System

Abstract

To provide a system that effectively manages progress in the user's diet and provides suitable advice.SOLUTION: A system according to an embodiment comprises a reception unit, an advice unit, an execution unit, an analysis unit, and a conversation unit. The reception unit receives the user's input regarding the diet deadline. The advice unit provides daily advice based on the information input through the reception unit. The execution unit executes advice each time a measurement is recorded with a weighing scale or a body composition device. The analysis unit analyzes past data and identifies the optimal meal or exercise for the user. The conversation unit provides conversational assistance to the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to effectively manage diet progress and provide appropriate advice.

[0005] The system according to the embodiment aims to effectively manage the user's diet progress and provide appropriate advice. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an advice unit, an execution unit, an analysis unit, and a conversation unit. The reception unit allows the user to input a deadline for dieting. The advice unit provides daily advice based on the information input by the reception unit. The execution unit executes the advice every time a record is taken with a weight scale or a body composition scale. The analysis unit analyzes past data and identifies optimal diet or exercise for the user. The conversation unit assists the user in a conversational manner. Effect of the Invention

[0007] The system according to the embodiment can effectively manage the user's diet progress and provide appropriate advice. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The diet support system according to the embodiment of the present invention is a system that supports dieting in cooperation with a weight scale or a body composition scale. This diet support system inputs a diet deadline, and provides advice every day with the deadline as a target. Each time the user records with the weight scale or the body composition scale every day, the advice is executed at that timing. In addition, advice is also given on the diet and exercise to be taken based on past data. Furthermore, the system assists the user in a conversational manner. For example, the user inputs a diet deadline. For example, the user sets a goal such as "I want to lose 5 kg in three months." This information is input to the system. Next, the system provides advice every day with the set deadline as a target. For example, specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes." Each time the user records with the weight scale or the body composition scale every day, advice is executed at that timing. For example, if the user is losing weight, the system provides an encouraging message such as "You're doing well, keep it up," and if the user is gaining weight, the system provides advice such as "You need to reconsider your diet." In addition, the system provides advice on the diet and exercise to be taken based on past data. For example, if past data shows that the user lost weight after eating a certain meal, the system will advise the user to eat that meal again. Also, if a certain exercise was effective, the system will advise the user to continue that exercise. Finally, the system assists the user in a conversational manner. For example, if the user asks, "What should I eat today?" the system will provide specific advice such as, "Try to eat more vegetables today." In this way, the user can proceed with their diet while interacting with the system. This allows the diet assistance system to effectively support the user's diet.

[0029] The diet support system according to the embodiment includes a reception unit, an advice unit, an execution unit, an analysis unit, and a conversation unit. The reception unit receives a diet deadline input by the user. For example, the user sets a goal such as "I want to lose 5 kg in 3 months." This information is input to the system. The advice unit provides advice every day based on the information input by the reception unit. For example, specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes." The execution unit executes advice every time a record is taken with a weight scale or a body composition scale. For example, if weight is decreasing, an encouraging message such as "You're doing well, keep it up," is provided, and if weight is increasing, advice such as "You need to reconsider your diet." The analysis unit analyzes past data and provides advice on what to eat and what exercise to take. For example, if past data shows that the user lost weight when eating a specific meal, the analysis unit advises the user to eat that meal again. Also, if a specific exercise was effective, the analysis unit advises the user to continue that exercise. The conversation unit provides appropriate advice in response to the user's questions. For example, when a user asks, "What should I eat today?", the conversation unit provides specific advice such as, "Try to eat more vegetables today." In this way, the diet support system according to the embodiment can effectively support the user's diet.

[0030] The reception unit allows the user to input a deadline for dieting. For example, the user sets a goal such as "I want to lose 5 kg in 3 months." This information is input to the system. The reception unit allows the user to input detailed information such as the current weight, body fat percentage, and lifestyle habits as well as a specific target weight and period when setting a goal. This allows the system to accurately grasp the user's current situation and provide more appropriate advice. Furthermore, the reception unit allows the user to input a motivation or reason for achieving the goal when setting a goal. For example, by inputting a specific reason such as "because it was pointed out in a health check" or "for the wedding," the system can provide a message to increase the user's motivation. In addition, the reception unit can periodically check the progress of the goal even after the user sets the goal, and can correct or reset the goal as necessary. For example, if the user achieves the goal halfway through, or conversely, if the user does not reach the goal, the reception unit prompts the user to set a new goal. This allows the reception unit to flexibly manage the user's diet goals and always provide optimal support.

[0031] The advice unit provides advice every day based on the information input by the reception unit. For example, specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes" is provided. The advice unit provides advice that is individually customized according to the user's goals and current situation. For example, if the user is allergic to a particular food ingredient or does not like a particular exercise, an alternative suggestion is presented accordingly. The advice unit also provides advice that is feasible within a reasonable range according to the user's life rhythm and schedule. For example, on busy days, it suggests short but effective exercises, and on days when there is more time, it recommends longer exercises. Furthermore, the advice unit continuously improves the content of the advice based on the user's progress and feedback. For example, if the user provides feedback such as "it was easy to implement" or "it was effective" in response to a particular piece of advice, the advice unit will continue to provide that advice in the future. Conversely, if the user provides feedback such as "it was difficult to implement" or "it was ineffective," it will suggest a different piece of advice. In this way, the advice unit can provide the most suitable advice for the user and support the success of dieting.

[0032] The execution unit executes advice every time a record is taken with a weight scale or a body composition scale. For example, if the user is losing weight, the execution unit provides an encouraging message such as "You're doing well, keep it up," and if the user is gaining weight, the execution unit provides advice such as "You need to reconsider your diet." When the user records changes in weight and body composition on a daily basis, the execution unit automatically transmits the data to the system and analyzes them in real time. This allows the user to manage data without any hassle. The execution unit also checks whether the user has performed the advice and provides feedback according to the execution status. For example, if the user performs the suggested exercise, the execution unit provides an encouraging message such as "You did a good job," and if the user does not perform the exercise, the execution unit provides a message such as "Please try again next time." Furthermore, the execution unit adjusts the content of the advice according to the user's execution status and progress. For example, if the user is losing weight smoothly, the execution unit provides advice to maintain the current state, and conversely, if the user is gaining weight, the execution unit suggests that the user review the content of their diet and exercise. This allows the execution unit to provide appropriate support according to the user's situation and support the success of the diet.

[0033] The analysis unit analyzes past data and gives advice on what to eat and what to exercise. For example, if the past data shows that the user lost weight after eating a certain meal, the analysis unit advises the user to eat that meal again. If a certain exercise was effective, the analysis unit advises the user to continue that exercise. The analysis unit analyzes the user's past meal and exercise data in detail to identify effective patterns and trends. For example, it finds cases where exercising at a certain time of day is more effective, or where eating certain ingredients is more likely to help the user lose weight. The analysis unit also provides customized advice according to the user's constitution and lifestyle. For example, if the user is a nocturnal person, the analysis unit provides advice on exercises and meals that are easy to perform at night. Furthermore, the analysis unit provides scientifically based advice based on the latest research and data. For example, the analysis unit suggests meals that incorporate the latest research results in nutrition and introduces effective exercise methods. As a result, the analysis unit can provide the user with optimal meal and exercise advice and support successful dieting.

[0034] The conversation unit provides appropriate advice in response to the user's questions. For example, when the user asks "What should I eat today?", the conversation unit provides specific advice such as "Try to eat more vegetables today." The conversation unit uses natural language processing technology to understand the user's questions and generate appropriate answers. For example, when the user asks "I'm not good at exercising. What should I do?", the conversation unit provides advice such as "Start with light exercise that you can do without straining yourself." In addition, the conversation unit provides more personalized advice based on the user's past questions and feedback. For example, when the user has provided feedback such as "I don't like vegetables" in the past, the conversation unit provides advice such as "If it's difficult to eat vegetables, one way to do it is to make them into a smoothie and consume them." In addition, the conversation unit provides messages to increase the user's motivation. For example, the conversation unit provides encouraging messages such as "You did a great job today" and encouraging messages such as "You're almost there until you achieve your goal." In this way, the conversation unit can provide appropriate and personalized advice in response to the user's questions and support the success of the diet.

[0035] The advice unit can provide the user with specific diet or exercise advice. The advice unit, for example, provides the user with specific diet advice. For example, it proposes a meal plan that takes into account calorie restriction and nutritional balance. The advice unit can also provide the user with specific exercise advice. For example, it proposes an exercise plan such as walking, jogging, or strength training. Furthermore, the advice unit can adjust the diet and exercise advice according to the user's physical condition and life rhythm. For example, if the user is not feeling well, it suggests light exercise or a meal that is easy to digest. In this way, the advice unit can improve the effectiveness of the diet by providing the user with specific diet and exercise advice.

[0036] The execution unit can adjust the advice based on changes in the user's weight or body composition. For example, if the user's weight is decreasing, the execution unit provides an encouraging message. For example, it provides a message such as "You're doing well, keep it up." In addition, the execution unit can also suggest a review of the user's diet if the user's weight is increasing. For example, it provides advice such as "You need to review your diet. Reduce your calories." In addition, the execution unit can adjust the advice based on changes in the user's body composition. For example, if the body fat percentage is increasing, it suggests increasing the amount of exercise. This allows the execution unit to provide more effective diet support by adjusting the advice based on changes in the user's weight or body composition.

[0037] The analysis unit can analyze past data and identify the optimal diet or exercise for the user. For example, if the past data shows that the user lost weight after eating a specific diet, the analysis unit advises the user to eat that diet again. For example, the analysis unit provides advice such as "You lost weight when you ate this diet in the past, so we recommend that you eat it again." In addition, if a specific exercise is effective, the analysis unit can advise the user to continue that exercise. For example, the analysis unit provides advice such as "You lost weight when you did this exercise in the past, so we recommend that you continue." In addition, the analysis unit can evaluate the effectiveness of diet and exercise based on the user's past data and propose an optimal plan. As a result, the analysis unit can identify the optimal diet and exercise for the user by analyzing past data, enabling effective diet support.

