Healthy dietary nutrition collocation guidance platform based on artificial intelligence

Abstract

The invention discloses a healthy diet nutrition collocation guidance platform based on artificial intelligence, and the platform comprises the steps: obtaining a diet collocation plan needing to be implemented by a user, extracting a needed estimated time length corresponding to the diet collocation plan, dividing the needed estimated time length into X observation sub-time zones according to the time length range of the needed estimated time length, and carrying out the calculation of the X observation sub-time zones. When the divided observation sub-time zones are reached, the weight change condition of the user in the current observation sub-time zone is analyzed, the implemented diet matching plan is adjusted, and the adjusted diet matching plan is used as the diet matching plan temporarily implemented by the user in the next observation sub-time zone, so that dynamic adjustment of the diet matching plan is realized; and the continuity and stability of the weight losing effect of the user in the implementation process are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of dietary nutrition matching, and in particular to a healthy dietary nutrition matching guidance platform based on artificial intelligence. Background Art

[0002] In modern society, with the improvement of living standards and changes in dietary structure, obesity has gradually become a global public health issue; weight loss, as an important means to deal with obesity and related health problems, has attracted more and more attention, and obese people need to lose weight through a healthy diet.

[0003] Although the existing AI-based healthy diet nutrition matching guidance platform provides solutions to a certain extent, it still has several shortcomings: The platform provides personalized healthy meal plans based on users’ personal information and dietary preferences, but during implementation, it cannot dynamically adjust meal plans based on users’ weight changes at different stages to ensure the sustainability and stability of weight loss effects; In addition, the existing guidance platforms have a low level of intelligence when users need to communicate with professional nutritionists remotely. They cannot conduct a comprehensive assessment of the user evaluations, waiting times, and professional experience of each professional nutritionist, so as to push the best professional nutritionist at the current time to the user and select him.

[0004] To this end, we launched an artificial intelligence-based healthy diet nutrition matching guidance platform. Summary of the invention

[0005] In view of this, the present invention provides a healthy diet nutrition matching guidance platform based on artificial intelligence to solve the problems raised by the above background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions: a healthy diet nutrition matching guidance platform based on artificial intelligence, comprising: Information collection module: users create accounts and input personal information and dietary preferences; the personal information and dietary preferences input by users are integrated into a comprehensive data package of users and sent to the plan generation module; Plan generation module: receiving the user's comprehensive data package, parsing and evaluating it, thereby generating the corresponding meal matching plans for each group of users; sending the meal matching plans generated by the user to the user interaction module; wherein each meal matching plan also includes the estimated time required for the user to reach the ideal weight loss weight after implementing the corresponding meal matching plan; User interaction module: receiving each set of meal matching plans generated by the user and sending them to the user, and the user receiving each set of meal matching plans and selecting the meal matching plan to be implemented; Observation and evaluation module: obtain the dietary plan that the user needs to implement, and extract the required estimated duration corresponding to the dietary plan, and divide the required estimated duration into X observation sub-time zones according to the duration range of the group of required estimated durations; X is the total number of divided observation sub-time zones; when reaching the divided observation sub-time zones, adjust the implemented dietary plan accordingly based on the results of user feedback; Expert consultation module: When the user triggers the consultation signaling, the query merit Ft of each expert at the current time point is analyzed, and the ranking results based on the query merit Ft of each expert are pushed to the user. After the user selects the corresponding expert, a remote communication connection is established with the expert.

[0007] In some embodiments, a comprehensive data package of a user is received, parsed and evaluated, thereby generating a meal matching plan for each group of users, specifically: First, the gender, weight, height and age are extracted from the user's personal information, and the user's basal metabolic rate is calculated based on this; At the same time, the total amount of exercise of the user in the past week is obtained, and the range of values ​​of each group of exercise amount corresponding to the total amount of exercise is preset, and each group of exercise amount value range is set to correspond to an activity level coefficient, and the total amount of exercise of the user in the past week is matched with the preset range of values ​​of each group of exercise amount, so as to obtain the activity level coefficient of the user; Multiply the user's basal metabolic rate and activity level coefficient to obtain the user's estimated daily energy expenditure; extract the user's weight and ideal weight loss goal from the user's personal information, and perform difference calculation to obtain the user's weight loss amount; generate each group of meal matching plans corresponding to the user based on the user's weight loss amount and estimated energy expenditure; The user's weight loss amount and estimated energy consumption are input into a pre-constructed database to obtain various groups of dietary matching plans for the user at the current time point; the database includes various groups of preset weight loss amount value ranges, and each group of preset weight loss amount value ranges corresponds to multiple groups of estimated energy consumption value ranges, and each group of estimated energy consumption value ranges is set to correspond to multiple groups of dietary matching plans.

