Intelligent meal planning method and apparatus, electronic device, and storage medium
By constructing a joint scheduling model and combining individualized information of family members with food inventory information, the generated dietary planning scheme solves the problem of near-expiry food not being consumed in time in existing technologies, and achieves efficient utilization of food and reduction of waste.
Patent Information
- Application Number
- CN202611278119.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-21
- Publication Date
- 2026-11-10
AI Technical Summary
Existing smart meal planning solutions cannot effectively adapt to the individual needs of family members in real-world home settings, resulting in near-expiry ingredients being wasted due to not being consumed in time.
By acquiring individualized information about family members and food inventory information, a joint scheduling model is constructed. The scheduling objective is to consume food with remaining shelf life below a preset near-expiration threshold. Based on the constraints of available meal times and single-meal portion sizes, a meal planning scheme is generated to ensure that near-expiration food is consumed in a timely manner.
The generated meal plans are theoretically and practically feasible in terms of ingredients, reducing manual adjustments by users, increasing the adoption rate of plans, ensuring the timely consumption of near-expiry ingredients, and reducing food waste.
Smart Images

Figure CN123072631A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of smart kitchen technology, and in particular to smart meal planning methods, devices, electronic devices and storage media. Background Technology
[0002] With the continuous development of smart kitchen technology, family meal planning, as a key link connecting food management, dietary needs, and cooking execution, has become a research hotspot in this field. Currently, meal planning in the smart kitchen field is mainly divided into two categories: food management and meal recommendation technologies. Food management solutions record the entry time and shelf life of ingredients, and remind users when they are about to expire. Based on this, some meal recommendation solutions have begun to use the near-expiration information of ingredients to recommend recipes. For example, some solutions can obtain the near-expiration information of existing foods in the refrigerator and prioritize recommending recipes containing near-expiration foods; other solutions sort ingredients according to the remaining days of their shelf life to prompt users to prioritize using ingredients that are close to their expiration date; in addition, some solutions have proposed a food inventory system based on expiration date weighting, whose recipe recommendations can be based on inventory levels and the time when food expires or spoils.
[0003] However, in real-world home applications, the results of the aforementioned recommendations sometimes do not match the actual circumstances of family members. This necessitates users making numerous manual adjustments to the recommendations, impacting the user experience and the actual adoption rate of the solutions. Consequently, near-expiry ingredients are not consumed in time and go to waste. Therefore, improving the adaptability of dietary planning solutions to real-world home scenarios is a pressing technical problem that needs to be solved in this field. Summary of the Invention
[0004] To address the problems of existing technologies, this application provides an intelligent meal planning method, device, electronic device, and storage medium. The technical solution is as follows: On the one hand, an intelligent diet planning method is provided, the method comprising: Obtain individualized information for multiple family members; the individualized information includes at least information on each member's available meal times and the amount of food consumed per meal; Obtain food inventory information; the food inventory information includes at least the shelf life of each food item; Determine the remaining shelf life of each ingredient based on its stated shelf life; The scheduling target is to consume ingredients whose remaining shelf life is lower than a preset near-expiration threshold from the ingredient inventory information. A joint scheduling model is constructed based on the dining time information and single meal quantity information of the multiple members. Solve the joint scheduling model to generate a meal planning scheme; the meal planning scheme includes at least the food allocation scheme and dish scheme for each member during each meal period.
[0005] On the other hand, a smart meal planning device is provided, the device comprising: The individual information acquisition module is used to acquire individualized information of multiple family members; the individualized information includes at least the meal times and the amount of food consumed per meal for each member; The ingredient information acquisition module is used to acquire ingredient inventory information; the ingredient inventory information includes at least the shelf life of each ingredient. The shelf-life determination module is used to determine the remaining shelf life of each ingredient based on its stated shelf-life. The model building module is used to construct a joint scheduling model with the remaining shelf life of ingredients in the food inventory information below a preset near-expiration threshold as the scheduling target, and with the dining time information and single meal quantity information of the multiple members as the basic constraints. The model solving module is used to solve the joint scheduling model and generate a meal planning scheme; the meal planning scheme includes at least the food allocation scheme and dish scheme for each member during each meal period.
[0006] In one exemplary implementation, the individualized information further includes dietary target information for each member, and the food inventory information further includes the food category for each food item; the model building module includes: The additional constraint construction module is used to construct the joint scheduling model with the dietary target information of each member as additional constraints, so that when solving the joint scheduling model, the allocation of food categories that conflict with the dietary target information is restricted or the food category is excluded from the feasible allocation scheme.
[0007] In one exemplary embodiment, the apparatus further includes a scheduling priority determination module, which is used to determine the scheduling priority of each ingredient according to its remaining shelf life after determining the remaining shelf life of each ingredient, so that ingredients with shorter remaining shelf life are assigned higher scheduling priority in the joint scheduling model.
[0008] In one exemplary embodiment, the individualized information further includes dietary restrictions, health indicators, and dietary goals for each member; the food inventory information further includes the stock levels of each food ingredient; the model solving module includes: The quantity allocation module is used to allocate the quantity of each ingredient among the at least two members according to the single meal quantity information of each member when the dining time information of at least two members overlaps. The allocation priority determination module is used to determine the allocation priority of the insufficient ingredients among the members based on the dietary restrictions, health indicators and dietary goals of each member when the stock of any ingredient is insufficient to meet the consumption needs of at least two members at the same time. The ingredient allocation module is used to allocate the ingredient that is in short supply to each member according to the allocation priority among the members, and to supplement the remaining usage needs of each member with other ingredients in the inventory.
[0009] In one exemplary embodiment, the device further includes a cooking scheduling module for decomposing the dish plan in the meal planning scheme into cooking control commands and scheduling various smart kitchen appliances to perform cooking operations after outputting the meal planning scheme. The cooking scheduling module includes: The instruction decomposition module is used to decompose the dish plan in the diet plan into cooking control instructions and determine the smart kitchen appliances corresponding to each cooking control instruction. The device information acquisition module is used to acquire the device status information and available time period information of each smart kitchen appliance; The timing arrangement module is used to arrange the cooking timing of each smart kitchen appliance according to the device status information and the available time period information; The instruction sending module is used to send each cooking control instruction to the corresponding smart kitchen appliance at the corresponding timing node according to the cooking sequence, so that each smart kitchen appliance can perform cooking operations according to the corresponding cooking control instruction.
[0010] In one exemplary embodiment, the device further includes a feedback update module for updating individualized member information based on cooking execution feedback and user satisfaction information after each cooking control command is sent to the corresponding smart kitchen appliance at the corresponding timing node. The feedback update module includes: The feedback receiving module is used to receive the execution status information, energy consumption information and time information transmitted back by the smart kitchen appliance, and form cooking execution feedback; The completion rate generation module is used to generate the meal completion rate information of each member based on the cooking execution feedback. The satisfaction acquisition module is used to acquire user satisfaction information of each member regarding the dietary planning scheme; The information update module is used to update the individualized information of the corresponding member based on the dietary completion information and the user satisfaction information.
