Patent Application
20160379520
Various embodiments relate generally to electrical and electronic hardware, computer software, wired and wireless network communications, and wearable computing and audio devices for monitoring and managing health and wellness. More specifically, disclosed are methods, interfaces, and computer-readable media to generate predictive consumable recommendations and indicators (e.g., food scores) to determine nutrient density of health-promoting consumables, such as health-promoting nutrients in consumables including food, drink, supplements, and the like.
Conventional techniques for assessing nutritional qualities of a food item and for recommending food items for consumption typically require a person to understand the complexities of nutrition science. Further, the various formats of nutrition labels usually organizes nutritional information in a manner that confuses a reader as to whether a certain food item is sufficient to meet one's nutritional and health-related goals. It is not uncommon for a nutrition label to recite more than 15 numbers for which the reader needs to comprehend to readily assess the nutritional value of a food product. Such nutrition labels and other traditional techniques for conveying nutrition information are not well-suited to enable the reader to compare the nutritional benefits of one product against another product. Further, traditional food logging devices typically are calorie-centric; that is, known food logging techniques principally track calories, with nutritional-related information being tracked secondarily.
Thus, what is needed is a solution for conveying nutritional information effectively without the limitations of conventional techniques.
Various embodiments or examples (“examples”) of the invention are disclosed in the following detailed description and the accompanying drawings:
Various embodiments or examples may be implemented in numerous ways, including as a system, a process, an apparatus, a user interface, or a series of program instructions on a computer readable medium such as a computer readable storage medium or a computer network where the program instructions are sent over optical, electronic, or wireless communication links. In general, operations of disclosed processes may be performed in an arbitrary order, unless otherwise provided in the claims.
A detailed description of one or more examples is provided below along with accompanying figures. The detailed description is provided in connection with such examples, but is not limited to any particular example. The scope is limited only by the claims and numerous alternatives, modifications, and equivalents are encompassed. Numerous specific details are set forth in the following description in order to provide a thorough understanding. These details are provided for the purpose of example and the described techniques may be practiced according to the claims without some or all of these specific details. For clarity, technical material that is known in the technical fields related to the examples has not been described in detail to avoid unnecessarily obscuring the description.
In view of the foregoing, the structures and/or functionalities of nutrition intake evaluator 150, which may be implemented in hardware, software, or a combination thereof, as described herein, can facilitate communication to a user of a relative degree of healthiness of a dish, a meal, or food item. In accordance with various embodiments, an indicator (e.g., a “food score”) is an efficient or compressed representation indicative of the health-related qualities of a consumable item, and enables a user to determine the impact of a food item on their health with little to negligible effort (e.g., “at a glance”). In some cases, an indicator of the various embodiments can provide a non-calorie metric for comparing the nutritional benefits of different consumable items, and need not require a quantity or an amount of a food item to determine an indicator. Thus, an indicator can convey, for example, an optimal (e.g., highest) ratio of healthy nutrients (e.g., naturally-occurring foods) to unhealthy nutrients (e.g., processed foods) independent of a quantity or weight of consumable items, according to some examples. In at least one example, the use of indicators described herein enables a user to determine a degree of healthy eating even though one or more meals may not be logged over the course of one or more days. Moreover, the use of an indicator, as a metric, facilitates a comparison among meal choices when a user desires to select a healthy choice.
As shown in
Nutrition intake evaluator 150 includes a nutrition density indicator generator 152, a recommendation engine 154, an interface controller 156, and a nutrition density correlator 158. Further, nutrition intake evaluator 150 is also configured to receive state data 111, conditional data 113, goal data 114, other data 115, and weighting data 116, and the like. State data 111 includes any type of data describing an active state of the user (e.g., a type of activity in which user is engaged, such as walking, running, sitting, etc., the intensity of engaging in such an activity, durations of such activities, times of day in which an activity typically occurs, physiological characteristics, such as heart rate, associated in an activity, rate of caloric burn, amount of calories expended, hydration levels, and the like). State data 111 also includes sleep-related data, such as data representing the quality of sleep (e.g., sufficiency of REM sleep, etc.), the quantity of sleep, and other sleep-related durations of sleep, times of day in which sleep typically occurs, physiological characteristics, such as heart rate, associated with sleep, and the like. Further, state data 111 can also include mood-related data that describes an emotional or affective state of the user (e.g., whether a user is content, stressed, lethargic, happy, angry, upset, depressed, etc.) during any time period, including over multiple units of time (e.g., multiple days).
Condition data 113 includes data describing one or more conditions of a person. For example, condition data 113 can describe whether a user is suffering from a disease (e.g., chronic or otherwise), such as hypertension, heart disease, arthritis, cancer, diabetes, asthma, etc., or whether the user has an injury. Condition data 113 also can describe food allergies, such as to gluten, nuts, shell fish, dairy, etc., or a propensity (or lack thereof) to consume a food item. Condition data 113 also includes data describing whether a woman is pregnant, or a person has a cold or the flu, or the like. Goal data 114 includes data describing one or more goals, such as a number of steps per day, an amount of sleep per night, weight-loss goals, rate of weight loss, fitness goals, selective eating goals (e.g., eating certain foods with a certain nutrient for addressing a certain ailment), and the like. Other data 115 includes data describes other information that may be usable with, or to form, an indicator value or food score. Data 115 can also include data that describes biometric information, such as an age, a gender, a height, a weight, a body type, a BMI, etc. Weighting data 116 includes weight values for application against intermediate, individual, or subsets of scores or any type of score based on, for example, a type of nutrient being evaluated. A food item including trans fats (e.g., trans-unsaturated fatty acids, etc.) may be associated with a food score that is weighted to indicate the health-impairing effects such as nutrient.