[0008] In some embodiments, when the divided observation sub-time zone is reached, analysis is performed based on the results of user feedback, specifically: Set the estimated weight range of the user when arriving at each observation sub-time zone. If the weight detected by the user when arriving at a certain observation sub-time zone is higher than the corresponding set estimated weight range, an evaluation signaling is triggered and sent to the user; After receiving the triggered evaluation signaling, the user confirms it, extracts the user's weight in the current observation sub-time zone and the highest value in the estimated weight range, and calculates the difference to obtain the user's weight loss distance in the current observation sub-time zone; Preset the distance value ranges for weight loss distance, set each distance value range to correspond to an additional coefficient; match the weight loss distance of the user in the current observation sub-time zone with the preset distance value ranges for each group, so as to obtain the additional coefficient.

[0009] In some embodiments, when arriving at the divided observation sub-time zone, performing analysis based on the result of user feedback further includes: Construct a weight change trend graph of the user at each time point in the current observation sub-time zone, draw the numerical points in the weight change trend graph corresponding to the user's weight value at each time point in the current observation sub-time zone, and connect adjacent numerical points to obtain a weight line; Calculate the slope of each weight line and the angle between it and the horizontal line. If the angle between a weight line and the horizontal line is acute, mark the slope of the weight line as the weight loss slope. If the angle between a weight line and the horizontal line is obtuse, mark the slope of the weight line as the rebound slope. All weight loss slopes and rebound slopes are summed up respectively, thereby obtaining the total weight loss value and total rebound value of the user in the current observation sub-time zone; the weight loss status value of the user in the current observation sub-time zone is obtained by calculating the total weight loss value / total rebound value; The calculated weight loss status value is used to determine the user's weight loss trend in the current observation sub-time zone. If the weight loss status value is greater than 1, the user's weight loss status is determined to be a gradual weight loss trend. If the weight loss status value is less than 1, the user's weight loss status is determined to be an excessive weight rebound trend.

[0010] In some embodiments, the implemented dietary plan is adjusted accordingly, specifically: An adjustment coefficient is set to correspond to the gradual weight loss trend and the excessive weight rebound trend respectively; the dietary plan implemented by the user is extracted, the daily calorie intake in the dietary plan is extracted and multiplied by the additional coefficient and the adjustment coefficient, that is, the daily calorie intake × additional coefficient × adjustment coefficient, to obtain the adjusted daily calorie intake, and the alternative food in the dietary plan is pushed to the user. After the user completes the selection, the daily calorie intake in the dietary plan is equal to the adjusted daily calorie intake; The adjusted dietary plan is used as the dietary plan temporarily implemented by the user in the next observation sub-time zone.

[0011] In some embodiments, the query merit Ft of each expert at the current time point is analyzed, specifically: Obtain all experts who are online at the current time point, and use all experts who are online as candidate experts for the user at the current time point; The number of users waiting to be connected to each candidate expert is counted and used as the waiting index s1 of each candidate expert; the number of service users, years of employment, and user evaluations are extracted from the historical data of each candidate expert; the number of service users and years of employment of each candidate expert are converted into experience scores according to the preset conversion rules; the weight coefficients of the number of service users corresponding to the experience score and the years of employment corresponding to the experience score are preset; Multiply the experience score corresponding to the number of users served by each candidate expert and the experience score corresponding to the years of experience of each candidate expert by the corresponding preset weight coefficient, and then sum them up to obtain the experience index s2 of each candidate expert; Obtain the user evaluations of each candidate expert group; and calculate the average of the user ratings of each candidate expert group, thereby obtaining the service index s3 of each candidate expert; Using the formula , weighted calculation is performed on the waiting index s1, experience index s2 and service index s3 of each candidate expert to obtain the query merit Ft of each candidate expert; where ei, zi and qi are the influence weight factors of the waiting index s1, experience index s2 and service index s3 respectively; where i=1, 2 or 3, and the query merit Ft of each candidate expert under different influence weight factors is calculated respectively.

