Smart health management

Abstract

A system for personalized health management utilizes an iterative process of data collection, analysis, and recommendation to identify and address the root causes of physical, mental, and cognitive performance issues. The system continuously collects diverse health data from various sources, including real-time tracking, manual input, and external databases. Through repeated causal analysis, it identifies patterns and refines the understanding of underlying health issues, similar to a scientific experiment's iterative process. Based on this ongoing analysis, the system generates personalized recommendations for diet, activities, and scheduling, dynamically adjusting to new insights. Automated guidance and feedback are provided to users to help them achieve optimal health and performance, with each cycle of analysis further narrowing down root causes and improving recommendations.

Description

Detailed description of the invention

[0001] Referring to Figure 1, a computerized system to facilitate the tracking, analysis, recommendation and guidance of meal plans, activities, routine schedules, lifestyles, environment and general health education designed to help users reach their optimal health state and mental and physical performance. In one embodiment is designed to be web-based and therefore includes at least one web server containing the modules, algorithms and databases. The modules and algorithms are coded to communicate with databases and execute the data monitoring and tracking, data analysis, cause finding and various recommendations. In a preferred embodiment, the system communicates with the users’ devices via an internet connection, but is understood that other types of electronic communications could be used. The users’ devices can be computer, tablets smart phones and smart wearable devices ideally, but can also be other forms of devices. The computerized system also includes databases of users including, but not limited to, a multitude of database tables such as use’s anthropometries, physiological, and biochemical databases, physical and cognitive performance databases, physical and mental health database, user voice, image, and video database, user diet and nutrition databases, user activity, inactivity and sleep databases, user miscellaneous feedback database, user environment database, user medical history and abnormality databases, user drug intake databases, and user schedule database. The computerized system also includes databases of expert knowledge including, but not limited to, a multitude of database tables such as anthropometrical, physiological and biochemical databases, physical and cognitive performance databases, mental health database, voice, image and video diagnostics databases, food composition and nutrition recommendation databases, activity, inactivity, sleep and occupation databases, environment databases, relational causality databases, diseases diagnostics database, therapies databases, and schedule database. These non-limiting databases of the present invention will become apparent to those skilled in the art that other knowledge databases can be added in the future without altering the nature of the current invention. The computerized system also includes databases of machine-learning including, but not limited to, a multitude of database tables such as machine-learning process data and machine-learning result data derived from machine-learning algorithms. The machine-learning algorithms can be trained in both offline environments, in which the algorithms could be pre-trained by programmers, or online environment, in which the algorithms can learn from live data monitored and recorded through various means. The multitude of modules may automatically utilize the latest rulesets derived by machine-learning algorithm.

[0002] Referring to Figure 2. The main objectives are: 1) Record and monitor a multitude of user data; 2) Analyze and determine user’s health, performance and lifestyle; 3) Determine any problems in user’s health and performance; 4) Determine the causes to the problems; 5) Determine short, mid and long term optimal personal health related and physical, mental and cognitive performance targets for each user to improve health and performance; 6) Determine the methods to reach the optimal personal health and performance targets; 7) Generate various recommendations, such as diet, activities, sleep, environment, therapies and schedule, based on the previously determined methods and targets; 8) Guide the users to reach their ideal health state in accordance with the generated recommendations.

[0003] The system records and monitors at least the user’s anthropometries, physiological and biochemical measurements, food and nutritional intake, schedule, activities, inactivities, sleep, physical and cognitive performance, physical health, mental health, and living environment. By analyzing the user’s current and historic data against health and performance expert knowledge databases, the system determines the health status of the users. The health status of a user can be categorized in four categories, (1) Optimal health and performance, (2) Suboptimal health and performance, (3) Subhealth, (4) Diseased. The system aims to maintain the user at the optimal health and performance state. However, if a user who is at suboptimal health and performance state but wishes to maintain the current state of health and performance, the system can give recommendations in accordance with the user’s choosing. Otherwise, if any part of the user’s health parameters is suboptimal or worse or the user reports suboptimal or worse health and performance, the system will establish improvement targets for the suboptimal health status. The improvement targets can include but not limited to anthropometric targets such as weight and muscle mass, body fat and circumferences of various parts of the body; physiological and biochemical targets such as blood pressure, blood sugar, blood oxygen and cholesterol level, nutritional targets; nutritional targets such as whether every nutrition has meet the minimum dietary requirement and distribution of nutrients in different meals; physical activities targets such as types of activities done, different parts of muscles exercises, the amount and duration of activities done, and the time at which the activities were done; health impacting behaviors and choices such as ways of cooking and substance abuse, and environmental targets such as temperature, humidity and air quality in both indoor and outdoor environments.

[0004] The existing guidelines and health standards are set at average or minimum requirement values for most of the population, these values are generally not optimal for individuals on apersonal level. In addition, an individual’s optimal values are constantly changing based on the individual’s activities, inactivities, sleep, physical and mental health state, diet, and what the individual wants to accomplish in terms of work, studies or other mental or physical tasks. For instance, for the same individual, his optimal values will change when he changes his activities from doing his desk job work to doing work out. To overcome this problem, the system will use the comprehensively collected user data to determine the ideal health and performance parameters using a multitude of algorithms, which may comprise of traditional programming and machine learning algorithms including but not limited to variously classification algorithms, Supervised and Unsupervised Machine-Learning, Reinforcement Learning and Causal Machine Learning. The algorithms evaluate the user’s health and performance, identifies the negatives and the positives of the user’s health and performance, determines the causes of the negatives and the positives, then generates a set of short-, mid- and long-term health and performance targets and methods to reach said targets to alleviate the negatives. The recommendation module then makes schedule, diet, activities, inactivities, sleep, environment and therapies recommendations based on the targets and methods determined. This process will repeat indefinitely to help the users to reach and maintain their ideal health and performance.

[0005] Depending on the nature of the user’s health or performance problem, the system may suggest the user to seek assistance from health professionals. After the user returns from the doctors, the system will acquire the prescribed therapies and incorporate them into the system’s analysis and recommendations. These recommendations can include activities, inactivities, sleep, diet, environment changes, and schedule.

[0006] To reinforce and to complement the above main recommendations, the system provides a multitude of education, guidance and reminders. The system uses user’s health information and health guidelines to suggest the user to do regular physical checkups and doctor visits. The program uses cooking guidelines to guide users to cook healthily. This can include proper way to prepare the foods to minimize pesticides and bacteria and proper temperature to cook the foods to maintain the most of the nutritional values and prevent or reduce the chance of creating inedible foods such as burnt foods or poisonous foods. The program provides users a grocery list based on the recommended meals from program. The system guides user to correctly store foods to maximize the foods storage to prevent or minimize spoilage. The program uses physical activities guidelines to guide user to perform physical activities correctly and safely to prevent injuries. The program educates and guide users to prevent smoking and substance abuse and provides users information onovercoming substance abuse. The program educates and guides users to proper hygiene to prevent infectious diseases and viruses. This can include proper ways to wash hands and usage of condoms, etc. The program educates and guides users on giving first aid on one’s self or others, such as CPR and Heimlich maneuver, etc. The specifics of each function will be described in detail below.

