A dietary assessment method and system based on condiment health monitoring

By combining intelligent condiment containers with cloud services and algorithms, the problem of condiment bottles being unable to monitor usage has been solved, enabling personalized dietary assessments and healthy recipe recommendations, thus improving the scientific nature and automation of dietary management.

CN116130059BActive Publication Date: 2026-11-17UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202310124063.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-02-16
Publication Date
2026-11-17
Estimated Expiration
2043-02-16

AI Technical Summary

Technical Problem

Existing condiment bottles cannot monitor and provide suggestions on the amount of condiments used by users, and lack intelligent and personalized dietary assessment functions.

Method used

By making the condiment container intelligent and combining it with existing cloud services and algorithms, fuzzy comprehensive evaluation, hierarchical analysis and collaborative filtering algorithms are used to monitor users' condiment intake and recommend personalized recipes.

Benefits of technology

It enables scientific assessment of condiment intake and personalized recipe recommendations, helping users gradually shift to a healthier diet, while also featuring digitalization and automation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116130059B_ABST
    Figure CN116130059B_ABST
Patent Text Reader

Abstract

This invention relates to the field of dietary health monitoring technology, and more particularly to a dietary assessment method and system based on condiment health monitoring. Addressing the gap between existing user dietary plans and condiments, which affects user health, this invention employs a fuzzy comprehensive evaluation algorithm to assess user condiment intake and introduces daily healthy dish recommendations and recipe-assisted cooking modules. It can simultaneously quantify the fuzzy intake of multiple condiments, allowing users to gradually switch to healthier eating habits without drastically altering their dietary preferences, enjoying food while pursuing health.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of dietary health monitoring technology, and in particular to a dietary assessment method and system based on health monitoring of condiments. Background Technology

[0002] Existing condiment bottles either focus on attractive design to draw consumers' attention, or on dispensing mechanisms for quantitative dispensing, or even include weighing displays. However, these designs only address the bottle itself and do not provide monitoring or recommendations regarding the amount of condiments used by the user. Summary of the Invention

[0003] To enable the monitoring and recommendations of users' condiment usage, this invention innovatively integrates intelligent condiment storage devices, combines existing cloud services and algorithms, and improves the algorithms to better suit the products, thus designing a dietary assessment method and system based on condiment health monitoring.

[0004] This invention is achieved through the following technical solution:

[0005] A dietary assessment method based on condiment health monitoring, characterized by the following steps:

[0006] Extract and analyze user dietary information.

[0007] The analysis of user dietary information specifically includes:

[0008] A. Cluster all the dishes in the recipes and analyze them to obtain representative dishes, i.e., cluster centers, in order to design a dietary preference questionnaire;

[0009] B. Calculate the intake of various condiments by users, establish an evaluation matrix based on the membership function, and use the analytic hierarchy process (AHP) to assess the health impact of condiments.

[0010] Personalized recipe recommendations are made based on dietary preference questionnaires and health assessment results using a user-based collaborative filtering algorithm.

[0011] Furthermore, the clustering of all dishes in the recipe specifically involves:

[0012] A1. Randomly select k initial samples as initial cluster centers. The k represents the number of samples. This indicates the amount of a certain seasoning used in the dish in the initial cluster center;

[0013] A2. For each sample in the dataset , This represents the amount of a certain seasoning used in any dish. It calculates the distance from the sample to the k cluster centers and assigns it to the cluster corresponding to the cluster center with the smallest distance.

[0014] A3. For each category , For the clusters obtained in step A2, recalculate the cluster centers of the clusters. ;

[0015] A4. Repeat steps A2 and A3 until the termination condition is met, which is the minimum error change.

[0016] Furthermore, the assessment of the health impact specifically involves:

[0017] B1. Establish a comprehensive evaluation index set:

[0018] ;

[0019] Wherein, U represents the index set, which is a general set composed of factors influencing the evaluation object. The i-th factor representing the object of evaluation, i.e., different seasonings;

[0020] B2. Establish a comprehensive evaluation set:

[0021] ;

[0022] Wherein, V represents the evaluation set, which is the set of all possible outcomes that the evaluator will make regarding the evaluated object. This represents the j-th evaluation result, i.e., the evaluation index set for different amounts of seasonings.

[0023] B3. Create a membership function to obtain the evaluation matrix;

[0024] When the membership degree of the i-th element in the index set U to the j-th element in the evaluation set V is Then, the result of the single-factor evaluation of the i-th element is represented by a fuzzy set as follows: The evaluation matrix represents an evaluation set of n single indicators. Composition matrix;

[0025] B4. Determine the weight vector;

[0026] In the evaluation process, each indicator Assign a weight That is, assigning weights to the importance of different seasonings. Then we obtain the weight vector:

[0027] ;

[0028] Where B represents the weight vector of the weight set of each indicator;

[0029] B5. Establish a comprehensive evaluation model.

