Household healthy diet recommendation system

Abstract

The invention discloses a household healthy diet recommendation system. The system comprises a data processing module, a management module, a recommendation generation module, a taboo substitution module and a situation adaptation module. The data processing module collects and stores health parameters of family members; the management module generates a real-time inventory signal; the recommendation generation module receives the nutrition demand signal and the real-time inventory signal, and generates an initial recommendation menu in combination with a preset menu database; the taboo substitution module performs substitution analysis on taboo food materials in the initial recommended menu according to a preset diet taboo rule; and the situation adaptation module is connected to the external environment sensor and the user behavior monitoring equipment. According to the healthy diet recommendation system based on the family, the problem of collaborative recommendation of different nutritional requirements and real-time scenes of multiple family members can be solved.

Description

Technical Field

[0001] The present invention relates to the interdisciplinary technical field of smart healthy homes and artificial intelligence recommendation systems, the field of wearable health monitoring devices, and particularly to a healthy diet recommendation system for home use. Background Art

[0002] Current healthy diet recommendation technologies are primarily targeted at individual users and struggle to adapt to the needs of multi-family settings. Traditional systems, such as those based on personal health data, can only generate recommendations based on a single user's physiological indicators. When family members have conflicting nutritional needs—for example, a child's development requires a high-calcium diet while the elderly need to control their cholesterol intake—the system is unable to coordinate and optimize the overall menu, forcing users to manually adjust recommendations, significantly reducing efficiency. Regarding ingredient management, existing technologies rely on manual input of inventory information and lack deep integration with smart kitchen devices. When recommended recipes don't match actual inventory, approximately 30% of households abandon the system due to frequent purchase adjustments. The lack of dynamic adaptability is also a significant drawback: mainstream systems use static nutritional models and lack real-time activity and sleep data collected by wearable devices or temperature and humidity information collected by environmental sensors. These systems are unable to respond to sudden health changes (such as a cold requiring vitamin C supplements) or shifting dietary needs due to seasonal changes.

[0003] Addressing dietary restrictions also has limitations. Existing solutions often rely on simple filtering mechanisms to directly exclude allergenic or religiously prohibited ingredients, lacking intelligent strategies based on nutritionally equivalent substitutions. This mechanized approach can easily lead to key nutrient deficiencies, and international studies have shown that this leads to high rates of dietary imbalance in households. Summary of the Invention

[0004] In view of the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a family-based healthy diet recommendation system to solve the problem of differentiated nutritional needs of multiple family members and real-time scenario collaborative recommendation. The present invention integrates the health parameters of family members through a data processing module and uses a multi-objective optimization algorithm to generate a collaborative nutritional demand signal; the management module links the kitchen monitoring equipment to obtain real-time inventory data; the recommendation generation module outputs the initial recipe based on the above signal; the taboo substitution module automatically replaces conflicting ingredients based on the knowledge graph; the context adaptation module dynamically modifies the recipe based on the environment and user behavior data; these four modules use a closed-loop iterative mechanism to ultimately output a family diet plan that meets nutritional balance, inventory matching, taboo avoidance, and scenario adaptation.

[0005] The present invention provides a family-based healthy diet recommendation system, comprising: The data processing module collects and stores the health parameters of family members and generates nutritional demand signals based on a multi-objective optimization algorithm; Management module: The management module connects to the kitchen inventory monitoring equipment to obtain food type and shelf life data and generate real-time inventory signals; The recommendation generation module receives the nutritional demand signal and the real-time inventory signal, and generates the initial recommended recipe based on the preset recipe database. The taboo substitution module performs substitution analysis on the taboo ingredients in the initial recommended recipe according to the preset dietary taboo rules, generates a substitution instruction signal and feeds it back to the recommendation generation module to output the final recipe; The context adaptation module is connected to external environmental sensors and user behavior monitoring equipment to generate dynamic adjustment signals and transmit them to the recommendation generation module, triggering the correction of recipe calories and nutritional content based on real-time scenarios; Among them, the recommendation generation module, the taboo replacement engine, and the situational adaptation module form a closed-loop iteration until the final recipe that meets nutritional needs, inventory status, and dynamic scenario constraints is output.

