recommendation generation unit 154, and an update unit 155. For example, the control unit 150 is a CPU (Central Processing Unit), etc.

[0086] The acquisition unit 151 acquires the user's schedule information 60 from the input unit 120 or an external device, and stores the acquired schedule information 60 in the storage unit 140. The acquisition unit 151 also acquires basic information 141 from the input unit 120, etc., and stores the acquired basic information 141 in the storage unit 140.

[0087] The implementation time identification unit 152 identifies the implementation time based on the frequency score of the preference parameter 50 and the schedule information 60. The implementation time identification unit 152 outputs the identified implementation time to the recommendation generation unit 154. The process by which the implementation time identification unit 152 identifies the implementation time is the same as the process for identifying the implementation time described in Figures 6 and 7. In addition, if the implementation time includes a user's schedule, the implementation time identification unit 152 also outputs the user's schedule.

[0088] The state determination unit 153 generates state information 142 by determining the user's state and stores the state information 142 in the storage unit 140. The process by which the state determination unit 153 determines the user's state is the same as the process for determining the user's state described in Figure 8. For example, the state determination unit 153 displays screens 70, 70a, 70b, and 70c described in Figure 8 on the display unit 130 and determines the user's state based on the information input to each screen 70, 70a to 70c.

[0089] The recommendation generation unit 154 generates a prompt based on the implementation time, preference parameters 50, basic information 141, and status information 142. If the implementation time includes the user's schedule, the recommendation generation unit 154 selects prompt 80 shown in Figure 9 and sets information regarding the implementation time, preference parameters 50, and basic information 141. On the other hand, if the implementation time does not include the user's schedule, the recommendation generation unit 154 selects prompt 90 shown in Figure 10 and sets information regarding the implementation time, preference parameters 50, and basic information 141.

[0090] The recommendation generation unit 154 generates a prompt and then inputs the prompt to the LLM to generate recommendations. For example, the recommendation generation unit 154 uses the LLM API (Application Programming Interface) or the like to access an LLM server on the network and exchange data.

[0091] Based on the execution time and the time information from the timer 135, the recommendation generation unit 154 outputs the generated recommendation to the display unit 130 and displays it at the timing of the execution.

[0092] The update unit 155 obtains the user's implementation status regarding the recommendation from the input unit 120 and updates the preference parameter 50. The process by which the update unit 155 updates the preference parameter 50 is the same as the process described in Figures 4 and 5.

[0093] Next, an example of the processing procedure of the information processing device 100 according to this embodiment will be described. Figure 12 is a flowchart of the processing procedure of the information processing device according to this embodiment. As shown in Figure 12, the information processing device 100 sets the preference parameter 50 to an initial value (step S101). The acquisition unit 151 of the information processing device 100 acquires the schedule information 60 and stores it in the storage unit 140 (step S102). The acquisition unit 151 acquires the basic information 141 from the input unit 120 and stores it in the storage unit 140 (step S103).

[0094] The execution time determination unit 152 of the information processing device 100 determines the execution time based on the schedule information 60 (step S104). The status determination unit 153 of the information processing device 100 determines the user's status and generates status information (step S105).

[0095] The recommendation generation unit 154 of the information processing device 100 generates a prompt based on the execution time, preference parameters 50, basic information 141, and status information 142 (step S106). The recommendation generation unit 154 generates a recommendation from the prompt using LLM (step S107).

[0096] The recommendation generation unit 154 displays the recommendation on the display unit 130 when the time for implementation arrives (step S108). The update unit 155 of the information processing device 100 updates the preference parameters 50 based on the user's implementation status of the recommendation (step S109).

[0097] The information processing device 100 executes the process shown in Figure 12 at predetermined intervals (for example, every day). Note that the initial value setting of the preference parameter 50 shown in step S101 is done only the first time, and in the processing of the next day, the value of the preference parameter 50 from the previous day is used as is (the process in step S101 is skipped).

[0098] Next, we will describe an example of a recommendation screen displayed on the display unit 130 by the information processing device 100. Figures 13 and 14 are diagrams showing examples of recommendation screens. Let's explain Figure 13. Figure 13 is an example of a recommendation screen when the implementation time does not include the user's schedule. The information processing device 100 displays a timeline 131 on the display unit 130 and displays a recommendation 132 at the time corresponding to the implementation time on the timeline.

[0099] Next, Figure 14 will be explained. Figure 14 is an example of a recommendation screen when the implementation time includes the user's schedule. The information processing device 100 displays the recommendation 133 in the corner of the display unit 130. When the implementation time includes the user's schedule, the information processing device 100 makes recommendations to the extent that they do not interfere with the user's work.

[0100] Next, the effects of the information processing device 100 according to this embodiment will be described. The information processing device 100 identifies the time to be performed based on the preference parameters 50 and the schedule information 60, recommends exercise content based on the preference parameters 50, basic information 141 and the time to be performed, and repeatedly performs a process to update the preference parameters 50 based on the implementation status of the recommendations. This makes it possible to provide useful information that can help alleviate a lack of exercise.