[0038] The conversation unit can provide advice in response to a user's question. For example, when the user asks, "What should I eat today?", the conversation unit provides specific advice. For example, the conversation unit provides advice such as, "Try to eat more vegetables today." In addition, when the user asks, "What kind of exercise should I do?", the conversation unit can also provide exercise advice. For example, the conversation unit provides advice such as, "Try to walk for 30 minutes." Furthermore, the conversation unit can refer to past data and analysis results in order to provide appropriate advice in response to the user's question. In this way, the conversation unit can resolve the user's doubts and support the user's diet by providing appropriate advice in response to the user's question.

[0039] The reception unit can analyze the user's past diet history and suggest a deadline setting method. The reception unit, for example, refers to a diet period in which the user was successful in the past and suggests a similar deadline. For example, it makes a suggestion such as "Let's set a three-month deadline by referring to the diet period in which the user was successful in the past." The reception unit can also suggest a different deadline so that the user can avoid a diet period in which the user failed in the past. For example, it makes a suggestion such as "Let's set a six-month deadline this time to avoid a period in which the user failed in the past." Furthermore, the reception unit can analyze the most effective period from the user's past diet history and suggest it. For example, it makes a suggestion such as "We found from past data that a four-month period is the most effective, so let's set a four-month deadline." In this way, the reception unit can propose an optimal deadline setting method by analyzing the user's past diet history, and increase the success rate of dieting.

[0040] The reception unit can perform filtering based on the user's current health condition and lifestyle habits when inputting the diet deadline. The reception unit, for example, evaluates the user's current health condition and proposes a reasonable deadline. For example, it makes a suggestion such as "Let's set a reasonable deadline in consideration of the user's current health condition." The reception unit can also propose a realistic deadline in consideration of the user's lifestyle habits (busyness at work and family situation). For example, it makes a suggestion such as "Let's set a realistic deadline in consideration of the lifestyle habits." Furthermore, the reception unit can also propose an achievable deadline based on the user's current weight and body composition. For example, it makes a suggestion such as "Let's set an achievable deadline based on the user's current weight and body composition." As a result, the reception unit can set a realistic deadline by performing filtering based on the user's current health condition and lifestyle habits.

[0041] When inputting a diet deadline, the reception unit can preferentially present a deadline with high relevance in consideration of the geographical location information of the user. The reception unit, for example, proposes a deadline that matches the climate and season of the area where the user lives. For example, it makes a suggestion such as "Let's set a realistic deadline in accordance with the climate and season of the area where you live." The reception unit can also propose a deadline that matches events and occasions in the area where the user lives. For example, it makes a suggestion such as "Let's set a deadline in accordance with local events and occasions." Furthermore, the reception unit can also propose a realistic deadline based on the food culture and lifestyle habits of the area where the user lives. For example, it makes a suggestion such as "Let's set a realistic deadline based on the food culture and lifestyle habits of the area." As a result, the reception unit preferentially proposes a deadline with high relevance in consideration of the geographical location information of the user, thereby enabling realistic goal setting.

[0042] The reception unit can analyze the user's social media activity when inputting a diet deadline, and present a related deadline. The reception unit, for example, proposes a deadline that matches a goal or event shared by the user on social media. For example, it makes a suggestion such as "Let's set a deadline according to the goal shared on social media." The reception unit can also analyze the user's social media activity pattern and propose a realistic deadline. For example, it makes a suggestion such as "Let's set a realistic deadline based on the social media activity pattern." Furthermore, the reception unit can also propose a deadline based on health and fitness trends that the user follows on social media. For example, it makes a suggestion such as "Let's set a deadline based on the health and fitness trends that you follow." As a result, the reception unit proposes a related deadline by analyzing the user's social media activity, and it becomes possible to set realistic goals.

[0043] When providing advice, the advice unit can change the level of detail of the advice based on the user's past successful dieting examples. The advice unit provides detailed advice, for example, by referring to a dieting method that the user has been successful in the past. For example, the advice unit provides advice such as "We will provide you with detailed advice by referring to a method that has been successful in the past." The advice unit can also provide concise advice so that the user avoids a dieting method that has failed in the past. For example, the advice unit provides advice such as "We will provide you with concise advice to avoid a method that has failed in the past." Furthermore, the advice unit can provide specific advice on diet and exercise based on the user's past successful examples. For example, the advice unit provides advice such as "We will provide you with specific advice on diet and exercise based on past successful examples." This allows the advice unit to adjust the level of detail of the advice based on the user's past successful dieting examples, thereby enabling more effective advice.

[0044] When providing advice, the advice unit can use different advice algorithms depending on the user's current health condition. For example, when the user is in good health, the advice unit provides advice on active exercise and diet. For example, the advice unit provides advice such as "Your health is good, so exercise and eat actively." In addition, when the user is in poor health, the advice unit can also provide advice on light exercise and diet. For example, the advice unit provides advice such as "Your health does not seem to be good, so exercise lightly and eat easily digestible foods." In addition, when the user has a specific health problem, the advice unit can also provide advice corresponding to that problem. For example, the advice unit provides advice such as "We will provide advice corresponding to a specific health problem." This allows the advice unit to apply different advice algorithms depending on the user's current health condition, thereby enabling more appropriate advice to be provided.

[0045] The advice unit can set a priority order of advice based on the user's life rhythm when providing advice. For example, if the user is a morning person, the advice unit provides important advice in the morning hours. For example, the advice unit provides advice such as "important advice will be provided in the morning hours in accordance with the morning person's life rhythm." In addition, if the user is a night person, the advice unit can also provide important advice in the evening hours. For example, the advice unit provides advice such as "important advice will be provided in the evening hours in accordance with the night person's life rhythm." In addition, the advice unit can also provide advice at an optimal timing in accordance with the user's life rhythm. For example, the advice unit provides advice such as "advice will be provided at an optimal timing in accordance with the life rhythm." In this way, the advice unit can provide more effective advice by determining the priority order of advice based on the user's life rhythm.

[0046] The advice unit can change the order of advice based on the user's meal history when providing advice. The advice unit, for example, suggests an optimal meal order based on the user's meal history in the past. For example, the advice unit gives advice such as "We suggest an optimal meal order based on the meal history in the past." In addition, when the user has eaten a specific meal, the advice unit can also suggest a meal to be eaten after the user has eaten. For example, the advice unit gives advice such as "We suggest a meal to be eaten after eating a specific meal." Furthermore, the advice unit can analyze the user's meal history and suggest an effective meal order. For example, the advice unit gives advice such as "We analyze the meal history and suggest an effective meal order." In this way, the advice unit can provide more effective advice by adjusting the order of advice based on the user's meal history.

[0047] When executing advice, the execution unit can select an execution method by referring to the user's past weight fluctuation data. For example, the execution unit selects a similar execution method by referring to a weight fluctuation pattern that the user has been successful in the past. For example, the execution unit makes a suggestion such as "We will select a similar execution method by referring to a weight fluctuation pattern that has been successful in the past." In addition, the execution unit can select a different execution method so that the user avoids a weight fluctuation pattern that has failed in the past. For example, the execution unit makes a suggestion such as "We will select a different execution method to avoid a weight fluctuation pattern that has failed in the past." In addition, the execution unit can analyze the user's past weight fluctuation data and select the most effective execution method. For example, the execution unit makes a suggestion such as "We will analyze the past weight fluctuation data and select the most effective execution method." In this way, the execution unit can select the optimal execution method by referring to the user's past weight fluctuation data, and provide effective advice.

[0048] The execution unit can change the execution content based on the user's current physical condition when executing advice. For example, when the user is in good health, the execution unit executes advice on active exercise and diet. For example, it makes a suggestion such as "Since your health is good, you should exercise and eat actively." In addition, when the user is in poor health, the execution unit can also execute advice on light exercise and diet. For example, it makes a suggestion such as "Since you do not seem to be in good health, you should do light exercise and eat foods that are easy to digest." Furthermore, when the user has a specific health problem, the execution unit can also execute advice corresponding to that problem. For example, it makes a suggestion such as "Execute advice corresponding to the specific health problem." In this way, the execution unit can customize the execution content based on the user's current physical condition, thereby enabling more appropriate advice to be provided.

[0049] The execution unit can select an execution method in consideration of the geographical location information of the user when executing advice. The execution unit executes advice according to, for example, the climate and season of the area where the user lives. For example, it makes a suggestion such as "execute advice according to the climate and season of the area where the user lives." The execution unit can also execute advice according to events and occasions in the area where the user lives. For example, it makes a suggestion such as "execute advice according to local events and occasions." Furthermore, the execution unit can also execute realistic advice based on the food culture and lifestyle habits of the area where the user lives. For example, it makes a suggestion such as "execute realistic advice based on the food culture and lifestyle habits of the area." As a result, the execution unit can provide realistic advice by selecting an optimal execution method in consideration of the geographical location information of the user.

[0050] When executing advice, the execution unit can analyze the user's social media activity and present the execution content. The execution unit executes advice tailored to goals and events shared by the user on social media, for example. For example, the execution unit makes a suggestion such as "execute the advice in accordance with the goals shared on social media." The execution unit can also analyze the user's social media activity pattern and execute realistic advice. For example, the execution unit makes a suggestion such as "execute realistic advice based on the social media activity pattern." Furthermore, the execution unit can also execute advice based on health and fitness trends that the user follows on social media. For example, the execution unit makes a suggestion such as "execute advice based on the health and fitness trends that you are following." As a result, the execution unit can propose related execution content and provide realistic advice by analyzing the user's social media activity.

