Intelligent catering system and diet management method

Abstract

The invention relates to the technical field of catering diet management, in particular to an intelligent catering system and a diet management method. The server comprises a data acquisition module, an optimization module, a sending module, a data receiving module, an identification module and a putting module; wherein the optimization module is used for determining a catering type corresponding to the catering when the catering needs to be carried out on a patient, calling food corresponding to the catering type from a corresponding food database, and carrying out random matching based on the called food to form a plurality of food matching sets; according to the current physical state data, the personal basic information and the medical basic information of the patient, selecting the healthiest food matching from the plurality of food matching sets; and the putting module is used for putting a related video which explains the eating importance corresponding to the unselected food and the benefit degree to the patient to the user side according to the identified unselected food in the healthy food collocation.

Description

Technical Field

[0001] The present invention relates to the technical field of meal preparation and food management, and in particular to an intelligent meal preparation system and a food management method. Background Art

[0002] As people's living standards improve and their health awareness increases, the importance of a reasonable diet becomes increasingly prominent. However, traditional meal planning often relies on experience or simple calculations of nutrients, lacks personalized and scientific support, and is difficult to meet the needs of different groups of people, especially those with specific diseases or in recovery.

[0003] The existing meal distribution system mainly has the following problems:

[0004] The recipes provided by most meal-matching software are relatively generic and fail to fully take into account individual differences, such as basic personal information such as age, gender, weight, and activity level, as well as basic medical information such as medical history and treatment status. As a result, the food combinations are not personalized enough and cannot provide patients with the healthiest food combinations.

[0005] At the same time, after completing the food matching, patients do not pay enough attention to the foods they do not like to eat, which leads to patients' resistance to the matching plan and results in low actual patient compliance with the matching plan. Summary of the invention

[0006] One of the purposes of the present invention is to provide an intelligent meal preparation system and a diet management method, which can provide the healthiest food combination for patients while eliminating the patients' resistance to food combination as much as possible when preparing meals for patients, thereby improving the patients' compliance with the healthiest food combination.

[0007] In order to achieve the above object, an intelligent meal distribution system is provided, including a service end and a user end;

[0008] The server includes:

[0009] A data collection module is used to obtain the basic information of the patient, including basic personal information and basic medical information;

[0010] It is also used to collect the patient's current physical condition data in real time when meals need to be prepared for the patient;

[0011] The optimization module is used to determine the meal type corresponding to the meal when it is necessary to prepare meals for the patient, and based on the determined meal type, retrieve the food corresponding to the meal type from the corresponding food database, and randomly match the retrieved food to form several food matching sets; based on the current physical condition data, personal basic information and medical basic information corresponding to the patient, based on the preset improved optimization algorithm, select the healthiest food matching from several food matching sets; the meal types include breakfast type, lunch type and dinner type;

[0012] A sending module, used for sending the corresponding healthiest food combination to the corresponding user terminal;

[0013] A data receiving module, for receiving the actual food combinations of the patient under the corresponding meal type collected by the user terminal within a preset time period after sending the healthiest food combinations to the user terminal;

[0014] an identification module, for identifying the unselected food corresponding to the healthiest food combination according to the actual food combination of the patient under the corresponding meal type and the corresponding healthiest food combination, and determining the corresponding unselected food as food that the patient does not like;

[0015] The delivery module is used to deliver to the user terminal relevant videos describing the importance of eating the unselected foods and their benefits to patients based on the unselected foods in the identified healthiest food combination.

[0016] The technical principle and effect of this solution: In this solution, the server will first obtain the patient's basic information. By obtaining the patient's basic information, the server can know the patient's personal basic information and the corresponding basic medical information, and have a comprehensive understanding of the patient's personal condition and medical condition.

[0017] At the same time, when preparing meals for patients, the patient's current physical condition data will be collected in real time.

