Diet scheme recommendation method and system based on machine learning and linear programming

Abstract

The invention provides a diet scheme recommendation method and system based on machine learning and linear programming, and the method comprises the steps: obtaining multi-source user data, and obtaining a user health target based on the multi-source user data; providing a food nutrition database, generating an initial personalized diet suggestion by using a machine learning algorithm based on the user health target, and recommending the initial personalized diet suggestion; tracking user feedback according to the initial personalized diet suggestion, performing dynamic analysis on information fed back by the user, and correcting a health target of the user; when the target deviation of the information fed back by the user is smaller than a set threshold value, continuing to push the original diet suggestions; and otherwise, obtaining a user deviation reason, and correcting the initial personalized diet suggestion in real time by using a linear programming algorithm. According to the method, the accuracy of diet suggestions is improved through a machine learning algorithm, the diet scheme is optimized by using a linear programming algorithm, and dynamic self-adaptive personalized diet suggestion recommendation and tracking are realized.

Description

Technical Field

[0001] The present invention relates to the technical fields of linear programming algorithms and machine learning algorithms. Specifically, it relates to a method and system for recommending diet plans based on machine learning and linear programming, and also relates to a corresponding computer terminal and a computer-readable storage medium. Background Art

[0002] With the acceleration of the modern life rhythm and the continuous improvement of people's attention to health, reasonable diet management is crucial for achieving health goals, and personalized diet recommendation technologies proposed for health purposes and nutritional needs have emerged as the times require. Existing personalized diet recommendation technologies usually require users to integrate data from different channels by themselves, or separately conduct health management and diet planning in different applications, increasing the operation difficulty and time cost for users.

[0003] In addition, existing personalized diet recommendation technologies usually also have problems such as insufficient comprehensiveness and depth of data sources, untimely information update, and insufficient personalization degree, and cannot truly meet the general applicability requirements and accuracy requirements of diet recommendation plans. At the same time, there is also a lack of effective basis and means for optimizing the implementation of the recommendation plan. Currently, no description or report of similar technologies to the present invention has been found, and no similar materials at home and abroad have been collected either. Summary of the Invention

[0004] In view of the above deficiencies in the prior art, the present invention provides a method and system for recommending diet plans based on machine learning and linear programming, and also provides a corresponding computer terminal and a computer-readable storage medium.

[0005] According to one aspect of the present invention, there is provided a method for recommending a diet plan based on machine learning and linear programming, including:

[0006] Obtaining multi-source user data, and obtaining user health goals based on the multi-source user data;

[0007] Providing a food nutrition database, generating initial personalized diet recommendations based on the user health goals by using machine learning algorithms, and making recommendations;

[0008] Tracking user feedback for the initial personalized diet recommendations, dynamically analyzing the information of the user feedback, and correcting the user health goals;

[0009] When the target deviation of the information of the user feedback is less than a set threshold, continue to push the original diet recommendations; otherwise, obtain the reasons for the user deviation, and use linear programming algorithms to correct the initial personalized diet recommendations in real time.

[0010] According to another aspect of the present invention, there is provided a diet plan recommendation system based on machine learning and linear programming, including:

[0011] A data acquisition module, which is used to acquire multi-source user data and obtain user health goals based on the multi-source user data;

[0012] A diet recommendation module, which is used to provide a food nutrition database, generate initial personalized diet suggestions based on the user health goals using machine learning algorithms, and make recommendations;

[0013] A plan correction module, which is used to track user feedback for the initial personalized diet suggestions, dynamically analyze the information of the user feedback, and correct the user health goals; when the target deviation of the information of the user feedback is less than a set threshold, continue to push the original diet suggestions; otherwise, obtain the reason for the user deviation, and use the linear programming algorithm to perform real-time correction on the initial personalized diet suggestions.

[0014] According to the third aspect of the present invention, there is provided a computer terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it can be used to execute the method described above in the present invention, or run the system described above in the present invention.

[0015] According to the fourth aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can be used to execute the method described above in the present invention, or run the system described above in the present invention.