[0051] The analysis unit can adjust the analysis algorithm by referring to past data during analysis. The analysis unit selects an optimal analysis algorithm based on, for example, the user's past weight fluctuation data. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past weight fluctuation data." The analysis unit can also select an effective analysis algorithm based on the user's past diet history. For example, the analysis unit makes a suggestion such as "We will select an effective analysis algorithm based on the past diet history." The analysis unit can also select an optimal analysis algorithm based on the user's past exercise history. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past exercise history." This allows the analysis unit to optimize the analysis algorithm by referring to past data, thereby enabling more effective analysis.

[0052] The analysis unit can change the analysis method based on the user's current health condition during analysis. For example, when the user is in good health, the analysis unit applies an aggressive analysis method. For example, the analysis unit makes a suggestion such as "Since your health condition is good, apply an aggressive analysis method." In addition, when the user is in poor health, the analysis unit can apply a light analysis method. For example, the analysis unit makes a suggestion such as "Since your health condition is not good, apply a light analysis method." In addition, when the user has a specific health problem, the analysis unit can apply an analysis method corresponding to the problem. For example, the analysis unit makes a suggestion such as "Apply an analysis method corresponding to the specific health problem." In this way, the analysis unit can customize the analysis method based on the user's current health condition, thereby enabling more appropriate analysis.

[0053] The analysis unit can weight the analysis data based on the user's life rhythm during analysis. For example, if the user is a morning person, the analysis unit weights the morning data for analysis. For example, the analysis unit makes a suggestion such as "We will weight the morning data for analysis in accordance with the morning person's life rhythm." In addition, if the user is a night person, the analysis unit can weight the night data for analysis. For example, the analysis unit makes a suggestion such as "We will weight the night data for analysis in accordance with the night person's life rhythm." In addition, the analysis unit can weight the data at an optimal timing in accordance with the user's life rhythm. For example, the analysis unit makes a suggestion such as "We will weight the data at an optimal timing in accordance with the life rhythm." This allows the analysis unit to weight the analysis data based on the user's life rhythm, making it possible to perform a more effective analysis.

[0054] The analysis unit can improve the accuracy of the analysis by referring to the user's dietary history during the analysis. The analysis unit, for example, selects an optimal analysis method based on the history of meals taken by the user in the past. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis method based on the history of meals taken in the past." In addition, when the user takes a specific meal, the analysis unit can also analyze the data after the user takes the meal by placing emphasis on the data after the user takes the meal. For example, the analysis unit makes a suggestion such as "We will analyze the data after the user takes the specific meal." In addition, the analysis unit can analyze the user's dietary history and apply an effective analysis method. For example, the analysis unit makes a suggestion such as "We will analyze the dietary history and apply an effective analysis method." As a result, the analysis unit can improve the accuracy of the analysis by referring to the user's dietary history, thereby enabling more effective analysis.

[0055] The conversation unit can provide an answer by referring to the user's past question history during a conversation. The conversation unit provides a related answer based on, for example, the content of a question asked by the user in the past. For example, the conversation unit makes a suggestion such as "We will provide you with a related answer based on the content of your past questions." The conversation unit can also select the most effective answer from the user's past question history. For example, the conversation unit makes a suggestion such as "We will select the most effective answer from your past question history." The conversation unit can also analyze the content of questions asked by the user in the past and provide an optimal answer. For example, the conversation unit makes a suggestion such as "We will analyze the content of your past questions and provide you with an optimal answer." This allows the conversation unit to provide an optimal answer by referring to the user's past question history, enabling an effective conversation.

[0056] The conversation unit can change the conversation content based on the user's current health condition during the conversation. For example, when the user is in good health, the conversation unit provides positive conversation content. For example, the conversation unit makes a suggestion such as "Since your health condition is good, we will provide you with positive conversation content." In addition, when the user is in poor health, the conversation unit can also provide light conversation content. For example, the conversation unit makes a suggestion such as "Since you do not seem to be in good health, we will provide you with light conversation content." In addition, when the user has a specific health problem, the conversation unit can also provide conversation content corresponding to that problem. For example, the conversation unit makes a suggestion such as "We will provide you with conversation content corresponding to the specific health problem." In this way, the conversation unit can customize the conversation content based on the user's current health condition, thereby enabling a more appropriate conversation.

[0057] The conversation unit can provide optimal conversation content in consideration of the geographical location information of the user during conversation. The conversation unit provides conversation content that matches, for example, the climate and season of the area where the user lives. For example, it makes a suggestion such as "We will provide you with conversation content that matches the climate and season of the area where you live." The conversation unit can also provide conversation content that matches events and occasions in the area where the user lives. For example, it makes a suggestion such as "We will provide you with conversation content that matches the events and occasions of the area." Furthermore, the conversation unit can also provide realistic conversation content based on the food culture and lifestyle of the area where the user lives. For example, it makes a suggestion such as "We will provide you with realistic conversation content based on the food culture and lifestyle of the area." As a result, the conversation unit provides optimal conversation content in consideration of the geographical location information of the user, thereby enabling realistic conversation.

[0058] The conversation unit can present conversation content by analyzing the user's social media activity during the conversation. The conversation unit provides conversation content that matches, for example, goals and events shared by the user on social media. For example, the conversation unit makes a suggestion such as "We will provide you with conversation content that matches your goals shared on social media." The conversation unit can also analyze the user's social media activity pattern to provide realistic conversation content. For example, the conversation unit makes a suggestion such as "We will provide you with realistic conversation content based on your social media activity pattern." Furthermore, the conversation unit can also suggest conversation content based on health and fitness trends that the user follows on social media. For example, the conversation unit makes a suggestion such as "We will suggest conversation content based on the health and fitness trends that you follow." As a result, the conversation unit proposes related conversation content by analyzing the user's social media activity, making it possible to have a realistic conversation.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The reception unit can analyze the user's past diet history and suggest a deadline setting method. For example, by referring to a diet period in which the user was successful in the past, the reception unit can suggest a similar deadline. For example, the reception unit can make a suggestion such as "Let's set a three-month deadline by referring to a diet period in which the user was successful in the past." The reception unit can also suggest a different deadline so that the user can avoid a diet period in which the user was unsuccessful in the past. For example, the reception unit can make a suggestion such as "Let's set a six-month deadline this time to avoid a period in which the user was unsuccessful in the past." Furthermore, the reception unit can analyze the most effective period from the user's past diet history and suggest it. For example, the reception unit can make a suggestion such as "We found from past data that a four-month period is the most effective, so let's set a four-month deadline." In this way, the reception unit can propose an optimal deadline setting method by analyzing the user's past diet history, thereby increasing the success rate of the diet.

[0061] The reception unit can perform filtering based on the user's current health condition and lifestyle habits when inputting a diet deadline. For example, the reception unit evaluates the user's current health condition and proposes a reasonable deadline. For example, the reception unit makes a suggestion such as "Let's set a reasonable deadline in consideration of the user's current health condition." In addition, the reception unit can also propose a realistic deadline in consideration of the user's lifestyle habits (busyness at work and family situation). For example, the reception unit makes a suggestion such as "Let's set a realistic deadline in consideration of the lifestyle habits." In addition, the reception unit can also propose an achievable deadline based on the user's current weight and body composition. For example, the reception unit makes a suggestion such as "Let's set an achievable deadline based on the user's current weight and body composition." In this way, the reception unit can set a realistic deadline by performing filtering based on the user's current health condition and lifestyle habits.

[0062] When providing advice, the advice unit can use different advice algorithms depending on the user's current health condition. For example, if the user is in good health, advice on active exercise and diet is provided. For example, advice such as "Your health is good, so exercise and eat actively" is provided. In addition, the advice unit can also provide advice on light exercise and diet when the user is in poor health. For example, advice such as "Your health does not seem to be good, so exercise lightly and eat easily digestible meals" is provided. Furthermore, if the user has a specific health problem, the advice unit can also provide advice corresponding to that problem. For example, advice such as "We will provide advice corresponding to the specific health problem" is provided. This allows the advice unit to apply different advice algorithms depending on the user's current health condition, thereby enabling more appropriate advice to be provided.

[0063] When executing advice, the execution unit can select an execution method by referring to the user's past weight fluctuation data. For example, the execution unit selects a similar execution method by referring to a weight fluctuation pattern that the user has been successful in the past. For example, the execution unit makes a suggestion such as "We will select a similar execution method by referring to a weight fluctuation pattern that has been successful in the past." In addition, the execution unit can select a different execution method so that the user avoids a weight fluctuation pattern that has failed in the past. For example, the execution unit makes a suggestion such as "We will select a different execution method to avoid a weight fluctuation pattern that has failed in the past." In addition, the execution unit can analyze the user's past weight fluctuation data and select the most effective execution method. For example, the execution unit makes a suggestion such as "We will analyze the past weight fluctuation data and select the most effective execution method." In this way, the execution unit can select the optimal execution method by referring to the user's past weight fluctuation data, and provide effective advice.

[0064] The analysis unit can adjust the analysis algorithm by referring to past data during analysis. For example, the analysis unit selects an optimal analysis algorithm based on the user's past weight fluctuation data. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past weight fluctuation data." The analysis unit can also select an effective analysis algorithm based on the user's past diet history. For example, the analysis unit makes a suggestion such as "We will select an effective analysis algorithm based on the past diet history." The analysis unit can also select an optimal analysis algorithm based on the user's past exercise history. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past exercise history." This allows the analysis unit to optimize the analysis algorithm by referring to past data, thereby enabling more effective analysis.

[0065] During a conversation, the conversation unit can provide an answer by referring to the user's past question history. For example, the conversation unit provides a related answer based on the content of a question asked by the user in the past. For example, the conversation unit makes a suggestion such as "We will provide you with a related answer based on the content of a question asked in the past." The conversation unit can also select the most effective answer from the user's past question history. For example, the conversation unit makes a suggestion such as "We will select the most effective answer from the past question history." The conversation unit can also analyze the content of questions asked by the user in the past and provide an optimal answer. For example, the conversation unit makes a suggestion such as "We will analyze the content of past questions and provide you with an optimal answer." This allows the conversation unit to provide an optimal answer by referring to the user's past question history, enabling an effective conversation.