[0012] In some embodiments, the number of service users and years of experience of each candidate expert are converted into experience scores according to preset conversion rules, specifically: Preset the quantity value range and the number of years value range corresponding to the number of service users and the number of years of experience respectively, and set each group of quantity value range and the number of years value range to correspond to a group of experience scores respectively; match the number of service users and the number of years of experience of each candidate expert with the corresponding quantity value range and the number of years value range respectively, so as to obtain the experience scores corresponding to the number of service users and the number of years of experience of each candidate expert respectively.

[0013] In some embodiments, the sorting results based on the query merit Ft of each expert are pushed to the user. Specifically, based on the query merit Ft of each candidate expert, they are sorted from large to small, and the candidate expert with the largest query merit when i=1, the candidate expert with the largest query merit when i=2, and the candidate expert with the largest query merit when i=3 are selected. The results are integrated into a recommended expert lineup and pushed to the user. After the user selects the corresponding expert, the number of users to be connected and the number of users served by the expert are increased by one.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains a dietary matching plan that a user needs to implement, and extracts the required estimated duration corresponding to the dietary matching plan, divides the required estimated duration into X observation sub-time zones according to the duration range of the group of required estimated durations, analyzes the weight change of the user in the current observation sub-time zone when the divided observation sub-time zone is reached, adjusts the implemented dietary matching plan, and uses the adjusted dietary matching plan as the dietary matching plan temporarily implemented by the user in the next observation sub-time zone, thereby achieving dynamic adjustment of the dietary matching plan and ensuring the continuity and stability of the weight loss effect of the user during the implementation process; The present invention can more effectively recommend suitable experts to users by analyzing relevant indicators of online experts in real time and obtaining the query merit value of each expert when the user triggers the consultation signal, improve service efficiency and interactivity, and realize intelligent analysis and matching, which not only improves service efficiency and user satisfaction, but also contributes to the long-term development and ecological construction of the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 It is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0016] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete, and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0017] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless explicitly defined as such herein.