Nutrition density indicator generator 152 is configured to generate at least an indicator based on nutrition data 109. In some cases, the generation of the indicator can be influenced based on other data, such as state data 111, conditional data 113, goal data 114, other data 115, and/or weighting data 116. In some embodiments, nutrition density indicator generator 152 is configured to generate, for example, a weighted average of a number of intermediate scores derived from evaluating a number of nutrients in association with other nutrients or consumable characteristics (e.g., per number of calories, such as per 100 calories, or any other food-related characteristic). In some cases, nutrition density indicator generator 152 can apply different weighting values from weighting data 116 to solicit or promote an increase in a particular nutrient. For example, during cold and flu season, weighting data 116 can weight food items including vitamin C more heavily than the spring and summer seasons. As another example, nutrition density indicator generator 152 can customize determination of a value of an indicator as a function of a person's nutritional needs based on age and gender.
Recommendation engine 154 is configured to generate data 190 representing one or more recommended consumable items that are substantially similar to a requested consumable item, whereby the recommended consumable items may have higher indicator values (e.g., higher food scores), which, in turn, indicate that at least a recommended consumable item may be more healthier than a user-requested consumable item. For example, consider that a user is searching for a breakfast cereal that is sweetened artificially (e.g., having food score of 6.6). Recommendation engine 154 is configured to search for other breakfast cereals that are similar to the searched breakfast cereal (e.g., similar in taste, based on ingredients, consumer reviews, etc.) and to present at least on other breakfast cereal that has a higher food score (e.g., 7.2).
Nutrition density correlator 158 is configured to correlate a food score to other information, such as state data 111 (e.g., a user's mood, activity level, quality of sleep, etc.), conditional data 113, goal data 114, other data 115, and/or weighting data 116, and to generate informational “insight” data 192 as either observations, notifications, or recommended courses of action. Nutrition density correlator 158 can also generate data describing trends between a user's food score over time against other data. For example, one set of trend data can depict a relationship between higher daily food scores and longer durations in which a user performs an activity (e.g., more laps at a swimming pool). In some examples, nutrition density correlator 158 is configured to track and correlate food scores to daily activity, sleep, and mood so that nutrition density indicator generator 152 can adapt a food scoring determination process based on one or more of a daily activity, sleep, mood, etc.
Interface controller 156 is configured to receive data generated by other elements of nutrition intake evaluator 150 for generating signals to present an indicator value to interfaces 112a and 112b. Further, interface controller 156 can be configured to receive signals indicating a food-related requests, whereby an indicator value or food score for a prospective meal can be determined and presented via an interface. As such, interface controller 156 is configured to graphically convey to a user (e.g., in a formatted arrangement as stored in a databased and/or displayed visually to a user) an optimal food or drink choice based on, for example, a compress representation of a degree of healthiness which is accessible to a user. In various embodiments, nutrition intake evaluator 150 may generate data arrangements configured to effectuate efficient nutrition-related selections for urging a user to effectively consume optimally calculated ingredients and/or nutrients.
Nutrient evaluator 402, which is optional in some instances, is configured to determine whether a consumable item includes threshold amounts of nutrients and/or associated nutrition information to sufficiently form an effective indicator or intermediate indicator (e.g., an effective food score or intermediate food score). In one example, nutrient evaluator 402 can be configured to enable the scoring of a consumable item if a consumable item includes a total number of carbohydrates, an amount of sugar, an amount of fiber, an amount of protein, and at least two or more of: (1.) a total amount of fat, (2.) an amount of saturated fat, and (3.) an amount of unsaturated fat. In at least one case, nutrient evaluator 102 enables scoring if an amount of calories is non-zero. According to various embodiments, more or fewer of the aforementioned nutrient requirements may be implemented by nutrient evaluator 402 to determine whether to score one or more consumable items. For example, nutrient evaluator 402 may determine an indicator as a function of an amount of sodium and/or cholesterol According to at least one embodiment, nutrient evaluator 402 is configured to perform a calorie check by calculating a total number of calories based on the following equation:
Total calories=4*[total amount of carbohydrates (g)+protein (g)]+9*[total amount of fat (g)],
whereby nutrient evaluator 402 can enable the scoring of the consumable item if the total calories from nutrient information 401 is within, for example, 30% of the above calculated total calories (or vice versa).
Nutrient association characterizer 404 is configured to characterize associations between a nutrient and one or more other nutrients or consumable characteristics. Nutrient association characterizer 404 is configured to identify a nutrient 431a and determine an association between nutrient 431a, as a first element, and a second element (i.e., another nutrient, a consumable characteristic, or any other item.). According to some examples, nutrient association characterizer 404 is configured to identify a nutrient 431a and determine an association 403 between nutrient 431a and another nutrient 431b. Association 403 can represent any type of relationship (e.g., numerical relationship) between an amount of nutrient 431a and an amount of nutrient 431b, and, as such, association 403 can contribute to a determination of an intermediate score 407 (e.g., a nutrient-related score). Association 403 can be indicative of a nutrient density based on at least nutrients 431a and 431b, whereby nutrient 431a can represent an amount of a health-promoting nutrient and nutrient 431b can represent an amount of a health-impairing nutrient. To illustrate, consider that an example of association 403 is a ratio of an amount of protein (in grams) to an amount of saturated fat (in grams) in a consumable item.
