Nutrition evaluation method and system

Abstract

The invention relates to the technical field of nutrition evaluation, in particular to a nutrition evaluation method. The method comprises the following steps: S1, creating a personal virtual image in a meta universe; s2, collecting health data of the user; s3, performing virtual interaction in the matched health course to generate a virtual interaction text; s4, scanning and deleting the virtual interaction text to obtain a health assessment text; and S5, performing matching analysis on the health data and the health assessment text to determine whether to correct the real-time relevancy into the corrected relevancy. According to the method, the timeliness and the accuracy of evaluation are improved by combining nutrition evaluation with the interaction characteristics of the meta universe, data cleaning is performed on the virtual interaction text, the matching degree between the health data and the health evaluation text is calculated, and when the matching degree is low, the standard relevancy is adaptively increased, so that the evaluation accuracy is improved. Therefore, a more suitable health course is recommended next time, and the management capability and adaptability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of nutrition assessment, and in particular to a nutrition assessment method. Background Art

[0002] Dietary nutrition is the basis of human survival. The human body continuously renews itself, all of which are derived from the food we eat every day. The human body needs to obtain a certain amount of various essential nutrients from the diet every day to meet a series of complex biochemical reactions in the life process. If there is too much or insufficient nutrient in the food we eat, malnutrition will occur. Malnutrition includes nutrient deficiency, imbalance and excess. Any form of malnutrition will have an adverse effect on health over time. In order to help people safely consume various nutrients, nutritionists have recommended reference intakes of certain nutrients based on relevant knowledge since the early 20th century.

[0003] The multi-objective nutrition model and optimization algorithm based on fuzzy theory are based on the nutrition curve analysis method. They comprehensively consider individual age, height, weight, gender, exercise status, environment, individual body tissue condition, living habits, eating habits, disease status and other conditions. A multi-objective nutrition model based on fuzzy theory has been re-established, and appropriate optimization methods have been used to obtain the optimization results of the individual's overall nutritional needs, laying the foundation for further dietary nutrition decisions.

[0004] With the development of metaverse technology, it becomes possible to use virtual environments for personal health management, providing more flexible and dynamic assessment and guidance methods.

[0005] Patent document No. 112837783B discloses a method and device for evaluating nutrition of patients, which includes: obtaining the disease type of the patient and the patient's lifestyle information and food intake information within a predetermined time; searching for a nutrition weight distribution model corresponding to the disease type of the patient according to a pre-stored relationship table between the disease type and the nutrition weight distribution model; and evaluating the nutrition of the patient using the nutrition weight distribution model and the patient's lifestyle information and food intake information within a predetermined time. Traditional nutrition evaluation methods often rely on paper questionnaires and face-to-face consultations, which cannot update and analyze the user's health data in a timely manner, resulting in lags and limitations in the evaluation results. Summary of the invention

[0006] To this end, the present invention provides a nutrition assessment method to overcome the problems in the prior art of lack of timely updating and analysis of user's health data, resulting in lags and limitations in assessment results and poor management capabilities of the nutrition assessment system.

[0007] To achieve the above object, the present invention provides a nutrition assessment method, comprising:

[0008] Create a personal avatar in the Metaverse and enter its basic information, including account number, health goal data, height, age, weight and gender;

[0009] Collecting health data of users through smart devices, including physiological data, daily diet records and health product purchase records;

[0010] Matching a number of health course packages in a health course database according to the basic information, calculating real-time relevance according to the basic information, selecting a matching health course from each of the health course packages according to the real-time relevance, performing virtual interaction in the matching health course, and generating a virtual interaction text;

[0011] Scanning and deleting the virtual interactive text to obtain a health assessment text;

[0012] A matching analysis is performed on the health data and the health assessment text, and it is determined whether to correct the real-time relevance to a corrected relevance according to the analysis result.

[0013] Further, matching health courses in a health course database according to the basic information includes:

[0014] According to the health target data, a number of health course packages are selected and marked in the health course database, and the marked health course packages are extracted to obtain the initial screening courses;

[0015] BMI is calculated based on height and weight, real-time relevance is calculated based on BMI and health target data, and the real-time relevance is judged based on standard relevance to determine the priority of health courses, and the course with the highest priority is selected as the matching course.