[0018] Later, when the patient needs to be given a meal, that is, when it is meal time, the meal type corresponding to this meal will be determined, that is, whether it is breakfast type, lunch type or dinner type. By determining the meal type corresponding to this meal, the food corresponding to the meal type can be retrieved from the food database, that is, the food that can be eaten for each meal type is defined. For example, steamed buns are of breakfast type, braised beef shreds are of lunch type and also of dinner type. According to the various foods of the corresponding meal types, multiple food combination sets are formed by random combination. Then, according to the patient's current physical condition data, personal basic information and basic medical information, based on the preset improved optimization algorithm, the healthiest food combination is selected from several food combination sets. Through the setting of the improved optimization algorithm in this step, the healthiest food combination for the patient can be selected from many combinations, and then it can be fed back to the patient's user end. The patient can actually eat the meal type according to the healthiest food combination received by the user end. Of course, in this process, it is far from enough to just select the healthiest food combination. After all, the healthiest food combination may not be the best for the patient. For example, there may be foods that the patient does not eat. In the specific implementation of the healthiest food combination, The effect will be greatly reduced, that is, although there is the healthiest food combination, the patient is very repulsive, resulting in poor dining effect and inability to supplement the best nutrition. In order to enable the patient to receive all the foods in the healthiest food combination as much as possible, in this solution, after sending the healthiest food combination to the user end, the actual food combination of the patient under the corresponding meal type collected by the user end is received within a preset time period; according to the actual food combination of the patient under the corresponding meal type and the corresponding healthiest food combination received, the corresponding unselected food in the healthiest food combination is identified, and the corresponding unselected food is determined as the food that the patient does not like; according to the unselected food in the identified healthiest food combination, a video about the importance of eating the unselected food and its benefits to the patient is played to the user end. By pushing the relevant video about the importance of eating the unselected food and its benefits to the patient, the patient on the user end can pay attention to the consumption of the unselected food, thereby guiding the patient to better receive the unselected food the next time.

[0019] 1. By obtaining the patient's personal information and the patient's physical condition data corresponding to the meal, and setting the food into different meal types, the improved optimization algorithm is used to select the healthiest food combination under the corresponding meal type, thus achieving the most personalized and healthiest meal for the patient while fully considering the nutritional value of the food.

[0020] 2. After identifying the healthiest food combination, if the patient refuses to accept it, the difference between the actual food combination and the healthiest food combination can be identified to identify the unselected food and mark it as food that the patient does not like. Then, the importance of eating the unselected food and the benefits to the patient's health can be released to provide health education to the patient, which not only helps the patient understand the nutritional value of food and its help to the patient's condition, but also guides the patient to gradually accept more healthy food, thereby improving eating habits. That is, when preparing meals for patients, it can provide the healthiest food combination while eliminating the patient's resistance to food combination as much as possible, thereby improving the patient's compliance with the healthiest food combination.

[0021] Further, the optimization module includes:

[0022] A determination and retrieval module is used to determine the meal type corresponding to the meal when a meal needs to be prepared for the patient, and based on the determined meal type, retrieve various foods corresponding to the corresponding meal type from the corresponding food database;

[0023] The initial screening module is used to randomly generate N initial populations according to the foods corresponding to the corresponding meal types retrieved, and the individuals of the initial populations are the corresponding food matching sets; and based on the preset restriction conditions, the individuals of the corresponding populations are screened and judged. If the conditions are met, it is a feasible solution, otherwise it is an infeasible solution;

[0024] A fitness calculation module, used to calculate the first fitness and the second fitness of the selected population;

[0025] The calculation formula of the first fitness is as follows:

[0026]

[0027] In the formula, f1 is the first fitness, D1 is the food combination health of the corresponding population, h i (x) is the content of the i-th nutrient corresponding to the x-th food in the population, m i is the target intake of the ith nutrient, w i is the weight value of the i-th nutrient, n is the total number of nutrient types, k is the total number of foods corresponding to the population, and Z j is the health index score corresponding to the jth food, a j is the weight value corresponding to the jth food;