[0006] In one embodiment of the present invention, the health parameters collected in the data processing module include the age, gender, basal metabolic rate, chronic disease history and exercise habit data of family members. The multi-objective optimization algorithm generates differentiated nutrition allocation signals for different members by establishing a nutrition demand association matrix among family members. When a conflict of special nutrition demands among family members is detected, the cross-member nutrition compensation mechanism is automatically triggered to generate a coordinated nutrition demand signal, and the signal is transmitted to the recommendation generation module to achieve overall nutritional balance for the family.

[0007] In one embodiment of the present invention, the management module analyzes the food images collected by the kitchen inventory monitoring equipment through the image recognition unit, identifies the type of food and records the storage time; when it is detected that the shelf life of the food is approaching the threshold, it generates an inventory warning signal, combines the preset food consumption rate model to predict the inventory gap in the next N days, generates a real-time inventory signal containing a warning mark and transmits it to the recommendation generation module, driving the system to give priority to recommending recipe plans that consume food that is nearing its expiration date.

[0008] In one embodiment of the present invention, after receiving the nutritional requirement signal and the real-time inventory signal, the recommendation generation module first screens a set of candidate recipes from the recipe database based on the ingredient matching degree, and then performs multiple rounds of iterative optimization on the candidate recipes through a genetic algorithm; during each iteration, the ingredient combination is adjusted according to the alternative instruction signal feedback from the taboo substitution module, and an initial recommended recipe that meets the nutritional constraints and has the highest inventory matching degree is output.

[0009] In one embodiment of the present invention, the taboo substitution module has a built-in food substitution knowledge graph, which contains the physical and chemical properties, taste characteristics and nutritional composition of the food; when it is detected that there are ingredients in the initial recommended recipe that conflict with the preset dietary taboo rules, the knowledge graph is searched for alternative ingredients based on semantic similarity, and an alternative instruction signal including an alternative path and a nutritional compensation plan is generated and fed back to the recommendation generation module.

[0010] In one embodiment of the present invention, the context adaptation module obtains real-time physiological indicators of family members through user behavior monitoring devices, including heart rate variability, sleep duration and step count data; obtains temperature, humidity and seasonal information through environmental sensors; and when it is detected that physiological indicators deviate from the health baseline or environmental parameters suddenly change, it generates dynamic adjustment signals for calorie intake, vitamin ratio and water supplementation needs, triggering the recommendation generation module to make real-time corrections to the nutritional components of the recipe.

[0011] In one embodiment of the present invention, the recommendation generation module performs the following operations during the closed-loop iteration process: after receiving the replacement instruction signal fed back by the taboo replacement module, it recalculates the nutritional matching degree of the recipe, and triggers a new round of optimization if the nutritional deviation exceeds the tolerance threshold; at the same time, it receives the dynamic adjustment signal of the context adaptation module to perform calorie compensation calculation, and terminates the iteration and outputs the final recipe when and only when the recipe simultaneously meets the nutritional requirement signal constraints, real-time inventory signal availability and dynamic adjustment signal adaptability.

[0012] In one embodiment of the present invention, the management module is further connected to the local supermarket price database, and generates a periodic shopping list based on the food shortage data in the real-time inventory signal and combined with historical consumption records; the list divides the purchasing priorities by nutritional category, and marks the cost-effective alternative food options of the season, and guides users to optimize their purchasing decisions through a visual interface output.

[0013] In one embodiment of the present invention, a method for constructing a knowledge graph for food substitution includes: collecting food substitution cases from professional nutrition literature to establish an initial relationship network, and continuously optimizing the weights of substitution paths through user feedback data; when the substitution instruction signal is executed, automatically recording the user's satisfaction score for the substitution recipe and reversely updating the association strength parameters of the knowledge graph.