[0066] The process flow of the first embodiment will be briefly described below.

[0067] Step 1: The reception unit receives the user's diet deadline. For example, the user sets a goal such as "I want to lose 5 kg in 3 months." This information is entered into the system. Step 2: The advice section provides daily advice based on the information entered by the reception section. For example, it provides specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes." Step 3: The executive unit executes advice every time the user records their weight on a scale or body composition monitor. For example, if the user is losing weight, the executive unit will provide an encouraging message such as "You're doing well, keep it up," and if the user is gaining weight, the executive unit will provide advice such as "You need to reassess your diet." Step 4: The analysis unit analyzes past data and gives advice on diet and exercise. For example, if past data shows that the user lost weight after eating a certain meal, the analysis unit will advise the user to eat that meal again. Also, if a certain exercise was effective, the analysis unit will advise the user to continue that exercise. Step 5: The conversation unit provides appropriate advice in response to the user's question. For example, if the user asks, "What should I eat today?", the conversation unit provides specific advice such as, "Try to eat more vegetables today."

[0068] (Example 2) The diet support system according to the embodiment of the present invention is a system that supports dieting in cooperation with a weight scale or a body composition scale. This diet support system inputs a diet deadline, and provides advice every day with the deadline as a target. Each time the user records with the weight scale or the body composition scale every day, the advice is executed at that timing. In addition, advice is also given on the diet and exercise to be taken based on past data. Furthermore, the system assists the user in a conversational manner. For example, the user inputs a diet deadline. For example, the user sets a goal such as "I want to lose 5 kg in three months." This information is input to the system. Next, the system provides advice every day with the set deadline as a target. For example, specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes." Each time the user records with the weight scale or the body composition scale every day, advice is executed at that timing. For example, if the user is losing weight, the system provides an encouraging message such as "You're doing well, keep it up," and if the user is gaining weight, the system provides advice such as "You need to reconsider your diet." In addition, the system provides advice on the diet and exercise to be taken based on past data. For example, if past data shows that the user lost weight after eating a certain meal, the system will advise the user to eat that meal again. Also, if a certain exercise was effective, the system will advise the user to continue that exercise. Finally, the system assists the user in a conversational manner. For example, if the user asks, "What should I eat today?" the system will provide specific advice such as, "Try to eat more vegetables today." In this way, the user can proceed with their diet while interacting with the system. This allows the diet assistance system to effectively support the user's diet.

[0069] The diet support system according to the embodiment includes a reception unit, an advice unit, an execution unit, an analysis unit, and a conversation unit. The reception unit receives a diet deadline input by the user. For example, the user sets a goal such as "I want to lose 5 kg in 3 months." This information is input to the system. The advice unit provides advice every day based on the information input by the reception unit. For example, specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes." The execution unit executes advice every time a record is taken with a weight scale or a body composition scale. For example, if weight is decreasing, an encouraging message such as "You're doing well, keep it up," is provided, and if weight is increasing, advice such as "You need to reconsider your diet." The analysis unit analyzes past data and provides advice on what to eat and what exercise to take. For example, if past data shows that the user lost weight when eating a specific meal, the analysis unit advises the user to eat that meal again. Also, if a specific exercise was effective, the analysis unit advises the user to continue that exercise. The conversation unit provides appropriate advice in response to the user's questions. For example, when a user asks, "What should I eat today?", the conversation unit provides specific advice such as, "Try to eat more vegetables today." In this way, the diet support system according to the embodiment can effectively support the user's diet.

[0070] The reception unit allows the user to input a deadline for dieting. For example, the user sets a goal such as "I want to lose 5 kg in 3 months." This information is input to the system. The reception unit allows the user to input detailed information such as the current weight, body fat percentage, and lifestyle habits as well as a specific target weight and period when setting a goal. This allows the system to accurately grasp the user's current situation and provide more appropriate advice. Furthermore, the reception unit allows the user to input a motivation or reason for achieving the goal when setting a goal. For example, by inputting a specific reason such as "because it was pointed out in a health check" or "for the wedding," the system can provide a message to increase the user's motivation. In addition, the reception unit can periodically check the progress of the goal even after the user sets the goal, and can correct or reset the goal as necessary. For example, if the user achieves the goal halfway through, or conversely, if the user does not reach the goal, the reception unit prompts the user to set a new goal. This allows the reception unit to flexibly manage the user's diet goals and always provide optimal support.

[0071] The advice unit provides advice every day based on the information input by the reception unit. For example, specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes" is provided. The advice unit provides advice that is individually customized according to the user's goals and current situation. For example, if the user is allergic to a particular food ingredient or does not like a particular exercise, an alternative suggestion is presented accordingly. The advice unit also provides advice that is feasible within a reasonable range according to the user's life rhythm and schedule. For example, on busy days, it suggests short but effective exercises, and on days when there is more time, it recommends longer exercises. Furthermore, the advice unit continuously improves the content of the advice based on the user's progress and feedback. For example, if the user provides feedback such as "it was easy to implement" or "it was effective" in response to a particular piece of advice, the advice unit will continue to provide that advice in the future. Conversely, if the user provides feedback such as "it was difficult to implement" or "it was ineffective," it will suggest a different piece of advice. In this way, the advice unit can provide the most suitable advice for the user and support the success of dieting.

[0072] The execution unit executes advice every time a record is taken with a weight scale or a body composition scale. For example, if the user is losing weight, the execution unit provides an encouraging message such as "You're doing well, keep it up," and if the user is gaining weight, the execution unit provides advice such as "You need to reconsider your diet." When the user records changes in weight and body composition on a daily basis, the execution unit automatically transmits the data to the system and analyzes them in real time. This allows the user to manage data without any hassle. The execution unit also checks whether the user has performed the advice and provides feedback according to the execution status. For example, if the user performs the suggested exercise, the execution unit provides an encouraging message such as "You did a good job," and if the user does not perform the exercise, the execution unit provides a message such as "Please try again next time." Furthermore, the execution unit adjusts the content of the advice according to the user's execution status and progress. For example, if the user is losing weight smoothly, the execution unit provides advice to maintain the current state, and conversely, if the user is gaining weight, the execution unit suggests that the user review the content of their diet and exercise. This allows the execution unit to provide appropriate support according to the user's situation and support the success of the diet.

[0073] The analysis unit analyzes past data and gives advice on what to eat and what to exercise. For example, if the past data shows that the user lost weight after eating a certain meal, the analysis unit advises the user to eat that meal again. If a certain exercise was effective, the analysis unit advises the user to continue that exercise. The analysis unit analyzes the user's past meal and exercise data in detail to identify effective patterns and trends. For example, it finds cases where exercising at a certain time of day is more effective, or where eating certain ingredients is more likely to help the user lose weight. The analysis unit also provides customized advice according to the user's constitution and lifestyle. For example, if the user is a nocturnal person, the analysis unit provides advice on exercises and meals that are easy to perform at night. Furthermore, the analysis unit provides scientifically based advice based on the latest research and data. For example, the analysis unit suggests meals that incorporate the latest research results in nutrition and introduces effective exercise methods. As a result, the analysis unit can provide the user with optimal meal and exercise advice and support successful dieting.

[0074] The conversation unit provides appropriate advice in response to the user's questions. For example, when the user asks "What should I eat today?", the conversation unit provides specific advice such as "Try to eat more vegetables today." The conversation unit uses natural language processing technology to understand the user's questions and generate appropriate answers. For example, when the user asks "I'm not good at exercising. What should I do?", the conversation unit provides advice such as "Start with light exercise that you can do without straining yourself." In addition, the conversation unit provides more personalized advice based on the user's past questions and feedback. For example, when the user has provided feedback such as "I don't like vegetables" in the past, the conversation unit provides advice such as "If it's difficult to eat vegetables, one way to do it is to make them into a smoothie and consume them." In addition, the conversation unit provides messages to increase the user's motivation. For example, the conversation unit provides encouraging messages such as "You did a great job today" and encouraging messages such as "You're almost there until you achieve your goal." In this way, the conversation unit can provide appropriate and personalized advice in response to the user's questions and support the success of the diet.

[0075] The advice unit can provide the user with specific diet or exercise advice. The advice unit, for example, provides the user with specific diet advice. For example, it proposes a meal plan that takes into account calorie restriction and nutritional balance. The advice unit can also provide the user with specific exercise advice. For example, it proposes an exercise plan such as walking, jogging, or strength training. Furthermore, the advice unit can adjust the diet and exercise advice according to the user's physical condition and life rhythm. For example, if the user is not feeling well, it suggests light exercise or a meal that is easy to digest. In this way, the advice unit can improve the effectiveness of the diet by providing the user with specific diet and exercise advice.

[0076] The execution unit can adjust the advice based on changes in the user's weight or body composition. For example, if the user's weight is decreasing, the execution unit provides an encouraging message. For example, it provides a message such as "You're doing well, keep it up." In addition, the execution unit can also suggest a review of the user's diet if the user's weight is increasing. For example, it provides advice such as "You need to review your diet. Reduce your calories." In addition, the execution unit can adjust the advice based on changes in the user's body composition. For example, if the body fat percentage is increasing, it suggests increasing the amount of exercise. This allows the execution unit to provide more effective diet support by adjusting the advice based on changes in the user's weight or body composition.