[0101] For example, if a user is unable to perform an exercise, their preference parameter score decreases, causing the exercise to become easier and more manageable, making it easier for the user to exercise. On the other hand, if the user is able to perform the exercise, their preference parameter score increases, causing the exercise to become moderately challenging, preventing boredom and encouraging continued exercise.

[0102] The information processing device 100 generates a prompt based on the execution time, preference parameters 50, basic information 141, and state information 142, and generates a recommendation by inputting the generated prompt into the LLM. This makes it possible to generate input information for the LLM that will provide useful information to the user. In this embodiment, the use of LLM has been described, but other generative AI (Artificial Intelligence) may also be used.

[0103] The information processing device 100 further determines whether the scheduled time coincides with a time scheduled by the user, and switches prompts based on this determination. This enables the generation of prompts for creating recommendations tailored to the user's schedule.

[0104] In the above embodiment, the present invention was described in a case where it is implemented using the information processing device 100, but it is not limited to this. For example, the functions of the information processing device 100 may be executed on multiple servers. Also, the information processing device 100 may access the user's mobile terminal and display recommendations, etc., on the user's mobile terminal.

[0105] Next, an example of a computer hardware configuration that realizes the same functions as the information processing device 100 described above will be explained. Figure 15 is a diagram showing an example of a computer hardware configuration that realizes the same functions as the information processing device in the embodiment. As shown in Figure 15, the computer 200 has a CPU 201 that performs various calculations, an input device 202 that receives data input from the user, and a display 203. The computer 200 also has a communication device 204 that exchanges data with external devices via a wired or wireless network, and an interface device 205. The interface device 205 may have a microphone, speaker, etc., connected to it. The computer 200 also has a RAM 206 that temporarily stores various information and a hard disk drive 207. Each of the devices 201 to 207 is connected to a bus 208.

[0106] The hard disk drive 207 includes an acquisition program 207a, an execution time identification program 207b, a status determination program 207c, a recommendation generation program 207d, and an update program 207e. The CPU 201 reads each of the programs 207a to 207e and loads them into the RAM 206.

[0107] The acquisition program 207a functions as the acquisition process 206a. The execution time identification program 207b functions as the execution time identification process 206b. The status determination program 207c functions as the status determination process 206c. The recommendation generation program 207d functions as the recommendation generation process 206d. The update program 207e functions as the update process 206e.

[0108] The processing of acquisition process 206a corresponds to the processing of acquisition unit 151. The processing of execution time determination process 206b corresponds to the processing of execution time determination unit 152. The processing of state determination process 206c corresponds to the processing of state determination unit 153. The processing of recommendation generation process 206d corresponds to the processing of recommendation generation unit 154. The processing of update process 206e corresponds to the processing of update unit 155.

[0109] Furthermore, programs 207a to 207e do not necessarily have to be stored on the hard disk drive 207 from the beginning. For example, each program could be stored on a "portable physical medium" such as a flexible disk (FD), CD-ROM, DVD, magneto-optical disk, or IC card inserted into the computer 200. Then, the computer 200 could read and execute each program 207a to 207e.

[0110] With regard to embodiments including each of the above examples, the following additional information is disclosed.

[0111] (Note 1) Preference parameters, including exercise load and frequency of exercise, are stored in a memory device. Based on the frequency of the aforementioned preference parameters and the user's schedule information, the time at which the user will perform exercise is identified. Based on the aforementioned preference parameters, exercise load, user basic information, and the aforementioned exercise duration, a recommendation for exercise content is generated. The preference parameters are updated based on the user's performance of the exercise content when the recommendation is presented to the user. An information processing program characterized by having a computer perform the processing.

[0112] (Note 2) The information processing program according to Note 1, characterized in that the process for identifying the preference parameters identifies the implementation time based on the frequency of the updated preference parameters, and the process for generating the recommendations generates the recommendations based on the exercise load of the updated preference parameters.

[0113] (Note 3) The information processing program described in Note 1, wherein the updating process increases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is performed by the user, and decreases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is not performed by the user.

[0114] (Note 4) The information processing program described in Note 1, characterized in that the generation process generates a prompt based on the exercise load of the preference parameters, the user's basic information, and the execution time, and generates the recommendation by inputting the generated prompt into LLM (Large Language Models).

[0115] (Note 5) The information processing program according to Note 4, characterized in that the process for identifying further identifies whether the execution time is a scheduled time for the user, and the process for generating further executes a process to switch prompts based on whether the execution time is a scheduled time for the user.

[0116] (Note 6) The information processing program described in Note 4, characterized in that the process of generating the information further utilizes information about the user's state to generate a prompt.

[0117] (Note 7) Preference parameters, including exercise load and frequency of exercise, are stored in a memory device. Based on the frequency of the aforementioned preference parameters and the user's schedule information, the time at which the user will perform exercise is identified. Based on the aforementioned preference parameters, exercise load, user basic information, and the aforementioned exercise duration, a recommendation for exercise content is generated. The preference parameters are updated based on the user's performance of the exercise content when the recommendation is presented to the user. An information processing method characterized in that the processing is performed by a computer.