[0014] In one embodiment of the present invention, the situational adaptation module is provided with an emergency scenario response mechanism: when acute abnormal health indicators are detected in family members, a high-priority dynamic adjustment signal is immediately generated, forcing the recommendation generation module to increase the density of specific nutrients during the iteration process; at the same time, a dietary intervention reminder is sent to the user terminal until the mandatory constraints are lifted after the health indicators return to the normal range.

[0015] The present invention provides a healthy diet recommendation system for family use. The present invention integrates the health parameters of family members through a data processing module and uses a multi-objective optimization algorithm to generate a collaborative nutritional demand signal; the management module links the kitchen monitoring equipment to obtain real-time inventory data; the recommendation generation module outputs an initial recipe based on the above signal; the taboo substitution module automatically replaces conflicting ingredients based on the knowledge graph; the situation adaptation module dynamically modifies the recipe according to the environment and user behavior data; the four modules use a closed-loop iterative mechanism to ultimately output a family diet plan that meets nutritional balance, inventory matching, taboo avoidance and scenario adaptation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a system architecture diagram for a family-based healthy diet recommendation system; Figure 2 A schematic diagram showing the workflow of a healthy diet recommendation system for family use. DETAILED DESCRIPTION

[0018] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0019] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0020] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0021] See Figure 1 , shown is a family-based healthy diet recommendation system of the present invention, comprising a data processing module, a management module, a recommendation generation module, a taboo substitution module, and a context adaptation module. The data processing module collects and stores the health parameters of family members and generates a nutritional requirement signal based on a multi-objective optimization algorithm; the management module connects to the kitchen inventory monitoring device to obtain food type and shelf life data and generates a real-time inventory signal; the recommendation generation module receives the nutritional requirement signal and the real-time inventory signal and generates an initial recommended recipe in combination with a preset recipe database; the taboo substitution module performs a substitution analysis on the taboo ingredients in the initial recommended recipe according to the preset dietary taboo rules, generates a substitution instruction signal and feeds it back to the recommendation generation module to output the final recipe; the context adaptation module connects to the external environment sensor and user behavior monitoring device, generates a dynamic adjustment signal and transmits it to the recommendation generation module, triggering the recipe calorie and nutrient content correction based on the real-time scenario; wherein, the recommendation generation module forms a closed loop iteration with the taboo substitution engine and the context adaptation module until the final recipe that meets the nutritional requirements, inventory status and dynamic scenario constraints is output.