[0007] Still referring to Figure Process Loop, analysis methods may use any suitable method to determine health and lifestyle patterns, including without limitation classification algorithms such as Regressions, Decision Tree and Support Vector Machine. Analysis methods may use any suitable method to determine problems and causes, including without limitation classification algorithm, such as Regressions, Decision Tree and Support Vector Machine, anomaly finding algorithms, such as Support Vector Machine, Restricted Boltzmann machine and decision tree and cause finding algorithms, such as Self Organizing Maps, Deep Belief Networks, Causal Machine-Learning and Causal Reinforcement Learning.

[0008] In an alternative or additional approach, all of the user’s data can be fed into a neural network, such as a Feed Forward Backpropagation Neural Network, to find deeper hidden layers of previously not determined relationships among data points.

[0009] Referring to Figure 3, the health analysis system takes all user’s health related data to determine the user’s health and improvement targets and methods. The system can utilize but not limited to a multitude of machine learning algorithms to classify and categorize each of the health- related data. The data include but are not limited to: (1) anthropometrical data such as weight, height, circumferences and sizes of different parts of the body, etc.; (2) physiological and biochemical data such as body composition, blood sugar, hormones, blood vitamins, etc.; (3) dietary information such as nutrition, types and amount of foods, ingredients of the foods, etc.; (4) activities, inactivities and sleep, such as duration, time, frequency types and amount of exercises, eating, drug taking, sitting, reading, working, studying, napping, sleeping, etc.; (5) schedule which is when each activity or inactivity is performed, (6) medical history such as disability, allergies, diseases and disorders, etc.; (7) administration and intake of drug, supplement and other non-food; (8) physical performance such as how much weight can one lift, how quickly can one run, how long can one run at a certain speed, the cardiovascular measurements during the activities, etc.; (9) cognitive performance such as how well can one remember, pattern recognition, problem solving, etc.; (10) mental health; (11) voice, audio, image and video of the user and user’s excretion, secretion and other body shedding including but not limited to nail, hair and skin; (12) physical and psychological feeling and mood; (13) user’s feedbacks such as how the user feels after doing anactivity, whether there is any pain and how much pain, how well rested the user is, how tired the user is, etc.; (14) doctor’s diagnostics such as physical exams, medical exams, medical scans, etc.; (15) environment and environmental factors such as location, temperature, humidity, air quality, light intensity, etc.; (16) any property and metadata of the above data such as quantity, frequency, time, location temperature, humidity, lightly intensity, noise level, etc.

[0010] This process can be concurrent with the user’s activities. As the user is doing activities, if the user is wearing a device, such as a smart watch that can track the user’s activities and physiological data such as heart rate and blood pressure, the system can take the data that is being recorded and feed it into the algorithms to aid the classification and categorization process. The system will use the classification and categorization to establish relationships among all factors of the user’s health and performance. The system will compare current and historic data to determine if any changes to the user’s health or performance has occurred. The system will query the user’s health related data to find the changes that may associate with the changed in the user’s health and performance. The system will also compare the user’s health related data with known health indices. If there’s no known health index available to compare against, the system will use the user’s feedbacks and performance data to determine the health. Physical performance can be determined by how the user performs in various sports activities. Cognitive performance can be determined by cognitive tests, user’s feedbacks and device tracked data. The device tracked data can include but not limited to user’s temperature, heart rate, breathing rate, blood pressure, blood sugar, blood oxygen, physical movement and imagery and video recordings. The imagery and video recordings can be used to monitor the user’s facial and bodily movements to determine how well the user is concentrating. Machine learning algorithms can be utilized to process the imagery and video. After determining that there are health or performance related problems, the system will determine which factors are the causes. This cause finding process can include but not limited to any suitable methods such as supervised machine learning algorithms such as classification algorithms and unsupervised machine learning algorithms such as causal machine learning. After identifying the causes to the problems, the system will determine how to adjustment the different health and performance targets to reach the optimal health and performance state of the user. The system will also analyze the past improvement recommendations to determine whether the past recommendations are inaccurate and needed to be adjusted. The improvement adjustments consist of but not limited to changing nutrition intake, food type, the amount, frequency, intensity and type of activities and inactivities, and environment. The system will then determine which methods caneffectively integrate the new targets into the user’s daily life. The methods include but not limited to diet, activities, inactivities and the scheduling of them. It should be noted that there still are many unknown factors that affect people’s health and performance, so long as the factors, that will be discovered in the future, will be able to fit into the scope of the management of diet and activities, the system will be able to accommodate the addition of new data.

[0011] Figure 4 and 5 depict an exemplary implementation of cause finding module. Regular cause-finding Machine-Learning algorithms focus on predicting outcomes by calculating the likelihood of an outcome, which is at the correlation stage, rather than truly understanding causality. Causal Machine-Learning solves this issue by proving or disproving whether a correlation is a causation. Reinforcement Learning is an automated machine-learning training method based on rewarding desired behaviors or outcomes and / or punishing undesired ones in order to find the most efficient method to accomplish a task. Causal Reinforcement Learning is the combination of Causal Machine-Learning and Reinforcement Learning by using the Reinforcement Learning’s automated process to pilot the Causal Machine-Learning algorithms to find the causation.

[0012] The cause-finding module receives a problem or multiple problems determined by the Health Analysis Module. The module queries expert knowledge databases on whether there are known cause(s) for the specific problem(s). If no known cause(s) can be found, the module queries the expert knowledge databases and the user’s health-related databases for any correlation related to the problem. The module then queries expert knowledge databases and machine-learning databases to find if any correlation has past determined weight(s) for similar problems. It should be noted that the correlation(s) and weight(s) are not essential in the cause finding module, but they can potentially speed up the algorithm. The module picks the most likely correlation as the theorized cause. The module will query the knowledge databases on the theorized cause and find the variables and factors that can affect on the theorized cause and their respective weight. Then the module will query the knowledge databases on methods that can alter the previously found variables and factors and the methods’ weights. The module will then generate at least one synthetic control group and at least one synthetic test group, which is composed of the varying methods that alter the different previously determined variables and factors. The synthetic control and test group(s)’s parameters are then sent to the associated recommendation module, where the parameters are used to make recommendations. The recommendations are then sent to the users and guidance module will guide the users through the recommendations. The control group and test group(s)’s user data monitored and recorded will then be analyzed to determine whether the synthetic test group(s) can test thelegitimacy of the theorized cause(s). If the algorithms determine that the theorized cause cannot be proved to be an actual cause, the module will pick the next most likely correlations as the theorized causes until there is either a theorized caused that can be proved to be an actual cause or there are no more correlations to be theorized as causes, which will then be flagged to be reviewed by humans. If the theorized cause is proved to be an actual cause, then the cause, causal relationships and their respective weight will be stored into the respective expert knowledge databases. If the theorized cause cannot be proved to be an actual cause, then the theorized cause is marked as none cause correlations and stored into the appropriate databases. The entire process of cause finding is also stored into machine-learning databases.