[0028] The calculation formula of the second fitness is as follows:

[0029]

[0030] In the formula, f2 is the second fitness, D2 is the cost score value corresponding to the corresponding population, and s r is the number of foods corresponding to the r-th food in the population, Price(r) is the single cost score corresponding to the r-th food; Price(y) is the preset minimum single cost score, and A is a random number greater than 0 and less than or equal to 1;

[0031] A selection module is used to select a population whose first fitness is less than or equal to a first fitness threshold according to the first fitness corresponding to the population within a first preset number of iterations, and select the first three populations with the largest second fitness from the populations eliminated at this time, and save them in a spare library;

[0032] When the first preset number of iterations is exceeded, the current population is combined with the population in the standby library to form a new population, and a population corresponding to the current population whose second fitness is greater than a preset second fitness threshold is selected;

[0033] The crossover mutation module is used to cross and mutate the selected population to obtain the offspring population;

[0034] A loop module is used to continue to execute the judgment of the restriction conditions in the initial screening module after obtaining the offspring population until a preset number of iterations is met;

[0035] The output module is used to output the offspring population as the optimal solution set of multi-objective optimization, and select a offspring population from the optimal solution set as the corresponding healthiest food combination.

[0036] Beneficial effect: In this scheme, when the initial population is randomly generated, it is not randomly matched, but the food corresponding to the corresponding meal type is selected for random matching, so as to ensure that the matched combination basically meets the requirements of the corresponding meal type, which greatly improves the convergence speed of the subsequent algorithm.

[0037] Secondly, the constraints in the initial screening module will be judged in each cycle, so that the offspring population input in each cycle is a feasible solution, further improving the convergence speed.

[0038] Of course, in each cycle, when calculating the fitness of the population, the fitness of the population is selected through the selection calculation of the first fitness and the second fitness, so that the selected population can be healthier and more cost-effective, and when calculating the fitness of the low cost, the corresponding fitness calculation is made more random by setting the random number A, which improves the globality of the algorithm and can avoid falling into the problem of local optimal solution.

[0039] Furthermore, the delivery module includes:

[0040] A statistics module, for counting the number of times that the unselected food is not selected in the most healthful food combination identified corresponding to the current meal type, and forming a corresponding table of the number of times that the unselected food is not selected;

[0041] The patient habit collection module is used to collect browsing data corresponding to the browsing of various browsing modes performed by the patient using the user terminal according to the user terminal corresponding to the patient, and analyze the browsing habits corresponding to the patient using the corresponding user terminal based on the collected browsing data, and determine the browsing weight value corresponding to each browsing mode;

[0042] The push module is used to dynamically adjust the push frequency value corresponding to each browsing mode when the patient uses the corresponding user terminal according to the browsing weight value corresponding to each browsing mode and the number of times the corresponding non-selected food is not selected, and based on the push frequency value of each browsing mode, when the user uses the user terminal to browse the corresponding browsing mode, the user terminal is presented with a relevant video that explains the importance of eating the non-selected food and the benefits to the patient according to the estimated frequency value of the corresponding browsing mode.

[0043] Beneficial effect: By counting the number of times that the unselected foods were not selected, a table of unselected times is formed. This module can help the system accurately identify which foods are often not selected by patients, laying the foundation for further health education and food recommendations.

[0044] By collecting patients' browsing data, analyzing their browsing habits, and determining the browsing weights of various browsing methods, we can ensure that the pushed content is more in line with the patients' interests and habits, thereby increasing their acceptance of healthy food.

[0045] Based on the patient’s feedback and browsing habits, the system can adjust the push strategy in real time to make the health education videos more relevant to the patient’s needs. This dynamic adjustment mechanism enables the system to continuously optimize meal recommendations and improve the patient’s dietary compliance.