[0077] The analysis unit can analyze past data and identify the optimal diet or exercise for the user. For example, if the past data shows that the user lost weight after eating a specific diet, the analysis unit advises the user to eat that diet again. For example, the analysis unit provides advice such as "You lost weight when you ate this diet in the past, so we recommend that you eat it again." In addition, if a specific exercise is effective, the analysis unit can advise the user to continue that exercise. For example, the analysis unit provides advice such as "You lost weight when you did this exercise in the past, so we recommend that you continue." In addition, the analysis unit can evaluate the effectiveness of diet and exercise based on the user's past data and propose an optimal plan. As a result, the analysis unit can identify the optimal diet and exercise for the user by analyzing past data, enabling effective diet support.

[0078] The conversation unit can provide advice in response to a user's question. For example, when the user asks, "What should I eat today?", the conversation unit provides specific advice. For example, the conversation unit provides advice such as, "Try to eat more vegetables today." In addition, when the user asks, "What kind of exercise should I do?", the conversation unit can also provide exercise advice. For example, the conversation unit provides advice such as, "Try to walk for 30 minutes." Furthermore, the conversation unit can refer to past data and analysis results in order to provide appropriate advice in response to the user's question. In this way, the conversation unit can resolve the user's doubts and support the user's diet by providing appropriate advice in response to the user's question.

[0079] The reception unit can estimate the user's emotions and adjust the timing of diet deadline input based on the estimated user's emotions. For example, when the user is stressed, the reception unit delays the input timing so that the user can input in a relaxed state. For example, the reception unit provides a message such as "Please wait a little while before inputting so that the user can input in a relaxed state." In addition, when the user is highly motivated, the reception unit can prompt the user to input the deadline immediately and actively set goals. For example, the reception unit provides a message such as "Now that you are highly motivated, let's set a goal immediately." In addition, when the user is tired, the reception unit can send a reminder to prompt the user to input the next day. For example, the reception unit provides a message such as "You seem tired, so let's set a goal again tomorrow." As a result, the reception unit adjusts the timing of diet deadline input based on the user's emotions, making it possible to set goals at a more appropriate timing. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0080] The reception unit can analyze the user's past diet history and suggest a deadline setting method. The reception unit, for example, refers to a diet period in which the user was successful in the past and suggests a similar deadline. For example, it makes a suggestion such as "Let's set a three-month deadline by referring to the diet period in which the user was successful in the past." The reception unit can also suggest a different deadline so that the user can avoid a diet period in which the user failed in the past. For example, it makes a suggestion such as "Let's set a six-month deadline this time to avoid a period in which the user failed in the past." Furthermore, the reception unit can analyze the most effective period from the user's past diet history and suggest it. For example, it makes a suggestion such as "We found from past data that a four-month period is the most effective, so let's set a four-month deadline." In this way, the reception unit can propose an optimal deadline setting method by analyzing the user's past diet history, and increase the success rate of dieting.

[0081] The reception unit can perform filtering based on the user's current health condition and lifestyle habits when inputting the diet deadline. The reception unit, for example, evaluates the user's current health condition and proposes a reasonable deadline. For example, it makes a suggestion such as "Let's set a reasonable deadline in consideration of the user's current health condition." The reception unit can also propose a realistic deadline in consideration of the user's lifestyle habits (busyness at work and family situation). For example, it makes a suggestion such as "Let's set a realistic deadline in consideration of the lifestyle habits." Furthermore, the reception unit can also propose an achievable deadline based on the user's current weight and body composition. For example, it makes a suggestion such as "Let's set an achievable deadline based on the user's current weight and body composition." As a result, the reception unit can set a realistic deadline by performing filtering based on the user's current health condition and lifestyle habits.

[0082] The reception unit can estimate the user's emotion and determine the priority of deadlines to be input based on the estimated user's emotion. For example, when the user is in a hurry, the reception unit prioritizes and proposes short-term goals. For example, the reception unit makes a suggestion such as "You seem to be in a hurry, so let's set a short-term goal." In addition, when the user is relaxed, the reception unit can also prioritize and propose long-term goals. For example, the reception unit makes a suggestion such as "You seem to be relaxed, so let's set a long-term goal." In addition, when the user is feeling anxious, the reception unit can set gradual goals and provide a sense of security. For example, the reception unit makes a suggestion such as "You seem to be anxious, so let's set a gradual goal." As a result, the reception unit determines the priority of deadlines to be input based on the user's emotion, thereby enabling more appropriate goal setting. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0083] When inputting a diet deadline, the reception unit can preferentially present a deadline with high relevance in consideration of the geographical location information of the user. The reception unit, for example, proposes a deadline that matches the climate and season of the area where the user lives. For example, it makes a suggestion such as "Let's set a realistic deadline in accordance with the climate and season of the area where you live." The reception unit can also propose a deadline that matches events and occasions in the area where the user lives. For example, it makes a suggestion such as "Let's set a deadline in accordance with local events and occasions." Furthermore, the reception unit can also propose a realistic deadline based on the food culture and lifestyle habits of the area where the user lives. For example, it makes a suggestion such as "Let's set a realistic deadline based on the food culture and lifestyle habits of the area." As a result, the reception unit preferentially proposes a deadline with high relevance in consideration of the geographical location information of the user, thereby enabling realistic goal setting.

[0084] The reception unit can analyze the user's social media activity when inputting a diet deadline, and present a related deadline. The reception unit, for example, proposes a deadline that matches a goal or event shared by the user on social media. For example, it makes a suggestion such as "Let's set a deadline according to the goal shared on social media." The reception unit can also analyze the user's social media activity pattern and propose a realistic deadline. For example, it makes a suggestion such as "Let's set a realistic deadline based on the social media activity pattern." Furthermore, the reception unit can also propose a deadline based on health and fitness trends that the user follows on social media. For example, it makes a suggestion such as "Let's set a deadline based on the health and fitness trends that you follow." As a result, the reception unit proposes a related deadline by analyzing the user's social media activity, and it becomes possible to set realistic goals.

[0085] The advice unit can estimate the user's emotions and adjust the way of expressing advice based on the estimated user's emotions. For example, if the user is depressed, the advice unit provides advice that includes many encouraging words. For example, it provides encouraging words such as "You seem to be depressed, so let's try our best." In addition, if the user is highly motivated, the advice unit can also provide specific and challenging advice. For example, it provides specific advice such as "Now that you are highly motivated, let's try harder." In addition, if the user is feeling anxious, the advice unit can also provide advice that gives a sense of security. For example, it provides advice such as "You seem to be anxious, so let's proceed with peace of mind." This allows the advice unit to adjust the way of expressing advice based on the user's emotions, thereby enabling more effective advice. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0086] When providing advice, the advice unit can change the level of detail of the advice based on the user's past successful dieting examples. The advice unit provides detailed advice, for example, by referring to a dieting method that the user has been successful in the past. For example, the advice unit provides advice such as "We will provide you with detailed advice by referring to a method that has been successful in the past." The advice unit can also provide concise advice so that the user avoids a dieting method that has failed in the past. For example, the advice unit provides advice such as "We will provide you with concise advice to avoid a method that has failed in the past." Furthermore, the advice unit can provide specific advice on diet and exercise based on the user's past successful examples. For example, the advice unit provides advice such as "We will provide you with specific advice on diet and exercise based on past successful examples." This allows the advice unit to adjust the level of detail of the advice based on the user's past successful dieting examples, thereby enabling more effective advice.

[0087] When providing advice, the advice unit can use different advice algorithms depending on the user's current health condition. For example, when the user is in good health, the advice unit provides advice on active exercise and diet. For example, the advice unit provides advice such as "Your health is good, so exercise and eat actively." In addition, when the user is in poor health, the advice unit can also provide advice on light exercise and diet. For example, the advice unit provides advice such as "Your health does not seem to be good, so exercise lightly and eat easily digestible foods." In addition, when the user has a specific health problem, the advice unit can also provide advice corresponding to that problem. For example, the advice unit provides advice such as "We will provide advice corresponding to a specific health problem." This allows the advice unit to apply different advice algorithms depending on the user's current health condition, thereby enabling more appropriate advice to be provided.

[0088] The advice unit can estimate the user's emotion and change the length of advice based on the estimated user's emotion. For example, when the user is in a hurry, the advice unit provides short advice that is to the point. For example, the advice unit provides advice such as "You seem to be in a hurry, so we will provide you with short advice that is to the point." In addition, when the user is relaxed, the advice unit can provide longer advice that includes detailed explanations. For example, the advice unit provides advice such as "You seem to be relaxed, so we will provide you with longer advice that includes detailed explanations." In addition, when the user is anxious, the advice unit can provide polite advice to give a sense of security. For example, the advice unit provides advice such as "You seem to be anxious, so we will provide you with polite advice to give you a sense of security." This allows the advice unit to adjust the length of advice based on the user's emotion, thereby enabling more effective advice. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0089] The advice unit can set a priority order of advice based on the user's life rhythm when providing advice. For example, if the user is a morning person, the advice unit provides important advice in the morning hours. For example, the advice unit provides advice such as "important advice will be provided in the morning hours in accordance with the morning person's life rhythm." In addition, if the user is a night person, the advice unit can also provide important advice in the evening hours. For example, the advice unit provides advice such as "important advice will be provided in the evening hours in accordance with the night person's life rhythm." In addition, the advice unit can also provide advice at an optimal timing in accordance with the user's life rhythm. For example, the advice unit provides advice such as "advice will be provided at an optimal timing in accordance with the life rhythm." In this way, the advice unit can provide more effective advice by determining the priority order of advice based on the user's life rhythm.

[0090] The advice unit can change the order of advice based on the user's meal history when providing advice. The advice unit, for example, suggests an optimal meal order based on the user's meal history in the past. For example, the advice unit gives advice such as "We suggest an optimal meal order based on the meal history in the past." In addition, when the user has eaten a specific meal, the advice unit can also suggest a meal to be eaten after the user has eaten. For example, the advice unit gives advice such as "We suggest a meal to be eaten after eating a specific meal." Furthermore, the advice unit can analyze the user's meal history and suggest an effective meal order. For example, the advice unit gives advice such as "We analyze the meal history and suggest an effective meal order." In this way, the advice unit can provide more effective advice by adjusting the order of advice based on the user's meal history.