[0013] Figure 6 and 7 depict an exemplary implementation of cause finding module. The cause finding module receives a problem or multiple problems determined by the Health Analysis Module. The module queries expert knowledge databases on whether there are known cause(s) for the specific problem(s). If no known cause(s) can be found, the module queries the expert knowledge databases and the user’s health-related databases for any correlation related to the problem. The module then queries expert knowledge databases and machine-learning databases to find if any correlation has past determined weight(s) for similar problems. It should be noted that the correlation(s) and weight(s) are not essential in the cause finding module, but they can potentially speed up the algorithm. The module picks the most likely correlation as the theorized cause. The module will query the knowledge databases on the theorized cause and find the variables and factors that can affect the theorized cause and their respective weight. Then the module will query the knowledge databases on methods that can alter the previously found variables and factors and the methods’ weights. If the module determines that it’s not appropriate or available to do an Online Causal Reinforcement learning and that there are enough relevant Online or Offline training / learning data from the machine-learning databases to be used for this particular scenario, an Offline Causal Reinforcement is then initiated. Offline Causal Reinforcement learns from other Online or Offline Causal Reinforcement training processes on how and why they arrived at the end conclusion and apply the same or appropriately altered process with the current variables and factors to try to prove the theorized cause. If the algorithms determine that the theorized cause cannot be proved to be an actual cause, the module will pick the next most likely correlations as the theorized causes until there is either a theorized caused that can be proved to be an actual cause or there are no more correlations to be theorized as causes, which will then be flagged to be reviewed by humans. If the theorized cause is proved to be an actual cause, then the cause, causalrelationships and their respective weight will be stored into the respective expert knowledge databases. If the theorized cause cannot be proved to be an actual cause, then the theorized cause is marked as none cause correlations and stored into the appropriate databases. The entire process of cause finding is also stored into machine-learning databases.

[0014] Figure 8 and 9 depict an exemplary implementation of cause finding module. The cause-finding module receives a problem or multiple problems determined by the Health Analysis Module. The module queries expert knowledge databases on whether there are known cause(s) for the specific problem(s). If no known cause(s) can be found, the module queries the expert knowledge databases and the user’s health-related databases for any correlation related to the problem. The module then queries expert knowledge databases and machine-learning databases to find if any correlation has past determined weight(s) for similar problems. It should be noted that the correlation(s) and weight(s) are not essential in the cause-finding module, but they can potentially speed up the algorithm. The module picks the most likely correlation as the theorized cause. The module will query the knowledge databases on the theorized cause and find the variables and factors that affect the theorized cause and their respective weight. Then the module will query the knowledge databases on methods that can alter the previously found variables and factors and the methods’ weights. If the module determines that it’s not appropriate or available to do an Online Causal Reinforcement learning and that there are not enough relevant Online or Offline training / 1 earning process data from the machine-learning databases to be used for this particular scenario but there are enough conclusion data from expert knowledge databases and / or machinelearning databases, a Do-Calculus Causal Reinforcement is then initiated. Do-Calculus Causal Reinforcement learns from the conclusions of causes and the causal relationships without knowing the process of how and why the conclusions are made. The module learns from the conclusion data and the causal relationship data and determines the likelihood of the theorized cause is an actual cause. If the algorithms determine that the theorized cause cannot be proved to be an actual cause, the module will pick the next most likely correlations as the theorized causes until there is either a theorized caused that can be proved to be an actual cause or there are no more correlations to be theorized as causes, which will then be flagged to be reviewed by humans. If the theorized cause is proved to be an actual cause, then the cause, causal relationships and their respective weight will be stored into the respective expert knowledge databases. If the theorized cause cannot be proved to be an actual cause, then the theorized cause is marked as none cause correlations and stored into theappropriate databases. The entire process of cause finding is also stored into machine-learning databases.

[0015] Figure 10 is another exemplary implementation of cause finding module. Due to the nature of Offline and Do-Calculus Causal Reinforcement being mainly theoretical, the accuracy of the conclusion may be low. In order to improve upon the accuracy and to further test the theory, the cause finding module can pick out the Offline or Do-Calculus conclusions and run them through Online algorithms when Online algorithms become available and the Offline and Do-Calculus conclusions will be processed as theorized causes in the Online algorithms, which the process will proceed as normal.

[0016] Figure 11, 12 and 13 depict an exemplary implementation of the process of the analysis and recommendation of activities and the scheduling process of the recommended activities. The module queries the user’s activity database and determines the most likely activities the user will do in a certain day during a certain time. The module queries an activity database in expert knowledge database for the important of the activities. Non-alterable activities, such as work, school and commute, are determined and placed in the schedule timetable in the usual time. Then the module will start Activities Recommendation module to recommend activities to fill in the schedule timetable. Then the Diet Recommendation Module will be started to fulfill the nutritional needs of the user based on the activities.

[0017] The time, location, environment, duration, intensity, type of activities performed and the preceding activities leading up to the current activity can all have different effect for the current activity and any later activities. For instance, a few minutes of moderate to intense intensity activities may boost concentration, memory and other mental work-related performance, and prolonged low intensity work will lower mental work performance. Eating appropriately size snacks and meals with proper nutrition a certain amount of time before, during and after a workout session may boost physical performance and reduce injuries.

[0018] The system records time, location, environment, duration, intensity, type of all activities performed, performance and user body parameters. Activities comprise of all physical and mental activities, eating, administering non-food, and resting. Body parameters includes but not limited to body temperature, heart rate, blood pressure, blood sugar, blood oxygen and breathing rate. The system will determine the patterns in the user’s activities and categorize the activities based on time, duration, intensity and type. Methods of recording can include body worn devices such as smart watches, tracking functions and app from smart phones, video camera that can recordusers’ actions, facial expression and body movements. The system will then use the user performance of the activities and the body parameters and other data collected from the recording functions and determine events that negatively affects the user’s health or performance and then flag the events for alteration. The system will also analyze the location, environment and nature of the activities and determine what kind of activities are appropriate for such conditions and situations to recommend. For instance, it’s not appropriate to recommend the user to do several sets of bench press when the user is at work, however, a few sets of push up could be appropriate.

[0019] The Activities Recommendation Module will also take into consideration of recent activities within a certain time frame, for instance, within a week, to figure out a total amount of exercises in different groups of muscles, the type of the exercise, whether it’s muscle stretching or shortening, the intensity, the effect of the exercises on the user, whether there has been improvement in the user’s physical performances such as strength and endurance, and extends into mental and cognitive performance.