[0022] Figure 1As shown in the figure, the data processing module serves as the input of the system and collects structured health parameters of family members through the user interface or IoT devices, including age, gender, basal metabolic rate, chronic disease records and exercise habits data; the module has a built-in multi-objective optimization algorithm engine, which converts individual needs into family collaborative objective functions by establishing a nutritional demand association matrix for family members, and finally outputs a quantitative nutritional demand signal - this signal contains the daily total demand range of macronutrients such as protein, fat, and carbohydrates, as well as the member distribution weights of micronutrients such as calcium, iron, and vitamins; the management module connects to kitchen smart devices (such as refrigerator image sensors and electronic scales) through a data interface to obtain food images and weight data in real time, analyzes the food types through the image recognition unit and associates them with the local food database to obtain the standard shelf life; by comparing the food entry timestamp with the current time, the remaining shelf life percentage is calculated. When it is detected that the remaining shelf life of a certain food is lower than the set threshold, the early warning mechanism is activated to generate a real-time inventory signal with a priority label - this signal contains a list of available ingredients, identification of ingredients that are about to expire, and predicted inventory gaps.The recommendation generation module receives the above-mentioned nutritional demand signals and real-time inventory signals, and first performs a primary screening in the preset recipe database: the candidate recipes whose nutritional data and nutritional demand signals match higher than the benchmark value are included in the set, and then a secondary filtering is performed based on the availability of ingredients in the real-time inventory signal; the filtered candidate set is optimized using a genetic algorithm for multiple rounds, and each iteration calculates a comprehensive score including nutritional balance, inventory matching, and cooking complexity, and outputs the initial recommended recipe; after receiving the initial recommended recipe, the taboo substitution module calls the preset dietary taboo rule library (including allergens, religious taboos, personal preferences and other constraints) for conflict detection; when conflicting ingredients are identified, the knowledge graph-based substitution engine is activated: the graph stores three-dimensional indicators of the similarity of physical and chemical properties between ingredients (such as protein content difference ≤15%), taste characteristic correlation (trained through sensory evaluation data), and cooking function substitutability (such as leavening agent substitution relationship), retrieves the best substitution path based on weighted similarity, and generates a substitution instruction signal ——The signal includes the replaced ingredients, recommended replacement ingredients, nutritional compensation coefficient and cooking process adjustment suggestions; the situational adaptation module accesses the smart wearable device and environmental sensor network through the Bluetooth / WiFi protocol, and analyzes the user's heart rate variability, sleep stage data, daily step count and ambient temperature and humidity in real time; when it detects that the physiological indicators deviate from the healthy baseline (such as the heart rate is 20% higher than the resting value for 2 consecutive hours) or the environment changes suddenly (such as the temperature drops by 5°C), the dynamic nutrition correction model is triggered to generate a dynamic adjustment signal - this signal includes the calorie increase or decrease ratio, vitamin supplement type and water supplementation recommended value; the above modules form a closed-loop workflow: after the recommendation generation module transmits the initial recommended recipe to the taboo substitution module, it receives the substitution instruction signal to reconstruct the recipe; the reconstructed recipe is then transmitted to the situational adaptation module for real-time correction; if the revised recipe is determined by the nutritional balance verification engine to deviate from the nutritional demand signal constraint, it returns to the recommendation generation module to start a new round of optimization until all constraints are synchronously met and the final recipe is output to the user terminal.

[0023] Furthermore, the types of health parameters are expanded to cover four dimensions: 1) basic physiological data (age, gender, height and weight, body fat percentage), 2) health status data (chronic disease records entered by users such as diabetes, hypertension and clinical test indicators such as fasting blood glucose values), 3) behavioral habit data (daily exercise intensity and physical exertion level of work collected through questionnaires), 4) special period markers (such as pregnant women markers, postoperative recovery period markers); the multi-objective optimization algorithm operation process includes three stages: the first stage is to build an independent nutrition model for members, calculate the individual's daily calorie needs based on the basal metabolic rate, and set nutritional restriction conditions based on chronic disease records (such as limiting the proportion of carbohydrate intake for diabetic patients); the second stage is to establish a family collaborative association matrix to define the compensation relationship between conflicting nutrients (for example, when children's calcium needs are lower than the elderly's calcium needs, the relationship between conflicting nutrients and ... In the third stage, a Pareto optimal solution search algorithm is used to maximize the family's overall nutritional balance index while meeting the nutritional bottom line of all members, and finally output a nutritional demand signal with member allocation weights. The cross-member nutritional compensation mechanism is the core innovation. When the algorithm detects that there are irreconcilable nutritional conflicts between two or more members (such as the conflict between the folic acid needs of pregnant women and those who avoid spinach), a three-level processing flow is initiated: 1) looking for alternative sources of similar nutrients in ingredients, 2) compensating for the gap through nutritional supplements (adding vitamin tablets recommendations in the recipe notes column), and 3) triggering staggered time allocation. The coordinated nutritional demand signal output by this mechanism contains the conflict solution code for direct call by the recommendation generation module.