[0011] In one exemplary embodiment, the apparatus further includes a model reconstruction module, which is used to reconstruct the joint scheduling model in response to changes in the food inventory information or the individualized information of the multiple members.
[0012] On the other hand, an electronic device is provided, including a processor and a memory, wherein the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the intelligent meal planning method of any of the above aspects.
[0013] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the intelligent meal planning method as described above.
[0014] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the intelligent meal planning method of any of the above aspects.
[0015] This application's embodiments explicitly set the available meal times and individual meal quantities of family members as basic constraints, making the time availability and quantity limits for each member at specific times an insurmountable prerequisite for all subsequent decisions. The system targets the consumption of ingredients with remaining shelf lives below a preset near-expiration threshold, proactively driving the planning process based on "which ingredients most urgently need to be consumed." Furthermore, by constructing and solving a joint scheduling model, the above objectives and constraints are placed within a unified mathematical framework for joint scheduling. The resulting meal plan satisfies the allocation of ingredients and the arrangement of dishes for each member at each meal time, and the plan itself incorporates the proactive consumption of near-expiration ingredients. Therefore, the output meal plan is not only theoretically feasible at the ingredient level but also realistically feasible in a family setting, eliminating the need for manual adjustments by the user. This improves the adoption rate of the plan while ensuring that near-expiration ingredients are promptly incorporated into the actual implementation plan, effectively reducing food waste. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating an intelligent meal planning method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating the method for allocating ingredients among members during the model solving process provided in this application embodiment; Figure 3 This is a flowchart illustrating the method for executing a dietary plan after its generation, as provided in an embodiment of this application. Figure 4 This is a structural block diagram of an intelligent meal planning device provided in an embodiment of this application; Figure 5 This is a hardware structure block diagram of a computer device that runs an intelligent diet planning method, as provided in an embodiment of this application. Detailed Implementation
[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0020] It is understood that in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.
[0021] Please see Figure 1The diagram illustrates a flowchart of an intelligent dietary planning method provided in an embodiment of this application. It should be noted that while this specification provides method steps as shown in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive methods. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or product execution, the method can be executed sequentially according to the embodiments or accompanying drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown... Figure 1 As shown, the method may include: S101, obtain individualized information of multiple family members.
[0022] Individualized information includes at least the meal times and portion sizes for each member. Specifically, individualized information refers to a set of information characterizing the individual differences in dietary habits among each family member. This information is collected, stored, and updated on an individual member basis, distinct from common information collected at the family level. Acquisition methods may include manual input by users in health applications, synchronous collection by wearable devices or home monitoring devices, and automatic inference based on historical dietary feedback. In the joint scheduling model, individualized information constitutes the data source for the constraints of each member, enabling the model's output dietary plan to reflect the differences among members, rather than generating a uniform family dietary plan.
[0023] The available dining time slots refer to the time intervals during which each member can actually eat within a day or a predetermined planning period. These slots are measured in "time periods" and are designed to accommodate the time flexibility required for cooking and dining. This information can include differentiated settings for weekdays and rest days, as well as temporary time changes due to work, study, social activities, etc. In the joint scheduling model, available dining time slots serve as a fundamental constraint; the cooking completion time for any dish must fall within the corresponding member's available dining time slot. Otherwise, the plan is not feasible in a real-world family setting, thus ensuring the plan's feasibility from a time perspective.
[0024] The single-meal food quantity information refers to the total amount of food or energy that each member needs to consume in a single meal (including breakfast, lunch, dinner, and snacks). The unit of measurement may include mass (grams), energy (kilocalories), or standardized servings. This information can be calculated based on the member's age, gender, weight, activity level, and dietary goals, or it can be statistically corrected based on historical meal data. In the joint scheduling model, the single-meal food quantity information serves as a fundamental constraint, limiting the upper and lower limits of food allocation for each member during each meal period to avoid over-allocation leading to waste or under-allocation leading to unmet needs.
[0025] In practice, individualized information is achieved by constructing differentiated user profiles for multiple family members at different times. Specifically, the system supports independent profiles for multiple accounts within a family. Each member's individualized information includes not only meal times and individual meal portions, but also basic information, dietary restrictions, health indicators, and dietary goals. This user profile uses a temporal LSTM (Long Short-Term Memory) update model to dynamically update each member's individualized information daily, weekly, or by meal time, reflecting changes in members' dietary preferences and health status in a timely manner. In practical applications, the model's response time is less than 1.5 seconds, and its matching accuracy is higher than 98.5%. Furthermore, when multiple members plan their meals in parallel during the same meal time, the system can automatically allocate food quantities based on each member's individual meal portion information, avoiding conflicts in food needs among members.
[0026] S103, obtain ingredient inventory information.
[0027] The food inventory information includes at least the shelf life of each food item. Specifically, food inventory information refers to the status information of all food items currently available for cooking in the household, and its scope can include refrigerated inventory, frozen inventory, room temperature storage inventory, and food items that have been purchased but not yet stored.
[0028] The shelf life refers to the final time point at which each ingredient maintains its quality under specified storage conditions. It can be derived from ingredient packaging labeling, an experience database corresponding to the ingredient category, or a manual setting at the time of warehousing. The shelf life is the benchmark for calculating the remaining shelf life, and its accuracy directly affects the rationality of near-expiration judgments and scheduling priorities.
[0029] In practice, food inventory information is collected and managed through a food lifecycle management module, covering the entire lifecycle of food procurement, storage, preservation, near-expiration, and spoilage. The collected information includes not only shelf life but also food category, quantity, warehousing time, shelf life, optimal consumption period, preset near-expiration threshold, storage location, and storage temperature. Based on this information, the system can automatically calculate the spoilage rate and utilization rate of each food ingredient, achieving refined perception of food inventory status and prioritizing subsequent scheduling based on inventory, shelf life, and near-expiration status.
[0030] S105, determine the remaining shelf life of each ingredient based on its shelf life.
[0031] The remaining shelf life refers to the time interval from the current time to the shelf life, which decreases dynamically over time and needs to be recalculated each time the joint scheduling model is built or rebuilt.
[0032] In an exemplary implementation, the step S105 above may include the following step: determining the scheduling priority of each ingredient according to its remaining shelf life, so that ingredients with shorter remaining shelf life are assigned a higher scheduling priority in the joint scheduling model.
[0033] Among them, scheduling priority refers to the degree of priority of each ingredient in the dietary planning scheme in the joint scheduling model. Its implementation in the model may include: assigning different weight coefficients to ingredients with different priorities in the objective function, allocating ingredients in order of priority during the solution process, or transforming priority into hierarchical optimization objectives in multi-objective optimization.