[0020] The recommendation module can employ the use of machine learning to help recommending the most situational and environmentally appropriate and effective activities. Supervised machine learning such as classification algorithms can help classify and categorize activities that are clearly labeled. This can be used to determine which activities are the best in categories such as building different muscle’s mass, improving muscle strength, muscle quality, muscle endurance. Unsupervised machine learning algorithms can make use of users’ physical, mental and cognitive performance data to further classify and categorize the activities in terms of their role in helping user’s performance. This can also be used towards determining the appropriateness of the activities in different scenarios. For instance, activity, schedule, location and environment data can be collected to determine which activities the users have actually completed. The program can learn from this data to determine which activities the users can do and like to do in different scenarios. Machine learning algorithms such as recommendation system and reinforcement machine learning can be utilized to recommend the activities and their respective amount, intensity and duration.

[0021] After the recommendation processes complete, the analysis and recommendations, if any, are sent to the user. The user can choose to modify the template and submit the modification for another analysis. This process can infinitely repeat until the user finalizes the template or choose not to follow the recommendations and submit the template. Lastly, the program will store theuser’s template to the user’s database for physical activities and routines, and the template itself will be stored to the user’s database for templates.

[0022] One implementation of inactivity monitor and notice module helps to prevent the user from staying inactive for a prolonged amount of time, which has strong links to multiple chronic diseases found by many proven research studies. The module works in multitude of ways, one for users who do not have or not actively equipping an electronic device that can track physical activity and another for those who are equipping a said device. For those who are equipping a said device, the program will use the device’s GPS, accelerometer, gyroscope, altimeter, speedometer, pedometer and timer to find out whether the user has been inactive for a prolonged amount of time, for example 2 hours. And when the program detects prolonged inactivity, the program will send user a message or alarm and a list of physical activities that is short in duration, moderate in intensity, for example 3 MET, easy to do, for example walk around, and appropriate, for example it will not suggest go for a swim or play soccer, to remind the user to do some physical activities. Moreover, for those who do not have or are not actively equipping such device, the program will use the user’s physical activities schedule and find the prolonged inactivity in the schedule and give the same aforementioned reminder to the user. If the user does have a physical activities schedule planned for the present, the program will access the user’s physical activity schedule history and attempt to find whether a pattern in user’s physical activities for the current day of the week. For example, if the program finds that on multiple Mondays in the past, the user does deskwork for three hours from 08:30 AM to 11:30 AM, and the program will note down that the user will likely do the same activity in the present and the future. If the program finds such inactivity pattern, it will send the aforementioned reminder to the user at the time during the found patterns. If no pattern can be found, the program can send user regular reminders to do moderate intensity activities regularly, For example, every two hours. The user can also manually set a reminder and the time interval or specific times the reminders should be sent.

[0023] Referring to Figure 14, an exemplary implementation of diet recommendation module is designed to allow a user to dynamically customize a meal plan for him or herself or for his or her household, whether in whole or in part, at the same time while ensuring the following: 1). everyone’s all nutritional requirement will be met and not exceed the upper limits of nutrient intake, which includes all, but not limited to, nutrients included in the Dietary Reference Intake set by the USDA, NUT and the FDA, essential and nonessential amino acids, and other nutrients that have not yet have established nutritional requirements; 2). meals will be the same or similar in ingredient andcooking style; 3). the cooking and preparation time fit in the cook’s schedule; 4). the meals are in the styles that the users prefer; 5). none of the ingredients are in the users’ dislike, prohibited due to allergies or religion or other reason. The program can recommend single meal to multiple meals for one day or multiple days in the present or the future.

[0024] The program will start by requesting preferences from the user. The preferences may include, but not limited to, style of the meals, number of the meals, cooking and preparation time, types of the ingredient, specific ingredients, etc. Then the program will receive the user’s preferences, and access and pull the user’s physical activities for the days the user want the recommendations. If no physical activities are found or planned for the day(s) the user want the diet recommendations, the program will ask the user if he or she wants to input the physical activities or wants the program to estimate nutritional requirement based on user’s and user’s household members’ activity level and anthropometries and physiological data instead. The program will then use the physical activities data or the estimation to calculate if any additional nutrients are needed to be increased to the existing DRI nutrient list. For example, for a typical male adult with sedentary to light activity level, an intake of 1.2mg of Thiamin per day is the DRI recommended value; but for someone who has expended more energy than the average adult male, approximately a 0.5 mg of Thiamin per day per 1,000 kcals is needed to fulfd the nutritional need but not exceeding 3.0 mg in total per day. Additional nutritional requirement can include, but not limited to calories, fat, protein, carbohydrate, Vitamin A, thiamin, riboflavin, niacin, Vitamin B6, Vitamin B12, folic ac acid, biotin, Vitamin C, Vitamin D, Vitamin E, Vitamin K, calcium, phosphorous, magnesium, sodium, potassium, chloride, iron, zinc, iodine, selenium, copper, manganese, chromium, etc. The program will also access the users’ health database and find additional nutritional requirements caused by health issues or medications. For example, for someone who is diabetic, sugar and glucose need to be severely limited or even eliminated from the diet.

[0025] The program will compile the variance in nutrient intake for each person in the user’s household if the user wants diet recommendation for his or her household. If more recommendation is wanted for more than one person at the same time, the program will compare the users’ entire nutritional requirement, and categorize the users into different recommendation groups if needed. For example, a 4-year-old, 3 feet tall and 50 pounds male child has vastly different nutrient requirement than a 30-year-old, 6 feet tall and 150 pounds female adult, and just by giving the child a proportionally smaller serving of the same meal that the adult eats is usually not able to satisfy the child’s nutritional requirement. In addition, if the user has specified a budget range andthere is local grocery pricing data available for the user in the system’s grocery pricing database, the program can exclude out of budget ingredients or form list on only in-budget ingredients. The program will use all dietary restrictions for the user(s), favorite foods, and other user’s preferences and the nutritional requirement as query parameters and find recipes and meals and combine them into different meals to fulfil the said parameters. It should be noted that the food recommended can be a single food item such as an apple, a manufactured food such as an energy bar, a restaurant made food such as a hamburger or a sandwich, recipes uploaded by users and staff in the program, or a combination of the aforementioned.

[0026] If the user requests recommendation for a full day’s meal, the program will find the user’s physical activities scheduled for the specific day from the database or query the user for the information if no schedule is found. The user can also choose to not enter in the physical activities and use program estimated nutritional requirement. Depending on the user’s preferences on number of meals per day, for example, most people eat three meals per day, some people may eat four or five or even more meals per day, while Muslims during Ramadan may only eat two meals a day, a breakfast and a dinner, the program will use course energy and nutrition ratio, pre-established by the personalized health manager which will be described in detail later, to find appropriate meals for each course.

