Advice provision system, advice provision program, and advice provision method

Abstract

The present invention relates to an advice provision system, an advice provision program, and an advice provision method that provide advice for efficient body shaping tailored to the user's desired body shape. [Solution] An advice provision system according to one embodiment of the present invention is an advice provision system that provides advice for shaping up to a target user, comprising: an ideal body type identification unit that identifies which of a predetermined number of ideal body types the target user aims for based on information input by the target user; and an advice generation unit that generates advice regarding at least one of diet and exercise for shaping up the target user's body to the ideal body type.

Description

Technical Field

[0001] The present invention relates to an advice providing system, an advice providing program, and an advice providing method for providing advice for shaping up.

Background Art

[0002] Techniques have been developed to evaluate a user's diet and activity content and generate advice for shaping up according to the evaluation results. For example, Patent Document 1 discloses a lifestyle improvement proposal device that generates a message for proposing lifestyle improvement based on lifestyle information such as a user's weight gain rate, number of steps, and dietary intake, and environmental information such as weather and temperature.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the invention described in Patent Document 1 above, when lifestyle information and environmental information satisfy predetermined conditions, a predetermined message corresponding to those conditions is presented to the user. Here, when shaping up, the user may have in mind a target body type such as a "muscular body type" or a "waisted body type". In such a case, even if uniform advice is provided for shaping up, it may be inefficient or have a reverse effect for some users.

[0005] The present invention relates to an advice providing system, an advice providing program, and an advice providing method for providing advice for efficient shaping up according to a user's target body type.

Means for Solving the Problems

[0006] An advice provision system according to one embodiment of the present invention is an advice provision system that provides advice to target users for weight loss, An ideal body type identification unit identifies which of several predetermined ideal body types the target body type of the user is aiming for, based on the information entered by the user. The system includes an advice generation unit that generates advice regarding at least one of diet and exercise to shape up the body shape of the target user to the ideal body shape.

[0007] An advice provision program according to one embodiment of the present invention is an advice provision program that provides advice to a target user for weight loss, and the information processing device comprises: Based on the information entered by the user to whom the service is provided, the step of identifying which of the predetermined multiple ideal body types the user desires is: The process involves generating advice regarding at least one of diet and exercise to shape up the body shape of the target user to the ideal body shape.

[0008] An advice provision method according to one embodiment of the present invention is an advice provision method that provides advice to a target user for weight loss, wherein the advice provision device is Based on the information entered by the user to whom the service is provided, the system identifies which of the predefined ideal body types the user desires. The system generates advice regarding at least one of diet and exercise to help the target user shape up to the ideal body shape. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide advice for efficient body shaping tailored to the user's desired body shape. [Brief explanation of the drawing]

[0010] [Figure 1] It is a block diagram showing the configuration of an advice providing system according to an embodiment of the present invention. [Figure 2] It is an example of a screen for presenting question items presented to a user from an advice providing device included in the advice providing system. [Figure 3] It is an example of a screen for presenting a dietary habit classification result presented to a user from the advice providing device. [Figure 4] It is a graph and a schematic diagram showing the "appearance rate" for each body part regarding "a body type like a model / idol". [Figure 5] It is an example of answers by a plurality of users aiming for "a body type like a model / idol". [Figure 6] It is a graph and a schematic diagram showing the "appearance rate" for each body part regarding "a body type that can exercise with children". [Figure 7] It is an example of answers by a plurality of users aiming for "a body type that can exercise with children". [Figure 8] It is a graph and a schematic diagram showing the "appearance rate" for each body part regarding "a muscular body type". [Figure 9] It is an example of answers by a plurality of users aiming for "a muscular body type". [Figure 10] It is a graph and a schematic diagram showing the "appearance rate" for each body part regarding "a body type with a constriction". [Figure 11] It is an example of answers by a plurality of users aiming for "a body type with a constriction". [Figure 12] It is a graph and a schematic diagram showing the "appearance rate" for each body part regarding "a toned body type". [Figure 13] It is an example of answers by a plurality of users aiming for "a toned body type". [Figure 14] It is a graph and a schematic diagram showing the "appearance rate" for each body part regarding "a body type that passes a health check". [Figure 15]Examples of responses from multiple users aiming for a "body type that doesn't show up in health checkups". [Figure 16] This is a flowchart showing the operation of the above advice providing device.

Embodiments for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the configurations, numerical values, processing flows, functional elements, etc. described in the following embodiments are merely examples, and modifications and changes thereof are free, and are not intended to limit the technical scope of the present invention to the following description. In this specification, a "system" shall include one or more information processing devices. For example, a single information processing device can also constitute a system, and when a plurality of information processing devices cooperate to perform functions such as a web server, these information processing devices can also constitute a system. Further, as described in the following embodiments, a "system" may include an information processing device that functions as a web server and one or more terminal devices.

[0012] An advice providing system according to an embodiment of the present invention will be described. Since the advice providing system according to this embodiment also functions as a dietary habit classification system, the following advice providing system can also be read as a dietary habit classification system.

[0013] [Configuration of Advice Providing System] The configuration of the advice providing system according to this embodiment will be described. As shown in FIG. 1, the advice providing system 100 according to this embodiment includes a dietary habit classification generation device 10 and an advice providing device 20.

[0014] The advice providing system 100 is a system that provides advice to users for body fat reduction or prevention of lifestyle-related diseases. "Body fat reduction" includes visceral fat reduction, abdominal circumference reduction, weight reduction, body fat percentage reduction, and resolution of metabolic syndrome. Further, "prevention of lifestyle-related diseases" includes improvement of hypertension, improvement of hyperglycemia, improvement of lipid abnormalities, and elimination of obesity.

[0015] The advice provision system 100 generates advice using biometric indicators. These biometric indicators represent the body's state and include waist circumference, VFA (Visceral Fat Area), FBS (Fasting blood sugar), TG (Triglyceride), HDL-C (High Density Lipoprotein Cholesterol), SBP (Systolic Blood Pressure), and DBP (Diastolic Blood Pressure).

