Towards diet management with automatic reasoning and persuasive - PowerPoint PPT Presentation

Towards diet management with automatic reasoning and persuasive natural language generation Luca Anselma and Alessandro Mazzei Dipartimento di Informatica, Università di Torino, Italy

Nutrition • The diet is an important factor influencing diseases • Necessity to encourage the world’s population toward a healthy diet (FAO) • Many states specialized general guidelines by adopting strategies related to their food history • in the literature systems of Dietary Reference Values (DRVs) recommended to be followed for significant amounts of time • In a diet it is necessary to consider parameters such as the total energy requirements and the specific required amount of nutrients and macronutrients such as proteins, carbohydrates and lipids

An example • John, a 40-year-old male who is 1.80 m tall and weighs 71.3 kg has an estimated basal metabolic rate of 1690 kcal/day (Schofield equation) • Taking into account his physical activity (e.g., a sedentary lifestyle) he has a total energy requirement of 2450 kcal/day • Moreover, it is recommended that such energy intake is provided by: • 260 kcal/day of proteins, • 735 kcal/day of lipids and • 1455 kcal/day of carbohydrates • In this section we focus on the total energy requirement; the macronutrients can be dealt with separately in the same way

• The main factors to be accounted for are 1. the diet that the user intends to follow, 2. the food that s/he has eaten in the last days, and 3. the nutritional values of the dishes and their specific recipes • Often a user is not able to carefully follow a diet for a number of reasons • Important to support the user in devising the consequences and to dynamically adapt the rest of the so that the global Dietary Reference Values could nevertheless be reached

The problem User model In the everyday activity (sex, age, weight, there may be deviations lifestyle) from the ideal diet Diet described as: • total energy intake What are the (kcal) consequences of such • carbohydrates (kcal) deviations on the diet for • proteins (kcal) the rest of the week? • lipids (kcal) for a significant amount of time

The MADiMAN project Artificial Intelligence for diet management • NLP for recipe analysis • Automate Reasoning about diet and recipes • Persuasive multimedia NLGeneration Collaboration with hospital dietitians (“Molinette” hospital of Torino, third largest hospital in Italy)

System architecture 3. N LU /I E Servi ce 2. D i etM anager 1. APP Servi ce R eci pe 4. R easoner Servi ce 5. N LG Servi ce D B users D B reci pes

The MADiMAN project • The system we propose is useful for a) evaluating the compatibility of a dish with a diet allowing small and occasional episodes of diet disobedience, b) determining what are the consequences of eating a specific dish on the rest of the diet, c) showing such consequences to the user thus empowering her/him and, moreover, d) motivating the user in following the diet by persuading her/him to minimize the acts of disobedience.

The MADiMAN project • The system could be commercially attractive at least in: • medical context, where users (e.g. patients affected by essential obesity) are strongly motivated to strictly follow a diet and need tools that help them • (healthy) restaurant-chains context, where the effort of deploying the system can be rewarded by an increase in customer retention.

The MADiMAN project Artificial Intelligence for diet management • NLP for recipe analysis • Automate Reasoning about diet and recipes • Persuasive multimedia NLGeneration Cloud Architecture

Architecture of the system 3. N LU /I E Servi ce 2. D i etM anager 1. APP Servi ce R eci pe 4. R easoner Servi ce 5. N LG Servi ce D B users D B reci pes

STP • Simple Temporal Problem [Dechter et al. 91] • Conjunction of bounds on differences (STP constraints) Represents the conjunction of bounds on differences: min A ≤ End(A) – Start(A) ≤ max A … min Z ≤ End(S) – Start(A) ≤ max Z

STP • The constraint propagation is performed by Floyd-Warshall's all-pairs shortest paths, O(n 3 ) • It checks the consistency and also gives the minimal network , i.e., the equivalent network with the strictest implied constraints Represents min' A ≤ End(A) – Start(A) ≤ max' A … min' Z ≤ End(S) – Start(A) ≤ max' Z

Reasoning about diet • We adopt STP and represent Dietary Reference Values as STP constraints and energy (kcal) instead of time • Example: John’s total energy intake must be 2450 kcal/day for a week