[0027] If the user requests recommendation for a singular meal, the program will access user’s food intake database and find consumed foods in the specific day. It will prompt the user to enter in consumed foods if none is found in the database. It will also find the user’s physical activities scheduled for the specific day from the database or query the user for the information if no schedule is found. The user can also choose to not enter in the physical activities and use program estimated nutritional requirement. If the diet recommendation is for the first meal of the day, the program will find, from the food and recipe databases, a breakfast that fits the course energy and nutrition ratio and the user’s preferences while not exceeding any nutrient upper limit or contains any prohibited foods, such as allergens or religion prohibited foods, or prohibited nutrients, such as added sugar if the user is diabetic. If the meal is not the first meal of the day, but not the last meal of the day, the program will find a meal, such as a lunch or a mid-day meal, that fits the course energy and nutrition ratio and the user’s preferences while not exceeding any nutrient upper limit or contains any prohibited foods or nutrients. If the meal is the last meal of the day, the program will find a meal or dinner that completes the user’s nutritional requirement and fits the user’spreferences while not exceeding any nutrient upper limit or contains any prohibited foods or nutrients.

[0028] If there are different recommendation groups, the program will, should the user choose to use this function, make diet recommendations based on the same or similar main ingredients and other sub ingredients in order to make the cooking procedures simpler. It should be noted that the program prioritizes meal combinations that will give the different groups the same meals. It will give different meals only if the same meals cannot satisfy everyone’s nutritional requirement.

[0029] The users will receive the recommendation and can send feedbacks or request changes to be made to the recommendations should they be unsatisfied by the recommendations.

[0030] The meal planner can factor in all of the following in the process of coming up with a meal plan for the user. The factors include, nutritional requirements, these can include all nutrients on the Dietary Reference Intake chart and other nutrients not specified by the DRI such as tryptophan; cooking styles, such as boil, bake and stir-fry; ingredients, such as user likes and dislikes; allergies, which will exclude specific allergy causing ingredients; religion, which will exclude specific religion prohibited and should be avoided ingredients; ethnics, which will narrow down the meal planning on the user’s ethnics or the user’s selected ethnics. For example, a Chinese user may only want Chinese Cuisine and Japanese Cuisine and the program will only select the Chinese and Japanese ethnic meals; special conditions, such as diabetes, which will exclude most foods with glucose contents and some foods with over the limit fructose to glucose conversion ratios; ingredient availability, which is a regional foods availability database that will eliminate meals that have ingredients that are not available to the user’s region; time, which will suit the user’s schedule and preferred time spent on food preparation and cooking; cooking equipment, which will eliminate meals that cannot be cooked without these specified cooking equipment. For example, if any recipe states a pressure cooker is needed and the user does not have one and does not wish to purchase one, these recipes will be eliminated from the meal planning; budget and price, a regional food pricing database will help the program make sure that the meals planned will not exceed the user’s chosen budget; food safety, a food safety database will record all present food safety issues, these can include regional food virus outbreak, toxins within the foods, nutrients that can cause unhealthy conditions when overdosed, genetically modified foods’ toxins, pesticides and herbicides on foods from certain farms or areas, these information can help the program eliminatefoods or provide notices to the user on foods with these food safety issues and how to prevent getting poisoned.

[0031] After the user accepts the meal plan, the program will form a grocery list using all of the ingredients in the meal plan and save the grocery list to the server. All of the same ingredients from different recipes will be merged together. Since many ingredients do not need to be purchased frequently, such as condiments like vegetable oil, salt and black pepper, the program, at the user’s choice, will not include these types of ingredients in the grocery list. And an estimate pricing for individual ingredients and total pricing can also be included in the grocery list. Pricing estimation is done by accessing local foods pricing database, and the average price can be calculated through this way. If any store is partnered with the program, the program can acquire pricing on items from the stores.

[0032] In addition to the nutrition analysis module, the program will also access a food safety database in which it will look for food safety issues that exist in any of the ingredients of the recipe. For example, an outbreak of E. coli virus in romaine lettuce in multiple states in the USA, if any recipe contains romaine lettuce, the program will tag these recipes with E. coli virus, and every time these recipes are accessed by any user in the affected states, the user will be notified of this issue and be given instructions on how to safely prepare the romaine lettuce, such as thoroughly wash and cooking the romaine lettuce in above 60 degrees Celsius for over 2 minutes. And when this food safety issue is resolved, if ever, the program will deactivate the specific food safety issue tag from all recipes that contain these tags and users will not be notified of these nonexistent food safety issues.

[0033] It should be noted that the food safety database will include all present food safety issues, and will be updated regularly to reflect any changes in the issues.

[0034] Referring to Figure Ingredient Learning, an exemplary implementation of ingredient learning. In order to make the accurate ingredient adjustments, each ingredient needs to be learned of its features. Classification and categorization algorithms are used to establish the relationship among each ingredient’s nutrition, food type, usage, taste, texture, price, location and season. Classification and categorization algorithms also establish relationships among different ingredients based on their features. The findings are then stored in a relational database for ingredient. This enables the Ingredient Adjustment Module to be able to quickly and accurately pick out the most appropriate additional or replacement ingredient best fit to the user’s personalized meal plans.

[0035] Referring to Figure 15 and 16, an exemplary implementation of ingredient adjustment module adjusts the recipe’s ingredient to match the nutrition requirement determined by the health analysis module. It queries the ingredient relational database established by the Ingredient Learning Module. It will subtract or add the amount of different ingredients until the recipe’s nutritional value matches the nutritional requirement. Preferably, it will focus on the ingredients that contributes mainly to the nutrients that need to be adjusted. Also preferably, it will try to maintain the ingredient relative ratio to preserve the recipe’s taste and look. It can utilize but not limited to machine learning algorithms such as reinforcement machine learning to help adjust the ingredients. A Reinforcement Learning algorithm can be utilized to make the adjustments. The algorithm can be trained by programmers to simulate different scenarios. The ruleset and learning process of adjustment found by the algorithms in different scenarios are then stored in a machine-learning database. During real time usage, the module queries machine-learning database for the closest matching ruleset and learning process and runs the algorithm.

[0036] Referring to Food Inventory, it depicts an exemplary food inventory tracking method. This method will track user’s food purchases and will aid the program in guiding the users to correct food preservation and storage and meal plan revisions. The program will prompt the user to input in these ingredients and their respective quantity to the program, whether pre-existing in the user’s inventory or bought in the future. Every time user purchases new groceries, preferably purchased according to the program generated grocery lists, the system will prompt whether the foods purchased match the grocery list. If yes, the program will record these foods into the user’s food inventory database; if not, the program will ask the user to input the foods purchased and record them into the food inventory database. There are multiple ways for the user to input these purchased foods into the program, manually typing into food inventory form, audio recognition, receipt scanning, which is a form of image recognition. These methods are the same as the aforementioned various data entry methods. In addition to these methods, if the stores from which the user purchased foods from are partnered with the program, the store can provide user’s purchase history to the program, and the program will automatically acquire and record the foods upon receiving the receipt number or other receipt identifying ID such as barcode from the user. When the inventory becomes low, for example, only 2 days of foods left, the program will give user notice to start the next meal planning and plan on doing another grocery shopping list.