[0016] Due to the adoption of the above technical solutions, compared with the prior art, the present invention has at least one of the following beneficial effects:

[0017] The present invention increases the comprehensiveness of user data collection, accurately identifies the nutritional demands of users, deeply considers the specific health goals of users (such as the prevention or rehabilitation needs of specific diseases), and through a diet recommendation algorithm, in addition to meeting the intake requirements of major nutrients, also comprehensively considers factors such as the need to increase food diversity and taste preferences, increasing the general applicability of the diet recommendation plan.

[0018] The present invention realizes the diet tracking and recording function, combines multi-channel user reach, increases the frequency of users' active feedback on diet intake, and dynamically adjusts the diet recommendation plan.

[0019] The present invention accurately and real - time analyzes the user's physical signs through multi - source data such as medical examination and test data and smart device data of the user, combines the user's health goals (such as weight loss, muscle gain, prevention of chronic diseases, etc.) and nutritional needs, uses a nutrition algorithm based on deep learning to generate personalized diet recommendations, and effectively tracks the user's diet intake. According to the diet intake, the diet recommendations and health goals are corrected based on a linear programming algorithm, which will provide users with convenient and scientific diet guidance to help them better manage their own health. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By reading the following detailed description of non - restrictive embodiments with reference to the accompanying drawings, other features, objects, and advantages of the present invention will become more apparent:

[0021] Figure 1 It is a flowchart of the working process of a diet plan recommendation method based on machine learning and linear programming in an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of the component modules of a diet plan recommendation system based on machine learning and linear programming in an embodiment of the present invention.

[0023] Figure 3 It is a flowchart of the working process of a diet plan recommendation method and system based on machine learning and linear programming in a preferred embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following is a detailed description of the embodiments of the present invention: These embodiments are implemented on the premise of the technical solution of the present invention, and detailed implementation manners and specific operation processes are given. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention.

[0025] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0026] Existing personalized diet recommendation technologies usually require users to integrate data from different channels by themselves or separately conduct health management and diet planning in different applications, which increases the operation difficulty and time cost for users. To address the above problems, an embodiment of the present invention provides a diet plan recommendation method based on machine learning and linear programming. This method improves the accuracy of diet recommendations through machine learning algorithms, and optimizes the diet plan using linear programming algorithms, achieving dynamic and adaptive personalized diet recommendation and tracking.

[0027] Specifically, as Figure 1 shown, the diet plan recommendation method based on machine learning and linear programming provided by this embodiment may include the following operations:

[0028] S1. Obtain multi-source user data and obtain the user's health goals based on the multi-source user data;

[0029] S2. Provide a food nutrition database, generate an initial personalized diet recommendation based on the user's health goals using machine learning algorithms, and make a recommendation;

[0030] S3. Track the user's feedback on the initial personalized diet recommendation, dynamically analyze the information feedback by the user, and revise the user's health goals;

[0031] S4. When the target deviation of the information feedback by the user is less than the set threshold, continue to push the original diet recommendation; otherwise, obtain the reason for the user's deviation and use linear programming algorithms to make real-time corrections to the initial personalized diet recommendation.

[0032] To achieve the comprehensiveness and depth of data sources, in some preferred embodiments, the above S1, Obtain multi-source user data and obtain the user's health goals based on the multi-source user data, may further include the following operations:

[0033] S11. The multi-source user data includes: offline medical treatment data, key index data collected by devices, and manual record data of users;

[0034] S12. Clean the multi-source user data and mark the user's physical state labels to obtain sample data;

[0035] S13. Extract key indicators from the sample data, identify the user's health demands, and obtain the user's health goals.

[0036] To achieve the scientific nature of diet recommendations, in some preferred embodiments, the above S2, Provide a food nutrition database, includes:

[0037] S21. Obtain data on various food classifications, glycemic index, and nutritional components to obtain basic food information;

[0038] S22. Maintain information on single foods, common composite foods, their proportions of main nutrients, micronutrients, and glycemic index based on the basic information of the foods.

[0039] S23. Based on different health goals, obtain the nutritional element intake requirements for the corresponding health goals, and then obtain the corresponding types of foods to be ingested and the content of nutritional elements, form a benchmark diet plan, and construct a food nutrition database.