[0091] The execution unit can estimate the user's emotion and change the execution timing of the advice based on the estimated emotion of the user. For example, when the user is stressed, the execution unit executes the advice in a relaxed state. For example, the execution unit makes a suggestion such as "execute the advice in a relaxed state." In addition, when the user is highly motivated, the execution unit can also execute the advice immediately. For example, the execution unit makes a suggestion such as "execute the advice immediately now that you are highly motivated." In addition, when the user is tired, the execution unit can also send a reminder to execute the advice the next day. For example, the execution unit makes a suggestion such as "You seem tired, so let's execute the advice again tomorrow." This allows the execution unit to adjust the execution timing of the advice based on the user's emotion, thereby enabling more effective advice. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0092] When executing advice, the execution unit can select an execution method by referring to the user's past weight fluctuation data. For example, the execution unit selects a similar execution method by referring to a weight fluctuation pattern that the user has been successful in the past. For example, the execution unit makes a suggestion such as "We will select a similar execution method by referring to a weight fluctuation pattern that has been successful in the past." In addition, the execution unit can select a different execution method so that the user avoids a weight fluctuation pattern that has failed in the past. For example, the execution unit makes a suggestion such as "We will select a different execution method to avoid a weight fluctuation pattern that has failed in the past." In addition, the execution unit can analyze the user's past weight fluctuation data and select the most effective execution method. For example, the execution unit makes a suggestion such as "We will analyze the past weight fluctuation data and select the most effective execution method." In this way, the execution unit can select the optimal execution method by referring to the user's past weight fluctuation data, and provide effective advice.

[0093] The execution unit can change the execution content based on the user's current physical condition when executing advice. For example, when the user is in good health, the execution unit executes advice on active exercise and diet. For example, it makes a suggestion such as "Since your health is good, you should exercise and eat actively." In addition, when the user is in poor health, the execution unit can also execute advice on light exercise and diet. For example, it makes a suggestion such as "Since you do not seem to be in good health, you should do light exercise and eat foods that are easy to digest." Furthermore, when the user has a specific health problem, the execution unit can also execute advice corresponding to that problem. For example, it makes a suggestion such as "Execute advice corresponding to the specific health problem." In this way, the execution unit can customize the execution content based on the user's current physical condition, thereby enabling more appropriate advice to be provided.

[0094] The execution unit can estimate the user's emotion and set the execution priority of advice based on the estimated user's emotion. For example, when the user is in a hurry, the execution unit prioritizes short-term advice. For example, it makes a suggestion such as "Since it seems that you are in a hurry, we will prioritize short-term advice." In addition, when the user is relaxed, the execution unit can also prioritize long-term advice. For example, it makes a suggestion such as "Since it seems that you are relaxed, we will prioritize long-term advice." In addition, when the user is feeling anxious, the execution unit can also prioritize gradual advice. For example, it makes a suggestion such as "Since it seems that you are feeling anxious, we will prioritize gradual advice." In this way, the execution unit can determine the execution priority of advice based on the user's emotion, thereby enabling more effective advice. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0095] The execution unit can select an execution method in consideration of the geographical location information of the user when executing advice. The execution unit executes advice according to, for example, the climate and season of the area where the user lives. For example, it makes a suggestion such as "execute advice according to the climate and season of the area where the user lives." The execution unit can also execute advice according to events and occasions in the area where the user lives. For example, it makes a suggestion such as "execute advice according to local events and occasions." Furthermore, the execution unit can also execute realistic advice based on the food culture and lifestyle habits of the area where the user lives. For example, it makes a suggestion such as "execute realistic advice based on the food culture and lifestyle habits of the area." As a result, the execution unit can provide realistic advice by selecting an optimal execution method in consideration of the geographical location information of the user.

[0096] When executing advice, the execution unit can analyze the user's social media activity and present the execution content. The execution unit executes advice tailored to goals and events shared by the user on social media, for example. For example, the execution unit makes a suggestion such as "execute the advice in accordance with the goals shared on social media." The execution unit can also analyze the user's social media activity pattern and execute realistic advice. For example, the execution unit makes a suggestion such as "execute realistic advice based on the social media activity pattern." Furthermore, the execution unit can also execute advice based on health and fitness trends that the user follows on social media. For example, the execution unit makes a suggestion such as "execute advice based on the health and fitness trends that you are following." As a result, the execution unit can propose related execution content and provide realistic advice by analyzing the user's social media activity.

[0097] The analysis unit can estimate the user's emotion and select analysis data based on the estimated user's emotion. For example, when the user is feeling stressed, the analysis unit prioritizes analysis of data that is effective for stress reduction. For example, the analysis unit makes a suggestion such as "We will prioritize analysis of data that is effective for stress reduction." In addition, when the user is highly motivated, the analysis unit can also prioritize analysis of challenging data. For example, the analysis unit makes a suggestion such as "Now that your motivation is high, we will prioritize analysis of challenging data." In addition, when the user is feeling anxious, the analysis unit can also prioritize analysis of data that gives a sense of security. For example, the analysis unit makes a suggestion such as "Since you seem to be feeling anxious, we will prioritize analysis of data that gives a sense of security." This allows the analysis unit to select analysis data based on the user's emotion, thereby enabling more effective analysis. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0098] The analysis unit can adjust the analysis algorithm by referring to past data during analysis. The analysis unit selects an optimal analysis algorithm based on, for example, the user's past weight fluctuation data. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past weight fluctuation data." The analysis unit can also select an effective analysis algorithm based on the user's past diet history. For example, the analysis unit makes a suggestion such as "We will select an effective analysis algorithm based on the past diet history." The analysis unit can also select an optimal analysis algorithm based on the user's past exercise history. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past exercise history." This allows the analysis unit to optimize the analysis algorithm by referring to past data, thereby enabling more effective analysis.

[0099] The analysis unit can change the analysis method based on the user's current health condition during analysis. For example, when the user is in good health, the analysis unit applies an aggressive analysis method. For example, the analysis unit makes a suggestion such as "Since your health condition is good, apply an aggressive analysis method." In addition, when the user is in poor health, the analysis unit can apply a light analysis method. For example, the analysis unit makes a suggestion such as "Since your health condition is not good, apply a light analysis method." In addition, when the user has a specific health problem, the analysis unit can apply an analysis method corresponding to the problem. For example, the analysis unit makes a suggestion such as "Apply an analysis method corresponding to the specific health problem." In this way, the analysis unit can customize the analysis method based on the user's current health condition, thereby enabling more appropriate analysis.

[0100] The analysis unit can estimate the user's emotion and change the frequency of analysis based on the estimated user's emotion. For example, when the user is feeling stressed, the analysis unit reduces the frequency of analysis to reduce the burden. For example, the analysis unit makes a suggestion such as "Since you seem to be feeling stressed, we will reduce the frequency of analysis to reduce the burden." In addition, when the user is highly motivated, the analysis unit can increase the frequency of analysis to provide detailed data. For example, the analysis unit makes a suggestion such as "Now that you are highly motivated, we will increase the frequency of analysis and provide detailed data." In addition, when the user is feeling anxious, the analysis unit can perform analysis at a moderate frequency to give a sense of security. For example, the analysis unit makes a suggestion such as "Since you seem to be feeling anxious, we will perform analysis at a moderate frequency to give a sense of security." This allows the analysis unit to adjust the frequency of analysis based on the user's emotion, thereby enabling more effective analysis. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0101] The analysis unit can weight the analysis data based on the user's life rhythm during analysis. For example, if the user is a morning person, the analysis unit weights the morning data for analysis. For example, the analysis unit makes a suggestion such as "We will weight the morning data for analysis in accordance with the morning person's life rhythm." In addition, if the user is a night person, the analysis unit can weight the night data for analysis. For example, the analysis unit makes a suggestion such as "We will weight the night data for analysis in accordance with the night person's life rhythm." In addition, the analysis unit can weight the data at an optimal timing in accordance with the user's life rhythm. For example, the analysis unit makes a suggestion such as "We will weight the data at an optimal timing in accordance with the life rhythm." This allows the analysis unit to weight the analysis data based on the user's life rhythm, making it possible to perform a more effective analysis.

[0102] The analysis unit can improve the accuracy of the analysis by referring to the user's dietary history during the analysis. The analysis unit, for example, selects an optimal analysis method based on the history of meals taken by the user in the past. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis method based on the history of meals taken in the past." In addition, when the user takes a specific meal, the analysis unit can also analyze the data after the user takes the meal by placing emphasis on the data after the user takes the meal. For example, the analysis unit makes a suggestion such as "We will analyze the data after the user takes the specific meal." In addition, the analysis unit can analyze the user's dietary history and apply an effective analysis method. For example, the analysis unit makes a suggestion such as "We will analyze the dietary history and apply an effective analysis method." As a result, the analysis unit can improve the accuracy of the analysis by referring to the user's dietary history, thereby enabling more effective analysis.

[0103] The conversation unit can estimate the user's emotions and adjust the content of the conversation based on the estimated user's emotions. For example, when the user is depressed, the conversation unit provides a conversation that includes many encouraging words. For example, the conversation unit provides encouraging words such as "You seem to be depressed, so let's do our best." In addition, when the user is highly motivated, the conversation unit can also provide a specific and challenging conversation. For example, the conversation unit provides a specific conversation such as "Now that you are highly motivated, let's work even harder." In addition, when the user is feeling anxious, the conversation unit can also provide a conversation that gives a sense of security. For example, the conversation unit provides a conversation such as "You seem to be anxious, so let's proceed with peace of mind." This allows the conversation unit to adjust the content of the conversation based on the user's emotions, thereby enabling a more effective conversation. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0104] The conversation unit can provide an answer by referring to the user's past question history during a conversation. The conversation unit provides a related answer based on, for example, the content of a question asked by the user in the past. For example, the conversation unit makes a suggestion such as "We will provide you with a related answer based on the content of your past questions." The conversation unit can also select the most effective answer from the user's past question history. For example, the conversation unit makes a suggestion such as "We will select the most effective answer from your past question history." The conversation unit can also analyze the content of questions asked by the user in the past and provide an optimal answer. For example, the conversation unit makes a suggestion such as "We will analyze the content of your past questions and provide you with an optimal answer." This allows the conversation unit to provide an optimal answer by referring to the user's past question history, enabling an effective conversation.