[0037] Referring to Figure 17, an implementation of the trainer module. The trainer module will start by displaying information about the current workout, such as time needed, exercises,intensity, energy expenditure, equipment needed and safety notices. When the user selects “Start”, the program will give out text, audio, image or video instructions to the user depending on the user’s preference in the instructions. For example, if the exercise is bench pressure, the instruction in video form will instruct the user the proper techniques and forms of bench pressing, and the instruction is audio form will say, for example, “Start the first set of 3 reps. Up Down Up Down Up Down.” A timer will also start, and at regular intervals, depending on the intensity and types of the workout, safety notices and directions will be provided to the user. For example, in the instance of the user not having or not equipping a heart rate monitor that is connected to the program, after sprinting for 4 minutes, the program will ask the user to stop and check their heart rate. If the heart rate is above 80% of the user’s maximum heart rate, which when having exceedingly high heart rate for a prolonged amount of time, the risk of heart disease rises significantly, the program will instruct the user to rest a minute and then check the heart rate again. Moreover, if the heart rate drops to a safe range, the program will instruct the user to continue the workout. If the user is experiencing heartache, or other forms of abnormal conditions or injuries, such as a pulled muscle, the program will determine that these conditions cannot be appease by briefly resting and will instruct the user to stop the workout and depending on the seriousness of the conditions, the program may instruct the user to seek medical help. In the case of user equipping health monitors that can be connected to the program, the program will continuously monitor the user’s conditions and will give out instructions when any abnormality happens, such as abnormal heart rate. The process will repeat until the user finishes the workout plan.

[0038] Referring to Figure 18, an implementation of cooking instruction module is a program animated and timed cooking instruction with text instruction, computer synthesized audio instruction, and user uploaded image or video instructions. The instructions are obtained from the recipe uploading process discussed above. The user can choose the presentation forms of the cooking instruction. When the user selects a recipe and starts its cooking instruction, the module will access the recipe database and nutrition database for this particular recipe. The module will tell the user the necessary foods, ingredients and cooking utensils and wait for the user to finish this step and click “Next Step”. After the user is finished this step, the program will proceed to food preparation step, such as washing and cutting the foods. The module will also notify the user on how to correctly clean the foods to maximally remove the pesticides, herbicides and other harmful substances such as viruses from the foods. User will press “Start Cooking” soft button when finished with preparation, and the module will proceed to the first cook step instruction and start thetimer for this step. When the timer ends for this step, the module will ask the user whether this step is finished. If it is, the module will continue to the next step. If not, the module will wait until the user pressure “Next Step”. This process will repeat until the cooking is finished. When the cooking is finished, the module will give user instructions to separate the foods into different servings and the each serving’ quantity if the foods are prepared for multiple people.

[0039] In one exemplary implementation, the module gathers user’s health information and health status through questionnaires and tests and exams. These questionnaires, tests and exams include, but not limited in, user’s daily self-rated physical conditions, mental conditions, intelligence exams, memory exams, and physical readiness, strength, endurance exams. The module will use the user’s answers to these questions and determine the user’s health that is otherwise not able to be detected by regular anthropometries and physiological data. Through these answers, the module accesses the respective health guideline databases, for example mental health database for the mental health questions, and determine any causes to the user’s abnormal or unhealthy conditions if the user is deemed to be abnormal or unhealthy.

[0040] In addition to the questionnaires, the module will also use user anthropometrical, physiological and biochemical data for analysis. The module can calculate the many data derived values such as body mass index and percent body fat. And the blood profiles, if the user has provided any, can inform the module many in depth health related information, such as blood cholesterol and blood sugar level. The module will access the respective health guideline databases, for example body mass index databases for the calculated BMI, and identify any abnormal values, For example a high BMI or PBF. Then it will determine the potential causes to these abnormalities, for example, a high percent body can be caused by improper diet or lack of physical activities or the combination of both.

[0041] After the causes are identified, the module will determine the seriousness of the problems and whether the system has the capability to resolve the problems. If the problems are too serious or the system does not have the capability to resolve the problems, the module will suggest the user to seek help from medical professional. In addition, the module will provide the user with the determined causes and guide the user to the appropriate medical professionals. For example, the user is experiencing heartaches and the module determined to have a serious heart problem, the module will inform the user the problems and provide the user with heart diseases information, such as heart disease guidelines by the American Heart Association, and provide the user with a list of medical centers that can treat heart diseases and a list of cardiovascular doctors and help the usersetup appointments. If the doctor can provide the user with recommendations compatible with the program’s, the program will store these recommendations to the server and apply them to the user. For example, the doctor has provided a special nutritional requirement for the user, the doctor can use the system’s medical professional portal and replace the existing nutritional requirement. If the doctor does not use the system’s medical professional portal, the user can record the doctor’s recommendations to the system through various ways using the aforementioned information input system.

[0042] If the module determines that it has the capability to help the user to regain health, it will give the user appropriate suggestions, recommendation, guidance and changes. The module can help the user from four main categories. They are lifestyle and habits, food and nutrition, physical activities and routines, and environment. The module can provide help from each individual categories or a combination of these categories.

[0043] If the module determines one or more of the causes fall under the lifestyle and habits categories, it will give the user suggestions and recommendations to change one or more of the user’s lifestyles and habits. For example, the user reports respiratory system problems, and the module discovers the user is a smoker through further questioning on the reported problem. The module will access health information database and find smoking related information. Then it will suggest the user to quit smoking, and will provide the user with information on the cons of smoking and guidance to quit smoking. In addition, the module will give the user information such as smoking cessation center, or alternatives to smoking such as electronic cigarettes.

[0044] If the module determines one or more of the causes fall under food and nutrition category, it will determine whether the problem is specific food related or nutrition related. If it is food related, for example undiscovered food allergies, the module will add the allergy causing foods to the user’s prohibited food list. If it is nutrition related, the module will follow the appropriate guidelines and algorithms and adjust the nutritional requirement for the user accordingly. For example, an abnormally high percent body fat is detected, or the percent body fat is increasing when it is not supposed to be. The module examines the user’s nutrition intake history and determines that the user needs to ingest less fat. To solve this problem, the module will modify the user’s nutritional requirement and lower the fat consumption. In another example, the user reports to have experienced low blood pressure and muscle weakness, and after the module examining the user’s nutrition intake history, the module determines that low sodium and high magnesium intakes are the causes. To resolve this, the module will modify the user’s nutritional requirement, raise the sodiumintake and lower the magnesium intake per guideline. Depending on the changes in nutrition intake, physical activities and routines may need to be adjusted to comply with the new nutrition intake. For example, if the user’s energy intake is adjusted to be lower, to maintain the nutritional balance, physical activities caused nutritional expenditure needs to be lowered accordingly. This is done by reducing the intensity, duration or types of the physical activities performed by the user.