In another example, nutrient association characterizer 404 is configured to characterize in association 405 between nutrient 431a and a consumable characteristic 433, which is a characteristic of one or more consumables items (e.g., one or more food items). Association 405 also can represent any type of relationship (e.g., numerical relationship) between an amount of nutrient 431a and an amount associated with consumable characteristic 433. Further, association 405 can contribute to a determination of an intermediate score, from which indicator data 490 is derived. To illustrate, consider that an example of association 405 is a ratio of an amount of a nutrient (e.g., an amount of salt in milligrams) to an amount describing a characteristic in a consumable item (e.g., a unit amount of calories, such as 100 calories).
Note that nutrient association characterizer 404 can be configured to determine any number of associations from one or more nutrients 431a to one or more nutrients 431b, or to one or more consumable characteristics 433, to establish an indicator or food score. In some embodiments, a number of associations 403 and/or a number of associations 405 can be configured to include more or fewer associations to modify determination of indicator data 490 based on, for example, one or more of state data 111, conditional data 113, goal data 114, other data 115, weighting data 116, and the like.
Characterized association valuator 406 is configured to generate a value representative of an association characterized by nutrient association characterizer 404. Such a value can be descriptive of an amount, for example, of a health-promoting nutrient relative to an amount of a health-impairing nutrient for a food item. In some embodiments, the value derived by characterized association valuator 406 can be referred to as an immediate score 407, or a base score, that can be combined with other values representative of other associations characterized by nutrient association characterizer 404. In at least one example, a higher value that represents an association, such as a magnitude of a ratio, can be indicative of a more healthy combination of amounts of the corresponding nutrients (e.g., a more healthy combination of an amount of protein to an amount of saturated fats). Characterized association valuator 406 can determine a value by any manner, such as through a computation using equations, implementation of empirically-determined relationships, etc.
Weighting value unit 408 is configured to identify values of characterized associations, and further configured to apply a corresponding weight to either emphasize or deemphasize an impact of an intermediate score 407 in the formation of data representing food score 490. For example, condition data describing a user as having a hypertensive circulatory system can cause weighting value unit 408 to select a greater weighting value as applied to sodium (as a nutrient) to emphasize the deleterious effects of consuming food items having relatively large quantities of sodium. Weighting value unit 408 can be configured to apply different weighting values to different intermediate scores 407 as a function of any number of factors, whereby the one or more different weighting values can be configured to adapt food scoring for the particular needs of a user. Therefore, weighting value unit 408 can be configured to generate weighted, intermediate scores.
Nutrient-based modifier 410 is configured to modify a magnitude of an indicator or score to either boost or reduce the effects of a nutrient. In various examples, nutrient-based modifier 410 includes a booster 412 configured to boost effects of a nutrient, and a reducer 414 to reduce the effects of a nutrient. In some embodiments, nutrient-based modifier 410 can modify a magnitude of an intermediate score 407 or modify a weighted, intermediate score that may be generated by weighting value unit 408. In some cases, nutrient-based modifier 410 can modify a value of indicator data 490 representing a food score for a food item, or can modify a value of an indicator data 490 representing a food score for a combination of food items that constitute a meal, and the like.
To illustrate, consider a following example in which booster 412 is configured to add 1.5 points to a food score associated with any vegetable and/or fruit to emphasize the beneficial nutrients in such food, based on the quantities of vitamins, minerals, antioxidants and polyphenol content. Thus, booster 412 can be designed to encourage people to replace refined grains and sugars with vegetables and fruit. In another example, booster 412 is configured to add 0.5 points to a food score to boost a food score for a food item that is relatively high in potassium (e.g., in view of a USDA guideline or any other requirement, such as requested by a user). Thus, booster 412 is designed to encourage people to consume foods with relatively high potassium content, including beans, potatoes with skin, bananas, avocado, tomato, yogurt, dark leafy greens, etc. In yet another example, reducer 414 is configured to reduce or penalize a food score by an amount (e.g., −1.0 points) for food items that are relatively high in sodium content, thereby discouraging further consumption of foods with high levels of salt. Booster 412 and reducer 414 are not limited to the above-described nutrients and can operate in relation to any type of nutrient or consumable constituent.
Indicator calculator 420 is configured to receive one or more intermediate scores, one or more weighted, intermediate scores, and any other information for generating indicator data 490. In some embodiments, indicator data 490 represents a food score that is a weighted average of intermediate or “healthiness” scores.