[0034] Specifically, ingredients with shorter remaining shelf life are assigned higher scheduling priority, so that near-expiry ingredients are prioritized in the model solution. This further strengthens the consumption guarantee of near-expiry ingredients through the priority mechanism on the basis of the scheduling goal of "consuming near-expiry ingredients", and avoids sacrificing the consumption of near-expiry ingredients due to the model's multi-objective trade-off.
[0035] Specifically, scheduling priorities are determined according to the following rules: Foods nearing their expiration date with a remaining shelf life below a preset threshold are prioritized, followed by foods within their shelf life, and foods with sufficient inventory are used to supplement the remaining needs of each member. When food enters its near-expiration state, the system automatically triggers a strong recommendation mechanism and incorporates near-expiration foods into the meal planning scheme through a usage-maximizing combination method. In an exemplary implementation, the system can respond to a user's one-click operation by automatically packaging near-expiration foods and generating a "clearance meal," i.e., a menu composed of near-expiration foods, to maximize the consumption of these foods. In practical applications, the above-mentioned near-expiration priority scheduling can reduce food waste by at least 35%.
[0036] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application determine the scheduling priority of each ingredient according to its remaining shelf life, and introduce an independent priority guarantee mechanism in addition to the scheduling objective. The scheduling objective guides the consumption of near-expiry ingredients from the overall optimization direction, while the scheduling priority ensures that ingredients with shorter remaining shelf life are included in the plan first in terms of allocation order. The two form a dual drive of objective guidance and priority guarantee, avoiding the problem that the joint scheduling model sacrifices the consumption of near-expiry ingredients in order to pursue other optimization dimensions during the multi-objective trade-off process, thereby further strengthening the technical effect of timely consumption of near-expiry ingredients.
[0037] S107. Taking the remaining shelf life of ingredients in the food inventory information below the preset near-expiration threshold as the scheduling target, and using the dining time information and single meal quantity information of multiple members as the basic constraints, a joint scheduling model is constructed.
[0038] The preset near-expiry threshold refers to the time frame used to determine whether food is nearing its expiry date. When the remaining shelf life is below this threshold, the food is considered nearing its expiry date. This threshold can be set differently depending on the type of food. For example, the near-expiry threshold for leafy vegetables can be set to a shorter time frame, while the near-expiry threshold for root vegetables or frozen foods can be set to a longer time frame. The threshold setting can be based on factors such as the food's spoilage rate, household consumption habits, and the food's preservation characteristics. The preset near-expiry threshold is used to select foods that need to be consumed first from the inventory and use them as the target for scheduling.
[0039] In the mathematical framework of the joint scheduling model, the scheduling objective corresponds to the objective function, which is the direction of optimization pursued by the model when solving the problem. In this application, the consumption of ingredients with a remaining shelf life lower than the preset near-expiration threshold is set as the scheduling objective, so that the model can preferentially select the dietary planning scheme that can maximize the consumption of near-expiration ingredients in the feasible solution space.
[0040] The fundamental constraints correspond to the hard constraints that must be satisfied in the model, i.e., conditions that no feasible solution can violate. In this application, the available meal times and the amount of food per meal for multiple members are set as fundamental constraints because these two pieces of information directly determine the feasibility of the solution in a real-world family setting. If the available meal times constraint is violated, the dishes cannot be prepared within the members' available time; if the amount of food per meal constraint is violated, the allocation will not meet the members' actual needs. The difference between fundamental constraints and scheduling objectives is that the former limits the range of feasible solutions, while the latter determines the direction of the optimal solution within the range of feasible solutions.
[0041] The joint scheduling model refers to a scheduling model that combines the dietary needs of multiple family members with the inventory status of various ingredients within a unified mathematical framework for joint optimization. This joint approach is reflected in three dimensions: first, multi-member joint optimization, considering the individualized information of all family members simultaneously; second, multi-ingredient joint optimization, considering the shelf life and quantity of all inventory ingredients simultaneously; and third, multi-time period joint optimization, considering the arrangement of each meal period within the planning period. The model can be solved using integer programming, heuristic algorithms, or neural network-based reasoning methods, and its output is a dietary plan that simultaneously satisfies all constraints and optimizes the scheduling objective.
[0042] In an exemplary implementation, the individualized information also includes the dietary goal information of each member, and the food inventory information also includes the food category of each food item; the step of constructing the joint scheduling model in step S107 above may include the following steps: using the dietary goal information of each member as an additional constraint, constructing a joint scheduling model so that when solving the joint scheduling model, the allocation amount of food categories that conflict with the dietary goal information is restricted or the food category is excluded from the feasible allocation scheme.
[0043] Dietary goals refer to the dietary goals that each member expects to achieve, including but not limited to fat loss, muscle gain, blood sugar control, health maintenance, and nutritional needs targets for specific groups such as children and the elderly. This information can be quantified as nutrient intake ranges (such as the daily carbohydrate intake range, the lower limit of protein intake, etc.) or food category preferences.
[0044] Additional constraints refer to constraints superimposed on the basic constraints. The difference between them and basic constraints is that basic constraints determine the feasibility of the plan and are inviolable hard constraints; additional constraints determine the goal adaptability of the plan and can be flexibly adjusted or weighted under specific circumstances. Using dietary goal information as additional constraints allows the joint scheduling model to further adapt the plan to the health goals of each member while ensuring its feasibility.
[0045] In this context, food categories refer to classifications based on nutritional components, edible properties, or culinary uses. These classifications can be broad categories (e.g., vegetables, meats, staple foods) and subcategories (e.g., leafy greens, red meat, refined carbohydrates). When a food category conflicts with a member's dietary goals, the joint scheduling model can employ two approaches: first, restricting the allocated amount—not excluding the food category, but limiting its allocation within the member's dietary plan to a preset upper limit, suitable for scenarios requiring intake control but not complete prohibition; second, excluding it from feasible allocation schemes—removing the food category from the member's available food set during model solving, suitable for scenarios with fundamental conflicts with dietary goals. The choice between these two approaches can be automatically determined based on the degree of conflict or preset by the user.
[0046] Specifically, the joint scheduling model adopts an architecture combining Transformer and multi-objective optimization scheduling to form a four-dimensional integrated AI recommendation model encompassing "profile—ingredient lifecycle—dietary goals—time-sharing planning," achieving accurate, efficient, and low-waste dietary planning. The model's input dimensions can be expanded to 42 dimensions, with input features including individualized information for each member (profile dimension), full lifecycle information for ingredients (ingredient lifecycle dimension), dietary goal information for each member (dietary goal dimension), and available meal times for each member (time-sharing planning dimension). The model's output is a meal plan broken down by member, time, meal, and kitchen appliance. This means the dietary planning scheme includes not only ingredient allocation and dish plans for each member at each meal time, but also allocation plans for smart kitchen appliances corresponding to each dish. Furthermore, the model can set dedicated constraint layers for different dietary goals such as weight loss, muscle gain, blood sugar control, health maintenance, children, and the elderly. During the solution process, it restricts the allocation of ingredient categories that conflict with the corresponding dietary goals or excludes them from feasible allocation schemes, achieving a recommendation accuracy of 98.2%.