[0016] The advice provision system 100 utilizes specific biometric indicators depending on the symptoms for which advice is being provided. Hereinafter, the biometric indicators used by the advice provision system 100 will be referred to as "specific biometric indicators." Table 1 below shows examples of symptoms and specific biometric indicators. Note that the symptoms and specific biometric indicators are not limited to those shown here. For example, the specific biometric indicator for visceral fat accumulation may be waist circumference or body weight.

[0017] [Table 1]

[0018] The dietary habit classification generator 10 is an information processing device that generates dietary habit classifications. The dietary habit classification generator 10 analyzes users whose specific biological indicators are equal to or greater than the standard values ​​shown in Table 1 and generates dietary habit classifications. Hereinafter, these users will be referred to as "analyzed users." The number of analyzed users is not particularly limited, but 100 or more is preferable.

[0019] As shown in Figure 1, the eating habit classification generation device 10 comprises a data acquisition unit 11, an eating habit classification generation unit 12, and a ranking determination unit 13. The data acquisition unit 11 acquires "eating habit information," which is information about each target user's eating habits (including dietary habits, eating behavior, lifestyle behavior, exercise habits, and personality), and data of specific biometric indicators for multiple target users.

[0020] The dietary habit information consists of responses to 35 questions regarding dietary habits, as listed below. However, it is not limited to these items. Q01 Even if I'm not hungry, I can't help but eat if something smells delicious. Q02 If someone around me is eating something, I'll eat it too. Q03 When I'm feeling depressed, I tend to overeat. Q04 I consciously limit my food intake to avoid gaining weight. Q05 I feel like I'm hungry all day long. Q06 I feel guilty about overeating, so I'm reducing the amount I eat. Q07 I try to buy low-calorie foods. Q08 I think I eat faster than other people. Q09 Do you actively eat green and yellow vegetables? Q10 I like hamburgers, donuts, and potato chips. Q11 Do you actively choose foods that are high in dietary fiber? Q12 I prefer fish to meat. Q13 I often eat a late-night snack after dinner. Q14 I'm trying to reduce my intake of animal fats and increase my intake of plant-based fats and fish fats. Q15 I think I have a body type that gains weight more easily than other people. Q16 I think I won't have any energy if I don't eat. Q17 Meal times are all over the place. Q18 I have a sweet tooth. Q19 Eating a late-night snack Q20 I can't help but reach for fruit and sweets when they're out there. Q21 When I receive food as a gift, I eat it because I don't want to waste it. Q22 I can't help but buy more groceries than I actually need. Q23 I often have late dinners because of work. Q24 If there is an elevator or escalator, use it. Q25 I finish dinner more than two hours before going to bed. Q26 I don't like walking or cycling. Q27 I don't exercise much. Q28 I hardly chew at all Q29 I think it's more about not getting enough exercise than overeating. Q30 I'm a night owl and not a morning person. Q31 I'm lazy. Q32 Insightful Q33 Cooperative Q34 I am proactive. Q35 I get nervous easily

[0021] The user being analyzed selects one of the following options for each question: "Does not apply = 1", "Does not apply very well = 2", "Neither agree nor disagree = 3", "Somewhat agree = 4", or "Applies = 5", and answers accordingly to generate dietary habit information. Note that the above questions are just examples, and other questions may be used. Also, the number of questions is not limited to 35. The data acquisition unit 11 supplies the acquired dietary habit information and biometric indicator data to the dietary habit classification generation unit 12.

[0022] The dietary habit classification generation unit 12 performs factor analysis on the data supplied from the data acquisition unit 11 and generates multiple dietary habit classifications based on factors for biometric indicators of dietary habit information. The dietary habit classifications categorize the dietary habits of the target user and include classifications such as "low health consciousness," "snacking," "late-night eating," "eating quickly," "lack of exercise," "late-night meals," "low basal metabolism," and "other (does not fall into any of the above categories)."

[0023] "Low health consciousness" refers to a category of eating habits characterized by indifference to diet and exercise, and eating without considering health. For example, it has the following characteristics: [Diet] I don't try to buy low-calorie foods. • I don't actively eat green and yellow vegetables. • I don't actively choose foods that are high in dietary fiber. • I am trying to reduce my intake of animal fats and avoid plant-based fats and fish fats. I like hamburgers, donuts, and potato chips. I don't like fish more than meat. • I don't consciously restrict my food intake to avoid gaining weight. I feel guilty about overeating, so I haven't reduced the amount I eat. • Meal times are irregular. • Eat a late-night snack [motion] • Use the elevator or escalator if available. • Few steps I don't exercise much. I think it's more about not getting enough exercise than overeating. [Personality] • Lazy • Lack of insight Not proactive

[0024] "Snacking" is a category of eating habits characterized by a strong craving for sweets and a tendency to eat snacks without thinking, and it has the following characteristics, for example: [Diet] I like hamburgers, donuts, and potato chips. • I have a sweet tooth. I can't help but reach for fruit and sweets when they're out there. If someone around me is eating something, I'll eat it too. Even if I'm not hungry, I can't help but eat if something smells delicious. I tend to overeat when I'm feeling down. I eat food when I receive it because I don't want to waste it. [Meal contents] • High intake of lipids, plant-based lipids, saturated fatty acids, monounsaturated fatty acids, and sucrose. [motion] • Low muscle mass [Personality] I think I have a body type that gains weight more easily than other people. I feel like I won't have any energy if I don't eat. I can't rest easy unless I buy more groceries than I actually need. • Short • Low basal metabolic rate