In a first example, nutrition association characterizer 504 characterizes an association between protein, as a nutrient 501, and saturated fat, as nutrient 505, whereby the characterized association represents a magnitude of a ratio 530 of protein to saturated fat. A range of magnitudes for the ratio of protein to saturated fats is configured to adapt a food score to encourage people to eat food items that include protein with relatively low amounts of saturated fats to reduce risk factors for cardiovascular disease. Consider a second example, in which nutrition association characterizer 504 characterizes an association between fiber, as a nutrient 501, and a total amount of carbohydrates, as nutrient 505, whereby the characterized association represents a magnitude of a ratio 532 of fiber to total carbohydrates. A range of magnitudes for the ratio of fiber to total carbohydrates is configured to adapt a food score to encourage people to focus on foods having relatively high amounts of fiber, including foods such as vegetables, fruits and whole grains to help reduce the risk of cardiovascular disease, obesity and type II diabetes. Note, too that foods that are naturally high in fiber may be more nutrient dense, thereby helping to control insulin and blood sugar levels as well as promoting gastrointestinal health.
In a third example, nutrition association characterizer 504 characterizes an association between unsaturated fat, as a nutrient 501, and saturated fat, as nutrient 505, whereby the characterized association represents a magnitude of a ratio 534 of unsaturated fat to saturated fat. A range of magnitudes for the ratio of unsaturated fat to saturated fat may be configured to adapt a food score to include foods that have relatively more unsaturated fats, which promote health by lowering LDL (i.e., bad) cholesterol and by improving insulin levels for people with type II diabetes. Generating a food score that deemphasizes consumption of food that includes saturated fat can emphasize food items that reduce risk for heart disease. In a fourth example, nutrition association characterizer 504 characterizes an association between sugar, as a nutrient 501, and fiber, as nutrient 505, whereby the characterized association represents a magnitude of a ratio 536 of sugar to fiber. A range of magnitudes for the ratio of sugar to fiber can be configured to encourage people to reduce consumption of food items that include added sugars, thereby encouraging a person to lower their caloric intake without compromising nutrient. Further, foods that include added sugars may lack sufficient amounts of fiber to reduce insulin responses. In view of the foregoing, more or fewer ratios can be evaluated according to various embodiments. Further, note that other associations between other nutrients can be selected in accordance with, for example, the USDA dietary guidelines, user-defined nutrient guidelines, and the like.
Ratio magnitudes 530, 532, 534, and 536 are provided to characterized association valuator 506, which, in turn, generates values 580a, 580b, 580c, and 580d, respectively for the characterized associations. According to some embodiments, values 580a, 580b, 580c, and 580d can be determined, in at least some examples, as intermediate scores derived from
Weighting value unit 508 is configured to apply weights to intermediate scores associated with values 580a, 580b, 580c, and 580d to respectively generate weighted, intermediate scores 590a, 590b, 590c, and 590d, which, in turn, can be provided to an indicator calculator for generating a food score for one or more consumable items. In some examples, weighting value unit 508 is configured to apply a weight of three (“3”) to values 580a, 580b, 580c, and 580d. However, weighting value unit 508 can apply any other weights to values 580a, 580b, 580c, and 580d, according to other embodiments.
According to at least one embodiment, a nutrient evaluator 402 of
In a first example, nutrition association characterizer 704 characterizes an association 703 between trans fat, as a nutrient 701, and a unit of 100 calories, as consumable characteristic 705, whereby the characterized association represents a magnitude 730 of an amount of trans fat per 100 calories. A range of magnitudes of trans fat per 100 calories is configured to adapt a food score to encourage people to avoid most quantities of trans fat acids as they may be a relatively non-essential part of a diet and have been associated with increased of cardiovascular disease.
In a second example, nutrition association characterizer 704 characterizes an association 703 between sodium, as a nutrient 701, and an amount of sodium, as consumable characteristic 705, whereby the characterized association represents a magnitude 732 of sodium per 100 calories. A range of magnitudes of sodium per 100 calories is configured to adapt a food score to encourage people limit sodium intake to less than, for example, 2300 mg per day to assist in lowering blood pressure levels. Note that a default minimum amount of sodium may bet set to 1500 mg per day. In view of the foregoing, more or fewer associations between one or more nutrients and one or more consumable characteristics can be evaluated according to various embodiments. Further, note that other associations between other nutrients can be selected in accordance with, for example, the USDA dietary guidelines.
Magnitudes 730 and 732 are provided to characterized association valuator 706, which, in turn, generates values 780a and 780b, respectively for the characterized associations. According to some embodiments, values 780a and 780b can be determined, in at least some examples, as intermediate scores derived from
Weighting value unit 708 is configured to apply weights to intermediate scores associated with values 780a and 780b to respectively generate weighted, intermediate scores 790a and 790b, which, in turn, can be provided to an indicator calculator for generating a food score for one or more consumable items. In some examples, weighting value unit 708 is configured to apply a weight of three (“3”) to value 780a. Further, weighting value unit 708 is configured to apply either a weight of one (“1”) to value 780b, if a total amount of sodium over a unit time interval is less than 2300 mg, or a weight of three (“3”) to value 780b, if the sodium amount is or exceeds 2300 mg. However, weighting value unit 708 can apply other weights to values 780a and 780b, according to other embodiments.