[0024] In one embodiment of the present invention, the implementation scheme of the inventory monitoring and early warning function of the management module specifically includes: The technical architecture of the image recognition unit consists of three sub-modules: 1) Image pre-processing sub-module, which performs denoising, brightness correction and multi-angle stitching on the original images collected by the kitchen monitoring equipment; 2) Feature extraction sub-module, which uses convolutional neural networks to identify the morphological features of food ingredients (such as the granular crown of broccoli and the texture of salmon), and combines OCR technology to read the packaging date label; 3) Semantic association sub-module, which matches the recognition results with the local food database (for example, mapping "round red fruit entity" to tomato), and associates the standard nutritional data and typical shelf life of the food ingredient; the shelf life warning logic adopts a dynamic threshold mechanism: for perishable food ingredients such as poultry and livestock meat, a yellow warning is triggered when the remaining shelf life is set to ≤30%; for storable food ingredients such as dry goods and seasonings, a blue warning is triggered when the remaining shelf life is set to ≤10%; after the warning signal is generated The system automatically performs three operations: 1) marking warning ingredients and the number of days they can be safely consumed in real-time inventory signals; 2) predicting inventory gaps in the next three days based on historical consumption rates (for example, predicting the milk gap based on the average consumption of the past two weeks); 3) generating a "priority consumption list" and embedding it into the inventory signal to transmit to the recommendation generation module; the inventory-driven recipe optimization principle is reflected in the following: after the recommendation generation module parses the real-time inventory signal, it performs weighted sorting on the initial recipe set - recipes containing warning ingredients receive the highest priority weight (+50%), recipes containing regular inventory ingredients receive the basic weight, and the weight of recipes containing ingredients that need to be purchased is reduced to below the baseline value; at the same time, an inventory turnover rate optimization algorithm is introduced to ensure that high-warning level ingredients are recommended for consumption within 48 hours. It has been tested that this mechanism can reduce the household food waste rate by 27%.

[0025] like Figure 1 As shown in Figure 2, the optimization decision-making mechanism of the recommendation generation module is further refined into a three-level processing flow: The primary screening stage is achieved through a dual-channel matching engine: the first channel calculates the similarity between the nutrient target values ​​in the nutritional requirement signal (such as the daily protein requirement range) and the nutritional labels in the preset recipe database, and only retains candidate recipes with a matching degree higher than the system-set threshold; the second channel parses the ingredient availability list in the real-time inventory signal, eliminates recipes that contain out-of-stock ingredients or the proportion of ingredients that need to be purchased exceeds the tolerance upper limit, and generates a preliminary candidate set. The genetic algorithm optimization stage uses a chromosome encoding scheme: candidate recipes are deconstructed into gene sequences (main ingredient gene segment + auxiliary ingredient gene segment + cooking method gene segment), and after initializing the population, selection, crossover, and mutation operations are performed. The fitness function comprehensively calculates three indicators: 1) nutritional balance - based on the Euclidean distance between the candidate recipe's nutritional data and the nutritional demand signal, 2) inventory matching - weighted calculation based on the ingredient warning level in the real-time inventory signal (the weight coefficient of ingredients nearing expiration is increased to 1.8 times that of regular ingredients), and 3) cooking cost - correlating the recipe preparation time with the kitchenware complexity parameter. After each round of iteration, the top 20% of individuals in fitness are retained. When the improvement rate of the optimal solution for three consecutive generations is less than 0.5%, the optimization is terminated and the initial recommended recipe is output. The substitution-driven adjustment phase is initiated after receiving the substitution instruction signal fed back by the taboo substitution module: the substitution path indication (such as the "pork→shiitake mushroom" substitution pair) and the nutritional compensation coefficient (such as protein compensation +0.2g / 100g) in the parse signal are used to replace ingredients in the initial recommended recipe and recalculate the nutritional data; if the nutritional deviation after replacement exceeds the fault tolerance threshold, local re-optimization is triggered - while maintaining the original cooking method gene segment unchanged, only the auxiliary ingredient gene segment is mutated to fine-tune the taste matching, and finally a reconstructed recipe is generated and transmitted to the context adaptation module.