Reasoning about diet • To allow users to make small deviations attaining at the same time to the diet: • Over the longest periods of time (e.g., weeks) we impose the “ideal” values • Over the shortest periods (e.g., meals or days) we allow some deviations • For example, as long as the final weekly goal is reachable, John is allowed to deviate from the value of ±10% a day [2450·7,2450·7] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [0,0] [0,0] [0,0] [0,0] [0,0] [0,0] Sunday Thursday Friday Monday Tuesday Wednesday Saturday (for the sake of conciseness only days and not meals are represented here)

Reasoning about diet • Let us assume that John ate 2690 kcal on Sunday, Monday and Tuesday • We add to the STP such new information and propagate the constraints [2450·7,2450·7] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [2205,2695] [0,0] [0,0] [0,0] [0,0] [0,0] [0,0] Sunday Monday Tuesday Wednesday Thursday Friday Saturday John ate 2690 kcal on Sunday, Monday and Tuesday [2450·7,2450·7] [2690,2690] [2690,2690] [2205,2695] [2205,2695] [2690,2690] [2205,2695] [2205,2695] [0,0] [0,0] [0,0] [0,0] [0,0] [0,0] Sunday Tuesday Wednesday Thursday Friday Saturday Monday Constraint propagation [2270·4,2270·4] [2205,2465] [2690,2690] [2690,2690] [2690,2690] [2205,2465] [2205,2465] [2205,2465] [0,0] [0,0] [0,0] [0,0] [0,0] [0,0] Sunday Thursday Friday Saturday Monday Tuesday Wednesday

Reasoning about diet • Thus, John has to eat 2270 kcal/day for the rest of the week • For reaching such a goal he can assume between 2205 and 2465 kcal/day [2270·4,2270·4] [2690,2690] [2690,2690] [2690,2690] [2205,2465] [2205,2465] [2205,2465] [2205,2465] [0,0] [0,0] [0,0] [0,0] [0,0] [0,0] Sunday Monday Tuesday Wednesday Thursday Friday Saturday

Generating messages for the user • STP results must be interpreted to present to the user a meaningful feedback • When the user proposes a meal, we classify its macronutrients on the basis of the minimal network of the STP in two inconsistent cases: constraint from the • I.1: permanently inconsistent (i.e., minimal network inconsistent with the diet) • I.2: occasionally inconsistent (i.e., ideally consistent with the diet but inconsistent with the food already eaten) …

Generating messages for the user …and three consistent cases using max thresholds: not)balanced C.1 • C.1: consistent and not balanced IPER t 2 well) (IPO/IPER), C.2 balanced t 1 • C.2: consistent and well- perfectly) C.3 balanced balanced (IPO/IPER) and mean • C.3: consistent and perfectly perfectly) C.3 balanced balanced t 1 well) C.2 balanced t 2 IPO IPO/IPER indicate a lack/excess of not)balanced C.1 a macronutrient min

Generating messages for the user On the basis of the five cases, we generate a natural language message using a template-based NLG Notice that we use adverbs as little bit (poco), really (davvero) and emoticons to increase the communicative strength C D Message Template Translation IPO Questo piatto non va a ff atto bene, This dish is not good at all, I.1 contiene davvero pochissime proteine! it’s too poor in proteins! Ora non puoi mangiare questo piatto You cannot have this dish now perch´ e ` e poco proteico. Ma se domenica because it doesn’t provide enough proteins, I.2 IPO mangi un bel piatto di fagioli allora luned` ı but if you eat a nice dish of beans on Sunday, you can have it on Monday. potrai mangiarlo. C.1 IPO Va bene mangiare le patatine ma nei It’s OK to eat chips but in the next prossimi giorni dovrai mangiare pi` u proteine. days you’ll have to eat more proteins. Questo piatto va bene, ` e solo un po’ scarso This dish is OK, but it’s a bit poor di proteine. Nei prossimi giorni anche C.2 IPO in proteins. In the next days fagioli per` o! :) you’ll need beans too! :) Ottima scelta! Questo piatto ` e perfetto Great choice! This dish is perfect for C.3 - per la tua dieta :) your diet :)

Related works • Both academic studies (e.g., [Balintfy 1964, Iizuka et al. 2012]) and commercial apps related to nutrition (e.g. DailyBurn, Lose It!, MyNetDiary, A low GI Diet, Weight- Watchers) • Our dietary system presents two elements of novelty: 1) the use of automatic reasoning as a tool for verifying the compatibility of a specific recipe with a a. specific diet and for for determining the consequences of the choice of a b. specific dish and 2) the use of NLG techniques to produce the answer