[0025] "Late-night snacking" is a classification of eating habits where people are night owls and eat a late-night snack after dinner, and it has the following characteristics, for example. [Diet] • I often eat a late-night snack after dinner. • Eat a late-night snack • I often have late dinners because of work. • Meal times are all over the place. If someone around me is eating something, I'll eat it too. Even if I'm not hungry, I can't help but eat if something smells delicious. • I don't consciously restrict my food intake to avoid gaining weight. I tend to overeat when I'm feeling down. I feel like I'm hungry all day long. • I have a sweet tooth. I can't help but reach for fruit and sweets when they're out there. I eat food when I receive it because I don't want to waste it. [Meal contents] • High intake of energy, carbohydrates, and sucrose. • Low intake of animal protein, vitamin D, niacin, vitamin B6, vitamin B12, and alcohol. [motion] I don't exercise much. [Personality] I think I have a body type that gains weight more easily than other people. I can't rest easy unless I buy more groceries than I actually need. I'm a night owl and not a morning person. Lazy • Easily gets nervous • Young ·Emotionally unstable

[0026] "Eating quickly" is a category of eating habits characterized by a large physique and a tendency to eat food without chewing it properly. For example, it has the following characteristics: [Diet] I think I eat faster than other people. • I hardly ever chew. I eat food when I receive it because I don't want to waste it. • I haven't finished dinner more than two hours before going to bed. [Personality] • Overweight • High muscle mass • High basal metabolic rate

[0027] "Lack of exercise" is a classification of eating habits characterized by a dislike of exercise and insufficient consumption of meat and vegetables, and has the following characteristics, for example: [Diet] • I don't actively eat green and yellow vegetables. • I don't actively choose foods that are high in dietary fiber. I don't like fish more than meat. • I am trying to reduce my intake of animal fats and avoid plant-based fats and fish fats. I feel guilty about overeating, so I haven't reduced the amount I eat. [Meal contents] • Low intake of beta-carotene [motion] I don't like walking or cycling. • Few steps I don't exercise much. I think it's more about not getting enough exercise than overeating. [Personality] Lazy • High body fat percentage

[0028] "Late-night eating" is a classification of eating habits that involve having dinner late at night while drinking alcohol, and has the following characteristics, for example: [Diet] • I often have late dinners because of work. • I haven't finished dinner more than two hours before going to bed. • Meal times are all over the place. • I have a sweet tooth. [Meal contents] • Low intake of lipids, potassium, calcium, iron, zinc, copper, vitamin B1, vitamin C, saturated fatty acids, soluble dietary fiber, insoluble dietary fiber, total dietary fiber, and sucrose. • High alcohol consumption

[0029] "Decreased basal metabolism" refers to a type of eating habit where you gain weight even if you eat the same amount as before, and it has the following characteristics, for example. [Meal contents, portion sizes, meal times, exercise] No problem [Personality] • Older

[0030] The dietary habit classification generation unit 12 performs factor analysis on the dietary habit information and biometric indicator data of multiple target users. While the method of factor analysis is not limited, statistically analyzed data related to dietary habit information and biometric indicators are preferred. For example, various models can be employed, such as multiple regression analysis using statistical data, logistic regression models, multilayer perceptrons, neural networks such as CNNs (Convolutional Neural Networks) and RNNs (Recurrent Neural Networks), support vector machines using arbitrary kernel functions such as Gaussian kernels, random forests modeled as regression trees, models utilizing hidden Markov models, statistical models, probabilistic models, factor analysis, and correspondence tables. Furthermore, models that combine various models to perform a comprehensive judgment can also be employed. Among these, factor analysis using the principal component method with varimax rotation is particularly preferred.

[0031] Tables 2 and 3 below show the "factor loadings," "eigenvalues," "contribution rates," and "cumulative contribution rates" for each questionnaire item, calculated using the "principal component method with varimax rotation" for VFA, a bioindicator of visceral fat accumulation.

[0032] [Table 2]

[0033] [Table 3]

[0034] As shown in Tables 2 and 3, the dietary habit classification generation unit 12 sorts each question item into factors according to their factor loadings. For example, Q04, Q07, Q06, Q09, and Q11 are sorted into "Factor 1" because their factor loadings (indicated by black squares) for "Factor 1" exceed the standard value. The standard value is, for example, 0.4. Similarly, Q02, Q01, and Q20 are sorted into "Factor 2," Q19 and Q13 into "Factor 3," and Q08 and Q28 into "Factor 4." In addition, Q27 and Q29 are sorted into "Factor 5," and Q25 and Q23 into "Factor 6." The dietary habit classification generation unit 12 then generates dietary habit classifications such as "low health orientation" for each factor, according to the content of the question items sorted into each factor.

[0035] Similarly, for biomarkers other than VFA, the dietary habit classification generation unit 12 selects each question item for each factor according to its factor loading. Table 4 below shows the dietary habit classification for each factor for each symptom. As shown in Table 4, the dietary habit classification and the corresponding question items differ for each symptom. The dietary habit classification generation unit 12 supplies the generated dietary habit classification and "contribution rate" to the ranking determination unit 13.

[0036] [Table 4]

[0037] The ranking unit 13 determines the priority order among the dietary habit classifications in order of their contribution rate. In the examples in Tables 2 and 3, the contribution rate of "low health consciousness" (0.12) is the highest, followed by the contribution rate of "snacking" (0.11). The contribution rates then gradually decrease in the order of "eating late at night," "eating quickly," "lack of exercise," and "eating late at night." Therefore, the ranking unit 13 assigns the highest priority to "low health consciousness," followed by "snacking," "eating late at night," "eating quickly," "lack of exercise," and "eating late at night."

[0038] Table 4 shows the priority order of dietary habit classifications based on their contribution rates for each symptom. As shown in Table 4, the ranking unit 13 assigns the highest priority to "late-night eating" for "dyslipidemia," followed by "overeating," "lack of exercise," and "poor health consciousness." Similarly, for "hypertension," the highest priority is given to "late-night eating," followed by "snacking," "lack of exercise," "poor health consciousness," and "eating too quickly." For "hyperglycemia," the highest priority is given to "snacking," followed by "late-night eating," "lack of exercise," "irregular meal times," and "restricted food intake." The ranking unit 13 supplies the dietary habit classifications and priorities to the advice provision device 20. Note that the dietary habit classification names, contribution rates, and priorities will vary depending on the data used. The results disclosed in this specification are examples only. Priorities may be changed according to the user's desired improvement objectives.