[0040] To achieve the accuracy of diet recommendations, in some preferred embodiments, for the above S2, based on the user's health goals, use a machine learning algorithm to generate an initial personalized diet recommendation, and it may further include the following operations:

[0041] S24. Provide a machine learning model, and use the food nutrition database to train the machine learning model to obtain a nutrition model.

[0042] S25. Use the user's health goals as the input of the nutrition model, obtain the corresponding benchmark diet plan, and use multi-source user data to adjust the benchmark diet plan to generate a personalized diet recommendation plan.

[0043] In some preferred embodiments, for the above S25, the multi-source user data for adjusting the benchmark diet plan includes: physical sign information and life behavior information manually recorded by the user.

[0044] To enhance the precise management and correction of the user's diet and improve the accuracy of diet recommendations, in some preferred embodiments, for the above S3, track the user's feedback on the initial personalized diet recommendation, dynamically analyze the information feedback by the user, and correct the user's health goals, including:

[0045] S31. Through a reminder mechanism, prompt the user to achieve multi-channel reach for the initial personalized diet recommendation and obtain user feedback data.

[0046] S32. Extract key indicators from the user feedback data, dynamically analyze the extracted key indicators, identify the user's new health demands, and correct the user's health goals.

[0047] S33. Analyze the user feedback data to obtain the actual diet intake and the actual changes in physical signs for diet recommendation correction.

[0048] To achieve dynamic adjustment of the diet recommendation plan, in some preferred embodiments, for the above S4, the target deviation of the information feedback by the user can be obtained through the following method:

[0049] S41. Analyze the user feedback data to obtain the actual diet intake and the actual changes in physical signs.

[0050] S42. Compare the actual dietary intake and the actual changes in physical signs with the expected data, and the corresponding difference obtained is the target deviation.

[0051] In order to real-time correct the overall population tagging logic, dietary recommendations, and reminder plans based on the actual implementation of a single user's dietary recommendations and the analysis results of expected differences, and improve the accuracy of dietary recommendations. In some preferred embodiments, in the above S4, the initial personalized dietary advice is real-time corrected using a linear programming algorithm, and the following operations may further be included:

[0052] Update the baseline dietary plan in the food nutrition database using the corrected personalized dietary advice.

[0053] Among them, the linear programming algorithm mainly optimizes dietary recommendations by creating an objective function based on the goals of nutritional balance and user intake preferences, with nutritional requirements, food choices, and energy intake as constraints.

[0054] Based on the same inventive concept, an embodiment of the present invention also provides a dietary plan recommendation system based on machine learning and linear programming.

[0055] Specifically, as Figure 2 shown, the dietary plan recommendation system based on machine learning and linear programming provided by this embodiment may include the following modules:

[0056] A data acquisition module, which is used to acquire multi-source user data and obtain user health goals based on the multi-source user data;

[0057] A dietary recommendation module, which is used to provide a food nutrition database, generate initial personalized dietary advice based on user health goals using a machine learning algorithm, and make recommendations;

[0058] A plan correction module, which is used to track user feedback for the initial personalized dietary advice, dynamically analyze the information feedback by the user, and correct the user health goals; when the target deviation of the information feedback by the user is less than the set threshold, continue to push the original dietary advice; otherwise, obtain the reason for the user deviation and real-time correct the initial personalized dietary advice using a linear programming algorithm.

[0059] In some preferred embodiments, the above system may further include the following modules:

[0060] A user login module, which is used to acquire the account information of the currently logged-in person, verify whether the account information is legal or matching, and enter the system according to the permission information of the currently logged-in person; among them, the user login module acquires the account information through any of the following methods:

[0061] - Input the set account information, where the account information includes the username and user password;

[0062] - By scanning the QR code, cascade the relevant account information, where the account information includes the WeChat account;

[0063] The user management module is used to create or modify user information, where the user information includes account information, permission information, and other information set according to requirements.

[0064] The diet plan recommendation system based on machine learning and linear programming provided by the above embodiments of the present invention can be encapsulated as an application program and arranged on an intelligent terminal.

[0065] The working content of each functional module of the diet plan recommendation system provided by the above embodiments of the present invention will be further described in detail below.