[0046] Through user-side interaction, patients can actively browse health education videos and learn about the importance of unselected foods and their health benefits. This interactive approach increases patients' sense of participation and makes them more proactive in changing their eating habits.

[0047] Furthermore, the server also includes:

[0048] A recommendation module, for calculating the food similarity between each food corresponding to the corresponding meal type and the corresponding unselected food based on the corresponding unselected food and a preset food similarity calculation formula when the number of unselected times corresponding to the unselected food is greater than a preset number threshold, and selecting the food with the highest food similarity to replace the unselected food, and feeding back to the user end;

[0049] The preset food similarity calculation formula is:

[0050]

[0051] In the formula, X(B,C) is the food similarity between food B and food C, g z (B) is the information value corresponding to the zth feature information of food B, and p is the total number of feature information corresponding to food B.

[0052] Beneficial effects: By calculating the similarity of food, the recommendation module can find the food that is most similar to the unselected food, which may be more in line with the patient's taste and preference, thereby improving the patient's acceptance of the recommended food and thus improving compliance with the meal plan. This helps patients stick to a healthy diet in the long term. That is, based on the preset food similarity calculation formula, the patient is recommended the food with the highest similarity, thereby improving the patient's dietary compliance and health level. This method not only improves food acceptance, but also enhances user compliance and simplifies the decision-making process by dynamically adjusting the meal plan and personalized health education.

[0053] The present invention also discloses a diet management method, using the above-mentioned intelligent meal preparation system, comprising the following steps:

[0054] S1. Obtaining the basic information of the patient, including basic personal information and basic medical information;

[0055] S2. When it is necessary to prepare meals for the patient, the current physical condition data of the patient is collected in real time;

[0056] S3. When it is necessary to prepare meals for the patient, determine the meal type corresponding to the meal, and based on the determined meal type, retrieve the food corresponding to the meal type from the corresponding food database, and randomly match the retrieved food to form several food matching sets; based on the current physical condition data, personal basic information and medical basic information corresponding to the patient, based on the preset improved optimization algorithm, select the healthiest food matching from the several food matching sets; the meal types include breakfast type, lunch type and dinner type;

[0057] S4, sending the corresponding healthiest food combination to the corresponding user terminal;

[0058] S5. After sending the healthiest food combination to the user terminal, receiving the actual food combination of the patient under the corresponding meal type collected by the user terminal within a preset time period;

[0059] S6. According to the actual food combinations of the patient under the corresponding meal type and the corresponding healthiest food combinations received, the corresponding unselected foods in the healthiest food combinations are identified, and the corresponding unselected foods are determined as foods that the patient does not like;

[0060] S7. Based on the unselected foods in the identified healthiest food combination, a video is provided to the user terminal to explain the importance of eating the unselected foods and their benefits to the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a logic block diagram of an intelligent meal preparation system in Embodiment 1 of the present invention;

[0062] Figure 2 This is a flow chart of a diet management method in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0063] The following is further described in detail through specific implementation methods:

[0064] Embodiment 1

[0065] An intelligent meal distribution system, basically Figure 1 As shown, it includes a server and a user;

[0066] The server includes:

[0067] A data collection module is used to obtain the basic information of the patient, including basic personal information and basic medical information;

[0068] It is also used to collect the patient's current physical condition data in real time when meals need to be prepared for the patient;

[0069] The optimization module is used to determine the meal type corresponding to the meal when it is necessary to prepare meals for the patient, and based on the determined meal type, retrieve the food corresponding to the corresponding meal type from the corresponding food database, and randomly match the retrieved food to form several food matching sets; according to the patient's current physical condition data, personal basic information and basic medical information, based on a preset improved optimization algorithm, the healthiest food combination is selected from several food matching sets; the meal types include breakfast type, lunch type and dinner type; in this embodiment, different meal types correspond to different food categories, for example, the breakfast type corresponds to foods such as steamed buns, porridge, fried dough sticks, pancakes, soy milk, etc.