[0045] The diet part of this module can also determine the distribution of energy and nutrient intake in each meal of the day. The general energy intake recommendation in breakfast, lunch and dinner is 3:4:3. Such that in a 2,000 kcal diet, the distribution of energy intake in break to lunch to dinner is 600 kcal to 800 kcal to 600 kcal. This kind of recommendation cannot be used to optimize the user’s health and performance. The module will adjust the distribution of energy and nutrient intake for each meal in accordance with the user’s anthropometrical, physiological and biochemical measurements, activities, inactivities, sleep, schedule and the user’s feedbacks. The module calculates the energy expenditure and other nutrition requirement of the different activities, inactivities and sleep. Rate of digestion, metabolic rate, diseases such as diabetes, and a multitude of user’s health related indices are used to calculate when and how much each nutrition needs to be replenished. The diet recommendation module then recommends meals and snacks based on the nutritional requirements and subsequently calls the scheduling module to schedule the meals and snacks.

[0046] If the module determines one or more of the causes fall under the physical activity categories, it will follow the respective guidelines to adjust the physical activities, the physical activities intensity, duration, time frame during which the physical activities will be performed or suggest to cease any inappropriate physical activities or types of physical activities based on the types, intensity and environment in which the physical activities will be performed. For example, a user has reported fatigue and drowsiness in the mornings, and the user’s anthropometrical, physiological and biochemical measurements show normal values and the user has been following a proper meal plan while exercised appropriately according to recommendations. However, after examined the user’s physical activities routines, the module discovered that the user has been exercising intensely in the early mornings. The module determines that due to the high-energy expenditure in the mornings, the user, despite is overall energy and nutrition balanced, does not have enough energy for the morning activities and, therefore, experienced fatigue and drowsiness. The module will analyze the user’s daily physical activity routine and find appropriate alternative time frames for the exercises, or split the exercises to shorter time intervals spread across the day,and send the user the recommendations and the analysis. Alternatively, the module can change the user’s meal plan by making the breakfast recommendations higher in carbohydrates, fats and proteins (calories) and other nutrients, such as sodium and potassium due to significant quantities of them can be lost in sweat, and the other meals lower in the respective nutrients accordingly per the requirements of nutrition intake. In addition, should the intensity or duration of the physical activities be changed, the module will calculate the new nutritional requirements accordingly to reach nutrition intake and expenditure balance.

[0047] If the module determines one or more of the causes fall under the environment category, it will follow guidelines for environment health and provide user suggestions and guidance on how to improve the user’s environment. The environment issues can be classified as two main sections, indoor and outdoor. Indoor environment that affects most people’s lives mainly consist of harmful building and furnishing materials, ie. asbestos insulation and lead paint, hazardous gases from fuel-burning combustion appliances, ie. natural gas, carbon dioxide and carbon monoxide, temperature, humidity, indoor air pollutions, ie. second hand smoke, unhealthy cooking styles produced smoke, ie. vegetable oil smoke due to high cooking temperature, water source pollution, outdoor air pollution that leaks into indoor and natural harmful gases that leaks into indoor, ie. radon gas. Outdoor environment that affects most people’s lives mainly consist of temperature, humidity, air quality, air pollution and allergies, ie. pollen and certain plants. While the module cannot directly change, prevent or mitigate these health risk factors, it is capable of providing the user a series of guidelines and information and suggestions. For example, if user is experiencing a newly discovered pollen allergic reactions, the module may recommend the user to not go outside when the local pollen index is not safe for the user, or suggest the user to wear facemask when going outside. In addition, the module will record down the user’s newly discovered pollen allergy. It should be noted, if the user has reported pollen allergies, the recommendation module for physical activities would factor in those when making recommendations and suggestions as described above in the physical activity recommendation section. For another example, the user is experiencing sleep problems, and the module determined that it is due to the user’s sleeping environment, such as improper temperature, humidity, and light or noises from various sources such as electronics and from outside. The module can recommend the user to decrease or increase the room temperature and humidity to recommended levels, for example, 68 degrees Fahrenheit is determined to be the ideal sleeping temperature for most of the population. The module, in the example, can also instruct the user to remove light pollutions in the room, forexample, remove the light producing items from the room, cover over such items, or install blackout curtains. The module, in the example, can also suggest the user to wear earplugs, install sound insulation on doors and wall or install better sound proofing windows to reduce the noise pollutions.

[0048] The module will regularly inquire the user on the progress and status on the problems. It can provide further suggestions, recommendations and information based on any updates on the problems by repeating the algorithm. At the same time, it will record all of the process and data and provide relevant information to the other modules within the system.

[0049] In one exemplary implementation, the program utilizes several ways to determine the accuracy of the recommendations, suggestions and guidance in relation to the user’s health. One of the ways is to suggest the user to take physical exams, blood tests, urine test and other medical exams if the user has not uploaded these test results recently. The program can provide the user with locations of exam locations and appointments. Another way is the inquiry and questionnaire system. It works in several ways, one being questions and inquiries after each user event. The event stands for use’s physical activities, meals, actions, changes and any feedbacks to any of the system’s features. For example, after each exercise, either detected by user’s activity tracking devices or determined by the program using the user’s physical activities schedules, the program will inquire the user’s conditions and feelings about the activities. The feelings can be subject or objective, quantifiable or non-quantifiable. They can include but not limited to how the user feels how good his sleep is, does he feel happy, whether he is in pain, how much pain he’s feeling, how much optimism he has, how energized he is, whether he’s tired, whether he is sore, etc. The questions can include inquiries about the user’s heart rate if the user did not equip a program connected heart rate monitor, the user’s general feeling to the activities done, fatigue, strain on the body, comparisons with the past physical activities to judge things such as strength and stamina increase, and any abnormal conditions felt, such as short of breath and heartaches. The questions will revolve around the effect of the physical activities on the user’s body and the user’s feelings and conditions towards the physical activities. For another example, if the user does equip a program connected sleep tracking device when sleeping, when the user wakes up in the morning, the program will inquire the user about the sleep’s quality, total duration, how long it took to fall asleep, how many times the user woke up in the middle of the sleep, if the user woke up in the middle of the sleep, how long it took to fall back to sleep, and if the user had trouble with sleep, potential causes such as unwanted light and noises. The questions are preferably short in time completion and few in numbers for the maximum user convenience, but will be longer in time and more in numbers if the programdetermines the former option cannot provide sufficient information about the user’s conditions. The second method of inquiry focuses on the user’s psychology, mental health, memory, reaction time and intelligence. The part features mental health questionnaires for examining the user’s mental health and puzzles, memory games and IQ tests to determining the user’s memory, reaction time and intelligence. The test results will be compared with the past results to determine the user’s mental health progress. In addition, the test results and their respective history will be cross- examined with the user’s physical activities, nutrition intake, foods, other mental health results, anthropometries and physiological data, medical exam results, and environment histories to form links and patterns in an attempt to reveal the relationships and causes and effects each of the elements or the combination of the elements have on each other in order to determine the best combination of diet, physical activities, lifestyles and environment to reach the user’s most optimal physical and mental health. As mentioned above, the tests on memory, reaction time and intelligence are in the forms of questionnaires and games. In other words, they exist in different forms in order to appeal to different people with different interests. Lists of questions will usually not appeal to kids, and in order to get accurate and consistent, in terms of time intervals in between the tests, results to compare and be analyzed with other user data, program integrated games are made. These games may be puzzle games and image recognition and memory games. It should be noted that these games have different difficulties for different age groups, whereas they will be the easiest for the youngest and harder as the age increases up until reaching adult and elder age groups. It should also be noted that these tests, whether in question form or game form, can be used by all age groups regardless of forms.