[0039] The advice-providing device 20 is an information processing device that provides users with advice for reducing body fat or preventing lifestyle-related diseases. Hereinafter, users who are targeted to receive advice will be referred to as "target users." As shown in Figure 1, the advice-providing device 20 comprises a target user determination unit 21, a dietary habit information acquisition unit 22, a dietary habit classification unit 23, a record information acquisition unit 24, an evaluation unit 25, an ideal body type identification unit 26, an advice generation unit 27, and a presentation information generation unit 28.

[0040] The target user determination unit 21 determines which users are eligible for the service. The target user determination unit 21 can determine which users are eligible for the service if the above-mentioned specific biometric indicator exceeds a predetermined value. For example, in the case of VFA, the predetermined value is 10 cm for males. 2 Preferably 50 cm 2 More preferably 80 cm 2 More preferably 100 cm 2 For women, 10cm 2 Preferably 30 cm 2 More preferably 50cm 2 More preferably 80 cm 2 That's all. Also, for example, in the case of waist circumference, it is 85cm or greater for men and 90cm or greater for women.

[0041] The target user determination unit 21 can determine that a user is a target user if their specific biometric indicators, as entered by the user, exceed a predetermined value. Furthermore, the target user determination unit 21 can estimate the user's specific biometric indicators from the information entered by the user, and determine that a user is a target user if this estimated value exceeds the predetermined value.

[0042] For example, the target user determination unit 21 estimates the amount of visceral fat accumulation, such as VFA, from the physical information entered by the user, such as gender, age, height, weight, waist circumference, and image data that can estimate this information, and can determine that users whose estimated value exceeds a predetermined value are target users. The target user determination unit 21 may also determine target users based on information other than specific biometric indicators, or it may determine all users as target users.

[0043] The dietary habit information acquisition unit 22 acquires dietary habit information of the target user. The dietary habit information consists of answers to the 35 questions about dietary habits mentioned above. The dietary habit information acquisition unit 22 can generate a screen displaying the questions as shown in Figure 2, making it easier to answer by displaying one question per screen. The dietary habit information acquisition unit 22 may also acquire further personal data that affects the dietary habits of the target user, such as gender, age, place of residence, place of origin, occupation, and income.

[0044] The eating habit classification unit 23 classifies the eating habits of the target user based on the eating habit information into one of the eating habit classifications generated by the eating habit classification generation unit 12. As shown in Figure 1, the eating habit classification unit 23 includes an eating habit classification determination unit 31 and an eating habit classification determination unit 32.

[0045] The eating habit classification determination unit 31 determines whether each user's eating habits fall under each eating habit classification based on the eating habit information of each user. The eating habit classification determination unit 31 can determine whether each user's eating habits fall under each eating habit classification based on the answer scores of the question items selected for each eating habit classification. The rotation scores are the scores for "does not apply = 1", "does not apply very well = 2", "neither agree nor disagree = 3", "somewhat applies = 4", and "applies = 5" as described above.

[0046] For example, regarding visceral fat accumulation, the eating habit classification unit 31 determines that a user's eating habits fall under "low health orientation" if the answer scores for Q04, Q07, Q06, Q09, and Q11, which are classified as "low health orientation" (see Table 4), are all "does not apply = 1" or "somewhat does not apply = 2". Similarly, the eating habit classification unit 31 determines that a user's eating habits fall under "snacking" if the answer scores for Q02, Q01, and Q20, which are classified as "snacking," are all "applies = 5" or "somewhat applies = 4". In the same manner, the eating habit classification unit 31 determines whether a user's eating habits fall under "late-night eating," "eating too quickly," or "lack of exercise" based on the answer scores for each of the classified eating habits. Furthermore, the eating habit classification unit 31 determines that the eating habit of the target user falls under "eating late at night" if the answer score for question Q25, which is selected as "not applicable = 1" or "somewhat not applicable = 2", and the answer score for Q23 is "applicable = 5" or "somewhat applicable = 4".

[0047] Here, the eating habit classification determination unit 31 determines that the eating habits of the target user fall under multiple eating habit classifications if the response score meets the conditions in multiple eating habit classifications. Conversely, if the response score does not meet any of the conditions in any of the eating habit classifications, the eating habit determination unit 31 determines that the eating habits of the target user do not fall under any of the eating habit classifications.

[0048] Alternatively, the Eating Habit Classification Unit 31 determines that a user's eating habits fall under "low health orientation" if the sum of the answer scores for questions Q04, Q07, Q06, Q09, and Q11 (see Table 4), which are classified as "low health orientation," is above a threshold. Similarly, the Eating Habit Classification Unit 31 determines that a user's eating habits fall under "snacking" if the sum of the answer scores for questions Q02, Q01, and Q20, which are classified as "snacking," is above a threshold. In the same manner, the Eating Habit Classification Unit 31 determines whether a user's eating habits fall under each of the following categories based on the answer scores for the questions classified as "late-night eating," "eating too quickly," "lack of exercise," and "late-night meals."

[0049] In this case, the eating habit classification determination unit 31 determines that the eating habits of the target user fall under multiple eating habit classifications if the response score is above the threshold for multiple eating habit classifications. Conversely, if the response score is below the threshold for any of the eating habit classifications, the eating habit classification determination unit 31 determines that the eating habits of the target user do not fall under any of the eating habit classifications.

[0050] The eating habit classification determination unit 32 determines the eating habit classification of the target user based on the determination result from the eating habit classification judgment unit 31. If the eating habit classification judgment unit 31 determines that the target user's eating habits fall under one eating habit classification, the eating habit classification determination unit 32 decides to classify the target user's eating habits under that classification.

[0051] Furthermore, if the Eating Habit Classification Determination Unit 31 determines that a target user's eating habits fall under multiple eating habit classifications, the Eating Habit Classification Determination Unit 32 will classify the target user's eating habits into the eating habit classification with the highest priority (see Table 4) determined by the Ranking Determination Unit 13. For example, if the Eating Habit Classification Determination Unit 31 determines that a particular target user's eating habits regarding visceral fat accumulation fall under both "snacking" and "lack of exercise," the Eating Habit Classification Determination Unit 32 will classify the target user's eating habits into the "snacking" category, which has a higher priority.