[0018] See also Figure 1 As shown, the healthy diet nutrition matching guidance platform based on artificial intelligence includes information collection module, plan generation module, user interaction module, observation and evaluation module, and expert consultation module; The information collection module is used for users to create an account and enter personal information and dietary preferences; the personal information includes age, gender, height, current weight, ideal weight for weight loss, and amount of exercise; the dietary preferences include foods prohibited by the user due to preferences, food allergies, or intolerance; the personal information and dietary preferences entered by the user are integrated into a comprehensive data package of the user and sent to the plan generation module; The plan generation module is used to receive the user's comprehensive data package, analyze and evaluate it, and thereby generate each set of meal matching plans corresponding to the user; each set of meal matching plans should contain balanced macronutrients (protein, fat, carbohydrates) and micronutrients (vitamins, minerals); each set of meal matching plans generated by the user is sent to the user interaction module; each set of meal matching plans also includes the estimated time required for the user to reach the ideal weight loss weight after implementing the corresponding meal matching plan; Specifically: First, the user's gender, weight, height and age are extracted from the user's personal information, and the user's basal metabolic rate is calculated based on this information. The basal metabolic rate refers to the minimum energy consumption required for a person to maintain life in a quiet state (such as sleeping), which is estimated by the Harris-Benedict equation. At the same time, the total amount of exercise of the user in the past week is obtained, and the range of values ​​of each group of exercise amount corresponding to the total amount of exercise is preset, and each group of exercise amount value range is set to correspond to an activity level coefficient, and the total amount of exercise of the user in the past week is matched with the preset range of values ​​of each group of exercise amount, so as to obtain the activity level coefficient of the user; The activity level coefficient range is set at 1.2-1.9. The higher the total amount of exercise the user has done in the past week, the higher the activity level coefficient will be. Multiply the user's basal metabolic rate and activity level coefficient to obtain the user's estimated daily energy expenditure; extract the user's weight and ideal weight loss goal from the user's personal information, and perform difference calculation to obtain the user's weight loss amount; generate each group of meal matching plans corresponding to the user based on the user's weight loss amount and estimated energy expenditure; The user's weight loss amount and estimated energy consumption are input into a pre-constructed database, so as to obtain each group of dietary matching plans of the user at the current time point; the database includes each group of preset weight loss amount value ranges, and each group of preset weight loss amount value ranges corresponds to multiple groups of estimated energy consumption value ranges, and each group of estimated energy consumption value ranges is set to correspond to multiple groups of dietary matching plans; For example, The range of weight loss is 10-20 kg; Estimated energy expenditure range 1: 2500-2700 kcal / day; Meal plan 1: Breakfast: whole wheat bread with boiled eggs and low-fat milk (350 kcal); Lunch: Grilled fish with steamed vegetables and brown rice (500 kcal); Dinner: stir-fried lean meat and vegetables with a small amount of rice (450 kcal); Snack: one serving of fruit and a handful of nuts (150 kcal); Meal Plan 2: Breakfast: Greek yogurt with fresh berries and a small spoonful of honey (269 kcal); Lunch: Grilled Chicken Breast Salad (420 kcal); Dinner: Tofu and vegetable soup with brown rice (380 kcal) 380; Snack: a small bag of mixed nuts (no salt added) (170 kcal); The user interaction module is used to receive each set of meal matching plans generated by the user and send them to the user, and the user receives each set of meal matching plans and selects the meal matching plan to be implemented; the meal matching plan can be sent to the user's mobile terminal or email to remind the user to make the selection; If the dietary plan selected by the user contains prohibited foods that appear in the user's dietary preferences, alternative foods for the prohibited foods will be provided and sent to the user for the user to select as a replacement; The observation and evaluation module is used to obtain the dietary combination plan that the user needs to implement, and extract the required estimated duration corresponding to the dietary combination plan, and divide the required estimated duration into X observation sub-time zones according to the duration range of the required estimated duration of the group; X is the total number of divided observation sub-time zones, and the specific number is obtained according to the division ratio; when reaching the divided observation sub-time zone, based on the result of user feedback, the implemented dietary combination plan is adjusted accordingly; Specifically: Set the estimated weight range of the user when arriving at each observation sub-time zone. If the weight detected by the user when arriving at a certain observation sub-time zone is higher than the corresponding set estimated weight range, an evaluation signaling is triggered and sent to the user; The user confirms after receiving the triggered evaluation signaling; if the user rejects the triggered evaluation signaling, the implemented dietary plan will not be adjusted in the current observation sub-time zone; the user's weight in the current observation sub-time zone and the highest value in the estimated weight range are extracted, and the difference is calculated to obtain the user's weight loss distance in the current observation sub-time zone; Preset the distance value ranges of each group of weight loss distance, set each group of distance value ranges to correspond to an additional coefficient; match the weight loss distance of the user in the current observation sub-time zone with the preset distance value ranges of each group, so as to obtain the additional coefficient; The additional coefficient value range is set at 0.819-0.974; At the same time, a weight change trend graph of the user at each time point in the current observation sub-time zone is constructed, and the numerical points corresponding to the weight values ​​of the user at each time point in the current observation sub-time zone are plotted in the weight change trend graph, and adjacent numerical points are connected to obtain a weight line; Calculate the slope of each weight line and the angle between it and the horizontal line. If the angle between a weight line and the horizontal line is acute, mark the slope of the weight line as the weight loss slope. If the angle between a weight line and the horizontal line is obtuse, mark the slope of the weight line as the rebound slope. All weight loss slopes and rebound slopes are summed up respectively, thereby obtaining the total weight loss value and total rebound value of the user in the current observation sub-time zone; the weight loss status value of the user in the current observation sub-time zone is obtained by calculating the total weight loss value / total rebound value; The weight loss trend of the user in the current observation sub-time zone is determined by the calculated weight loss status value. If the weight loss status value is greater than 1, the user's weight loss status is determined to be a gradual weight loss trend. If the weight loss status value is less than 1, the user's weight loss status is determined to be an excessive weight rebound trend. It should be noted that, by calculating the weight loss status value, users can understand their weight loss status in a specific time period, thereby helping the platform to make more accurate adjustments. If the user's weight loss status is a gradual decrease in weight, it means that the user's weight in the current observation sub-time zone is mostly in a gradual decrease state and maintains a very good state. The corresponding adjustment to the dietary plan is relatively simple. If the user's weight loss status is an excessive rebound trend in weight, it means that the user's weight in the current observation sub-time zone is mostly in a repeated increase state. The corresponding dietary plan needs to be adjusted to a large extent.