[0070] The optimization module includes:

[0071] A determination and retrieval module is used to determine the meal type corresponding to the meal when a meal needs to be prepared for the patient, and based on the determined meal type, retrieve various foods corresponding to the corresponding meal type from the corresponding food database;

[0072] The initial screening module is used to randomly generate N initial populations according to the foods corresponding to the corresponding meal types retrieved, and the individuals of the initial populations are the corresponding food matching sets; and based on the preset restriction conditions, the individuals of the corresponding populations are screened and judged. If the conditions are met, it is a feasible solution, otherwise it is an infeasible solution;

[0073] A fitness calculation module, used to calculate the first fitness and the second fitness of the selected population;

[0074] The calculation formula of the first fitness is as follows:

[0075]

[0076] In the formula, f1 is the first fitness, D1 is the food combination health of the corresponding population, h i (x) is the content of the ith nutrient corresponding to the xth food in the population, n i is the target intake of the ith nutrient, w i is the weight value of the i-th nutrient, n is the total number of nutrient types, k is the total number of foods corresponding to the population, and Z j is the health index score corresponding to the jth food, a j is the weight value corresponding to the jth food;

[0077] The calculation formula of the second fitness is as follows:

[0078]

[0079] In the formula, f2 is the second fitness, D2 is the cost score value corresponding to the corresponding population, and s r is the amount of food corresponding to the r-th food in the population, Price(r) is the single cost score corresponding to the r-th food; Price(y) is the preset minimum single cost score, and A is a random number greater than 0 and less than or equal to 1; in this embodiment, the calculation method of the cost score value corresponding to the population is determined by judging the single cost score, which greatly improves the globality and randomness of the algorithm and can avoid looping into the local optimal solution.

[0080] A selection module is used to select a population whose first fitness is less than or equal to a first fitness threshold according to the first fitness corresponding to the population within a first preset number of iterations, and select the first three populations with the largest second fitness from the populations eliminated at this time, and save them in a spare library;

[0081] When the first preset number of iterations is exceeded, the current population is combined with the population in the standby library to form a new population, and a population corresponding to the current population whose second fitness is greater than a preset second fitness threshold is selected;

[0082] The crossover mutation module is used to cross and mutate the selected population to obtain the offspring population;

[0083] A loop module is used to continue to execute the judgment of the restriction conditions in the initial screening module after obtaining the offspring population until a preset number of iterations is met;

[0084] The output module is used to output the offspring population as the optimal solution set of multi-objective optimization, and select a offspring population from the optimal solution set as the corresponding healthiest food combination.

[0085] A sending module, used for sending the corresponding healthiest food combination to the corresponding user terminal;

[0086] A data receiving module, for receiving the actual food combinations of the patient under the corresponding meal type collected by the user terminal within a preset time period after sending the healthiest food combinations to the user terminal;

[0087] an identification module, for identifying the unselected food corresponding to the healthiest food combination according to the actual food combination of the patient under the corresponding meal type and the corresponding healthiest food combination, and determining the corresponding unselected food as food that the patient does not like;

[0088] The delivery module is used to deliver to the user terminal relevant videos describing the importance of eating the unselected foods and their benefits to patients based on the unselected foods in the identified healthiest food combination.

[0089] The delivery module includes:

[0090] A statistics module, for counting the number of times that the unselected food is not selected in the most healthful food combination identified corresponding to the current meal type, and forming a corresponding table of the number of times that the unselected food is not selected;

[0091] The patient habit collection module is used to collect browsing data corresponding to the browsing of various browsing modes performed by the patient using the user terminal according to the user terminal corresponding to the patient, and analyze the browsing habits corresponding to the patient using the corresponding user terminal based on the collected browsing data, and determine the browsing weight value corresponding to each browsing mode;

[0092] The push module is used to dynamically adjust the push frequency value corresponding to each browsing mode when the patient uses the corresponding user terminal according to the browsing weight value corresponding to each browsing mode and the number of times the corresponding unselected food is not selected, and based on the push frequency value of each browsing mode, when the user uses the user terminal to browse the corresponding browsing mode, the user terminal is presented with a video about the importance of eating the unselected food and the benefits to the patient according to the estimated frequency value of the corresponding browsing mode. In this embodiment, the push frequency value is related to the browsing weight value corresponding to each browsing mode of the patient and the number of times the unselected food is not selected, which greatly improves the rationality and feasibility of setting the push frequency value.