According to at least one embodiment, a nutrient evaluator 402 of
Indicator calculator 920 is configured to derive indicator 950 from data 590a, 590b, 590c, 590d, 790a and 790b based on one or more analysis techniques. In some embodiments, indicator calculator 920 is configured to calculate a food score as, for example, depicted as a weighted average 911. As shown, weighted average 911 is derived by emphasizing, via weights applied by a weighting value unit, certain nutrient-based associations to generate values 590a, 590b, 590c, 590d, 790a and 790b. In at least one case, values 590a, 590b, 590c, 590d, 790a and 790b are processed as values 990a, 990b, 990c, 990d, 990e, and 990f, which are then normalized to a food score scale (e.g., from 0 to 10). For example, a combination of values 990a, 990b, 990c, 990d, 990e, and 990f can be normalized by dividing with a number of values, N, which, in this example, is six (6). Note that indicator calculator 920 is not limited to generating a food score is described in
In the example shown, nutrition association characterizer 1004 is configured to characterize a number of associations of health-promoting nutrients relative to a unit amount of calories (e.g., 100 calories). Nutrient association characterizer 1004 is configured to derive a magnitude 1030 of fiber, a magnitude 1032 of protein, a magnitude 1034 of unsaturated fat, a magnitude 1036 of calcium, a magnitude 1037 of vitamin A, and a magnitude 1038 of vitamin C, the magnitudes of which can be relative per unit number of calories (e.g., 100 calories). Further, magnitudes 1030, 1032, 1034, 1036, 1037, and 1038 can be provided to characterized association valuator 1006, which, in turn, generates values 1080a, 1080b, 1080c, 1080d, 1080e and 1080f, respectively for the characterized associations. According to some embodiments, values 1080a, 1080b, 1080c, 1080d, 1080e and 1080f can be determined, in at least some examples, as intermediate scores derived from
To illustrate, consider that a selection of a meal or food items provides a magnitude 1036 of about 25 mg calcium per 100 calories. According to diagram 1145 in
Weighting value unit 1008 is configured to apply weights to intermediate scores associated with values 1080a, 1080b, 1080c, 1080d, 1080e and 1080f to respectively generate weighted, intermediate scores 1090a, 1090b, 1090c, 1090d, 1090e and 1090f, which, in turn, can be provided to an indicator calculator for generating a food score for one or more consumable items. In some examples, weighting value unit 1008 is configured to apply a weight of six (“6”) to value 1080a, apply a weight of four (“4”) to value 1080b, and a weight of two (“2”) to value 1080c. Further, weighting value unit 1008 is configured to apply a weight of one (“1”) to values 1080d, 1080e, and 1080f. However, weighting value unit 1008 can apply other weights to values 1080a to 1080f, according to other embodiments.
Note that a nutrient evaluator of the various embodiments can determine whether to enable or disable the use of the above-described magnitudes based on a presence of a corresponding nutrient in a food item.
Nutrient association characterizer 1204 is configured to derive a magnitude 1230 of sugar, a magnitude 1232 of saturated fat, a magnitude 1234 of trans fat, a magnitude 1236 of sodium, and a magnitude 1237 of cholesterol, the magnitudes of which can be relative per unit number of calories (e.g., 100 calories). Further, magnitudes 1230, 1232, 1234, 1236, and 1237 can be provided to characterized association valuator 1206, which, in turn, generates values 1280a, 1280b, 1280c, 1280d, and 1280e, respectively for the characterized associations. According to some embodiments, values 1280a, 1280b, 1280c, 1280d, and 1280e can be determined, in at least some examples, as intermediate scores derived from
To illustrate, consider that a selection of a meal or food items provides a magnitude 1236 of about 4.5 g sugar per 100 calories. According to the diagram 1300 in
Weighting value unit 1208 is configured to apply weights to intermediate scores associated with values 1280a, 1280b, 1280c, 1280d, and 1280e to respectively generate weighted, intermediate scores 1290a, 1290b, 1290c, 1290d, and 1290e, which, in turn, can be provided to an indicator calculator for generating a food score for one or more consumable items. In some examples, weighting value unit 1208 is configured to apply a weight of two (“2”) to values 1280a and 1280d. Further, weighting value unit 1208 is configured to apply a weight of four (“4”) to value 1280b, apply a weight of ten (“10”) to value 1280c, and a weight of one (“1”) to value 1280e. Note, however, weighting value unit 1208 is not so limiting and can apply other weights to values 1280a to 1280f, according to other embodiments.
Note that a nutrient evaluator of the various embodiments can determine whether to enable or disable the use of the above-described magnitudes based on a presence of a corresponding nutrient in a food item.
At 1512, a nutrient is identified. At 1514, either another nutrient or a consumable characteristic is identified. At 1516, an association is determined either between two nutrients or between a nutrient and a consumable characteristic, and the association is characterized to describe the relationship and/or dependency between the two items. In relationship and/or dependency can be expressed as, for example, a ratio, a magnitude, or by any other numerical or arithmetic representation. At 1518, a score is derived (e.g., a nutrient score or intermediate score). Flow 1500, responsive to an affirmative determination at 1522, can continue to 1522. At 1522, a determination is made as to whether to apply a weighting value. If so, the weight is applied to, for example, a nutrient score at 1524. If not, flow 1500 moves to 1526, at which a food score is determined (e.g., an indicator is calculated).
For example, consider that a user is searching for a breakfast cereal and a number of artificially sweetened cereals having average food scores of 6.6 are selected for presentation. Among the various artificially sweetened cereals are corn flakes frosted with sugar. Recommendation engine 1654 is configured to search for other breakfast cereals that are similar to the searched breakfast cereal (e.g., similar in taste, based on ingredients, consumer reviews, etc.) and present another breakfast cereal that has a higher food score (e.g., 7.2). For example, a food item that includes natural, unsweetened corn flakes, while substantially similar to default food items, can be presented to the user as a healthier choice.