[0066] The data acquisition module and the diet recommendation module are used to realize dynamic and adaptive personalized diet suggestions; specifically: according to the user's offline medical treatment (outpatient, inpatient, physical examination) data, the key index data collected by the user device, and the living habits manually recorded by the user, generate an initial diet recommendation plan in combination with the nutrition algorithm; and dynamically adjust the diet recommendation plan by incorporating more user behavior data during the diet plan cycle, such as diet records, acceptance of different foods, and physical feedback (such as weight changes, blood sugar fluctuations, etc.).

[0067] The plan correction module is used to realize tracking and recording the user's diet intake; specifically: provide multiple ways for the user to take pictures and upload, manually record, and scan the code to identify customized healthy meals to record the diet intake, and support customizing the proportion of the food portion recognized by taking pictures to achieve the purpose of accurately recording the diet intake; increase the enthusiasm for diet management through an incentive mechanism, such as obtaining virtual rewards, unlocking new diet suggestions, or consulting opportunities with dietitians when achieving certain stages of healthy diet goals, etc., to enhance the user's enthusiasm and participation in diet management.

[0068] As Figure 3 shown, the working process of the diet plan recommendation system includes the following steps:

[0069] Step 1, establish a food nutrition database: collect various food classifications (such as grains, meats, vegetables, fruits, milk, oils, etc.), GI values, and nutritional component data [including but not limited to the content of calories, proteins, carbohydrates, fats, dietary fiber, vitamins (A, B group, C, D, E, etc.), minerals (calcium, iron, zinc, magnesium, etc.)];

[0070] Step 2, generate a benchmark diet plan: design a nutrition algorithm according to different user labels (health goals) and nutritional principles to generate a benchmark diet combination plan;

[0071] Step 3: Collect and clean user health data: offline medical data (electronic medical records, laboratory examination information, medication records, and surgical records), health indicator data from the user's smart device, and physical information manually entered by the user, and label the user's physical status;

[0072] Step 4: Generate a personalized diet plan: Based on user tags, basic physical information (allergens), and eating habits (taste differences, dietary taboos, etc.), adjust the proportion of the baseline diet plan content and generate a personalized diet recommendation plan;

[0073] Step 5: Generate a diet record check-in plan and reach out through multiple channels to encourage users to develop the habit of recording their diet and dynamically monitor changes in diet intake and effects;

[0074] Step 6 provides multiple options for recording your diet: photo recognition, code scanning to identify fixed meal plans, and manual recording, all of which support custom adjustment of intake proportions;

[0075] Step 7: Dynamically analyze the difference between actual dietary intake and actual changes in physical signs and expectations. If the deviation is less than the set threshold (such as 20%), continue to push dietary recommendations as originally planned; if the deviation is greater than or equal to the set threshold (such as 20%), dynamically push a questionnaire based on the deviation item to collect the cause of the deviation, and then adjust the dietary recommendations.

[0076] It should be noted that the steps in the method provided by the present invention can be implemented by using the corresponding components in the system. Those skilled in the art can refer to the technical solution of the system to implement the step flow of the method, and can also refer to the technical solution of the method to implement the composition of the system. That is, the embodiments in the system and the embodiments in the method can be understood as preferred examples of each other, and will not be elaborated here.

[0077] The diet plan recommendation method and system provided by the above embodiments of the present invention can, based on the actual implementation of a single user's diet recommendation and the expected difference analysis results, revise the overall population labeling logic and diet recommendation and reminder plans in real time, thereby improving the accuracy of diet recommendations;

[0078] An embodiment of the present invention further provides a computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor can be used to execute any one of the methods described in the foregoing embodiments of the present invention, or to execute any one of the systems described in the foregoing embodiments of the present invention.

[0079] Optionally, a memory for storing programs; the memory may include volatile memory (e.g., random-access memory, such as static random-access memory (SRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), etc.); the memory may also include non-volatile memory, such as flash memory. The memory is used to store computer programs (such as application programs and functional modules for implementing the above method), computer instructions, etc. The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories. And the above computer programs, computer instructions, data, etc. may be called by the processor.

[0080] The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories. And the above computer programs, computer instructions, data, etc. may be called by the processor.