Claims

Any embodiment may include any of the optional or preferred features of the other embodiments. The exemplary embodiments herein disclosed are not intended to be exhaustive or to unnecessarily limit the scope of the invention. The exemplary embodiments were chosen and described in order to explain the principles so that others skilled in the art may practice the invention. Having shown and described exemplary embodiments, those skilled in the art will realize that many variations and modifications may be made to affect the described invention. Many of those variations and modifications will provide the same result and fall within the spirit of the claimed invention. It is the intention, therefore, to limit the invention only as indicated by the scope of the claims.We claim:

1. A system for personal health and lifestyle management, the system comprising: Obtaining user health related data through a plurality of different methods;Analyzing health related data using a health analysis system to determine user health and lifestyle patterns;Analyzing user’s current and historic health related data to determine the relationships among the data, health and lifestyle related problems, and the causes to the problems; Analyzing user’s current and historic health related data to determine physical, mental and cognitive performance problems, and the causes to the problems;Analyzing user’s current and historic health related data to determine optimal personalized health related and physical, mental and cognitive performance targets;Determining methods of improvement in order to achieve the previously determined targets; Generating activities recommendations in accordance with the previously determined methods and targets;Generating diet recommendations in accordance with the activities and the previously determined methods and targets;Generating scheduling recommendation in accordance with the diet, activities, environment and the previously determined methods and targets;Generating other recommendations in accordance with the previously determined methods and targets;Guiding users based on the generated parameters to help them reach or maintain optimal health and performance.

2. The method of claim 1, wherein the health-related data comprises of at least the following: (1) anthropometries, (2) physiological and biochemical data, (3) dietary information, (4)activities, (5) schedule, (6) medical history, (7) drug intake, (8) physical performance, (9) mental performance, (10) voice, (11) image and video of the user and user’s excrement, (12) emotions and mood, (13) user’s feedbacks.

3. The method of claim 2, the data can be obtained in real time via a tracker device, entered into the system manually or through voice and image recognition methods, and linked with other databases such as hospital and clinic’s databases.

4. The method of claim 1, the lifestyle patterns comprise of the time, duration, intensity, quantity, location, environment, quality, performance and type of all activities and inactivities of the user and any of the user’s anthropometries, physiological and biochemical data during the activities that is available.

5. The method of claim 1, the analysis and generation methods use one or more algorithms comprising of tradition or machine learning algorithms or mix use of both.

6. The method of claim 1, the analysis methods can be inside a neural network and work together as a whole or work separately dependently or independently with the other analysis methods.1117. The method of claim 1, the generation methods can be inside a neural network and work together as a whole or work separately dependently or independently with the other generation methods.

8. The method of claim 1, the optimal health related targets comprise of at least the following: (1) anthropometries, physiological and biochemical targets, (2) nutrition targets, (3) heart rate, (4) blood pressure, (5) blood oxygen, (6) blood sugar, (7) blood work.

9. The method of claim 1, wherein physical performance is determined by at least the following: (1) anthropometries, physiological and biochemical data, (2) cardiovascular strength, (3) cardiovascular endurance, (4) muscle strength, (5) muscle endurance, (6) muscle flexibility, (7) balance.

10. The method of claim 8, wherein muscles can be overall body muscles, muscle groups and individual muscles.

11. The method of claim 1, wherein mental and cognitive performance is determined by at least the following: (1) memory, (2) critical thinking, (3) creativity, (4) emotion and mood.

12. The method of claim 1, additional optimal health related and physical, mental and cognitive performance targets can be determined by the analysis algorithm(s) with addition of new data.

13. The method of claim 1, wherein the health managing methods to reach optimal health and physical, mental and cognitive performance adjust the following: (1) nutrition intake, (2) food types, (3) activities types, (4) activities intensity, (5) activities duration, (6) activities frequency, (7) scheduling, (8) environment to do the different activities in.

14. The method of claim 1, additional health managing adjustments can be determined by the analysis algorithm(s) with addition of new data.

15. The method of claim 11 and 13, wherein the newly determined targets and adjustments by the algorithm(s) can be automatically incorporated with the previously determined targets and adjustments.

16. The method of claim 1, wherein the diet generation method fulfdls all nutritional needs based on the user’s activities type, intensity, duration and time.

17. The method of claim 1, wherein the diet generation method takes into consideration of when and where the meal will be eaten.

18. The method of claim 1, wherein the activities generation method takes into consideration of when and where the activities will be performed.

19. The method of claim 1, wherein scheduling generation method takes into consideration of (1) the time and location the activities will be performed, (2) appropriateness of the activities in the environment, (3) relationship and effect of one activity to another.

20. The method of claim 18, wherein environment comprises of (1) location, (2) temperature, (3) humidity, (4) air pressure, (5) air quality, (6) noise level.

21. The method of claim 18, wherein relationship and effect of one activity to another comprise of (1) effect of food consumption on activities performance and efficiency at different timing and different amount of nutrition, (2) effect of activities on other activities at different timing, intensity and duration.

22. The method of claim 2, wherein obtaining user health related through image and video of the user and user’s excrement utilize automatic image and voice recognition algorithms to detect any irregular signs of diseases and disorders.

23. The method of claim 1, 19 and 21, wherein activities comprise of any activities and inactivities including all physical activities, cognitive activities, eating and resting.

24. The method of claim 1, wherein guiding users based on the generated parameters to help them reach or maintain optimal health and performance comprise of sending reminders to users’ devices based the system generated scheduling recommendations, instructing users onwhat to do, how to properly execute the activities, how long to do the activities and the quantity of the activities.

Images