To illustrate operation of recommendation 1654, consider the following example. A user enters a food item 1608 into the search field in an interface 1612 of mobile computing device 1610. In this case, a user is interested in consuming one or more hot dogs as a meal. Data 1640 representing a request for “hot dogs” is received into food selection engine 1660. Food selection engine 1660 determines the characteristics and attributes of a “hot dog,” based, at least in part, from data received from food characteristics database (“DB”) 1602. Food selection engine 1660 determines a subset of food items that substantially share characteristics and/or attributes based on an entered search term “hot dog” 1608. Food selection engine 1660 accesses health-related information, such as a food score, from a food score database (“DB”) 1604 to retrieve food scores for a subset of food items to be presented. Further, food selection engine 1660 generates data 1642 that are configured to display a subset of food items 1620 with accompanying food scores 1609 in interface 1612.
Food score enhancement unit 1662 is configured to detect a request for a food item, such as a hot dog, and is further configured to determine a healthier, but a similar alternative food item. Food score enhancement unit 1662 is configured to extract food characteristics from database 1602 to determine equivalent food items, and is further configured to extract from database 1604 food scores for equivalent food items that may be presented to the user as alternative food choices. In some examples, food score enhancement unit 1662 accesses meal archives database 1606 to detect whether a user has a predilection or dislike for any of the equivalent food items having higher food scores. After filtering out unfavorable equivalent food items, food score enhancement unit 1662 selects one or more alternative food items having enhanced food scores over items 1620. Further, food score enhancement unit 1662 is configured to identify at least one alternative food item for presentation as a food item 1622 via data 1644.
In the example shown in
According to some embodiments, nutrition density correlator 1758 is configured to receive food scores in real-time (or near real-time) as well as archived food scores from repository 1704. Further, nutrition density correlator 1758 is configured to analyze data from multiple sources such as activity data 1713, sleep data 1714, and mood data 1760 to determine whether there are any correlations among food scores (e.g., daily food scores) and a user's performance in an activity, such as walking, based on activity data 1713. Nutrition density correlator 1758 is also configured to analyze food score data and sleep data 1714 to determine whether there any correlations. Further, nutrition density correlator 1758 is configured to analyze food score data and mood data 1716 two also determine whether or any correlations.
In view of the foregoing, nutrition density correlator 1758 is configured to derive trend-related data between the food score, as described herein, and a state of a user. As shown in diagram 1700, nutrition density correlator 1758 is configured to determine a correlation between daily food scores and daily sleep scores for presentation in an interface 1712 of mobile computing device 1710. As shown here, relatively high food scores, such as food score 1771, occurs one day prior to a relatively high sleep score 1770. As this occurs more than one time, the user can infer that obtaining a relatively high food score may assist them in meeting their sleep goals as well as any other type of goals.
According to at least one example, nutrition density correlator 1758 includes an action generator 1720, which is configured to generate data representing an action to cause a response to, for example, a correlation between a food score and a score for an activity, for a sleep activity, and the like. In one case, action generator 1720 can generate a notification data 1701 to alert a user of a possible correlation with proposed actions to be taken in view of such a correlation. Further, action generator 1720 can generate configuration data 1703 that is designed to cause a food score determination process to be adapted in a manner responsive to trend data.
Diagram 1800 also depicts several repositories from which dynamic meal plan manager 1830 can receive data for generating various meal plans, especially responsive to various changes in context. As shown, a repository 1802 includes archived meal data for a user. This data describes previously-consumed meals and food items that likely may be acceptable for future consumption by a user. Repository 1804 includes a database of consumable items that describes various aspects of food items and nutritional information. Repository 1806 includes data specifying recipes and constituent ingredients from which a user can prepare meals to achieve various goals, including maintaining weight-loss goals in accordance with a food score. Repository 1808 includes identities of third-party food preparers, such as restaurants, that can deliver food items or prepare a meal for pickup. The nutritional information of the food items and meals and other menu-related items can be viewed by user to determine whether a meal prepared by the third-party prepare can meet an individual's health and wellness goals.
Dynamic meal plan manager 1830 of diagram 1800 is configured to receive food score data 1801 that describes food scores for a number of consumable items, food items, and meals. Dynamic meal plan manager 1830 also is configured to receive various forms of data, including activity data 1811 (e.g., data describing various characteristics of activities including work-related activities, exercise-related activities, or the like). Further, dynamic meal plan manager 1830 is configured to receive sleep data 1813, mood-related data 1814, biometric data 1815 (e.g., age, height, weight, gender, etc.), condition data 1816 (e.g., data describing a health-related condition including, but not limited to, chronic illness, such as diabetes, an allergy, any health-related frailty, such as a calcium deficiency, and the like), goal data 1817 (e.g., data describing various goals, such as a weight-loss goal, a nutritional-related goal, and the like). Diagram 1800 also illustrates that dynamic meal plan manager 1830 also receives context-related data, such as location data 1818 (e.g., data describing at least a user's geographic position and one or more locations at which food may be obtained), time data 1819 (e.g., data describing a time of day, a time duration before and after events, etc.), and social context data 1820 (e.g., data describing the identities of one or more persons with which a user consumes one or more food items, etc.).