[0081] A processor for executing the computer programs stored in the memory to implement each step in the method or each module in the system described in the above embodiments. For specific details, please refer to the relevant descriptions in the previous method and system embodiments.

[0082] The processor and the memory may be independent structures or integrated structures. When the processor and the memory are independent structures, the memory and the processor may be coupled and connected through a bus.

[0083] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, it can be used to execute the method of any one of the above embodiments of the present invention, or run the system of any one of the above embodiments of the present invention.

[0084] Among them, the computer-readable medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage media can be any available medium accessible by a general-purpose or dedicated computer. An exemplary storage media is coupled to the processor, enabling the processor to read information from and write information to the storage media. Of course, the storage media can also be a component of the processor. The processor and the storage media can be located in an ASIC. Additionally, the ASIC can be located in a user device. Of course, the processor and the storage media can also exist as discrete components in a communication device.

[0085] The diet plan recommendation method and system provided by the above embodiments of the present invention achieve the following technological innovations:

[0086] Comprehensiveness and depth of data sources: Not only the basic information input by the user is collected, but also medical data and physical examination data are integrated, enabling the system to understand the user's health condition more comprehensively. The physical sign data collected by intelligent devices, such as heart rate, sleep status, and heart rate changes during exercise, can provide a more in-depth basis for formulating health goals and nutritional needs.

[0087] Scientificity and accuracy of diet recommendations: Based on nutritional algorithms and combined with the user's multi-source data, more scientific and accurate diet recommendations can be provided. For example, if a certain vitamin deficiency is found in the user's physical examination data, the system will recommend food combinations rich in that vitamin and with improved absorption and utilization rate when combined with other foods; when calculating the food portion, factors such as the user's physical needs, exercise volume, and digestion ability will be comprehensively considered to ensure that the nutrients ingested by the user meet the needs without being excessive.

[0088] Degree of tight integration with the medical and health system: Since the system integrates medical data, the combination of this plan with the medical and health system is closer. Health management practitioners can understand the user's diet situation through this system and provide a more comprehensive treatment plan; users can also use this system under the guidance of health management practitioners to better manage their diet and health and achieve a closed-loop management of medical and health.

[0089] The diet plan recommendation method and system provided by the above embodiments of the present invention, compared with existing similar competitors, combine the user's medical data, physical examination data, activity data, and health goals to generate personalized diet recommendations and perform dynamic effect tracking, and have the following advantages:

[0090] More convenient user experience: It provides users with a one-stop service from health data collection, analysis to diet advice and tracking. Users don't need to switch between multiple systems or platforms, making it more convenient and faster to use. Existing systems may require users to integrate data from different channels by themselves, or conduct health management and diet planning separately in different applications, increasing the operation difficulty and time cost for users.

[0091] Optimizing treatment plans to improve treatment effects: Health management practitioners or dietitians can formulate personalized diet orders for users based on their medical conditions (such as diabetes, kidney disease, gastrointestinal diseases, etc.), examination reports (such as nutritional indicators shown in blood tests, liver function, etc.) and treatment plans. The system provides a diet tracking function, and users can feedback on the implementation of their diet. Health management practitioners and dietitians can adjust the treatment plan in a timely manner according to the feedback.

[0092] It can be widely applied to users' home health management. Its advantage lies in the close combination of the diet management module with medical diagnosis and treatment. Health management practitioners can adjust diet advice in real time according to the changes in users' medical conditions, ensuring that the diet plan plays a positive auxiliary role in treatment and recovery. At the same time, this also helps to improve users' compliance with the treatment plan and improve treatment effects.

[0093] Matters not covered in the above embodiments of the present invention are all well-known technologies in the art.

[0094] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific implementation manners. Those skilled in the art can make various deformations or modifications within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A diet plan recommendation method based on machine learning and linear programming, characterized in that, include: Acquire multi-source user data, and obtain a user health goal based on the multi-source user data; Providing a food nutrition database, using machine learning algorithms to generate initial personalized dietary suggestions based on the user's health goals, and making recommendations; Tracking user feedback on the initial personalized diet recommendations, dynamically analyzing the user feedback information, and revising the user's health goals; When the target deviation of the information fed back by the user is less than the set threshold, the original diet recommendation will continue to be pushed; otherwise, the reason for the user deviation will be obtained, and the initial personalized diet recommendation will be corrected in real time using a linear programming algorithm.