[0016] Further, outputting the nutritional risk score includes, prioritizing the health courses includes,

[0017] When the real-time relevance is less than the standard relevance, the health courses are sorted according to BMI;

[0018] When the real-time relevance is greater than or equal to the standard relevance, the health courses are sorted according to the course evaluation values.

[0019] Further, scanning and deleting the virtual interactive text includes:

[0020] Scanning the virtual interactive text with a preset scanning length to obtain a current detection text segment, and extracting nutrition-related keywords in the current detection text segment as real-time keywords;

[0021] Determining the number of the extracted real-time keywords, and matching and determining the real-time keywords with the nutrition keywords in the nutrition and health database to obtain keywords to be detected;

[0022] Perform repeated field detection on the keyword to be detected to obtain a continuous character segment, perform matching detection on the continuous character segment according to the keyword to be detected, and determine whether to delete the continuous character segment based on the result of the matching detection to obtain the health assessment text.

[0023] Further, determining the number of the extracted real-time keywords includes:

[0024] When the number of the extracted real-time keywords is greater than or equal to one, matching and judging the real-time keywords with the nutrition keywords in the nutrition and health database to determine whether to mark the real-time keywords;

[0025] When the number of the extracted real-time keywords is less than one, a matching determination is performed on the next detected text segment.

[0026] Further, matching and determining the real-time keyword with the nutrition keyword in the nutrition and health database includes:

[0027] Select a real-time keyword in chronological order, and match and determine the real-time keyword with the nutrition keyword in the nutrition and health database.

[0028] When there is a match with the nutrition keyword, obtaining the keyword to be detected;

[0029] If there is no match with the nutrition keyword, continue to make a match determination for the next real-time keyword until the scanning process of the virtual interactive text is completed to obtain the health assessment text.

[0030] Furthermore, the repeated field detection includes taking the character length of the keyword to be detected as the detection character length, taking the next adjacent character of the keyword to be detected as the starting node, performing repeated field detection on the virtual interactive text with the detection character length, and obtaining a continuous character segment.

[0031] Further, any nutrition keyword data packet includes nutrition keywords and associated keywords corresponding to the nutrition keywords;

[0032] The result of the matching detection includes obtaining the nutrition keyword and the associated keyword corresponding to the keyword to be detected in the nutrition and health database as a number of keywords to be matched, and performing matching detection on the continuous character segment according to each of the keywords to be matched.

[0033] If the keyword to be matched matches the continuous character segment, it is determined that duplicate data exists, the continuous character segment is deleted, and repeated field detection is continued for the keyword to be detected to obtain the continuous character segment, so as to perform matching detection on the continuous character segment;

[0034] If the keyword to be matched does not match the continuous character segment, it is determined that no duplicate data occurs, and the duplicate field detection of the keyword to be detected is completed. The next keyword to be detected is subjected to duplicate field detection, and the corresponding continuous character segment is obtained to determine whether to delete the continuous character segment.

[0035] Furthermore, matching analysis of the health data and the health assessment text includes:

[0036] Calculate the real-time matching degree between the health assessment text and the health data, and determine the real-time matching degree based on the standard matching degree.

[0037] When the real-time matching degree is less than the standard matching degree, the standard relevance is corrected to a corrected relevance;

[0038] When the real-time matching degree is greater than or equal to the standard matching degree, the standard relevance is not corrected;

[0039] Wherein, Kb'=Kb×[1+(Qb-Qs) / Qs], Kb' is the corrected relevance, Kb is the standard relevance, Qb is the standard matching degree, and Qs is the real-time matching degree.

[0040] On the other hand, the present invention also provides a nutrition assessment system applied to the above nutrition assessment method, comprising:

[0041] A virtual rendering module, used to create a personal virtual image in the Metaverse and input its basic information, including account number, health goal data, height, age, weight and gender;

[0042] A data collection module is used to collect the user's health data, including physiological data, daily diet records and health product purchase records;

[0043] A course matching module, used for matching a number of health course packages in a health course database according to the basic information, calculating a real-time relevance according to the basic information, and selecting a matching health course in each of the health course packages according to the real-time relevance;

[0044] A virtual interaction module, for providing a virtual scene for users to conduct virtual interaction in the matching health course;

[0045] An interaction recording module, which is connected to the virtual interaction module and is used to obtain virtual interaction text, scan and delete the virtual interaction text, and obtain a health assessment text;

[0046] The correction module is used to perform matching analysis on the health data and the health assessment text, and determine whether to correct the real-time correlation to the corrected correlation according to the analysis result.