[0047] Specifically, the judgment regarding conflicts with dietary goals is based on a pre-stored rule library of dietary goals and food categories. This rule library stores the food category restriction rules corresponding to each dietary goal, including prohibited rules and restricted rules: prohibited rules stipulate that the food category is completely excluded under the corresponding dietary goal, while restricted rules stipulate that the intake of the food category per unit time under the corresponding dietary goal does not exceed a preset threshold. When a member's dietary goal information includes multiple sub-goals, the system takes the intersection of the constraint rules corresponding to each sub-goal as the effective constraint for that member; when a food category falls within the restriction range of multiple dietary goals, the system takes the minimum value among the restriction thresholds as the upper limit for the allocation of that food category to that member.
[0048] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application introduce the dietary goal information of each member as an additional constraint condition into the joint scheduling model, and adopt two gradient processing methods for food categories that conflict with dietary goals: limiting the allocation amount or excluding them from feasible allocation schemes. This constructs a two-layer constraint architecture where basic constraints ensure executability and additional constraints ensure goal adaptability. This allows the model to further adapt the dietary planning scheme to the health goals of each member, such as fat loss, muscle gain, and blood sugar control, while ensuring that the scheme can be implemented. At the same time, the two gradient processing methods avoid the problem of excessive shrinkage of the feasible solution space caused by simple blacklist and whitelist filtering, and achieve a balance between goal adaptability and scheme diversity.
[0049] For example, the joint scheduling model can be formalized as a constrained multi-objective integer programming problem. Specifically, suppose there are M members in a family, N types of ingredients in the inventory, and T meal times within the planned period. Then, the decision variables of the model may include x_{m,n,t} (representing the amount of ingredient n allocated by member m in time time t) and y_{m,d,t} (representing whether member m arranges dish d in time time t, a 0-1 variable). The objective function of the model takes maximizing the consumption of near-expiry ingredients as its core objective, which can be expressed as maximizing the sum of the allocation amounts x_{m,n,t} of all ingredients n with remaining shelf life below a preset near-expiry threshold across all members m and time times t. At the same time, auxiliary objective terms related to the fit of each member's dietary goals can be introduced to form a multi-objective optimization problem. The model's constraints include at least the following: basic constraints, namely, the total amount of ingredients allocated to each member in each time period does not exceed the upper limit and is not lower than the lower limit corresponding to their single-meal food quantity information, and the cooking completion time of each dish falls within the interval defined by the corresponding member's available meal time information; ingredient inventory constraints, namely, the total amount of each ingredient allocated in all time periods does not exceed its inventory; and additional constraints, namely, the allocation of ingredient categories that conflict with members' dietary goals does not exceed a preset upper limit or is zero. Through the above formalization, the near-expiration ingredient consumption target and multi-member dietary constraints are placed under a unified mathematical framework for joint solution.
[0050] S109, solve the joint scheduling model to generate a meal planning scheme.
[0051] In practice, the joint scheduling model is solved using an architecture combining Transformer and multi-objective optimization scheduling. Specifically, the Transformer encoder is used to encode and fuse input features. Its input dimension can be extended to 42 dimensions. These 42-dimensional features can include: member-side features such as the encoding features of each member's available dining time, single meal quantity, dietary goals, dietary restrictions, and health indicators; ingredient-side features such as the remaining shelf life, inventory, ingredient category, storage temperature, and shelf-life of each ingredient; and global features such as time period encoding features and the mapping relationship between dishes and ingredients. The Transformer encoder captures the relationship between members, ingredients, and time periods through a self-attention mechanism, and outputs the fused contextual feature representation. The multi-objective optimization scheduling layer takes the context features output by the Transformer encoder as input and searches for solutions within the feasible solution space formed by the objective function and constraints. It can use constrained heuristic search algorithms (such as genetic algorithms, simulated annealing algorithms), branch and bound algorithms, or reinforcement learning-based solution strategies to output Pareto optimal solution sets or optimal solutions weighted by objective weights.
[0052] The meal planning scheme includes at least the food allocation plan and menu plan for each member during each meal period. Specifically, the meal planning scheme refers to the set of meal arrangements for each member during each meal period, output by the joint scheduling model, covering the predetermined planning period.
[0053] The ingredient allocation plan is represented by a four-tuple format: "Member - Meal Time - Ingredient Category - Allocated Quantity," indicating the distribution of each ingredient among members at each meal. The menu plan is represented by a four-tuple format: "Member - Meal Time - Dish," indicating the menu arrangement for each member at each meal time, with each dish consisting of one or more ingredients in a specific ratio. There is a correspondence between the ingredient allocation plan and the menu plan: the sum of the ingredient quantities for each dish in the menu plan yields the ingredient allocation plan. Together, they ensure that the meal planning scheme is quantifiable in terms of ingredient consumption and executable in terms of actual cooking.
[0054] In one exemplary implementation, the personalized information also includes each member's dietary restrictions, health indicators, and dietary goals; the food inventory information also includes the stock levels of each food item. Figure 2 As shown, the process of solving the joint scheduling model in step S109 above may include the following steps: S201, when the meal availability information of at least two members overlaps, the amount of each ingredient is allocated between at least two members based on the single meal quantity information of each member.
[0055] Among them, the allocation of usage refers to the process of dividing the available amount of a certain ingredient among the members when multiple members all need it during the same meal period. The allocation is based on the individual meal portion information of each member.
[0056] S203 When the stock of any ingredient is insufficient to meet the needs of at least two members at the same time, the priority of allocating the insufficient ingredient among the members shall be determined based on the dietary restrictions, health indicators and dietary goals of each member.
[0057] Among them, inventory refers to the actual usable quantity of each ingredient in the current inventory, which changes dynamically with the consumption, procurement and loss of ingredients.
[0058] Among them, dietary taboo information refers to information on foods or food categories that members cannot or should not consume due to allergies, religious beliefs, medical advice, or personal preferences. The difference between dietary taboo information and dietary goal information is that dietary taboos are usually inviolable prohibitions, while dietary goals are directional conditions that are expected to be achieved.
[0059] Health indicator information refers to physiological indicators that characterize the health status of each member, including but not limited to blood glucose, blood lipids, blood pressure, weight, and body fat percentage. Data sources may include medical examination reports, synchronous data from home testing devices, or continuous data collection from wearable devices. Health indicator information is used to assist in determining allocation priorities when food supplies are insufficient. For example, if a member's blood glucose level is abnormal, carbohydrate-rich foods can be allocated more preferentially to other members.
[0060] Allocation priority refers to the basis for determining the order or proportion in which members receive a particular ingredient when the available ingredients are insufficient to simultaneously meet the needs of all members. It differs from scheduling priority in that scheduling priority is a priority based on the ingredient itself, determining which ingredients are used first; allocation priority, on the other hand, is a priority based on the member, determining which member receives the scarce ingredients first. Allocation priority is determined comprehensively based on each member's dietary restrictions, health indicators, and dietary goals, ensuring that limited ingredient resources are allocated to members with more urgent needs or stricter dietary restrictions.