[0093] The server also includes:

[0094] A recommendation module, for calculating the food similarity between each food corresponding to the corresponding meal type and the corresponding unselected food based on the corresponding unselected food and a preset food similarity calculation formula when the number of unselected times corresponding to the unselected food is greater than a preset number threshold, and selecting the food with the highest food similarity to replace the unselected food, and feeding back to the user end;

[0095] The preset food similarity calculation formula is:

[0096]

[0097] In the formula, X(B,C) is the food similarity between food B and food C, g z(B) is the information value corresponding to the food B on the zth characteristic information, and p is the total number of characteristic information corresponding to the food B. In this embodiment, the preset number threshold value is also dynamically changed, and the preset number threshold value is adjusted according to the patient's current physical condition data and the average number of unselected foods in the historical matching. When the various indicators corresponding to the patient's current physical condition data are poor, and the corresponding average number of unselected foods is greater than the preset number value, the corresponding preset number threshold value will be adjusted to a smaller value.

[0098] like Figure 2 As shown, this embodiment also discloses a diet management method, using the above-mentioned intelligent meal distribution system, including the following steps:

[0099] S1. Obtaining the basic information of the patient, including basic personal information and basic medical information;

[0100] S2. When it is necessary to prepare meals for the patient, the current physical condition data of the patient is collected in real time;

[0101] S3. When it is necessary to prepare meals for the patient, determine the meal type corresponding to the meal, and based on the determined meal type, retrieve the food corresponding to the meal type from the corresponding food database, and randomly match the retrieved food to form several food matching sets; based on the current physical condition data, personal basic information and medical basic information corresponding to the patient, based on the preset improved optimization algorithm, select the healthiest food matching from the several food matching sets; the meal types include breakfast type, lunch type and dinner type;

[0102] S4, sending the corresponding healthiest food combination to the corresponding user terminal;

[0103] S5. After sending the healthiest food combination to the user terminal, receiving the actual food combination of the patient under the corresponding meal type collected by the user terminal within a preset time period;

[0104] S6. According to the actual food combinations of the patient under the corresponding meal type and the corresponding healthiest food combinations received, the corresponding unselected foods in the healthiest food combinations are identified, and the corresponding unselected foods are determined as foods that the patient does not like;

[0105] S7. Based on the unselected foods in the identified healthiest food combination, a video is provided to the user terminal to explain the importance of eating the unselected foods and their benefits to the patient.

[0106] Embodiment 2

[0107] Compared with the first embodiment, the difference of this embodiment is that: when the user uses the user terminal to browse in the corresponding browsing mode, the specific push strategy of delivering the relevant video describing the importance of eating the non-selected food and the benefits to the patient to the user terminal according to the estimated frequency value of the corresponding browsing mode is:

[0108] When it is detected that the browsing mode used by the user end is the APP corresponding to the present system, the relevant video corresponding to the unselected food that needs to be explained to the user is directly matched and called, and is directly pushed and delivered on the APP of the present system;

[0109] When it is detected that the browsing mode of the user using the user terminal is other APP, when it is detected that the user opens and uses the corresponding APP, the user terminal sends the application type corresponding to the APP opened and used by the user and the unselected food that needs to be explained to the customer to the server, and then the server obtains the video link corresponding to a video with the highest viewing rate corresponding to the unselected food in the APP corresponding to the application type according to the received application type and the unselected food that needs to be explained to the customer;

[0110] The server converts the obtained video link into a corresponding sharing link and feeds the sharing link back to the user.