[0052] Furthermore, if the Eating Habit Classification Determination Unit 31 determines that the target user's eating habits do not fall under any of the specified eating habit classifications, the Eating Habit Classification Determination Unit 32 can classify the target user's eating habits in a different category than the one generated for each factor. For example, if the Eating Habit Classification Determination Unit 32 determines that the target user's eating habits do not fall under any of the specified eating habit classifications regarding visceral fat accumulation, it will classify the target user's eating habits as "decreased basal metabolism." This is because, even though there are no problems with the target user's eating habits, the amount of visceral fat accumulation exceeds a specified value, and it can be determined that this is due to a decrease in basal metabolism.

[0053] The eating habit classification unit 23 classifies the eating habits of the target user into one of the following categories as described above. The eating habit classification unit 23 can generate a display screen of the eating habit classification as shown in Figure 3, and visually notify the target user of the classification result. The radar chart shows the response score for each eating habit classification. The eating habit classification unit 23 may also accept a selection of an eating habit classification from the target user and use the classification selected by the target user as the user's eating habit classification. This is effective when the target user is aware of their previously notified eating habit classification. The eating habit classification unit 23 supplies the target user's eating habit classification to the record information acquisition unit 24.

[0054] The record information acquisition unit 24 acquires record information, which is information about the meals and activities recorded by the target user. For each target user, the record information acquisition unit 24 generates a set of record items that include record items corresponding to the target user's dietary habit classification. Tables 5 and 6 below are examples of the set of record items generated by the record information acquisition unit.

[0055] [Table 5]

[0056] [Table 6]

[0057] Additionally, the record items may optionally include the intake of functional components such as chlorogenic acid and ALA-DAG (alpha-linolenic acid diacylglycerol), which contribute to suppressing body fat accumulation and preventing lifestyle-related diseases.

[0058] As shown in Tables 5 and 6, the group of record items generated by the record information acquisition unit includes "items categorized by dietary habit classification." These "items categorized by dietary habit classification" are record items categorized by dietary habit classification as determined by the dietary habit classification unit 23. Tables 5 and 6 show examples of record items for "low health orientation." Table 7 below shows record items for other dietary habit classifications. As these tables show, the record items for each dietary habit classification differ for each classification. Furthermore, calorie expenditure from sources other than walking may also be included in the record items for each dietary habit classification.

[0059] [Table 7]

[0060] Furthermore, the record item group may include "Nutrient Intake," as shown in Table 5. "Nutrient Intake" is a record item for the intake of one or more nutrients selected from protein, omega-3 fatty acids, and dietary fiber. In addition, the record item group may include record items such as "Lifestyle Points," "Daily Calorie Intake," "Steps Taken," and "Body Measurements," as shown in Table 6. Of the record item group, all items except "Dietary Habit Classification Items" are common to each target user. Hereinafter, "Dietary Habit Classification Items," "Protein," "Dietary Fiber," "Omega-3 Fatty Acids," and "Lifestyle Points" will each be referred to as "Major Items."

[0061] The record information acquisition unit 24 presents the generated set of record items to the target user. The record information acquisition unit 24 acquires the record information when the target user inputs the record content. The target user inputs the record content on a daily or weekly basis. The record information acquisition unit 24 supplies the acquired record information to the evaluation unit 25.

[0062] The evaluation unit 25 evaluates the causes of body fat accumulation or lifestyle-related disease for each target user based on the recorded information. Tables 8 and 9 below show the evaluation method performed by the evaluation unit 25.

[0063] [Table 8]

[0064] [Table 9]

[0065] The evaluation unit 25 aggregates record information for each target user over a certain evaluation period, for example, one week, and can score each record item by taking the average number of positive responses for that record item. For example, for the record item "I ate meals while considering nutritional balance" under "Low health consciousness," the evaluation unit 25 sets the score for that record item to the average number of "○"s over one week. Similarly, for other record items such as "I did not eat until I was full at any meal," the evaluation unit 25 sets the score for those record items to the average number of "○"s over one week.

[0066] The evaluation unit 25 can extract the record items with the highest scores (hereinafter referred to as "the record items") and the record items with the lowest scores (hereinafter referred to as "the lower record items") from among the record items. The highest record items are, for example, the record items with the highest scores (1st to 3rd place), and the lower record items are, for example, the record items with the lowest scores (1st to 3rd place). The evaluation unit 25 can evaluate the lower record items as items that require improvement in order to eliminate the causes of body fat accumulation or the causes of lifestyle-related diseases.

[0067] Furthermore, the evaluation unit 25 can evaluate the intake of nutrients for each target user based on the recorded information. The evaluation unit 25 can estimate the intake ratio and intake status of each nutrient from the scores of each recorded item, "protein," "omega-3 fatty acids," and "dietary fiber." In addition, the evaluation unit 25 can also estimate the "protein / fat ratio," "omega-3 fatty acid / fat ratio," and "dietary fiber / carbohydrate or sugar ratio" from the scores of each recorded item, "protein," "omega-3 fatty acids," and "dietary fiber."

[0068] In addition, the evaluation unit 25 can also evaluate "eating habits" or "personal information" for each target user based on the recorded information. "Eating habits" refers to one or more of the target user's eating quality, quantity, timing, eating style, and activity level, while "personal information" refers to at least one or more of the following: weight and waist circumference. The priority order of evaluation by the evaluation unit 25 is not limited, but as an example, it is preferable to give the highest priority to "quantity of food," followed by "activity level," "meal timing," "quality of food," "eating style," and "weight." The evaluation unit 25 supplies the evaluation results to the advice generation unit 27.