[0061] S205, allocate the ingredient to each member according to the allocation priority among the members based on the insufficient stock of the ingredient, and supplement the remaining usage needs of each member with other ingredients in the inventory.
[0062] Specifically, when dietary conflicts exist among multiple members, the system handles them through an automatic multi-member dietary conflict resolution mechanism. Multi-member dietary conflicts include, but are not limited to: time slot conflicts caused by overlapping meal times for multiple members; quantity allocation conflicts due to insufficient food resources to simultaneously meet the needs of all members; and equipment usage conflicts due to insufficient available time slots for smart kitchen appliances to simultaneously meet the cooking needs of all members. For the above-mentioned multi-member dietary conflicts, the system can use one or more of the following methods to resolve them: Based on each member's dietary restrictions, health indicators, and dietary goals, the system determines the priority of food allocation among members and allocates quantities according to this priority to resolve quantity allocation conflicts; for multi-member dietary conflicts that cannot be resolved through quantity allocation, the system adjusts the meal times of relevant members by staggering meal times, allowing conflicting members to execute their respective dietary plans during different meal times, thereby avoiding competition between food resources and kitchen appliance resources within the same time period; in addition, the system can also combine the available time slot information of each smart kitchen appliance for equipment scheduling to ensure that each member's dietary plan can be actually executed.
[0063] In practice, when supplementing the remaining needs of each member with other ingredients from the inventory, the system selects supplementary ingredients according to the following priorities: Ingredients with shorter remaining shelf lives are prioritized, i.e., those with higher scheduling priority, to simultaneously promote the consumption of near-expiration ingredients while supplementing the required quantity; among ingredients with similar remaining shelf lives, those similar in nutritional composition or culinary uses are prioritized to maintain the nutritional structure and cooking method of the original dish as much as possible; ingredients that conflict with the member's dietary goals or fall within the scope of the member's dietary restrictions are excluded. Through this selection mechanism, the ingredient supplementation process satisfies the usage needs of each member while also considering the consumption of near-expiration ingredients and alignment with dietary goals.
[0064] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application construct a three-level resolution mechanism for the problem of food resource competition when meal times overlap in multi-member families, namely, quantity allocation, allocation priority, and alternative supplementation. When food supplies are sufficient, fair quantity allocation is carried out based on single-meal portion information; when supplies are insufficient, allocation priority is determined based on dietary restrictions, health indicators, and dietary goals, so that limited food supplies are tilted towards members with more urgent needs or stricter restrictions; when there is still a quantity gap, other food supplies in the inventory are used to supplement the remaining quantity needs of each member. This three-level mechanism ensures that food allocation in multi-member scenarios is both fair and prioritizes key areas, without violating the dietary goals of each member, thus solving the technical problem in the prior art that multi-member planning can only be generated independently for each member and cannot handle resource competition among members.
[0065] Specifically, the solution process may include the following steps: Based on the context features output by the Transformer encoder, pre-sort the food preferences of each member at each time period to generate a candidate food set; within the candidate food set, solve the constraint satisfaction through a multi-objective optimization scheduling layer, that is, sequentially verify the food inventory constraint, single meal quantity constraint, available meal time constraint, and additional dietary target constraint, and prune or correct candidate solutions that violate the constraints; when the available meal time information of multiple members overlaps and the inventory of any food is insufficient to simultaneously meet the usage needs of at least two members, trigger the food allocation process among members, determine the allocation priority of insufficient food among members during the solution process, and complete the usage allocation; transform the solution-obtained decision variables x_{m,n,t} and y_{m,d,t} into a dietary planning scheme, wherein the decision variables x_{m,n,t} are summarized by member and meal time to form the food allocation scheme of each member at each meal time, and the decision variables y_{m,d,t} and their corresponding food information form the dish scheme of each member at each meal time.
[0066] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application explicitly set the consumption of ingredients with remaining shelf life below a preset near-expiration threshold as the scheduling target, and set the available meal times and single-meal food quantity information of multiple members as basic constraints. Under the unified mathematical framework of the joint scheduling model, the joint optimization of the consumption of near-expiration ingredients and the dietary needs of family members is achieved. Compared with the existing technologies that only recommend recipes based on near-expiration information or use member information only as a recommendation filter, the embodiments of this application take the consumption of near-expiration ingredients as the scheduling target driving the entire planning process, and take the time availability and food quantity boundaries of members as basic constraints. Thus, the output meal planning scheme not only actively consumes near-expiration ingredients at the ingredient level, but also has real feasibility in the actual family scenario. It eliminates the manual adjustment link of users, substantially improves the adoption rate of meal planning schemes, and fundamentally reduces the waste caused by the failure to consume near-expiration ingredients in a timely manner.
[0067] In one exemplary implementation, such as Figure 3 As shown, the following steps may be included after step S109: S301 breaks down the menu plans in the meal planning scheme into cooking control instructions and determines the smart kitchen appliances corresponding to each cooking control instruction.
[0068] Cooking control commands refer to the set of control signals that convert recipes into control signals that can be directly executed by smart kitchen appliances. These commands may include parameters such as cooking mode, temperature, time, heat level, water volume, and process steps. The command format must conform to the communication protocol of the corresponding smart kitchen appliance. Smart kitchen appliances are kitchen appliances with network communication capabilities that can receive remote control commands and transmit their operating status back, including but not limited to steam ovens, stoves, range hoods, and rice cookers. By breaking down recipes into cooking control commands and identifying corresponding smart kitchen appliances, automatic integration from meal planning to cooking execution is achieved, eliminating the need for users to manually set appliance parameters.
[0069] Specifically, the steps described above for breaking down the recipe into cooking control commands include automatically breaking down each dish into cooking parameters such as cooking temperature, cooking time, cooking mode, heat level, water volume, and procedures. These cooking control commands can be directly sent to the corresponding smart kitchen appliances, such as steam ovens, cooktops, range hoods, and rice cookers, without requiring manual setup by the user.
[0070] In practice, the step of breaking down a recipe into cooking control instructions is based on a pre-stored recipe-cooking parameter mapping library. This library stores standard cooking parameter templates for each recipe, including cooking mode, reference temperature range, reference time, heat level, recommended water volume, and sequence of steps. During breakdown, the system retrieves the corresponding standard cooking parameter template from the mapping library based on the recipe identifier in the recipe and adaptively adjusts the template parameters according to the actual ingredient quantities in the ingredient allocation plan. For example, it adjusts the cooking time or heat level proportionally based on increases or decreases in ingredient quantities. When determining the smart kitchen appliance corresponding to each cooking control instruction, the system matches the type of smart kitchen appliance with the corresponding cooking function based on the cooking mode (such as steaming, baking, frying, boiling, stir-frying, etc.) in the cooking control instruction. Then, combining the device status information and available time information of each device, the system selects the specific device that is currently available and can complete the cooking task before the target time node from the matched devices as the smart kitchen appliance corresponding to that cooking control instruction.