[0047] Compared with the prior art, the beneficial effect of the present invention lies in that, by combining nutrition assessment with the interactive characteristics of the metaverse, not only the timeliness and accuracy of the assessment are improved, but also the effect of nutrition intervention is improved by enhancing the user participation experience, which is helpful to promote the public's health awareness and the dissemination of nutrition knowledge. By matching the health course database according to the user's basic information in the metaverse to match the health course most relevant to the user, and generating text according to the user's virtual interactive feedback to record the course, generate virtual interactive texts such as health advice, nutrition tips, potential health risks, and lifestyle adjustment suggestions, and by performing data cleaning on the virtual interactive text, that is, deleting redundant or repeated information in the health assessment text, Convert the information in health data and assessment texts into comparable formats. For example, standardize the food portions, calories and other information in diet records to ensure data consistency. By extracting features from health data, such as BMI value, total calorie intake, main nutrients consumed (protein, fat, carbohydrates, vitamins, minerals, etc.), and extracting key suggestions and evaluation indicators from health assessment texts, such as reducing calorie intake, increasing exercise, improving certain nutritional deficiencies, etc., to calculate the degree of match between health data and health assessment texts. When the degree of match is low, adaptively increase the standard relevance to recommend more suitable health courses next time, thereby improving the management capabilities and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 Schematic diagram of a nutritional assessment method according to an embodiment of the present invention;

[0049] Figure 2 Schematic diagram of the connection of the nutrition assessment system according to the embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0052] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0053] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] See also Figure 1 As shown, it is a flow chart of a nutrition assessment method according to an embodiment of the present invention. The present invention provides a nutrition assessment method, comprising:

[0055] Step S1, creating a personal avatar in the Metaverse and inputting its basic information, the basic information including account number, health goal data, height, age, weight and gender;

[0056] Step S2, collecting the user's health data through a smart device, wherein the health data includes physiological data, daily diet records, and health care product purchase records, wherein the health care products include functional foods and dietary supplements;

[0057] Step S3, matching several health course packages in a health course database according to the basic information, calculating real-time relevance according to the basic information, selecting a matching health course from each of the health course packages according to the real-time relevance, performing virtual interaction in the matching health course, and generating a virtual interaction text;

[0058] Step S4, scanning and deleting the virtual interactive text to obtain a health assessment text;

[0059] Step S5, performing matching analysis on the health data and the health assessment text, and determining whether to correct the real-time relevance to a corrected relevance based on the analysis result.

[0060] The present invention combines nutrition assessment with the interactive characteristics of the metaverse, which not only improves the timeliness and accuracy of the assessment, but also improves the effect of nutrition intervention by enhancing the user's participation experience, which helps to promote the public's health awareness and the dissemination of nutrition knowledge. By matching the user's basic information in the health course database in the metaverse to match the health course most relevant to the user, and generating text based on the user's virtual interactive feedback to record the course, generate virtual interactive texts such as health advice, nutrition tips, potential health risks, and lifestyle adjustment suggestions, and perform data cleaning on the virtual interactive text, that is, deleting redundant or repeated information in the health assessment text, the health data is converted into The system can convert the information in the health data and the assessment text into a comparable format, for example, unify the food portion, calories and other information in the diet record to ensure data consistency, extract features from the health data, such as BMI value, total calorie intake, main nutrients consumed (protein, fat, carbohydrates, etc.), and extract key suggestions and evaluation indicators from the health assessment text, such as reducing calorie intake, increasing exercise, improving certain nutritional deficiencies, etc., to calculate the degree of match between the health data and the health assessment text, and adaptively increase the standard relevance when the match is low, so as to recommend a more suitable health course next time, thereby improving the management ability and adaptability of the system.

[0061] Specifically, matching health courses in a health course database according to the basic information includes:

[0062] According to the health target data, a number of health course packages are selected and marked in the health course database, and the marked health course packages are extracted to obtain the initial screening courses;

[0063] BMI is calculated based on height and weight, real-time relevance is calculated based on BMI and health target data, and the real-time relevance is judged based on standard relevance to determine the priority of health courses, and the course with the highest priority is selected as the matching course.