[0026] like Figure 1As shown, the knowledge graph architecture of the taboo substitution module consists of three elements: entity nodes, relationship edges, and dynamic weight parameters. Entity nodes cover all substitutable objects in the ingredient library, each storing standardized nutritional data and sensory feature vectors. Relationship edges define three types of substitution logic: physical and chemical substitution relationships are established based on a nutrient similarity matrix; taste substitution relationships are generated by training a flavor vector space model using a sensory evaluation database; and functional substitution relationships record the interchangeability of ingredients in cooking scenarios. The initial values ​​of the weight parameters are derived from authoritative nutrition literature and are updated in real time. The alternative decision engine operates in a four-step process: the conflict detection unit transmits the initial recommended recipe to the rule matcher, which compares it with a preset dietary taboo rule library and outputs the conflicting ingredient identifier and taboo type code. The alternative path searcher uses the conflicting ingredient as the search starting point and performs a breadth-first search along three types of relationship edges in the knowledge graph, returning a set of candidate alternatives. The multidimensional scorer calculates a comprehensive score for the candidate solutions, using the Euclidean distance algorithm for physical and chemical matching, a pre-trained flavor neural network model for taste similarity, and a cooking scenario matching table for functional equivalence. When the nutritional deviation between the optimal alternative and the original ingredient exceeds a tolerance, the compensation generator automatically adds a nutritional balance strategy. The resulting signal is packaged into an alternative instruction signal containing the alternative path, compensation plan, and cooking adjustment suggestions, which is then fed back to the recommendation generation module after verification. The graph self-optimization mechanism is implemented through a user feedback loop: the system collects user satisfaction ratings of alternative recipes and manual modification records. Positive feedback increases the weight coefficient of the corresponding relationship edge, while negative feedback triggers the relationship edge re-evaluation process. When the weight of a specific edge falls below the expiration threshold, the alternative path is automatically frozen.

[0027] Furthermore, the dynamic adjustment mechanism of the contextual adaptation module is implemented through a bimodal data channel. The physiological indicator response channel accesses the data stream of the smart wearable device, including exercise intensity data collected by the triaxial accelerometer, heart rate variability parameters collected by the optical heart rate sensor, and metabolic state indicators collected by the surface temperature sensor. When exercise intensity remains below the historical average by 25% for more than six hours, a calorie reduction coefficient signal is generated. When the heart rate variability SDNN value is below 50 milliseconds for two consecutive hours, a stress-responsive nutrition plan with an increase in B vitamins is triggered. When the deep sleep rate decreases by 20% compared to the baseline value, a tryptophan supplementation instruction is generated and transmitted to the recommendation generation module. The environmental parameter response channel integrates a multi-source sensor network: temperature and humidity sensors monitor the indoor and outdoor temperature gradient, air quality sensors capture PM2.5 and pollen concentrations, and the seasonal clock module provides solar term characteristics corresponding to the geographic location. When a temperature drop of more than five degrees Celsius is detected, a high-calorie density menu generation instruction is activated. When the pollen concentration exceeds the allergy threshold, allergenic ingredients are automatically blocked and antihistamine nutrients are recommended. The signal fusion unit uses a weighted decision matrix to process dual-channel instructions. The priority weight of the physiological indicator channel is set to 0.7, and the weight of the environmental channel is 0.3. When the dual-channel instructions conflict, the high-priority instruction is executed and a compensation note is added to the dynamic adjustment signal. For example, when high exercise demand conflicts with high temperature environment, the calorie increase instruction is executed and the note of "post-meal electrolyte supplementation" is added. The final dynamic adjustment signal is transmitted to the recommendation generation module to trigger the recipe correction.