[0118] (Note 8) The information processing method according to Note 7, characterized in that the process for identifying the preference parameters identifies the implementation time based on the frequency of the updated preference parameters, and the process for generating the recommendation generates the recommendation based on the exercise load of the updated preference parameters.

[0119] (Note 9) The information processing method according to Note 7, characterized in that the updating process increases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is performed by the user, and decreases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is not performed by the user.

[0120] (Note 10) The information processing method described in Note 7, characterized in that the generation process generates a prompt based on the exercise load of the preference parameters, the user's basic information, and the execution time, and generates the recommendation by inputting the generated prompt into LLM (Large Language Models).

[0121] (Note 11) The information processing method according to Note 10, characterized in that the process for identifying further identifies whether the execution time is a scheduled time for the user, and the process for generating further executes a process to switch prompts based on whether the execution time is a scheduled time for the user.

[0122] (Note 12) The information processing method according to Note 10, characterized in that the process of generating the information further utilizes information about the user's state to generate a prompt.

[0123] (Note 13) Preference parameters, including exercise load and frequency of exercise, are stored in a memory device. Based on the frequency of the aforementioned preference parameters and the user's schedule information, the time at which the user will perform exercise is identified. Based on the aforementioned preference parameters, exercise load, user basic information, and the aforementioned exercise duration, a recommendation for exercise content is generated. The preference parameters are updated based on the user's performance of the exercise content when the recommendation is presented to the user. An information processing device having a control unit that performs processing.

[0124] (Note 14) The information processing apparatus according to Note 13, characterized in that the process for identifying the preference parameters identifies the implementation time based on the frequency of the updated preference parameters, and the process for generating the recommendations generates the recommendations based on the exercise load of the updated preference parameters.

[0125] (Note 15) The information processing apparatus according to Note 13, characterized in that the updating process increases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is performed by the user, and decreases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is not performed by the user.

[0126] (Note 16) The information processing apparatus according to Note 13, characterized in that the generation process generates a prompt based on the exercise load of the preference parameters, the user's basic information and the execution time, and generates the recommendation by inputting the generated prompt into an LLM (Large Language Models).

[0127] (Note 17) The information processing apparatus according to Note 16, wherein the process for identifying further identifies whether the execution time is a scheduled time for the user, and the process for generating further executes a process for switching prompts based on whether the execution time is a scheduled time for the user.

[0128] (Note 18) The information processing apparatus according to Note 16, characterized in that the process of generating a prompt further utilizes information about the user's state. [Explanation of symbols]

[0129] 50 Preference Parameters 60 Schedule Information 100 Information Processing Devices 110 Communications Department 120 Input section 130 Display section 140 Storage section 141 Basic information 142 Status Information 150 Control Unit 151 Acquisition Department 152 Implementation Time Specification Department 153 State determination unit 154 Recommendation Generation Unit 155 Update Department

Claims

1. The preference parameters, including exercise load and frequency of exercise, are stored in the memory. Based on the frequency of the aforementioned preference parameters and the user's schedule information, the time at which the user will perform exercise is identified. Based on the aforementioned preference parameters, exercise load, user basic information, and the aforementioned exercise duration, a recommendation for exercise content is generated. The preference parameters are updated based on the user's performance of the exercise content when the recommendation is presented to the user. An information processing program characterized by having a computer perform the processing.

2. The information processing program according to claim 1, characterized in that the identifying process identifies the implementation time based on the frequency of the updated preference parameters, and the generating process generates the recommendation based on the exercise load of the updated preference parameters.

3. The information processing program according to claim 1, characterized in that the updating process increases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is performed by the user, and decreases the exercise load and frequency of the preference parameters when the exercise content included in the recommendation is not performed by the user.

4. The information processing program according to claim 1 is characterized in that the generation process generates a prompt based on the exercise load of the preference parameters, the user's basic information, and the execution time, and generates the recommendation by inputting the generated prompt into LLM (Large Language Models).

5. The information processing program according to claim 4, characterized in that the process for identifying further identifies whether the execution time is a scheduled time for the user, and the process for generating further executes a process to switch prompts based on whether the execution time is a scheduled time for the user.

6. The information processing program according to claim 4, characterized in that the process of generating the information further utilizes information about the user's state to generate a prompt.

7. The preference parameters, including exercise load and frequency of exercise, are stored in the memory. Based on the frequency of the aforementioned preference parameters and the user's schedule information, the time at which the user will perform exercise is identified. Based on the aforementioned preference parameters, exercise load, user basic information, and the aforementioned exercise duration, a recommendation for exercise content is generated. The preference parameters are updated based on the user's performance of the exercise content when the recommendation is presented to the user. An information processing method characterized in that the processing is performed by a computer.

8. The preference parameters, including exercise load and frequency of exercise, are stored in the memory. Based on the frequency of the aforementioned preference parameters and the user's schedule information, the time at which the user will perform exercise is identified. Based on the aforementioned preference parameters, exercise load, user basic information, and the aforementioned exercise duration, a recommendation for exercise content is generated. The preference parameters are updated based on the user's performance of the exercise content when the recommendation is presented to the user. An information processing device having a control unit that performs processing.

Images