[0071] S303, obtains device status information and available time period information for each smart kitchen appliance.
[0072] Device status information refers to the current operating status of each smart kitchen appliance, including but not limited to idle, cooking, scheduled, faulty, and offline states. This information is used to determine whether the device can immediately receive and execute new cooking control commands. Available time period information refers to the time interval within the predetermined planning cycle during which each smart kitchen appliance can perform cooking tasks, excluding periods when the device is already occupied or during maintenance or offline periods. Device status information and available time period information together form the basis for cooking sequence scheduling, ensuring that cooking control commands are issued only at available time points, avoiding command conflicts or device overload.
[0073] S305 arranges the cooking sequence of each smart kitchen appliance based on device status information and available time period information.
[0074] Cooking sequence refers to the time arrangement for each smart kitchen appliance to execute each cooking control command. Its arrangement needs to consider the following factors: First, the cooking time of each dish to ensure that the dishes are completed within the corresponding member's dining time; second, the available time period information of the smart kitchen appliances to avoid the same device performing multiple tasks at the same time; and third, the dependency relationship between dishes, such as some dishes needing to use the processed products of other dishes as input.
[0075] S307, according to the cooking sequence, sends each cooking control command to the corresponding smart kitchen appliance at the corresponding timing node, so that each smart kitchen appliance can perform cooking operations according to the corresponding cooking control command.
[0076] Among them, the timing node refers to the time point when each cooking control command is issued in the cooking sequence, which can be accurate to the minute. By issuing commands at the corresponding timing node according to the cooking sequence, collaborative cooking of multiple devices and multiple dishes is realized, so that each dish can be completed synchronously at the target time.
[0077] In practice, the aforementioned smart kitchen appliances communicate with the system via a combination of MQTT 3.1.1 protocol, CoAP protocol, and dedicated control frames for kitchen appliances, achieving deep collaboration among smart kitchen devices. Specifically, the smart refrigerator can synchronize food inventory information, temperature zone information, and preservation status information in real time, enabling the system to obtain the latest food inventory information promptly; each smart kitchen appliance can receive cooking control commands, transmit operating status information, and send anomaly alarms to the system when abnormalities occur; in addition, the health APP can synchronize dietary execution data and continuously correct the dietary target information of each member.
[0078] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application automatically decompose the menu plans in the meal planning scheme into cooking control instructions, and arrange the cooking sequence based on the device status information and available time information of the smart kitchen appliances, and finally send the instructions to the corresponding devices at the corresponding time nodes. This extends meal planning to the cooking execution stage, realizing execution-level linkage from meal planning to kitchen appliance control, eliminating the intermediate step of users manually setting kitchen appliance parameters; at the same time, the cooking sequence arrangement solves the problem of coordinated scheduling of multiple smart kitchen appliances, ensuring that each dish is completed synchronously during the members' mealtimes, making the meal planning scheme truly executable.
[0079] In one exemplary embodiment, after step S307, the following steps may be included: receiving execution status information, energy consumption information, and time information transmitted back by the smart kitchen appliance to form cooking execution feedback; generating meal completion information for each member based on the cooking execution feedback; obtaining user satisfaction information for each member regarding the meal planning scheme; and updating the individualized information of the corresponding member based on the meal completion information and user satisfaction information.
[0080] Among these, execution status information refers to the status feedback of the smart kitchen appliance during the execution of cooking control commands, including command reception confirmation, cooking start, progress of each step, cooking completion, and abnormal interruption. Energy consumption information refers to the amount of energy consumed during cooking, including but not limited to electricity, gas, and water, which can be used for energy consumption statistics and peak-shaving scheduling. Time usage information refers to the actual time consumed during the cooking process, which can be compared with the planned cooking time to assess the timeliness of cooking execution. These three types of information are transmitted back in real time by the smart kitchen appliance after cooking is completed or during cooking, forming the data foundation for cooking execution feedback.
[0081] Cooking execution feedback refers to the set of feedback information consisting of execution status, energy consumption, and time consumption information transmitted back by smart kitchen appliances. It reflects the actual execution status of the meal planning scheme at the cooking execution level. Meal completion information refers to the actual degree of completion of each member's meal planning scheme, calculated based on the cooking execution feedback. Its calculation methods may include: the ratio of the actual number of dishes cooked to the planned number of dishes, the ratio of the actual amount of ingredients consumed to the planned amount allocated, or the degree of consistency between the actual meal service time and the available meal time. Meal completion information is used to quantitatively evaluate the actual implementation of the scheme, providing an objective basis for subsequent individualized information updates.
[0082] User satisfaction information refers to each member's subjective evaluation of the meal plan. It can be obtained through methods such as post-meal ratings, likes or dislikes of dishes, feedback on leftover food, or implicit inferences based on member interactions. This information differs from meal completion information in that meal completion information is objective execution data, while user satisfaction information is subjective experience data.
[0083] Updating individualized information for each member involves adjusting fields such as meal quantity, dietary goals, and dietary restrictions based on meal completion and user satisfaction data. For example, if a member consistently gives high satisfaction ratings for high-protein dishes, their protein intake target can be appropriately increased. This update mechanism allows individualized information to dynamically evolve according to the member's actual needs, thereby continuously improving the adaptability of subsequent meal planning schemes.
[0084] Specifically, after executing cooking operations according to the received cooking control commands, the smart kitchen appliances send back execution status information, energy consumption information, and time information to the system, forming cooking execution feedback and thus constituting a closed-loop control of diet recommendation and cooking execution. The system generates diet completion information for each member based on the cooking execution feedback and, combined with user satisfaction information, scores the execution of the diet planning scheme. Based on this execution score, the system iteratively updates the joint scheduling model and the individualized information of each member, making the subsequently generated diet planning schemes more aligned with the actual needs of each member, thereby forming a feasible smart kitchen closed loop of diet execution evaluation and self-optimization. Furthermore, the system can also perform energy consumption and diet linkage statistics based on the energy consumption information sent back by each smart kitchen appliance and provide users with low-carbon and energy-saving suggestions.
[0085] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application form cooking execution feedback by receiving execution status information, energy consumption information, and time information returned by intelligent kitchen appliances, thereby generating dietary completion information for each member, and updating the individualized information of the corresponding member in combination with user satisfaction information. By combining objective execution data (dietary completion) and subjective experience data (user satisfaction) in two dimensions to drive the dynamic updating of individualized information, the system has the ability to learn and correct itself. The subsequently generated dietary plans can continuously meet the actual needs and preferences of members, thereby continuously improving the adaptability and adoption rate of the plans.
[0086] In one exemplary implementation, the method further includes: reconstructing the joint scheduling model in response to changes in food inventory information or individualized information of multiple members.