[0064] The health goal data in this embodiment is text data entered by the user, indicating that the goal the user hopes to achieve will directly affect the recommended course type. The health goal data is used to screen out the initial screening courses that meet the user's matching criteria in the health course database. Each course will have predefined labels, such as "weight loss course", "muscle building training", "nutrition knowledge course", "mental health course", etc., and BMI is calculated based on height and weight. The real-time correlation is calculated based on BMI and health goal data to check whether the health goal data entered by the user matches his or her own health level.

[0065] Specifically, the output nutrition risk score includes, and the prioritization of health courses includes,

[0066] When the real-time relevance is less than the standard relevance, the health courses are sorted according to BMI;

[0067] When the real-time relevance is greater than or equal to the standard relevance, the health courses are sorted according to the course evaluation values.

[0068] By comparing the real-time relevance with the standard relevance, when the real-time relevance is less than the standard relevance, it means that the health goal data is different from the user's own health level. In this case, courses are filtered according to BMI, that is, the user's actual health level, with the user's body mass index (BMI) as the final factor in determining the course type. When the real-time relevance is greater than or equal to the standard relevance, it means that the health goal data entered by the user is very consistent with his or her own health level. In this case, the system sorts the health courses according to user feedback and effectiveness of the courses, and prioritizes these courses. For example, the feedback on the "Fitness Plan for Overweight Men" is very good, and 80% of participating users achieve their weight loss goals, so it is placed in a higher priority.

[0069] Specifically, scanning and deleting the virtual interactive text includes:

[0070] Scanning the virtual interactive text with a preset scanning length to obtain a current detection text segment, and extracting nutrition-related keywords in the current detection text segment as real-time keywords;

[0071] Determining the number of the extracted real-time keywords, and matching and determining the real-time keywords with the nutrition keywords in the nutrition and health database to obtain keywords to be detected;

[0072] Perform repeated field detection on the keyword to be detected to obtain a continuous character segment, perform matching detection on the continuous character segment according to the keyword to be detected, and determine whether to delete the continuous character segment based on the result of the matching detection to obtain the health assessment text.

[0073] By analyzing and processing the recorded virtual interactive text, the repeated content appearing in the virtual interactive text can be efficiently identified, that is, by performing repeated field detection on the keyword, and continuously obtaining continuous character segments adjacent to the keyword and with the same character length, until it is determined that the continuous character segment does not match the keyword, the repeated field detection of the current keyword is stopped, thereby avoiding repeated matching of repeated real-time keywords in the database, that is, avoiding repeated detection of matches, improving data processing efficiency, deleting repeated content, processing data in a timely and effective manner, reducing repeated and redundant information in the virtual interactive text, improving data quality and availability, and analyzing the correlation between the health assessment text and the health data in more detail to analyze the user's health status and its relationship with the assessment recommendations, thereby improving the system's adaptability and management efficiency.

[0074] Specifically, determining the number of the extracted real-time keywords includes:

[0075] When the number of the extracted real-time keywords is greater than or equal to one, matching and judging the real-time keywords with the nutrition keywords in the nutrition and health database to determine whether to mark the real-time keywords;

[0076] When the number of the extracted real-time keywords is less than one, a matching determination is performed on the next detected text segment.

[0077] The preset scanning length in this embodiment is the size of the scanning window, which is set by the user according to needs and can be a fixed length of characters or words. The sliding window starts from the starting position of the virtual interactive text and slides on the virtual interactive text with a set length, each time sliding a fixed step length. The set preset scanning length is adjustable to flexibly scan and process the virtual interactive text to adapt to different text processing needs; the real-time keywords are nutrition-related keywords, and the real-time keywords are extracted from the nutrition vocabulary, and the keywords are extracted by matching the words in the text data with the nutrition-related words in the vocabulary.

[0078] By obtaining the current detection data segment, the real-time keywords in the current detection data segment are extracted to process or analyze the text data in the sliding window at each sliding window position. By adopting a fast scanning method, the recorded virtual interactive text is analyzed and processed. The method is simple and effective.

[0079] Specifically, matching and determining the real-time keyword with the nutrition keyword in the nutrition and health database includes:

[0080] Select a real-time keyword in chronological order, and match and determine the real-time keyword with the nutrition keyword in the nutrition and health database.

[0081] When there is a match with the nutrition keyword, obtaining the keyword to be detected;

[0082] If there is no match with the nutrition keyword, continue to make a match determination for the next real-time keyword until the scanning process of the virtual interactive text is completed to obtain the health assessment text.