Further to
Based on user-specific data, meal plan generator 1834 is configured to identify a number of various meal plans for a specific user as a function of the specific characteristics of the user, in terms of a condition of health, activity level, etc. Meal plan generator 1834 is configured to generate a number of meals for a user based on the following. For example, meal plan generator 1834 can access data in repository 1808 to determine availability of food at a third-party entity, such as restaurant. Also meal plan generator 1834 can access repository 1806 to receive recipe information (including ingredients) to enable a user to prepare the user's food or meal. Meal plan generator 1834 can access consumable database 1804 to identify the specific food items and nutrient-related information, as well as an accompanying food score.
Meal plan selector 1837 is configured to identify and convey a number of food plans and proposed meals for consumption. For example, meal plan selector 1837 can use at least some of the aforementioned user-specific data to generate data representing meals based on recipe information 1840 (i.e., meals in which a user prepares from scratch), and generate data 1841 representing meals that that can be obtained from proprietor, such as a muffin in a coffee shop. Also, meal data 1842 can be generated to identify a source or origin of food from which to receive a meal via a delivery service.
Context detector 1839 is configured to determine a context (as well as changes in context) of the user based on, for example, location data 1818, time data 1819, and social context data 1820. A change in location, time, and the like, typically causes a user to deviate from a current meal plan. So based on the time of day, and whether a person is at work, traveling out-of-state, at home, or at any other place, context detector 1839 determines such conditions and causes a meal plan to change dynamically in accordance with the context of the user.
Trigger manager 1836 is configured to monitor the various above-described data to match against a number of data files each representing a triggering condition. A data file for a trigger condition includes data representing one or more conditions that, when met, causes trigger manager 1836 to initiate an action, such as selecting a new meal and presenting an updated dynamic list of meals in real-time responsive to a change in the event or condition of the user. An action also can include generating a notification to alert the user of changes in that person's meal plan for the day, for the week, or any other time interval. Trigger manager 1836 is configured to receive data representing meal selections for different meals from meal plan generator 1834 and a context of the user from context detector 1839. Trigger manager 1836 is then configured to trigger a modification in a meal plan based on changes in context and other related data.
Consumable item selection predictor 2030 can be configured to predict a first food item to present to a user to select for food logging based on an analysis of the above-mentioned data. For example, consider that consumable item selection predictor 2030 can ascertain that a user is beginning a food logging process at a specific time of day, at a specific location, with a specific social context, and in view of the user's activity and condition. In view of this information, consumable item selection predictor 2030 can offer a food item that has a relatively high likelihood of being selected by a user.
Next, consider an example in which a user has selected a food item. According to some embodiments, selection detector 2032 is configured to detect selection of a food item, and selection filtering manager 2034 is configured to filter through a number of food items to select a subset of food items present to a user. In one case, selection filtering manager 2034 is configured to receive data indicating a likelihood of selection of a second food item based on the selection of the first food item. Archived food logging data 2002 includes a relatively large amount of data describing relationships among food item selected by large number of people. Selection correlator 2004 is configured to correlate the selections and, in some cases, is further configured to generate a probabilistic representation (e.g., a table) for predicting meal completion probabilistically. An example of a probabilistic presentation is depicted in
Referring back to
Consumable item inference controller 2037 is configured to receive data representing likely food items that may be selected after the selection of a first item. In response, consumable item inference controller 2037 is configured to generate inferred items 2040, 2041, 2042. For example, if the user selects coffee as a first item of food to be logged, consumable item inference controller 2037 can generate inferred items 2040, 2041, and 2042, to represent likely second selections of sugar, cream, and nonfat milk, respectively.
In some cases, computing platform can be disposed in wearable device or implement, a mobile computing device, or any other device.
Computing platform 2300 includes a bus 2302 or other communication mechanism for communicating information, which interconnects subsystems and devices, such as processor 2304, system memory 2306 (e.g., RAM, etc.), storage device 23012 (e.g., ROM, etc.), a communication interface 2313 (e.g., an Ethernet or wireless controller, a Bluetooth controller, etc.) to facilitate communications via a port on communication link 2321 to communicate, for example, with a computing device, including mobile computing and/or communication devices with processors. Processor 2304 can be implemented with one or more central processing units (“CPUs”), such as those manufactured by Intel® Corporation, or one or more virtual processors, as well as any combination of CPUs and virtual processors. Computing platform 2300 exchanges data representing inputs and outputs via input-and-output devices 2301, including, but not limited to, keyboards, mice, audio inputs (e.g., speech-to-text devices), user interfaces, displays, monitors, cursors, touch-sensitive displays, LCD or LED displays, and other I/O-related devices.
According to some examples, computing platform 2300 performs specific operations by processor 2304 executing one or more sequences of one or more instructions stored in system memory 2306, and computing platform 2300 can be implemented in a client-server arrangement, peer-to-peer arrangement, or as any mobile computing device, including smart phones and the like. Such instructions or data may be read into system memory 2306 from another computer readable medium, such as storage device 2308. In some examples, hard-wired circuitry may be used in place of or in combination with software instructions for implementation. Instructions may be embedded in software or firmware. The term “computer readable medium” refers to any tangible medium that participates in providing instructions to processor 2304 for execution. Such a medium may take many forms, including but not limited to, non-volatile media and volatile media. Non-volatile media includes, for example, optical or magnetic disks and the like. Volatile media includes dynamic memory, such as system memory 2306.