[0028] like Figure 1As shown, the closed-loop iteration mechanism implements process control through a five-order state machine. State 0 is the initialization phase: After the recommendation generation module completes the initial recipe generation, it sends a test request signal to the taboo substitution module and enters the pending state. State 1 performs taboo substitution detection: The taboo substitution module completes the recipe scan within 200 milliseconds. If there are conflicting ingredients defined by the rule base, it generates a substitution instruction signal and jumps to State 2; otherwise, it jumps directly to State 3. State 2 performs substitution reconstruction: The recommendation generation module parses the substitution instruction signal and executes the recipe update. After the update, it is tested by the nutrition verification engine. If the nutrient deviation does not exceed 8%, it returns to State 1 for re-verification. If the deviation exceeds the standard, the local optimization sub-process is initiated: the main ingredient gene segment is fixed, and the auxiliary ingredient gene segment is randomly selected to insert a substitution ingredient, and the optimization cycle is repeated until the nutritional constraints are met. State 3 performs context adaptation detection: The context adaptation module compares the current environmental / physiological data with the health baseline model. If correction is required, it generates a dynamic adjustment signal and jumps to State 4; otherwise, it jumps directly to State 5. State 4: Dynamic Correction: The recommendation generation module adjusts the nutrient ratio of the recipe based on the dynamic adjustment signal. If the correction causes the inventory matching degree to fall below 60%, the inventory rematching sub-process is activated, searching for sufficient items in the same category for replacement. State 5: Execution Termination Verification: The system simultaneously initiates a four-fold verification check. The nutrition verification unit detects whether the final recipe matches the nutritional requirement signal. The inventory verification unit confirms that all required ingredients are available in the real-time inventory signal list. The taboo verification unit performs a secondary rule scan. The scenario verification unit verifies the execution status of the dynamic adjustment instruction. If any verification fails, the error code is recorded and the process is restarted by returning to state 0. If all pass, the final recipe is output to the user terminal and a timestamped execution log is generated.

[0029] The present invention provides a healthy diet recommendation system for families. The system integrates the health parameters of family members through a data processing module and generates a collaborative nutritional demand signal using a multi-objective optimization algorithm. The management module links the kitchen monitoring equipment to obtain real-time inventory data. The recommendation generation module outputs an initial recipe based on the above signal. The taboo substitution module automatically replaces conflicting ingredients based on the knowledge graph. The situation adaptation module dynamically modifies the recipe according to the environment and user behavior data. The four modules use a closed-loop iterative mechanism to ultimately output a family diet plan that meets nutritional balance, inventory matching, taboo avoidance, and scenario adaptation.

[0030] Therefore, the present invention provides a family-based healthy diet recommendation system that can solve the problem of differentiated nutritional needs of multiple family members and collaborative recommendations in real-time scenarios.

[0031] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A healthy diet recommendation system for families, characterized in that: include: A data processing module, which collects and stores health parameters of family members and generates nutritional demand signals based on a multi-objective optimization algorithm; A management module, which is connected to the kitchen inventory monitoring equipment to obtain food type and shelf life data and generate real-time inventory signals; a recommendation generation module, the recommendation generation module receiving the nutritional requirement signal and the real-time inventory signal and generating an initial recommended recipe in combination with a preset recipe database; a taboo substitution module, which performs substitution analysis on taboo ingredients in the initial recommended recipe according to preset dietary taboo rules, generates a substitution instruction signal and feeds it back to the recommendation generation module to output a final recipe; A context adaptation module, which connects to external environmental sensors and user behavior monitoring devices to generate dynamic adjustment signals and transmit them to the recommendation generation module, triggering the correction of recipe calories and nutritional content based on real-time scenarios; The recommendation generation module, the taboo replacement engine, and the context adaptation module form a closed-loop iteration until the final recipe that meets nutritional requirements, inventory status, and dynamic scenario constraints is output.

2. A family-based healthy diet recommendation system according to claim 1, characterized in that: The health parameters collected in the data processing module include the age, gender, basal metabolic rate, chronic disease history and exercise habit data of family members. The multi-objective optimization algorithm generates differentiated nutrition allocation signals for different members by establishing a nutrition demand association matrix among family members. When a conflict of special nutrition needs among family members is detected, the cross-member nutrition compensation mechanism is automatically triggered to generate a coordinated nutrition demand signal, and the signal is transmitted to the recommendation generation module to achieve overall nutritional balance for the family.