[0105] The conversation unit can change the conversation content based on the user's current health condition during the conversation. For example, when the user is in good health, the conversation unit provides positive conversation content. For example, the conversation unit makes a suggestion such as "Since your health condition is good, we will provide you with positive conversation content." In addition, when the user is in poor health, the conversation unit can also provide light conversation content. For example, the conversation unit makes a suggestion such as "Since you do not seem to be in good health, we will provide you with light conversation content." In addition, when the user has a specific health problem, the conversation unit can also provide conversation content corresponding to that problem. For example, the conversation unit makes a suggestion such as "We will provide you with conversation content corresponding to the specific health problem." In this way, the conversation unit can customize the conversation content based on the user's current health condition, thereby enabling a more appropriate conversation.

[0106] The conversation unit can estimate the user's emotions and set conversation priorities based on the estimated user's emotions. For example, when the user is in a hurry, the conversation unit prioritizes short-term conversations. For example, it makes a suggestion such as "Since it seems that you are in a hurry, we will prioritize short-term conversations." In addition, when the user is relaxed, the conversation unit can also prioritize long-term conversations. For example, it makes a suggestion such as "Since it seems that you are relaxed, we will prioritize long-term conversations." In addition, when the user is feeling anxious, the conversation unit can also prioritize staged conversations. For example, it makes a suggestion such as "Since it seems that you are feeling anxious, we will prioritize staged conversations." In this way, the conversation unit can determine the priority of conversations based on the user's emotions, thereby enabling more effective conversations. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0107] The conversation unit can provide optimal conversation content in consideration of the geographical location information of the user during conversation. The conversation unit provides conversation content that matches, for example, the climate and season of the area where the user lives. For example, it makes a suggestion such as "We will provide you with conversation content that matches the climate and season of the area where you live." The conversation unit can also provide conversation content that matches events and occasions in the area where the user lives. For example, it makes a suggestion such as "We will provide you with conversation content that matches the events and occasions of the area." Furthermore, the conversation unit can also provide realistic conversation content based on the food culture and lifestyle of the area where the user lives. For example, it makes a suggestion such as "We will provide you with realistic conversation content based on the food culture and lifestyle of the area." As a result, the conversation unit provides optimal conversation content in consideration of the geographical location information of the user, thereby enabling realistic conversation.

[0108] The conversation unit can present conversation content by analyzing the user's social media activity during the conversation. The conversation unit provides conversation content that matches, for example, goals and events shared by the user on social media. For example, the conversation unit makes a suggestion such as "We will provide you with conversation content that matches your goals shared on social media." The conversation unit can also analyze the user's social media activity pattern to provide realistic conversation content. For example, the conversation unit makes a suggestion such as "We will provide you with realistic conversation content based on your social media activity pattern." Furthermore, the conversation unit can also suggest conversation content based on health and fitness trends that the user follows on social media. For example, the conversation unit makes a suggestion such as "We will suggest conversation content based on the health and fitness trends that you follow." As a result, the conversation unit proposes related conversation content by analyzing the user's social media activity, making it possible to have a realistic conversation.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The reception unit can analyze the user's past diet history and suggest a deadline setting method. For example, by referring to a diet period in which the user was successful in the past, the reception unit can suggest a similar deadline. For example, the reception unit can make a suggestion such as "Let's set a three-month deadline by referring to a diet period in which the user was successful in the past." The reception unit can also suggest a different deadline so that the user can avoid a diet period in which the user was unsuccessful in the past. For example, the reception unit can make a suggestion such as "Let's set a six-month deadline this time to avoid a period in which the user was unsuccessful in the past." Furthermore, the reception unit can analyze the most effective period from the user's past diet history and suggest it. For example, the reception unit can make a suggestion such as "We found from past data that a four-month period is the most effective, so let's set a four-month deadline." In this way, the reception unit can propose an optimal deadline setting method by analyzing the user's past diet history, thereby increasing the success rate of the diet.

[0111] The advice unit can estimate the user's emotions and adjust the way of expressing advice based on the estimated user's emotions. For example, if the user is depressed, advice containing many encouraging words is provided. For example, encouraging words such as "You seem to be depressed, so let's try our best" are provided. In addition, the advice unit can also provide specific and challenging advice when the user is highly motivated. For example, specific advice such as "Now that you are highly motivated, let's try harder." In addition, the advice unit can also provide advice that gives a sense of security when the user is feeling anxious. For example, advice such as "You seem to be anxious, so let's proceed with peace of mind." This allows the advice unit to adjust the way of expressing advice based on the user's emotions, thereby enabling more effective advice. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0112] The execution unit can estimate the user's emotion and change the execution timing of the advice based on the estimated emotion of the user. For example, when the user is stressed, the advice is executed in a relaxed state. For example, the execution unit makes a suggestion such as "execute the advice in a relaxed state." In addition, when the user is highly motivated, the execution unit can also execute the advice immediately. For example, the execution unit makes a suggestion such as "execute the advice immediately now that you are highly motivated." In addition, when the user is tired, the execution unit can also send a reminder to execute the advice the next day. For example, the execution unit makes a suggestion such as "You seem tired, so let's execute the advice again tomorrow." This allows the execution unit to adjust the execution timing of the advice based on the user's emotion, thereby enabling more effective advice. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0113] The analysis unit can estimate the user's emotion and select analysis data based on the estimated user's emotion. For example, when the user is feeling stressed, data effective for stress reduction is preferentially analyzed. For example, a suggestion such as "We will give priority to analyzing data effective for stress reduction" is made. In addition, when the user is highly motivated, the analysis unit can also preferentially analyze challenging data. For example, a suggestion such as "Now that your motivation is high, we will give priority to analyzing challenging data." In addition, when the user is feeling anxious, the analysis unit can also preferentially analyze data that gives a sense of security. For example, a suggestion such as "Since you seem to be feeling anxious, we will give priority to analyzing data that gives a sense of security." This allows the analysis unit to select analysis data based on the user's emotion, thereby enabling more effective analysis. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0114] The conversation unit can estimate the user's emotions and adjust the content of the conversation based on the estimated user's emotions. For example, if the user is depressed, the conversation unit provides a conversation that includes many encouraging words. For example, the conversation unit provides encouraging words such as "You seem to be depressed, so let's try our best." In addition, if the user is highly motivated, the conversation unit can also provide a specific and challenging conversation. For example, the conversation unit provides a specific conversation such as "Now that you are highly motivated, let's try even harder." In addition, if the user is feeling anxious, the conversation unit can also provide a conversation that gives a sense of security. For example, the conversation unit provides a conversation such as "You seem to be anxious, so let's proceed with peace of mind." This allows the conversation unit to adjust the content of the conversation based on the user's emotions, thereby enabling a more effective conversation. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0115] The reception unit can perform filtering based on the user's current health condition and lifestyle habits when inputting a diet deadline. For example, the reception unit evaluates the user's current health condition and proposes a reasonable deadline. For example, the reception unit makes a suggestion such as "Let's set a reasonable deadline in consideration of the user's current health condition." In addition, the reception unit can also propose a realistic deadline in consideration of the user's lifestyle habits (busyness at work and family situation). For example, the reception unit makes a suggestion such as "Let's set a realistic deadline in consideration of the lifestyle habits." In addition, the reception unit can also propose an achievable deadline based on the user's current weight and body composition. For example, the reception unit makes a suggestion such as "Let's set an achievable deadline based on the user's current weight and body composition." In this way, the reception unit can set a realistic deadline by performing filtering based on the user's current health condition and lifestyle habits.

[0116] When providing advice, the advice unit can use different advice algorithms depending on the user's current health condition. For example, if the user is in good health, advice on active exercise and diet is provided. For example, advice such as "Your health is good, so exercise and eat actively" is provided. In addition, the advice unit can also provide advice on light exercise and diet when the user is in poor health. For example, advice such as "Your health does not seem to be good, so exercise lightly and eat easily digestible meals" is provided. Furthermore, if the user has a specific health problem, the advice unit can also provide advice corresponding to that problem. For example, advice such as "We will provide advice corresponding to the specific health problem" is provided. This allows the advice unit to apply different advice algorithms depending on the user's current health condition, thereby enabling more appropriate advice to be provided.

[0117] When executing advice, the execution unit can select an execution method by referring to the user's past weight fluctuation data. For example, the execution unit selects a similar execution method by referring to a weight fluctuation pattern that the user has been successful in the past. For example, the execution unit makes a suggestion such as "We will select a similar execution method by referring to a weight fluctuation pattern that has been successful in the past." In addition, the execution unit can select a different execution method so that the user avoids a weight fluctuation pattern that has failed in the past. For example, the execution unit makes a suggestion such as "We will select a different execution method to avoid a weight fluctuation pattern that has failed in the past." In addition, the execution unit can analyze the user's past weight fluctuation data and select the most effective execution method. For example, the execution unit makes a suggestion such as "We will analyze the past weight fluctuation data and select the most effective execution method." In this way, the execution unit can select the optimal execution method by referring to the user's past weight fluctuation data, and provide effective advice.