Common forms of computer readable media includes, for example, floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, RAM, PROM, EPROM, FLASH-EPROM, any other memory chip or cartridge, or any other medium from which a computer can read. Instructions may further be transmitted or received using a transmission medium. The term “transmission medium” may include any tangible or intangible medium that is capable of storing, encoding or carrying instructions for execution by the machine, and includes digital or analog communications signals or other intangible medium to facilitate communication of such instructions. Transmission media includes coaxial cables, copper wire, and fiber optics, including wires that comprise bus 2302 for transmitting a computer data signal.
In some examples, execution of the sequences of instructions may be performed by computing platform 2300. According to some examples, computing platform 2300 can be coupled by communication link 2321 (e.g., a wired network, such as LAN, PSTN, or any wireless network) to any other processor to perform the sequence of instructions in coordination with (or asynchronous to) one another. Computing platform 2300 may transmit and receive messages, data, and instructions, including program code (e.g., application code) through communication link 2321 and communication interface 2313. Received program code may be executed by processor 2304 as it is received, and/or stored in memory 2306 or other non-volatile storage for later execution.
In the example shown, system memory 2306 can include various modules that include executable instructions to implement functionalities described herein. In the example shown, system memory 2306 includes a nutrition intake evaluator 2370, a dynamic meal plan manager 2372, and a consumable item selection predictor 2374, one or more of which can be configured to provide or consume outputs to implement one or more functions described herein.
In at least some examples, the structures and/or functions of any of the above-described features can be implemented in software, hardware, firmware, circuitry, or a combination thereof. Note that the structures and constituent elements above, as well as their functionality, may be aggregated with one or more other structures or elements. Alternatively, the elements and their functionality may be subdivided into constituent sub-elements, if any. As software, the above-described techniques may be implemented using various types of programming or formatting languages, frameworks, syntax, applications, protocols, objects, or techniques. As hardware and/or firmware, the above-described techniques may be implemented using various types of programming or integrated circuit design languages, including hardware description languages, such as any register transfer language (“RTL”) configured to design field-programmable gate arrays (“FPGAs”), application-specific integrated circuits (“ASICs”), or any other type of integrated circuit. According to some embodiments, the term “module” can refer, for example, to an algorithm or a portion thereof, and/or logic implemented in either hardware circuitry or software, or a combination thereof. These can be varied and are not limited to the examples or descriptions provided.
In some embodiments, a nutrition intake evaluator or one or more of its components (or a dynamic meal plan manager or a consumable item selection predictor), or any process or device described herein, can be in communication (e.g., wired or wirelessly) with a mobile device, such as a mobile phone or computing device, or can be disposed therein. In some cases, a mobile device, or any networked computing device (not shown) in communication with a nutrition intake evaluator (or a dynamic meal plan manager or a consumable item selection predictor) or one or more of its components (or any process or device described herein), can provide at least some of the structures and/or functions of any of the features described herein. As depicted in
For example, a nutrition intake evaluator (or a dynamic meal plan manager or a consumable item selection predictor), any of its one or more components, or any process or device described herein, can be implemented in one or more computing devices (i.e., any mobile computing device, such as a wearable device, an audio device (such as headphones or a headset) or mobile phone, whether worn or carried) that include one or more processors configured to execute one or more algorithms in memory. Thus, at least some of the elements in
As hardware and/or firmware, the above-described structures and techniques can be implemented using various types of programming or integrated circuit design languages, including hardware description languages, such as any register transfer language (“RTL”) configured to design field-programmable gate arrays (“FPGAs”), application-specific integrated circuits (“ASICs”), multi-chip modules, or any other type of integrated circuit. For example, a nutrition intake evaluator (or a dynamic meal plan manager or a consumable item selection predictor), including one or more components, or any process or device described herein, can be implemented in one or more computing devices that include one or more circuits. Thus, at least one of the elements in
According to some embodiments, the term “circuit” can refer, for example, to any system including a number of components through which current flows to perform one or more functions, the components including discrete and complex components. Examples of discrete components include transistors, resistors, capacitors, inductors, diodes, and the like, and examples of complex components include memory, processors, analog circuits, digital circuits, and the like, including field-programmable gate arrays (“FPGAs”), application-specific integrated circuits (“ASICs”). Therefore, a circuit can include a system of electronic components and logic components (e.g., logic configured to execute instructions, such that a group of executable instructions of an algorithm, for example, and, thus, is a component of a circuit). According to some embodiments, the term “module” can refer, for example, to an algorithm or a portion thereof, and/or logic implemented in either hardware circuitry or software, or a combination thereof (i.e., a module can be implemented as a circuit). In some embodiments, algorithms and/or the memory in which the algorithms are stored are “components” of a circuit. Thus, the term “circuit” can also refer, for example, to a system of components, including algorithms. These can be varied and are not limited to the examples or descriptions provided.
Although the foregoing examples have been described in some detail for purposes of clarity of understanding, the above-described inventive techniques are not limited to the details provided. There are many alternative ways of implementing the above-described invention techniques. The disclosed examples are illustrative and not restrictive.
This application claims the benefit of U.S. Provisional Patent Application No. 62/016,551, filed Jun. 24, 2014, which is herein incorporated by reference for all purposes.