[0087] Among them, change refers to a change in the state of food inventory information or individual information of multiple members relative to the state when the joint scheduling model was last built. The triggering sources may include: changes in inventory caused by food entering or leaving the warehouse, correction of food shelf life, temporary adjustment of the meal time of members, update of members' dietary goals, addition or removal of family members, etc.
[0088] Reconstructing the joint scheduling model refers to building and solving a new joint scheduling model from scratch based on the latest information after the changes, rather than simply adjusting local parameters on the original model. Changes may affect the constraints or structure of the objective function of the model, and local adjustments cannot guarantee the global optimality of the new model; by reconstructing, it can be ensured that the dietary planning scheme is always generated based on the latest family situation, guaranteeing the timeliness and accuracy of the scheme.
[0089] Specifically, the entire process covers ingredient inventory, meal planning, recipe recommendations, kitchen appliance timing, and peak electricity usage. Starting with ingredient inventory information, meal planning generates recipe plans, which are then broken down into cooking control commands and the cooking times of various smart kitchen appliances are scheduled. Simultaneously, peak electricity usage is managed by incorporating the energy consumption information of each smart kitchen appliance. When changes occur in ingredient inventory information, individual information of multiple components, or the status of any of the aforementioned stages, the entire process can be synchronously reconstructed within milliseconds. This means rebuilding the joint scheduling model and synchronously updating subsequent recipe recommendations, kitchen appliance timing, and other stages to ensure consistency across all stages and truly achieve integrated operation.
[0090] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application reconstruct the joint scheduling model in response to changes in food inventory information or individualized information of multiple members. Changes in food inventory or member information may alter the constraint structure or objective function of the model. Local adjustments cannot guarantee the global optimality of the new model, while a full reconstruction ensures that the dietary planning scheme is always globally optimized based on the latest family status, guaranteeing the timeliness and accuracy of the scheme, and enabling the system to dynamically adapt to the continuous changes in family food inventory and member needs.
[0091] In summary, the intelligent meal planning method provided in this application covers the entire lifecycle management of ingredients, including procurement, storage, preservation, near-expiration, and spoilage, and forms an execution-level linkage with intelligent kitchen appliances. This method not only pushes recipes but also participates in the issuance of cooking control commands and the adaptation of the cooking process. Through differentiated meal planning for multiple family members at different times, priority scheduling of near-expiration ingredients, and a closed-loop mechanism for meal execution feedback, it constructs a complete closed loop of "meal planning—recipe recommendation—kitchen appliance control—execution feedback—profile optimization," making the generated meal planning scheme highly practical, avoiding food waste, and truly integrating into the intelligent kitchen closed-loop ecosystem.
[0092] Corresponding to the intelligent diet planning methods provided in the above embodiments, this application also provides an intelligent diet planning device. Since the intelligent diet planning device provided in this application corresponds to the intelligent diet planning methods provided in the above embodiments, the implementation methods of the aforementioned intelligent diet planning methods are also applicable to the intelligent diet planning device provided in this embodiment, and will not be described in detail in this embodiment.
[0093] Please see Figure 4 The diagram shows a structural schematic of an intelligent diet planning device provided in an embodiment of this application. This device 400 has the function of implementing the intelligent diet planning method described in the above-described method embodiments. This function can be implemented by hardware or by hardware executing corresponding software. Figure 4 As shown, the device 400 may include: The individual information acquisition module 410 is used to acquire individualized information of multiple family members; the individualized information includes at least the meal times and the amount of food consumed per meal for each member; The ingredient information acquisition module 420 is used to acquire ingredient inventory information; the ingredient inventory information includes at least the shelf life of each ingredient. The expiration date determination module 430 is used to determine the remaining shelf life of each ingredient based on its expiration date. The model building module 440 is used to build a joint scheduling model with the remaining shelf life of ingredients in the food inventory information below the preset near-expiration threshold as the scheduling target, and with the dining time information and single meal quantity information of multiple members as the basic constraints. The model solving module 450 is used to solve the joint scheduling model and generate a meal planning scheme; the meal planning scheme includes at least the food allocation scheme and dish scheme for each member at each meal time.
[0094] In one exemplary implementation, the individualized information also includes dietary goal information for each member, and the food inventory information also includes the food category for each food item; the model building module 440 includes: The additional constraint construction module is used to construct a joint scheduling model with the dietary goal information of each member as additional constraints. This allows the joint scheduling model to restrict the allocation of food categories that conflict with the dietary goal information or exclude such food categories from feasible allocation schemes when solving the problem.
[0095] In an exemplary embodiment, the device 400 further includes a scheduling priority determination module, which is used to determine the scheduling priority of each ingredient according to its remaining shelf life after determining the remaining shelf life of each ingredient, so that ingredients with shorter remaining shelf life are assigned higher scheduling priority in the joint scheduling model.
[0096] In one exemplary implementation, the individualized information also includes dietary restrictions, health indicators, and dietary goals for each member; the food inventory information also includes the stock levels of each food ingredient; the model solving module 450 includes: The quantity allocation module is used to allocate the quantity of each ingredient among at least two members based on their single meal quantity information when the meal time information of at least two members overlaps. The allocation priority determination module is used to determine the allocation priority of the insufficient food among members when the stock of any food is insufficient to meet the needs of at least two members at the same time, based on each member's dietary restrictions, health indicators and dietary goals. The ingredient allocation module is used to allocate ingredients that are in short supply to each member according to the allocation priority among the members, and to supplement the remaining usage needs of each member with other ingredients in the inventory.
[0097] In one exemplary embodiment, the device 400 further includes a cooking scheduling module for decomposing the recipes in the meal planning scheme into cooking control commands and scheduling various smart kitchen appliances to perform cooking operations after outputting the meal planning scheme. The cooking scheduling module includes: The instruction decomposition module is used to decompose the menu plans in the meal planning scheme into cooking control instructions and determine the smart kitchen appliances corresponding to each cooking control instruction. The device information acquisition module is used to acquire the device status information and available time period information of each smart kitchen appliance; The timing arrangement module is used to arrange the cooking sequence of each smart kitchen appliance based on device status information and available time period information; The instruction sending module is used to send each cooking control instruction to the corresponding smart kitchen appliance at the corresponding timing node according to the cooking sequence, so that each smart kitchen appliance can perform cooking operations according to the corresponding cooking control instructions.
[0098] In one exemplary embodiment, the device 400 further includes a feedback update module for updating individualized member information based on cooking execution feedback and user satisfaction information after each cooking control command is sent to the corresponding smart kitchen appliance at the corresponding timing node. The feedback update module includes: The feedback receiving module is used to receive execution status information, energy consumption information and time information transmitted back by the smart kitchen appliance, and form cooking execution feedback; The completion rate generation module is used to generate meal completion rate information for each member based on cooking execution feedback. The satisfaction acquisition module is used to obtain user satisfaction information of each member regarding the dietary planning scheme; The information update module is used to update the individualized information of the corresponding members based on the meal completion information and user satisfaction information.