[0083] By matching the extracted keywords in chronological order when it is determined that the number of the extracted real-time keywords is greater than or equal to one, the orderliness of data processing is guaranteed and it is ensured that the health data and health assessment text do not contain redundant or repeated information.

[0084] Specifically, the repeated field detection includes taking the character length of the keyword to be detected as the detection character length, taking the next adjacent character of the keyword to be detected as the starting node, performing repeated field detection on the virtual interactive text with the detection character length, and obtaining a continuous character segment.

[0085] In this embodiment, since consecutive words may appear repeatedly, after matching a keyword, a repeated field detection is performed on the keyword. By continuously obtaining consecutive character segments adjacent to the keyword and with the same character length, until it is determined that the extended character segment does not match the keyword, the extended scanning detection of the current keyword is stopped, thereby avoiding repeated matching of repeated real-time keywords in the database, that is, avoiding repeated detection of matches, and improving data processing efficiency.

[0086] Specifically, any nutrition keyword data packet includes a nutrition keyword and an associated keyword corresponding to the nutrition keyword;

[0087] The result of the matching detection includes obtaining the nutrition keyword and the associated keyword corresponding to the keyword to be detected in the nutrition and health database as a number of keywords to be matched, and performing matching detection on the continuous character segment according to each of the keywords to be matched.

[0088] If the keyword to be matched matches the continuous character segment, it is determined that duplicate data exists, the continuous character segment is deleted, and repeated field detection is continued for the keyword to be detected to obtain the continuous character segment, so as to perform matching detection on the continuous character segment;

[0089] If the keyword to be matched does not match the continuous character segment, it is determined that no duplicate data occurs, and the duplicate field detection of the keyword to be detected is completed. The next keyword to be detected is subjected to duplicate field detection, and the corresponding continuous character segment is obtained to determine whether to delete the continuous character segment.

[0090] The nutritional keyword data packet set in this embodiment includes nutrients, nutritional indicators and dietary methods corresponding to nutrients, dietary supplements and allergens, and the associated keywords are words with the same semantics as nutrients. For example, if the nutrient is protein, the corresponding associated keywords are protein and amino acid chain.

[0091] In this embodiment, since the various expressions of nutrition and health also cause duplication and redundancy in nutrition and health data, multiple expressions of the same nutritional status are stored in the nutrition and health database to facilitate timely and effective data processing during keyword matching analysis, reduce duplication and redundant information in nutrition and health data, and improve data quality and availability.

[0092] Specifically, matching and analyzing the health data and the health assessment text includes:

[0093] Calculate the real-time matching degree between the health assessment text and the health data, and determine the real-time matching degree based on the standard matching degree.

[0094] When the real-time matching degree is less than the standard matching degree, the standard relevance is corrected to a corrected relevance;

[0095] When the real-time matching degree is greater than or equal to the standard matching degree, the standard relevance is not corrected;

[0096] Wherein, Kb'=Kb×[1+(Qb-Qs) / Qs], Kb' is the corrected relevance, Kb is the standard relevance, Qb is the standard matching degree, and Qs is the real-time matching degree.

[0097] In this embodiment, the real-time correlation is calculated based on BMI and health target data, or the correlation between health data and health assessment text is calculated using cosine similarity. Cosine similarity evaluates the similarity of two vectors by measuring the angle between them in space. The value range is between 0 and 1, where 1 indicates exactly the same and 0 indicates completely different. The standard matching degree is set to 70%, and is adjusted according to the actual application requirements.

[0098] Calculate real-time relevance based on BMI and health goal data, e.g.

[0099] User's BMI: 27 (i.e. overweight).

[0100] User health goal text: "Lose weight by 10 kg and improve eating habits".

[0101] BMI vector: 27;

[0102] Healthy target vector (assuming word embedding or TF-IDF processing): [0.8, 0.2, 0.5];

[0103] Comprehensive feature vector:

[0104] F = [27, 0.8, 0.2, 0.5];

[0105] By calculating the cosine similarity, the similarity value is obtained, and finally the real-time correlation between the user's health goal and the existing BMI is obtained.

[0106] Calculate the correlation between health data and health assessment text, e.g.