[0019] Set an adjustment coefficient for the gradual weight loss trend and the excessive weight rebound trend respectively; the adjustment coefficient corresponding to the gradual weight loss trend should be lower than the adjustment coefficient corresponding to the excessive weight rebound trend, and the adjustment coefficient range is set at 0.912-0.968; Extract the dietary plan implemented by the user, extract the daily calorie intake in the dietary plan and multiply it by the additional coefficient and the adjustment coefficient, that is, daily calorie intake × additional coefficient × adjustment coefficient, to obtain the adjusted daily calorie intake, and push the alternative food in the dietary plan to the user. After the user completes the selection, the daily calorie intake in the dietary plan is the same as the adjusted daily calorie intake; The adjusted dietary plan is used as the dietary plan temporarily implemented by the user in the next observation sub-time zone; It should be noted that if the user's weight detected in the next observation sub-time zone is within the corresponding set estimated weight range, the adjustment content of the dietary plan in the previous observation sub-time zone will be popped up and pushed to the user. After receiving it, the user decides whether to restore the initial content or maintain the adjusted content.

[0020] In summary, this process improves the effectiveness of meal pairing plans through personalized calorie adjustments and user participation, helping users achieve their weight loss goals more healthily and effectively; The expert consultation module is used to analyze the query merit Ft of each expert at the current time point when the user triggers the consultation signaling, and push the ranking results based on the query merit Ft of each expert to the user. After the user selects the corresponding expert, a remote communication connection is established with the expert; Specifically: Obtain all experts who are online at the current time point, and use all experts who are online as candidate experts for the user at the current time point; Count the number of users waiting to be connected for each candidate expert and use it as the waiting index s1 of each candidate expert; extract the number of service users, years of experience and user evaluation from the historical data of each candidate expert; convert the number of service users and years of experience of each candidate expert into experience scores according to the preset conversion rules; Preset the quantity value range and the length value range corresponding to the number of service users and the number of years of employment respectively, and set each group of quantity value range and length value range to correspond to a group of experience scores respectively; The experience score range is set to 1-5, which is preset by the technical staff and can be dynamically adjusted according to the actual situation later; For example, The preset value ranges for the number of service users and years of experience, as well as the corresponding experience scores, are as follows: The range of service user quantity: Range A: 0-100 users, experience score 1; Range B: 101-500 users, experience score 2; Range C: 501-1000 users, experience score 3; Range D: 1001-2000 users, experience score 4; Range E: 2001+ users, experience score 5; The range of years of employment: Range A: 0-5 years, experience score 1; Range B: 6-10 years, experience score 2; Range C: 11-15 years, experience score 3; Range D: 16-20 years, experience score 4; Range E: 21+ years, experience score 5; Weight coefficient: Weight coefficient of the number of service users: 0.4; Weight coefficient of years of experience: 0.6; Now, we have two candidate experts, their information is as follows: Expert A: Number of service users: 150 users; Years of experience: 8 years; Expert B: Number of service users: 800 users; Years in business: 16 years; Evaluation process: Number of matching service users: Expert A matches range B (101-500 users) and gets an experience score of 2; Expert B matches range D (1001-2000 users) and gets an experience score of 4; Matching years of experience: Expert A matches range B (6-10 years) and gets an experience score of 2; Expert B matches range D (16-20 years) and gets an experience score of 4; Calculate the overall experience score: Expert A's comprehensive experience score = (2 × weight factor 0.4) + (2 × weight factor 0.6) = 2.0; Expert B's comprehensive experience score = (4 × weight factor 0.4) + (4 × weight factor 0.6) = 4.0; According to this assessment, Expert B received a higher overall experience score because he served more users and had more years of experience; Match the number of service users and years of employment of each candidate expert with the corresponding number value range and years value range, so as to obtain the experience score corresponding to the number of service users and years of employment of each candidate expert; preset the weight coefficients of the experience score corresponding to the number of service users and the experience score corresponding to the years of employment; Multiply the experience score corresponding to the number of service users of each candidate expert and the experience score corresponding to the years of service by the corresponding preset weight coefficients, and then sum them up to obtain the experience index s2 of each candidate expert; the weight coefficient of the experience score corresponding to the number of service users should be smaller than the weight coefficient of the experience score corresponding to the years of service. If it is later found that the impact of the number of service users on the quality of experts is greater than expected, the technicians can adjust the weight coefficient; Obtain the user evaluation of each candidate expert; the user evaluation is the user's rating of the satisfaction with the consultation process after the connection is completed, and the rating range is set to 1-5. The higher the rating, the higher the user's recognition of the expert; and calculate the average of the user ratings of each candidate expert group to obtain the service index s3 of each candidate expert; Using the formula , weighted calculation is performed on the waiting index s1, experience index s2 and service index s3 of each candidate expert, so as to obtain the query merit Ft of each candidate expert; where ei, zi and qi are the influence weight factors of the waiting index s1, experience index s2 and service index s3 respectively; Where i=1,2 or 3, and the merit value Ft of each candidate expert under different influence weight factors is calculated respectively; when i is 1, e1>z1>q1; when i is 2, z2>q2>e2; when i is 3, q3>z3>e3; Based on the query merit Ft of each candidate expert, they are sorted from large to small, and the candidate expert with the largest query merit when i=1, the candidate expert with the largest query merit when i=2, and the candidate expert with the largest query merit when i=3 are selected. They are integrated into a recommended expert lineup and pushed to the user. After the user selects the corresponding expert, the number of users to be connected and the number of service users of the expert increases by one; The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factor and specific coefficient value in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0021] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An artificial intelligence-based healthy diet nutrition matching guidance platform, characterized by: include: Information collection module: users create accounts and enter personal information and eating habits preferences; Integrate the personal information and dietary preferences entered by the user into a comprehensive data package for the user and send it to the plan generation module; Plan generation module: receiving the user's comprehensive data package, parsing and evaluating it, thereby generating the corresponding meal matching plans for each group of users; sending the meal matching plans generated by the user to the user interaction module; wherein each meal matching plan also includes the estimated time required for the user to reach the ideal weight loss weight after implementing the corresponding meal matching plan; User interaction module: receiving each set of meal matching plans generated by the user and sending them to the user, and the user receiving each set of meal matching plans and selecting the meal matching plan to be implemented; Observation and evaluation module: obtain the dietary plan that the user needs to implement, and extract the required estimated duration corresponding to the dietary plan, and divide the required estimated duration into X observation sub-time zones according to the duration range of the group of required estimated durations; X is the total number of divided observation sub-time zones; when reaching the divided observation sub-time zones, adjust the implemented dietary plan accordingly based on the results of user feedback; Expert consultation module: When the user triggers the consultation signaling, the query merit Ft of each expert at the current time point is analyzed, and the ranking results based on the query merit Ft of each expert are pushed to the user. After the user selects the corresponding expert, a remote communication connection is established with the expert.

2. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 1, characterized in that: Receive the user's comprehensive data package, parse and evaluate it, and generate the user's corresponding meal matching plan, specifically: First, the gender, weight, height and age are extracted from the user's personal information, and the user's basal metabolic rate is calculated based on this; At the same time, the total amount of exercise of the user in the past week is obtained, and the range of values ​​of each group of exercise amount corresponding to the total amount of exercise is preset, and each group of exercise amount value range is set to correspond to an activity level coefficient, and the total amount of exercise of the user in the past week is matched with the preset range of values ​​of each group of exercise amount, so as to obtain the activity level coefficient of the user; Multiply the user's basal metabolic rate and activity level factor to get the user's estimated daily energy expenditure; Extracting the user's weight and ideal weight loss goal from the user's personal information, and performing difference calculation to obtain the user's weight loss amount; Generate meal plans for each group of users based on the user's weight loss and estimated energy consumption; The user's weight loss amount and estimated energy consumption are input into a pre-constructed database to obtain various groups of dietary matching plans for the user at the current time point; the database includes various groups of preset weight loss amount value ranges, and each group of preset weight loss amount value ranges corresponds to multiple groups of estimated energy consumption value ranges, and each group of estimated energy consumption value ranges is set to correspond to multiple groups of dietary matching plans.

3. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 1 is characterized in that: When arriving at the divided observation sub-time zone, analysis is performed based on the results of user feedback, specifically: Set the estimated weight range of the user when arriving at each observation sub-time zone. If the weight detected by the user when arriving at a certain observation sub-time zone is higher than the corresponding set estimated weight range, an evaluation signaling is triggered and sent to the user; After receiving the triggered evaluation signaling, the user confirms it, extracts the user's weight in the current observation sub-time zone and the highest value in the estimated weight range, and calculates the difference to obtain the user's weight loss distance in the current observation sub-time zone; Preset the distance value ranges for weight loss distance, set each distance value range to correspond to an additional coefficient; match the weight loss distance of the user in the current observation sub-time zone with the preset distance value ranges for each group, so as to obtain the additional coefficient.

4. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 3 is characterized in that: When arriving at the divided observation sub-time zone, analysis is performed based on the results of user feedback, including: Construct a weight change trend graph of the user at each time point in the current observation sub-time zone, draw the numerical points in the weight change trend graph corresponding to the user's weight value at each time point in the current observation sub-time zone, and connect adjacent numerical points to obtain a weight line; Calculate the slope of each weight line and the angle between it and the horizontal line. If the angle between a weight line and the horizontal line is acute, mark the slope of the weight line as the weight loss slope. If the angle between a weight line and the horizontal line is obtuse, mark the slope of the weight line as the rebound slope. All weight loss slopes and rebound slopes are summed up respectively, thereby obtaining the total weight loss value and total rebound value of the user in the current observation sub-time zone; the weight loss status value of the user in the current observation sub-time zone is obtained by calculating the total weight loss value / total rebound value; The calculated weight loss status value is used to determine the user's weight loss trend in the current observation sub-time zone. If the weight loss status value is greater than 1, the user's weight loss status is determined to be a gradual weight loss trend. If the weight loss status value is less than 1, the user's weight loss status is determined to be an excessive weight rebound trend.

5. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 4 is characterized in that: The dietary plan to be implemented is adjusted accordingly, specifically: An adjustment coefficient is set to correspond to the gradual weight loss trend and the excessive weight rebound trend respectively; the dietary plan implemented by the user is extracted, the daily calorie intake in the dietary plan is extracted and multiplied by the additional coefficient and the adjustment coefficient, that is, the daily calorie intake × additional coefficient × adjustment coefficient, to obtain the adjusted daily calorie intake, and the alternative food in the dietary plan is pushed to the user. After the user completes the selection, the daily calorie intake in the dietary plan is equal to the adjusted daily calorie intake; The adjusted dietary plan is used as the dietary plan temporarily implemented by the user in the next observation sub-time zone.

6. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 1, characterized in that: The query merit Ft of each expert at the current time point is analyzed as follows: Obtain all experts who are online at the current time point, and use all experts who are online as candidate experts for the user at the current time point; Count the number of users waiting to be connected for each candidate expert and use it as the waiting index s1 of each candidate expert; extract the number of service users, years of experience and user evaluation from the historical data of each candidate expert; convert the number of service users and years of experience of each candidate expert into experience scores according to the preset conversion rules; Preset the weight coefficients of the experience score corresponding to the number of service users and the experience score corresponding to the years of service; Multiply the experience score corresponding to the number of users served by each candidate expert and the experience score corresponding to the years of experience of each candidate expert by the corresponding preset weight coefficient, and then sum them up to obtain the experience index s2 of each candidate expert; Obtain the user evaluations of each candidate expert group; and calculate the average of the user evaluations of each candidate expert group, thereby obtaining the service index s3 of each candidate expert; Using the formula , weighted calculation is performed on the waiting index s1, experience index s2 and service index s3 of each candidate expert to obtain the query merit value Ft of each candidate expert; where ei, zi and qi are the influence weight factors of the waiting index s1, experience index s2 and service index s3 respectively; where i = 1, 2 or 3, and the query merit value Ft of each candidate expert under different influence weight factors is calculated respectively.

7. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 6, characterized in that: The number of service users and years of experience of each candidate expert are converted into experience scores according to the preset conversion rules, specifically: Preset the quantity value range and the number of years value range corresponding to the number of service users and the number of years of experience respectively, and set each group of quantity value range and the number of years value range to correspond to a group of experience scores respectively; match the number of service users and the number of years of experience of each candidate expert with the corresponding quantity value range and the number of years value range respectively, so as to obtain the experience scores corresponding to the number of service users and the number of years of experience of each candidate expert respectively.

8. The artificial intelligence-based healthy diet nutrition matching guidance platform according to claim 6, characterized in that: The ranking results based on the query merit Ft of each expert are pushed to the user. Specifically, based on the query merit Ft of each candidate expert, they are sorted from large to small, and the candidate expert with the largest query merit when i=1, the candidate expert with the largest query merit when i=2, and the candidate expert with the largest query merit when i=3 are selected. The recommended expert lineup is integrated and pushed to the user. After the user selects the corresponding expert, the number of users to be connected and the number of service users of the expert are increased by one.

Images