3. A family-based healthy diet recommendation system according to claim 1, characterized in that: The management module uses an image recognition unit to analyze food images collected by the kitchen inventory monitoring equipment, identify the type of food and record the storage time; when it is detected that the shelf life of the food is approaching the threshold, it generates an inventory warning signal, combines the preset food consumption rate model to predict the inventory gap in the next N days, generates a real-time inventory signal containing a warning mark and transmits it to the recommendation generation module, driving the system to prioritize recommending recipe solutions that consume food that is nearing its expiration date.

4. A family-based healthy diet recommendation system according to claim 1, characterized in that: After receiving the nutritional requirement signal and the real-time inventory signal, the recommendation generation module first screens a set of candidate recipes from the recipe database based on the ingredient matching degree, and then performs multiple rounds of iterative optimization on the candidate recipes using a genetic algorithm; During each iteration, the ingredient combination is adjusted according to the alternative instruction signal fed back by the taboo substitution module, and the initial recommended recipe that meets the nutritional constraints and has the highest inventory matching degree is output.

5. A family-based healthy diet recommendation system according to claim 1, characterized in that: The taboo substitution module has a built-in food substitution knowledge graph, which contains the relationship between the physical and chemical properties, taste characteristics and nutritional composition of the food. When it is detected that the initial recommended recipe contains ingredients that conflict with the preset dietary taboo rules, the knowledge graph is searched for alternative ingredients based on semantic similarity, and an alternative instruction signal containing an alternative path and a nutritional compensation plan is generated and fed back to the recommendation generation module.

6. A family-based healthy diet recommendation system according to claim 1, characterized in that: The context adaptation module obtains real-time physiological indicators of family members through user behavior monitoring devices, including heart rate variability, sleep duration and step count data; obtains temperature, humidity and seasonal information through environmental sensors; and when it monitors that physiological indicators deviate from the healthy baseline or environmental parameters suddenly change, it generates dynamic adjustment signals for calorie intake, vitamin ratio and water replenishment needs, triggering the recommendation generation module to make real-time corrections to the nutritional components of the recipe.

7. A family-based healthy diet recommendation system according to claim 1, characterized in that: During the closed-loop iteration process, the recommendation generation module performs the following operations: after receiving the replacement instruction signal fed back by the taboo replacement module, the nutritional matching degree of the recipe is recalculated, and if the nutritional deviation exceeds the tolerance threshold, a new round of optimization is triggered; at the same time, the dynamic adjustment signal of the context adaptation module is received to perform calorie compensation calculation, and the iteration is terminated and the final recipe is output when and only when the recipe simultaneously meets the nutritional requirement signal constraints, the real-time inventory signal availability and the adaptability of the dynamic adjustment signal.

8. The family-based healthy diet recommendation system according to claim 1, characterized in that: The management module is further connected to the local supermarket price database, and generates a periodic shopping list based on the food shortage data in the real-time inventory signal and historical consumption records; the list divides the purchasing priorities by nutritional category, and marks the cost-effective alternative food options of the season, and outputs guidance to users to optimize purchasing decisions through a visual interface.

9. The family-based healthy diet recommendation system according to claim 5, characterized in that: The method for constructing the food substitution knowledge graph includes: collecting food substitution cases from professional nutrition literature to establish an initial relationship network, and continuously optimizing the substitution path weights through user feedback data; when the substitution instruction signal is executed, automatically recording the user's satisfaction score for the substitution recipe and reversely updating the association strength parameters of the knowledge graph.

10. The family-based healthy diet recommendation system according to claim 1, characterized in that: The situational adaptation module is equipped with an emergency scenario response mechanism: when acute abnormal health indicators of family members are monitored, a high-priority dynamic adjustment signal is immediately generated, forcing the recommendation generation module to increase nutrient density during the iteration process; at the same time, a dietary intervention reminder is sent to the user terminal until the mandatory constraints are lifted after the health indicators return to the normal range.

Images