[0069] The Ideal Body Type Identification Unit 26 identifies which of several predefined ideal body types the target body type of the user is aiming for. Table 10 below shows examples of predefined ideal body types. Based on the information entered by the user, the Ideal Body Type Identification Unit 26 identifies which ideal body type the user is aiming for. Specifically, the Ideal Body Type Identification Unit 26 presents the user with the types of ideal body types shown in Table 10, and by the user's selection of an ideal body type, it can identify which ideal body type the user is aiming for. Hereinafter, the ideal body type identified by the Ideal Body Type Identification Unit 26 as the target body type of the user will be referred to as the "Target Ideal Body Type".

[0070] [Table 10]

[0071] Furthermore, the ideal body shape identification unit 26 may identify a target ideal body shape based on the subjective body shape information of the target user. Subjective body shape information that the user is concerned about is information about their body shape based on their subjective opinion, such as "I can't zip up the back of my shirt," "My stomach has gotten bigger than before," "I can no longer wear a size M shirt," "My legs are thicker than models'," "My belly fat gets in the way so I can't play soccer with my kids," "I don't have defined abs," "My upper arms are too thick so I can't do sharp dance moves," or "I had a specific health checkup and became eligible for specific health guidance." Alternatively, objective body shape information pointed out by others is information about the user's body shape based on objective observations from others other than the target user, such as "My daughter told me that I don't want to go out with her because I don't have a defined waist and it's not attractive."

[0072] The Ideal Body Type Identification Unit 26 extracts body parts that the target user is concerned about from such subjective body type information, or body parts that the target user is concerned about after being pointed out by others other than the target user from objective body type information, and can identify a target ideal body type according to those body parts. Specifically, the Ideal Body Type Identification Unit 26 can set the target ideal body type as the ideal body type with the highest "occurrence rate" of the body parts that the target user is concerned about or that have been pointed out by others, as described later. The Ideal Body Type Identification Unit 26 supplies the target ideal body type to the Advice Generation Unit 27.

[0073] The advice generation unit 27 generates advice regarding at least one of diet and exercise to help the target user shape up to their ideal body shape. Specifically, the advice generation unit 27 can identify body parts that should be shaped up according to the ideal body shape and generate advice according to those body parts.

[0074] The following are examples of body parts that should be toned up. However, the body parts that should be toned up are not limited to those listed below; other body parts may also be targeted. • Waist area • Legs (feet) • Skeleton ·Lower body ·arm ·chest Waist Thighs Buttocks

[0075] Figure 4 is a graph and schematic diagram showing the "occurrence rate" of each body part in relation to the "model / idol-like physique." The occurrence rate is calculated by asking multiple users who aim for a "model / idol-like physique" about the difference between their own physique and that of a "model / idol-like physique," and then aggregating the presence or absence of words related to each body part in their responses. Figure 5 is an example of responses from multiple users who aim for a "model / idol-like physique," with the parts related to body parts underlined. Note that the "multiple users" mentioned above are the users included in the survey and are not limited to the users to whom the data was provided.

[0076] In Figure 4, "N=59" indicates that 59 users provided responses. The frequency of "stomach / waistline" in Figure 4 is 20.3%, indicating that 20.3% of the 59 users mentioned "stomach / waistline" in their responses. In addition to "stomach / waistline," "legs / feet," "skeleton," and "waist" also appear frequently in Figure 4.

[0077] Figure 6 is a graph and schematic diagram showing the "occurrence rate" of each body part for "a body type that allows you to exercise with your children." Figure 7 is an example of responses from multiple users who aim for "a body type that allows you to exercise with your children," with the parts related to body parts underlined (the same applies to underlines below).

[0078] Figure 8 shows a graph and schematic diagram illustrating the "prevalence rate" of each body part for a "muscular physique." Figure 9 shows examples of responses from multiple users who aim for a "muscular physique." Figure 10 shows a graph and schematic diagram illustrating the "prevalence rate" of each body part for a "curvy physique." Figure 11 shows examples of responses from multiple users who aim for a "curvy physique."

[0079] Figure 12 shows a graph and schematic diagram illustrating the "prevalence rate" of each body part for a "toned physique." Figure 13 shows examples of responses from multiple users who aim for a "toned physique." Figure 14 shows a graph and schematic diagram illustrating the "prevalence rate" of each body part for a "physique that does not cause problems in health checkups." Figure 15 shows examples of responses from multiple users who aim for a "physique that does not cause problems in health checkups."

[0080] As shown in the graphs above, the body parts that users perceive as having a difference between their ideal body type and their own body type differ depending on the ideal body type. The body parts that users perceive as having a difference between their ideal body type and their own body type are as follows. Note that "stomach / waist area" is common to all ideal body types and is therefore omitted from the description.

[0081] Model / idol-like physique: legs (feet) and bone structure • Muscular build: Lower body, legs (feet) Body type suitable for exercising with children: legs (feet), arms, chest • A curvy figure: waist and lower body • Toned physique: arms, legs (feet), thighs, buttocks, chest • Body type that won't cause problems on a health checkup: None in particular

[0082] Thus, since the body parts that each user perceives as having a difference between their ideal body type and their own body type differ depending on the ideal body type, the advice generation unit 27 identifies the body parts that should be shaped up according to the target ideal body type and generates advice according to these body parts, thereby enabling efficient advice to be generated for each target user to shape up to their target ideal body type.

[0083] Specifically, the advice generation unit 27 can determine the priority of body parts in order of their frequency of appearance. For example, if the target ideal body shape is "a body shape like a model or idol," the order of frequency of appearance (see Figure 4) would be "stomach area," "legs (feet)," "skeleton," "arms," ​​"lower abdomen," "thighs," "buttocks," "chest," and "lower body." Therefore, the advice generation unit 27 can prioritize the body parts in this order and generate advice suitable for shaping up the body parts with the highest priority.

[0084] The advice generation unit 27 can generate advice for shaping up specific body parts, such as high-priority body parts. Specifically, it can generate advice on exercises suitable for shaping up the identified body parts. For example, when shaping up the lower body, the advice might be, "Walk for 30 minutes every day."