2. The method for recommending a diet plan based on machine learning and linear programming according to claim 1, wherein: The acquiring of multi-source user data and obtaining a user health goal based on the multi-source user data includes: The multi-source user data includes: offline medical treatment data, key indicator data collected by equipment, and user's manually recorded data; Cleaning the multi-source user data and labeling the user's physical status to obtain sample data; Key indicators are extracted from the sample data to identify user health demands and obtain user health goals.

3. The dietary plan recommendation method based on machine learning and linear programming according to claim 1, characterized in that The provision of a food nutrition database includes: Obtain data on food classification, glycemic index and nutritional composition to obtain basic food information; Based on the basic information of the food, maintain information on single foods and common complex foods and their main nutrient composition ratios, trace nutrients, and glycemic index; According to different health goals, the nutritional element intake requirements for the corresponding health goals are obtained, and then the corresponding food types and nutritional element contents required are obtained to form a baseline diet plan and build a food nutrition database; Generating initial personalized dietary recommendations based on the user's health goals using a machine learning algorithm includes: Providing a machine learning model, and using the food nutrition database to train the machine learning model to obtain a nutrition model; The user health goal is used as the input of the nutrition model to obtain a corresponding baseline diet plan, and the baseline diet plan is adjusted using the multi-source user data to generate a personalized diet recommendation plan.

4. The method for recommending a diet plan based on machine learning and linear programming according to claim 3, wherein: The multi-source user data used to adjust the baseline diet plan includes: physical sign information and life behavior information manually recorded by the user.

5. The diet plan recommendation method based on machine learning and linear programming according to claim 1, wherein Tracking user feedback on the initial personalized diet recommendation, dynamically analyzing the user feedback information, and revising the user health goal includes: Through a reminder mechanism, users are prompted to access the initial personalized dietary recommendations through multiple channels to obtain user feedback data; Extracting key indicators from the user feedback data, and dynamically analyzing the extracted key indicators to identify new health demands of users and revise their health goals; The user feedback data is analyzed to obtain actual dietary intake and actual changes in physical signs for use in dietary recommendation corrections.

6. The diet plan recommendation method based on machine learning and linear programming according to claim 1, wherein Also includes any one or more of the following: -The target deviation of the user feedback information is obtained by the following method: By analyzing the user feedback data, actual dietary intake and actual changes in physical signs are obtained; Compare the actual dietary intake and actual changes in physical signs with the expected data, and the corresponding differences are the target deviations; - the use of a linear programming algorithm to modify the initial personalized dietary recommendations in real time also includes: The baseline diet plan in the food nutrition database is updated using the revised personalized diet recommendation.

7. A diet plan recommendation system based on machine learning and linear programming, characterized in that: include: A data acquisition module, configured to acquire multi-source user data and obtain user health goals based on the multi-source user data; A diet recommendation module, which is used to provide a food nutrition database, generate initial personalized diet suggestions based on the user's health goals using a machine learning algorithm, and make recommendations; A plan modification module is used to track user feedback on the initial personalized diet recommendations, dynamically analyze the user feedback information, and modify the user's health goals; when the target deviation of the user feedback information is less than the set threshold, the original diet recommendations are continued to be pushed; otherwise, the reason for the user deviation is obtained, and the initial personalized diet recommendations are modified in real time using a linear programming algorithm.

8. The diet plan recommendation system based on machine learning and linear programming according to claim 7, characterized in that: Also includes: A user login module is used to obtain the account information of the current login person, verify whether the account information is legal or matches, and enter the system based on the permission information of the current login person; wherein, the user login module obtains the account information by any of the following methods: -Enter the account information you have set, including your username and password; - Scan the QR code to access related account information, including WeChat account information; User management module, which is used to create or modify user information, including account information, permission information, and other information set according to needs.

9. A computer terminal, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When executing the computer program, the processor can be used to perform the method according to any one of claims 1 to 6, or to run the system according to any one of claims 7 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can be used to perform the method according to any one of claims 1 to 6, or to run the system according to any one of claims 7 to 8.

Images