[0118] The analysis unit can adjust the analysis algorithm by referring to past data during analysis. For example, the analysis unit selects an optimal analysis algorithm based on the user's past weight fluctuation data. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past weight fluctuation data." The analysis unit can also select an effective analysis algorithm based on the user's past diet history. For example, the analysis unit makes a suggestion such as "We will select an effective analysis algorithm based on the past diet history." The analysis unit can also select an optimal analysis algorithm based on the user's past exercise history. For example, the analysis unit makes a suggestion such as "We will select an optimal analysis algorithm based on the past exercise history." This allows the analysis unit to optimize the analysis algorithm by referring to past data, thereby enabling more effective analysis.

[0119] During a conversation, the conversation unit can provide an answer by referring to the user's past question history. For example, the conversation unit provides a related answer based on the content of a question asked by the user in the past. For example, the conversation unit makes a suggestion such as "We will provide you with a related answer based on the content of a question asked in the past." The conversation unit can also select the most effective answer from the user's past question history. For example, the conversation unit makes a suggestion such as "We will select the most effective answer from the past question history." The conversation unit can also analyze the content of questions asked by the user in the past and provide an optimal answer. For example, the conversation unit makes a suggestion such as "We will analyze the content of past questions and provide you with an optimal answer." This allows the conversation unit to provide an optimal answer by referring to the user's past question history, enabling an effective conversation.

[0120] The process flow of the second embodiment will be briefly described below.

[0121] Step 1: The reception unit receives the user's diet deadline. For example, the user sets a goal such as "I want to lose 5 kg in 3 months." This information is entered into the system. Step 2: The advice section provides daily advice based on the information entered by the reception section. For example, it provides specific advice such as "Try to eat more vegetables today" or "Try to walk for 30 minutes." Step 3: The executive unit executes advice every time the user records their weight on a scale or body composition monitor. For example, if the user is losing weight, the executive unit will provide an encouraging message such as "You're doing well, keep it up," and if the user is gaining weight, the executive unit will provide advice such as "You need to reassess your diet." Step 4: The analysis unit analyzes past data and gives advice on diet and exercise. For example, if past data shows that the user lost weight after eating a certain meal, the analysis unit will advise the user to eat that meal again. Also, if a certain exercise was effective, the analysis unit will advise the user to continue that exercise. Step 5: The conversation unit provides appropriate advice in response to the user's question. For example, if the user asks, "What should I eat today?", the conversation unit provides specific advice such as, "Try to eat more vegetables today."

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0124] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0125] Each of the multiple elements including the above-mentioned reception unit, advice unit, execution unit, analysis unit, and conversation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and the user inputs the deadline for dieting. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice every day. The execution unit is realized, for example, by the control unit 46A of the smart device 14, and executes advice every time a record is taken with a weight scale or a body composition scale. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes past data to provide advice on meals and exercise to be taken. The conversation unit is realized, for example, by the control unit 46A of the smart device 14, and provides appropriate advice in response to a user's question. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0133] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0136] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements including the above-mentioned reception unit, advice unit, execution unit, analysis unit, and conversation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and the user inputs a deadline for dieting. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice every day. The execution unit is realized, for example, by the control unit 46A of the smart glasses 214, and executes advice every time a record is taken with a weight scale or a body composition scale. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes past data to provide advice on meals and exercise to be taken. The conversation unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides appropriate advice in response to a user's question. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0149] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0152] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements including the above-mentioned reception unit, advice unit, execution unit, analysis unit, and conversation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314, and the user inputs the deadline for dieting. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice every day. The execution unit is realized, for example, by the control unit 46A of the headset type terminal 314, and executes advice every time a record is taken with a weight scale or a body composition scale. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes past data to provide advice on meals and exercise to be taken. The conversation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides appropriate advice in response to a user's question. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0165] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0166] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0167] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0168] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0169] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0170] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0172] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] Each of the multiple elements including the above-mentioned reception unit, advice unit, execution unit, analysis unit, and conversation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and the user inputs the deadline for dieting. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice every day. The execution unit is realized, for example, by the control unit 46A of the robot 414, and executes advice every time a record is taken with a weight scale or a body composition scale. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes past data to provide advice on meals and exercise to be taken. The conversation unit is realized, for example, by the control unit 46A of the robot 414, and provides appropriate advice in response to a user's question. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0175] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0176] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0177] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0178] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0179] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0180] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0183] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0184] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0185] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0186] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0187] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0188] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0189] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0190] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0191] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0192] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0193] (Appendix 1) A reception unit for allowing a user to input a deadline for dieting; an advice unit that provides advice every day based on the information input by the reception unit; An executive section that gives advice every time a user records their weight or body composition using a scale; An analysis unit that analyzes past data and identifies optimal diet or exercise for a user; A conversation unit that assists the user in a conversational manner. A system characterized by: (Appendix 2) The advice unit: Providing specific dietary or exercise advice to users 2. The system of claim 1, (Appendix 3) The execution unit is Adjusting advice based on changes in a user's weight or body composition 2. The system of claim 1, (Appendix 4) The analysis unit is Analyze past data to identify optimal diet or exercise for the user 2. The system of claim 1, (Appendix 5) The conversation unit includes: Providing advice to users' questions 2. The system of claim 1, (Appendix 6) The reception unit is The system estimates the user's emotions and adjusts the timing of diet deadline input according to the estimated user emotions. 2. The system of claim 1, (Appendix 7) The reception unit is Analyze the user's past diet history and suggest ways to set deadlines 2. The system of claim 1, (Appendix 8) The reception unit is When entering a diet deadline, filter based on the user's current health condition and lifestyle habits 2. The system of claim 1, (Appendix 9) The reception unit is The user's emotions are estimated, and the priority of deadlines to be entered is determined according to the estimated user's emotions. 2. The system of claim 1, (Appendix 10) The reception unit is When entering a diet deadline, the system takes into account the user's geographic location information and prioritizes the most relevant deadlines. 2. The system of claim 1, (Appendix 11) The reception unit is When a diet deadline is entered, the system analyzes the user's social media activity and suggests relevant deadlines. 2. The system of claim 1, (Appendix 12) The advice unit: Estimate the user's emotions and adjust the way advice is presented according to the estimated user emotions 2. The system of claim 1, (Appendix 13) The advice unit: When providing advice, the level of detail of the advice is changed based on the user's past successes with dieting 2. The system of claim 1, (Appendix 14) The advice unit: When providing advice, different advice algorithms are used depending on the user's current health condition. 2. The system of claim 1, (Appendix 15) The advice unit: The system estimates the user's emotions and changes the length of advice depending on the estimated user emotions. 2. The system of claim 1, (Appendix 16) The advice unit: When providing advice, set the priority of advice based on the user's daily rhythm 2. The system of claim 1, (Appendix 17) The advice unit: When providing advice, change the order of advice based on the user's meal history 2. The system of claim 1, (Appendix 18) The execution unit is Estimate the user's emotions and change the timing of advice delivery according to the estimated user emotions 2. The system of claim 1, (Appendix 19) The execution unit is When providing advice, the method of providing advice is selected by referring to the user's past weight fluctuation data. 2. The system of claim 1, (Appendix 20) The execution unit is When advice is executed, the execution content is changed based on the user's current physical condition. 2. The system of claim 1, (Appendix 21) The execution unit is Estimate the user's emotions and set the priority of advice execution according to the estimated user emotions 2. The system of claim 1, (Appendix 22) The execution unit is When executing advice, the execution method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 23) The execution unit is When advice is executed, the system analyzes the user's social media activity and suggests what to do. 2. The system of claim 1, (Appendix 24) The analysis unit is Estimate the user's emotions and select analysis data based on the estimated user emotions. 2. The system of claim 1, (Appendix 25) The analysis unit is During analysis, historical data is referenced to adjust the analysis algorithm 2. The system of claim 1, (Appendix 26) The analysis unit is During analysis, change the analysis method based on the user's current health condition 2. The system of claim 1, (Appendix 27) The analysis unit is Estimate the user's emotions and change the frequency of analysis according to the estimated user emotions. 2. The system of claim 1, (Appendix 28) The analysis unit is During analysis, the analysis data is weighted based on the user's lifestyle. 2. The system of claim 1, (Appendix 29) The analysis unit is When analyzing, the accuracy of the analysis is improved by referring to the user's meal history. 2. The system of claim 1, (Appendix 30) The conversation unit includes: Estimate the user's emotions and adjust the content of the conversation according to the estimated user emotions 2. The system of claim 1, (Appendix 31) The conversation unit includes: During a conversation, provide answers by referencing the user's past questions 2. The system of claim 1, (Appendix 32) The conversation unit includes: During a conversation, change the conversation content based on the user's current health status 2. The system of claim 1, (Appendix 33) The conversation unit includes: Estimate the user's emotions and prioritize conversations according to the estimated user emotions 2. The system of claim 1, (Appendix 34) The conversation unit includes: During conversation, provide conversation content taking into account the user's geographic location 2. The system of claim 1, (Appendix 35) The conversation unit includes: During a conversation, the system analyzes the user's social media activity to present the conversation content 2. The system of claim 1, [Explanation of symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit for allowing a user to input a deadline for dieting; an advice unit that provides advice every day based on the information input by the reception unit; An executive section that gives advice every time a user records their weight or body composition using a scale; An analysis unit that analyzes past data and identifies optimal diet or exercise for a user; A conversation unit that assists the user in a conversational manner. A system characterized by:

2. The advice unit: Providing specific dietary or exercise advice to users 2. The system of claim 1 .

3. The execution unit is Adjusting advice based on changes in a user's weight or body composition 2. The system of claim 1 .

4. The conversation unit includes: Providing advice to users' questions 2. The system of claim 1 .

5. The reception unit is The system estimates the user's emotions and adjusts the timing of diet deadline input according to the estimated user emotions.

2. The system of claim 1 .

6. The reception unit is Analyze the user's past diet history and suggest ways to set deadlines 2. The system of claim 1 .

7. The reception unit is When entering a diet deadline, filter based on the user's current health condition and lifestyle habits 2. The system of claim 1 .

Images