[0085] Furthermore, the advice generation unit 27 can identify the current body shape of the target user (hereinafter referred to as "current body shape") and generate advice based on the difference between this current body shape and the target ideal body shape. The advice generation unit 27 can identify the current body shape by obtaining the size of body parts such as waist circumference, chest circumference, and circumference of each part of the legs and arms from the target user's input. In addition, the advice generation unit can also identify the current body shape by obtaining height, weight, body fat percentage, etc. from the target user's input and estimating the size of each body part based on these values.

[0086] Furthermore, the advice generation unit 27 can also identify the current body shape based on an image of the target user (hereinafter referred to as the "captured image"). Specifically, the advice generation unit 27 can identify the current body shape by extracting the contour of the target user through image processing of the captured image and calculating the size of each body part.

[0087] The advice generation unit 27 can reflect the difference between the current body shape and the target ideal body shape in the priority order for shaping up. Specifically, it can change the priority of body parts where the discrepancy between the current body shape and the target ideal body shape is large. For example, if the target ideal body shape is "a body shape like a model or idol," then, as mentioned above, the order of highest occurrence rate (see Figure 4) would be "stomach," "legs (feet)," "skeleton," "arms," ​​"lower abdomen," "thighs," "buttocks," "chest," and "lower body." On the other hand, if the discrepancy between the current body shape and the target ideal body shape is small for "stomach," "legs (feet)," and "skeleton," but large for "arms," ​​"thighs," and "buttocks," it is possible to increase the priority of the body parts with the largest discrepancies, for example, by changing the priority order to "arms," ​​"thighs," "buttocks," "stomach," "legs (feet)," "skeleton," "lower abdomen," "chest," and "lower body."

[0088] The advice generation unit 27 can also generate advice for weight loss based on the target ideal body shape and dietary habit classification results. The advice generation unit 27 can generate advice based on the evaluation results of the evaluation unit 25 for the causes of body fat accumulation or lifestyle-related disease, i.e., the scores for each recorded item.

[0089] Specifically, the advice generation unit 27 can generate advice that praises high-scoring record items and suggests improvements for lower-scoring record items. The advice generation unit 27 can also select record items from the lower-scoring record items that show potential for improvement and generate advice that suggests improvements for those record items. The advice generation unit 27 can select record items that show potential for improvement from the lower-scoring record items by excluding items with low scores in each record. Furthermore, the advice generation unit 27 can generate advice that encourages the eating habits of the target user in subsequent visits.

[0090] The method by which the advice generation unit 27 generates advice is not particularly limited, but in addition to using predefined phrases, the advice generation unit 27 can collect the obtained data, perform machine learning on it, and generate advice using the learning results. Furthermore, the advice generation unit 27 can generate advice based on nutritional guidance from experts such as registered dietitians. In addition, the advice generation unit 27 only needs to generate advice that is tailored to the target ideal body shape for each user.

[0091] Furthermore, when the advice generation unit 27 generates advice for shaping up according to the target ideal body shape and dietary habit classification, it can prioritize guidance based on factors that contribute to visceral fat reduction for each target user's dietary habit classification. Factors that contribute to visceral fat reduction can be identified by factor analysis. Table 11 below shows the factors that contribute to visceral fat reduction for each dietary habit classification. For example, if the dietary habit classification is "low health consciousness," then the advice can be prioritized in the following order: "I consciously reduced my food intake to avoid gaining weight," "I never ate until I was full at any meal," "I didn't eat processed meat products such as bacon, sausage, and salami," "Exercise intensity: 12-15 hours," and "I ate soy products such as tofu, natto, and soybeans."

[0092] [Table 11]

[0093] The presentation information generation unit 28 generates presentation information that includes advice supplied from the advice generation unit 27. The presentation information generation unit 28 can generate a presentation image that includes the generated presentation information and present the presentation information to the user. The presentation information may include the target ideal body shape of the target user. The presentation information generation unit 28 may also present the advice supplied from the advice generation unit 27 to the target user's instructor. Examples of instructors for the target user include registered dietitians, public health nurses, pharmacists, and other healthcare professionals. The presentation information generation unit 28 can tailor the advice presented to the instructor to the instructor's area of ​​expertise. Specifically, the presentation information generation unit 28 can generate presentation information that includes dietary advice and send it to a registered dietitian's terminal, and generate presentation information that includes exercise advice and send it to a healthcare professional's terminal, etc.

[0094] The advice provision system 100 has the configuration described above. The configurations of the dietary habit classification generation device 10 and the advice provision device 20 are functional configurations realized through the cooperation of hardware and software of an information processing device consisting of a CPU (Central Processing Unit) and RAM (Random Access Memory), etc. The software is a program that can be executed by the information processing device, and may also be a program recorded on a recording medium that can be read by the information processing device. Furthermore, the dietary habit classification generation device 10 and the advice provision device 20 may be separate information processing devices, or they may be a single information processing device.

[0095] [How the advice provision system works] The operation of the advice provision system 100 will now be described. As described above, the dietary habit classification generator 10 generates a dietary habit classification based on dietary habit information and biometric indicator data of multiple target users. The generation of the dietary habit classification only needs to be performed once when the advice provision system 100 is built, but it may be performed again after the system is built.

[0096] The advice-providing device 20 provides a shape-up program to the target user. As shown in Figure 16, the advice-providing device 20 operates both "before program execution" and "during program execution". Table 12 below shows the contents of "input", "judgment", and "output" before and during program execution.

[0097] [Table 12]

[0098] Before program implementation, as shown in Figure 16, the target user determination unit 21 determines the target users (St11). As shown in Table 12, the target user determination unit 21 can receive physical information input from the user and calculate specific biometric indicators. Furthermore, based on the specific biometric indicators, the target user determination unit 21 can determine whether or not each user is a target user for the program and output to each user whether or not they are a target user for the program.

[0099] Next, the dietary habit information acquisition unit 22 acquires the dietary habit information of the target user (St12), and the dietary habit classification unit 23 determines the dietary habit classification of the target user (St13). As shown in Table 12, the dietary habit information acquisition unit 22 receives input of dietary habit information from the target user, and the dietary habit classification unit 23 determines the dietary habit classification of the target user. Furthermore, the dietary habit classification unit 23 can output the dietary habit classification that applies to each target user (see Figure 3).