[0107] The health data and health assessment text are segmented separately, and the similarity between each health assessment segment and the health data is calculated. If the health data segment has a high similarity with the health assessment text segment, it means that the extracted features match. By converting the health data segment and the health assessment text segment into a vector form suitable for calculating cosine similarity, features are extracted from the health data segment and the health assessment text segment, such as protein intake (g), carbohydrate intake (g), fat intake (g), BMI value, blood sugar level (mmo l / L). For the health assessment text segment, the features corresponding to the corresponding suggestions are extracted, where the suggestions can be specific as "increase protein intake", "reduce fat intake", etc.

[0108] Convert the features into vectors to form health data vectors and evaluation text vectors;

[0109] Health data vector: health data = [protein intake, carbohydrate intake, fat intake, BMI, blood sugar level] = [50, 200, 70, 28, 6.5];

[0110] Health assessment text vector: assessment text = [recommended protein intake, recommended carbohydrate intake, recommended fat intake, recommended BMI, recommended blood sugar level] = [75, 150, 60, 25, 5.6];

[0111] The calculation formula of cosine similarity C is: C = A·B|A||B|;

[0112] Where: A·B represents the dot product of two vectors A and B, |A| and |B| are the vector norms (i.e. the lengths of the vectors).

[0113] When the calculated result is greater than the similarity threshold, it means that the health data segment and the health assessment text segment have a high similarity. The similarity threshold is set between 0.6 and 0.8, and is adjusted according to the actual matching needs.

[0114] In this embodiment, the standard matching degree is used to quantify the correlation between the health data and the health assessment text, expressed as a percentage. The real-time matching degree is the percentage of the number of matching features to the total number of features. The number of matching features indicates the number of features that are consistent or corresponding in the health data and the health assessment text. The total number of features indicates the number of all relevant features. A higher matching degree indicates that the health assessment text provides targeted suggestions for the user's health data, reflecting the accuracy of the matching courses and the accuracy of the assessment. If the matching degree is low, the standard relevance is adaptively increased to improve the accuracy of the matching courses, so that a more suitable health course can be recommended next time, thereby improving the accuracy of the matching courses and the assessment.

[0115] See also Figure 2As shown, it is a connection diagram of a nutrition assessment system according to an embodiment of the present invention. The present invention also provides a nutrition assessment system applied to the above-mentioned nutrition assessment method, comprising:

[0116] A virtual rendering module, used to create a personal virtual image in the Metaverse and input its basic information, including account number, health goal data, height, age, weight and gender;

[0117] A data collection module, used to collect the user's health data, the health data includes physiological data, daily diet records and health care product purchase records, the health care products include functional foods and dietary supplements;

[0118] A course matching module, used for matching a number of health course packages in a health course database according to the basic information, calculating a real-time relevance according to the basic information, and selecting a matching health course in each of the health course packages according to the real-time relevance;

[0119] A virtual interaction module, for providing a virtual scene for users to conduct virtual interaction in the matching health course;

[0120] An interaction recording module, which is connected to the virtual interaction module and is used to obtain virtual interaction text, scan and delete the virtual interaction text, and obtain a health assessment text;

[0121] The correction module is used to perform matching analysis on the health data and the health assessment text, and determine whether to correct the real-time correlation to the corrected correlation according to the analysis result.

[0122] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0123] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A nutritional assessment method, characterized in that: include, Create a personal avatar in the Metaverse and enter its basic information, including account number, health goal data, height, age, weight and gender; Collecting health data of users through smart devices, including physiological data, daily diet records and health product purchase records; Matching a number of health course packages in a health course database according to the basic information, calculating real-time relevance according to the basic information, selecting a matching health course from each of the health course packages according to the real-time relevance, performing virtual interaction in the matching health course, and generating a virtual interaction text; Scanning and deleting the virtual interactive text to obtain a health assessment text; A matching analysis is performed on the health data and the health assessment text, and it is determined whether to correct the real-time relevance to a corrected relevance according to the analysis result.

2. The nutritional assessment method according to claim 1, characterized in that: Matching health courses in a health course database according to the basic information includes: According to the health target data, a number of health course packages are selected and marked in the health course database, and the marked health course packages are extracted to obtain the initial screening courses; BMI is calculated based on height and weight, real-time relevance is calculated based on BMI and health target data, and the real-time relevance is judged based on standard relevance to determine the priority of health courses, and the course with the highest priority is selected as the matching course.

3. The nutritional assessment method according to claim 2, characterized in that: Outputs of nutritional risk scores include, prioritization of health courses include, When the real-time relevance is less than the standard relevance, the health courses are sorted according to BMI; When the real-time relevance is greater than or equal to the standard relevance, the health courses are sorted according to the course evaluation values.