[0099] In one exemplary embodiment, the device 400 further includes a model reconstruction module for reconstructing the joint scheduling model in response to changes in food inventory information or individualized information of multiple members.
[0100] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.
[0101] This application provides an electronic device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement any of the intelligent meal planning methods provided in the above method embodiments.
[0102] Memory is used to store software programs and modules. The processor executes these stored software programs and modules to perform various functional applications and data processing. Memory can primarily consist of a program storage area and a data storage area. The program storage area stores the operating system, application programs required for functionality, etc.; the data storage area stores data created based on device usage, etc. Furthermore, memory can include high-speed random access memory (RAM) and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory can also include a memory controller to provide the processor with access to the memory.
[0103] The method embodiments provided in this application can be executed in a computer terminal, server or similar computing device, that is, the above-mentioned electronic device may include a computer terminal, server or similar computing device. Figure 5 This is a hardware structure block diagram of a computer device for running an intelligent diet planning method provided in an embodiment of the present invention, such as... Figure 5 As shown, the internal structure of this computer device may include, but is not limited to, a processor, a network interface, and a memory. The processor, network interface, and memory within the computer device can be connected via a bus or other means, as illustrated in the embodiments of this specification. Figure 5 Taking the example of a connection between China and Israel via a bus.
[0104] The processor (or CPU, Central Processing Unit) is the computing and control core of the computer device. The network interface may optionally include a standard wired interface or a wireless interface (such as Wi-Fi, mobile communication interface, etc.). Memory is the storage device in the computer device used to store programs and data. It is understood that the memory here can be a high-speed RAM storage device, or a non-volatile storage device, such as at least one disk storage device; optionally, it can also be at least one storage device located remotely from the aforementioned processor. The memory provides storage space, which stores the operating system of the electronic device, including but not limited to: Windows (an operating system), Linux (an operating system), Android (a mobile operating system), iOS (a mobile operating system), etc., which are not limited in this invention; and the storage space also stores one or more instructions suitable for being loaded and executed by the processor, which can be one or more computer programs (including program code). In the embodiments of this specification, the processor loads and executes one or more instructions stored in the memory to implement the intelligent dietary planning method provided in the above method embodiments.
[0105] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in an electronic device to store at least one instruction or at least one program related to implementing an intelligent diet planning method. The at least one instruction or the at least one program is loaded and executed by the processor to implement any of the intelligent diet planning methods provided in the above-described method embodiments.
[0106] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0107] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0108] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0109] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.
[0110] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A smart diet planning method, characterized in that, The method includes: Obtain individualized information for multiple family members; the individualized information includes at least information on each member's available meal times and the amount of food consumed per meal; Obtain food inventory information; the food inventory information includes at least the shelf life of each food item; Determine the remaining shelf life of each ingredient based on its stated shelf life; The scheduling target is to consume ingredients whose remaining shelf life is lower than a preset near-expiration threshold from the ingredient inventory information. A joint scheduling model is constructed based on the dining time information and single meal quantity information of the multiple members. Solve the joint scheduling model to generate a meal planning scheme; the meal planning scheme includes at least the food allocation scheme and dish scheme for each member during each meal period.
2. The intelligent dietary planning method according to claim 1, characterized in that, The individualized information also includes dietary target information for each member, and the food inventory information also includes the food category for each food item; the construction of the joint scheduling model includes: The joint scheduling model is constructed using the dietary target information of each member as additional constraints, so that when solving the problem, the joint scheduling model restricts the allocation of food categories that conflict with the dietary target information or excludes the food category from the feasible allocation scheme.
3. The intelligent dietary planning method according to claim 1, characterized in that, After determining the remaining shelf life of each ingredient, the method further includes: The scheduling priority of each ingredient is determined according to its remaining shelf life, so that ingredients with shorter remaining shelf life are given higher scheduling priority in the joint scheduling model.
4. The intelligent dietary planning method according to claim 1, characterized in that, The individualized information also includes dietary restrictions, health indicators, and dietary goals for each member; the food inventory information includes the stock levels of each food ingredient; solving the joint scheduling model includes: When the dining time information of at least two of the multiple members overlaps, the amount of each ingredient is allocated among the at least two members according to the single meal quantity information of each member. When the stock of any ingredient is insufficient to meet the needs of at least two members at the same time, the priority of allocating the insufficient ingredient among the members is determined based on the dietary restrictions, health indicators and dietary goals of each member. The ingredient with insufficient stock is allocated to each member according to the allocation priority among the members, and the remaining usage needs of each member are supplemented with other ingredients in the inventory.
5. The intelligent dietary planning method according to any one of claims 1 to 4, characterized in that, After outputting the dietary plan, the method further includes: The menu in the dietary planning scheme is broken down into cooking control instructions, and the corresponding smart kitchen appliances for each cooking control instruction are determined. Obtain device status information and available time periods for each smart kitchen appliance; The cooking sequence of each smart kitchen appliance is arranged according to the device status information and the available time period information; According to the cooking sequence, each cooking control command is sent to the corresponding smart kitchen appliance at the corresponding timing node, so that each smart kitchen appliance can perform cooking operations according to the corresponding cooking control command.
6. The intelligent dietary planning method according to claim 5, characterized in that, After sending each cooking control command to the corresponding smart kitchen appliance at the corresponding timing node, the method further includes: Receive the execution status information, energy consumption information, and time information transmitted back by the intelligent kitchen appliance to form cooking execution feedback; Based on the cooking execution feedback, generate meal completion information for each member; Obtain user satisfaction information for each member regarding the dietary planning scheme; Based on the dietary completion information and the user satisfaction information, update the individualized information of the corresponding members.
7. The intelligent dietary planning method according to any one of claims 1 to 4, characterized in that, The method further includes: In response to changes in the food inventory information or the individualized information of the multiple members, the joint scheduling model is reconstructed.
8. An intelligent meal planning device, characterized in that, The device includes: The individual information acquisition module is used to acquire individualized information of multiple family members; the individualized information includes at least the meal times and the amount of food consumed per meal for each member; The ingredient information acquisition module is used to acquire ingredient inventory information; the ingredient inventory information includes at least the shelf life of each ingredient. The shelf-life determination module is used to determine the remaining shelf life of each ingredient based on its stated shelf-life. The model building module is used to construct a joint scheduling model with the remaining shelf life of ingredients in the food inventory information below a preset near-expiration threshold as the scheduling target, and with the dining time information and single meal quantity information of the multiple members as the basic constraints. The model solving module is used to solve the joint scheduling model and generate a meal planning scheme; the meal planning scheme includes at least the food allocation scheme and dish scheme for each member during each meal period.
9. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the intelligent dietary planning method as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing at least one instruction or at least one program, said at least one instruction or said at least one program being loaded and executed by a processor to implement the intelligent meal planning method as claimed in any one of claims 1 to 7.