[0100] Next, the ideal body type identification unit 26 identifies the target ideal body type (the ideal body type that the target user aims for, among several ideal body types) (St14). The ideal body type identification unit 26 may identify the target ideal body type by the selection of an ideal body type by the target user, or it may identify the target ideal body type based on the target user's subjective body type information or objective body type information pointed out by others.

[0101] During program execution, the recording information acquisition unit 24 acquires recording information (see Table 5) (St15), and the evaluation unit 25 evaluates the recording information (St16). The recording information acquisition unit 24 accepts input of recording information from the target users as shown in Table 12. The evaluation unit 25 calculates the score for each recording item and each major item, and extracts the above recording items and sub-record items. The evaluation unit 25 may also evaluate nutrient intake.

[0102] Next, the advice generation unit 27 generates advice (St17) regarding at least one of diet and exercise to help the target user shape up to their target ideal body shape. At this time, the advice generation unit 27 may identify the target user's current body shape and generate advice according to the difference between the current body shape and the target ideal body shape.

[0103] Next, the presentation information generation unit 28 generates presentation information including advice (St18). The presentation information generation unit 28 generates presentation information including advice and outputs it to at least one of each target user and their instructor.

[0104] The advice-providing device 20 performs the "pre-program implementation" operation, and then performs the "program implementation" operation at each evaluation period. The evaluation period is, for example, one week. The program implementation period is, for example, one month, and the advice-providing device 20 performs the "program implementation" operation once or multiple times within the program implementation period.

[0105] The advice provision system 100 provides advice to each target user in this manner. The operation of the advice provision system 100 described above is just one example; the advice provision system 100 only needs to provide target users with advice on at least one of the following: diet and exercise, to help them shape up their body to their target ideal body shape. In addition to providing advice, the classification of target users' eating habits can be used for product recommendations, service provision and collaboration, future predictions (body shape, lifestyle-related diseases, etc.), and introductions to peers (community building), etc.

[0106] [Effects of the advice provision system] As described above, in the advice provision system 100, the ideal body type identification unit 26 identifies the target ideal body type of the user, and the advice generation unit 27 generates advice regarding at least one of diet and exercise to shape up the target ideal body type of the user. Since the body parts that each user perceives as having a difference between their ideal body type and their own body type differ depending on the ideal body type, the advice provision system 100 identifies the target ideal body type of the user and generates advice to shape up to that target ideal body type, making it possible to efficiently bring the user's body type closer to the target ideal body type. Furthermore, in the advice provision system 100, the advice generation unit 27 identifies the target user's current body type and generates advice according to the difference between the current body type and the target ideal body type, making it possible to bring the user's body type closer to the target ideal body type even more efficiently.

[0107] Furthermore, the system may be combined with the advice system 100 to propose the most suitable insurance products. In addition, the advice system 100 may be offered as part of services provided by health guidance institutions, etc., in combination with health consultations, health checkups, health education, health coaching, health programs for smoking and lack of exercise, etc. Furthermore, the advice system 100 may be offered as part of services provided by health checkup institutions, etc., in combination with health checkups, cancer screenings, lifestyle-related disease checkups, prenatal checkups, health checkups conducted by companies for employee health management, etc.

[0108] Although embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the invention. In addition, preferred examples of the advice provision program and advice provision method are the same as those described above for the advice provision system.

[0109] Furthermore, the present invention may be applied to a system composed of multiple devices or to a single device. Moreover, the present invention is also applicable when an information processing program that realizes the functions of the embodiment is supplied to a system or device and executed by a built-in processor. Therefore, the technical scope of the present invention includes programs installed on a computer to realize the functions of the present invention on a computer, the medium on which the program is stored, the WWW (World Wide Web) server that allows the program to be downloaded, and the processor that executes the program. In particular, at least a non-transitory computer-readable medium containing a program that causes a computer to execute the processing steps included in the above-described embodiment is included in the technical scope of the present invention. [Explanation of Symbols]

[0110] 20…Advice-providing device 23…Eating habits classification department 24... Record Information Acquisition Unit 25…Evaluation Department 26…Ideal body type identification part 27... Advice generation unit 28…Presentation information generation unit 100... Advice provision system

Claims

1. An advice provision system that provides advice to target users for weight loss, An ideal body type identification unit identifies which of several predetermined ideal body types the target body type of the user is aiming for, based on the information entered by the user. An advice generation unit that generates advice regarding at least one of diet and exercise to shape up the body shape of the target user to the ideal body shape, An advice provision system equipped with the necessary features.

2. The advice generation unit identifies the body parts that should be shaped up according to the ideal body shape and generates the advice according to those body parts. The advice provision system according to claim 1.

3. The advice generation unit generates advice regarding exercises suitable for shaping up the aforementioned body part. The advice provision system according to claim 2.

4. The advice generation unit further identifies the current body shape of the target user based on the information entered by the target user, and generates the advice according to the difference between the current body shape and the ideal body shape. The advice provision system according to claim 1.

5. The Eating Habits Classification Unit classifies the eating habits of target users into one of several eating habit classifications based on the eating habit information of the target users. Furthermore, it is equipped with, The advice generation unit generates the advice according to the dietary habit classification and the ideal body type. The advice provision system according to claim 1.

6. An advice provision program that provides advice to target users for weight loss, and which includes an information processing device, The steps include: identifying which of the predefined ideal body types the user desires based on the information entered by the user; A step of generating advice regarding at least one of diet and exercise to shape up the body shape of the target user to the ideal body shape, A program that provides advice to help you implement solutions.

7. An advice provision method that provides advice to target users for weight loss, wherein the advice provision device is Based on the information entered by the user to whom the service is provided, the system identifies which of the predefined ideal body types the user desires. Generates advice regarding at least one of diet and exercise to shape the body shape of the target user to the ideal body shape. How to provide advice.

Images