[0111] After receiving the sharing link, the user end will immediately write the sharing link to the clipboard corresponding to the user end, and when the user opens and uses the corresponding APP, the sharing link on the clipboard will be pasted into the APP opened and used by the user at this time. At this time, the APP will play the video link corresponding to the sharing link.

[0112] Of course, when the application type corresponding to the corresponding sharing link is not the application type of the currently used APP, the APP interface corresponding to the sharing link can be called through the sharing link to play the video link of the sharing link.

[0113] In this embodiment, sharing of video links between different APPs of a user must be done with the authorization of the user.

[0114] Since push notifications occur after a user has already expressed an interest (through their browsing behavior), push content is more likely to capture the user’s attention and pique their interest.

[0115] Showing users relevant information immediately while they are using an app increases the likelihood that they will click and view it.

[0116] By embedding the video link into the application that the user is already using, it reduces the trouble of users switching applications and improves the overall user experience.

[0117] If the user is not using the system's APP but chooses other applications, the system can still convey information to them by sharing links, maintaining the continuity and effectiveness of information transmission.

[0118] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is described too much here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent meal distribution system, characterized in that: Including server and user side; The server includes: A data collection module is used to obtain the basic information of the patient, including basic personal information and basic medical information; It is also used to collect the patient's current physical condition data in real time when meals need to be prepared for the patient; The optimization module is used to determine the meal type corresponding to the meal when it is necessary to prepare meals for the patient, and based on the determined meal type, retrieve the food corresponding to the meal type from the corresponding food database, and randomly match the retrieved food to form several food matching sets; based on the current physical condition data, personal basic information and medical basic information corresponding to the patient, based on the preset improved optimization algorithm, select the healthiest food matching from several food matching sets; the meal types include breakfast type, lunch type and dinner type; A sending module, used for sending the corresponding healthiest food combination to the corresponding user terminal; A data receiving module, for receiving the actual food combinations of the patient under the corresponding meal type collected by the user terminal within a preset time period after sending the healthiest food combinations to the user terminal; an identification module, for identifying the unselected food corresponding to the healthiest food combination according to the actual food combination of the patient under the corresponding meal type and the corresponding healthiest food combination, and determining the corresponding unselected food as food that the patient does not like; The delivery module is used to deliver to the user terminal relevant videos describing the importance of eating the unselected foods and their benefits to patients based on the unselected foods in the identified healthiest food combination.

2. The intelligent meal distribution system according to claim 1, characterized in that: The optimization module includes: A determination and retrieval module is used to determine the meal type corresponding to the meal when a meal needs to be prepared for the patient, and based on the determined meal type, retrieve various foods corresponding to the corresponding meal type from the corresponding food database; The initial screening module is used to randomly generate N initial populations according to the foods corresponding to the corresponding meal types retrieved, and the individuals of the initial populations are the corresponding food matching sets; and based on the preset restriction conditions, the individuals of the corresponding populations are screened and judged. If the conditions are met, it is a feasible solution, otherwise it is an infeasible solution; A fitness calculation module, used to calculate the first fitness and the second fitness of the selected population; The calculation formula of the first fitness is as follows: In the formula, f1 is the first fitness, D1 is the food combination health of the corresponding population, h i (x) is the content of the i-th nutrient corresponding to the x-th food in the population, m i is the target intake of the ith nutrient, w i is the weight value of the i-th nutrient, n is the total number of nutrient types, k is the total number of foods corresponding to the population, and Z j is the health index score corresponding to the jth food, a j is the weight value corresponding to the jth food; The calculation formula of the second fitness is as follows: In the formula, f2 is the second fitness, D2 is the cost score value corresponding to the corresponding population, and s r is the number of foods corresponding to the r-th food in the population, Price(r) is the single cost score corresponding to the r-th food; Price(y) is the preset minimum single cost score, and A is a random number greater than 0 and less than or equal to 1; A selection module is used to select a population whose first fitness is less than or equal to a first fitness threshold according to the first fitness corresponding to the population within a first preset number of iterations, and select the first three populations with the largest second fitness from the populations eliminated at this time, and save them in a spare library; When the first preset number of iterations is exceeded, the current population is combined with the population in the standby library to form a new population, and a population corresponding to the current population whose second fitness is greater than a preset second fitness threshold is selected; The crossover mutation module is used to cross and mutate the selected population to obtain the offspring population; A loop module is used to continue to execute the judgment of the restriction conditions in the initial screening module after obtaining the offspring population until a preset number of iterations is met; The output module is used to output the offspring population as the optimal solution set of multi-objective optimization, and select a offspring population from the optimal solution set as the corresponding healthiest food combination.