4. The nutritional assessment method according to claim 1, characterized in that: Scanning and deleting the virtual interactive text includes: Scanning the virtual interactive text with a preset scanning length to obtain a current detection text segment, and extracting nutrition-related keywords in the current detection text segment as real-time keywords; Determining the number of the extracted real-time keywords, and matching and determining the real-time keywords with the nutrition keywords in the nutrition and health database to obtain keywords to be detected; Perform repeated field detection on the keyword to be detected to obtain a continuous character segment, perform matching detection on the continuous character segment according to the keyword to be detected, and determine whether to delete the continuous character segment based on the result of the matching detection to obtain the health assessment text.

5. The nutritional assessment method according to claim 4, characterized in that: Determining the number of the extracted real-time keywords includes: When the number of the extracted real-time keywords is greater than or equal to one, matching and judging the real-time keywords with the nutrition keywords in the nutrition and health database to determine whether to mark the real-time keywords; When the number of the extracted real-time keywords is less than one, a matching determination is performed on the next detected text segment.

6. The method for nutritional assessment according to claim 4, characterized in that: Matching the real-time keyword with the nutrition keyword in the nutrition and health database includes: Select a real-time keyword in chronological order, and match and determine the real-time keyword with the nutrition keyword in the nutrition and health database. When there is a match with the nutrition keyword, obtaining the keyword to be detected; If there is no matching item with the nutrition keyword, continue to make a matching determination for the next real-time keyword until the scanning process of the virtual interactive text is completed to obtain the health assessment text.

7. The method for nutritional assessment according to claim 4, characterized in that: The repeated field detection includes taking the character length of the keyword to be detected as the detection character length, taking the next adjacent character of the keyword to be detected as the starting node, performing repeated field detection on the virtual interactive text with the detection character length, and obtaining a continuous character segment.

8. The method for nutritional assessment according to claim 4, characterized in that: Any nutrition keyword data packet includes nutrition keywords and associated keywords corresponding to the nutrition keywords; The result of the matching detection includes obtaining the nutrition keyword and the associated keyword corresponding to the keyword to be detected in the nutrition and health database as a number of keywords to be matched, and performing matching detection on the continuous character segment according to each of the keywords to be matched. If the keyword to be matched matches the continuous character segment, it is determined that duplicate data exists, the continuous character segment is deleted, and repeated field detection is continued for the keyword to be detected to obtain the continuous character segment, so as to perform matching detection on the continuous character segment; If the keyword to be matched does not match the continuous character segment, it is determined that no duplicate data occurs, and the duplicate field detection of the keyword to be detected is completed. The next keyword to be detected is subjected to duplicate field detection, and the corresponding continuous character segment is obtained to determine whether to delete the continuous character segment.

9. The nutritional assessment method according to claim 4, characterized in that: Matching and analyzing the health data and the health assessment text includes: Calculate the real-time matching degree between the health assessment text and the health data, and determine the real-time matching degree based on the standard matching degree. When the real-time matching degree is less than the standard matching degree, the standard relevance is corrected to a corrected relevance; When the real-time matching degree is greater than or equal to the standard matching degree, the standard relevance is not corrected; Wherein, Kb'=Kb×[1+(Qb-Qs) / Qs], Kb' is the corrected relevance, Kb is the standard relevance, Qb is the standard matching degree, and Qs is the real-time matching degree.

10. A system applied to the nutrition assessment method according to any one of claims 1 to 9, characterized in that: include, A virtual rendering module, used to create a personal virtual image in the Metaverse and input its basic information, including account number, health goal data, height, age, weight and gender; A data collection module is used to collect the user's health data, including physiological data, daily diet records and health product purchase records; A course matching module, used for matching a number of health course packages in a health course database according to the basic information, calculating a real-time relevance according to the basic information, and selecting a matching health course in each of the health course packages according to the real-time relevance; A virtual interaction module, for providing a virtual scene for users to conduct virtual interaction in the matching health course; An interaction recording module, which is connected to the virtual interaction module and is used to obtain virtual interaction text, scan and delete the virtual interaction text, and obtain a health assessment text; The correction module is used to perform matching analysis on the health data and the health assessment text, and determine whether to correct the real-time correlation to the corrected correlation according to the analysis result.

Images