3. The intelligent meal distribution system according to claim 2, characterized in that: The delivery module includes: A statistics module, for counting the number of times that the unselected food is not selected in the most healthful food combination identified corresponding to the current meal type, and forming a corresponding table of the number of times that the unselected food is not selected; The patient habit collection module is used to collect browsing data corresponding to the browsing of various browsing modes performed by the patient using the user terminal according to the user terminal corresponding to the patient, and analyze the browsing habits corresponding to the patient using the corresponding user terminal based on the collected browsing data, and determine the browsing weight value corresponding to each browsing mode; The push module is used to dynamically adjust the push frequency value corresponding to each browsing mode when the patient uses the corresponding user terminal according to the browsing weight value corresponding to each browsing mode and the number of times the corresponding non-selected food is not selected, and based on the push frequency value of each browsing mode, when the user uses the user terminal to browse the corresponding browsing mode, the user terminal is presented with a relevant video that explains the importance of eating the non-selected food and the benefits to the patient according to the estimated frequency value of the corresponding browsing mode.

4. The intelligent meal distribution system according to claim 3, characterized in that: The server also includes: A recommendation module, for calculating the food similarity between each food corresponding to the corresponding meal type and the corresponding unselected food based on the corresponding unselected food and a preset food similarity calculation formula when the number of unselected times corresponding to the unselected food is greater than a preset number threshold, and selecting the food with the highest food similarity to replace the unselected food, and feeding back to the user end; The preset food similarity calculation formula is: Where X(B,C) is the food similarity between food B and food C, g z (B) is the information value corresponding to the zth feature information of food B, and p is the total number of feature information corresponding to food B.

5. A diet management method, using an intelligent meal preparation system according to any one of claims 1 to 4, characterized in that: The following steps are involved: S1. Obtaining the basic information of the patient, wherein the basic information of the patient includes basic personal information and basic medical information; S2. When it is necessary to prepare meals for the patient, the current physical condition data corresponding to the patient is collected in real time; S3. When a meal needs to be prepared for the patient, determine the meal type corresponding to the meal, retrieve the food corresponding to the meal type from the corresponding food database based on the determined meal type, and randomly match the retrieved food to form a plurality of food matching sets; According to the patient's current physical condition data, basic personal information and basic medical information, based on a preset improved optimization algorithm, the healthiest food combination is selected from a number of food combination sets; the meal types include breakfast type, lunch type and dinner type; S4, sending the corresponding healthiest food combination to the corresponding user terminal; S5. After sending the healthiest food combination to the user terminal, receiving the actual food combination of the patient under the corresponding meal type collected by the user terminal within a preset time period; S6. According to the actual food combinations of the patient under the corresponding meal type and the corresponding healthiest food combinations received, the corresponding unselected foods in the healthiest food combinations are identified, and the corresponding unselected foods are determined as foods that the patient does not like; S7. Based on the unselected foods in the identified healthiest food combination, a video is provided to the user terminal to explain the importance of eating the unselected foods and their benefits to the patient.

Images