[0030] Furthermore, the collaborative filtering algorithm for users specifically includes the following steps:

[0031] Collect user information;

[0032] Construct a user similarity calculation function;

[0033] Calculate the user similarity matrix;

[0034] Find the K users most similar to each user, and recommend dishes to the target users based on the preferences of the K users.

[0035] Furthermore, the user's dietary information specifically includes: user dietary preference information and the user's daily intake of condiments.

[0036] Furthermore, the user's condiment intake is specifically the difference between the weight of the condiment bottle on the current day and the weight of the condiment bottle on the previous day.

[0037] A dietary assessment system based on condiment health monitoring, characterized in that it includes:

[0038] The user diet information recording module is used to record dietary preference information and the amount of condiments consumed by users on the same day, and upload the user diet information to the cloud platform;

[0039] The recipe clustering and classification module is used to cluster all the dishes in the recipe and analyze them to obtain representative dishes, i.e., cluster centers, in order to design a dietary preference questionnaire.

[0040] The condiment health impact calculation module is used to calculate the user's intake of various condiments, establish an evaluation matrix based on the membership function, and use the analytic hierarchy process to evaluate the health impact of condiments.

[0041] The personalized recipe recommendation module uses a user-based collaborative filtering algorithm to recommend personalized recipes based on the dietary preference questionnaire obtained from the recipe clustering and classification module and the health assessment results obtained from the condiment health impact calculation module.

[0042] The health impact calculation module for condiments also includes:

[0043] The user's condiment weighing unit is used to automatically detect the weight of the condiment bottles for the day;

[0044] The user condiment intake calculation unit is used to calculate the difference between the weight of the condiment bottles on the current day and the weight of the condiment bottles on the previous day, and obtain the user's condiment intake on the current day.

[0045] Furthermore, the recipe clustering and classification module specifically comprises:

[0046] Randomly select k samples as initial cluster centers The number of samples is represented by k.

[0047] For each sample in the dataset Calculate the distance of a sample to k cluster centers and assign it to the cluster center with the smallest distance.

[0048] For each category Recalculate the cluster centers of the categories ;

[0049] The steps of repeatedly calculating the distance from the sample to the k cluster centers and classifying the samples, as well as recalculating the cluster centers, are repeated until a termination condition is met, which is the minimum error change.

[0050] Furthermore, the module for calculating the health impact of condiments specifically includes:

[0051] Establish a comprehensive evaluation index set:

[0052] ;

[0053] Wherein, U represents the index set, which is a general set composed of factors influencing the evaluation object. The i-th factor represents the factor that affects the evaluation object;

[0054] Establish a comprehensive evaluation set:

[0055] ;

[0056] Wherein, V represents the evaluation set, which is the set of all possible outcomes that the evaluator will make regarding the evaluated object. This represents the j-th evaluation result;

[0057] Create a membership function to obtain the evaluation matrix;

[0058] When the membership degree of the i-th element in the index set U to the j-th element in the evaluation set V is Then, the result of the single-factor evaluation of the i-th element is represented by a fuzzy set as follows: The evaluation matrix represents an evaluation set of n single indicators. Composition Matrix; Determine the weight vector;

[0059] In the evaluation process, each indicator Assign a weight That is, assigning weights to the importance of different seasonings. Then we obtain the weight vector:

[0060] ;

[0061] Where B represents the weight vector of the weight set of each indicator;

[0062] Establish a comprehensive evaluation model.

[0063] The beneficial effects of this invention are:

[0064] (1) This invention uses a fuzzy comprehensive evaluation algorithm to assess users' intake of condiments, which is scientific and reasonable. For problems involving multiple indicators and multiple objects, the either-or judgment method is obviously unsuitable, and different objects require different judgment methods, and some evaluation indicators are also fuzzy. This invention uses a fuzzy comprehensive evaluation algorithm, which can simultaneously quantify the fuzzy intake of multiple condiments;

[0065] (2) This invention introduces a daily healthy dish recommendation and recipe-assisted cooking module, which has a personalized feature. This invention also provides personalized recipe recommendations, allowing users to gradually switch to a healthier diet without significantly changing their own dietary preferences, so that they can enjoy food while pursuing health.

[0066] (3) Compared with ordinary food scales that require manual weighing and data recording, this invention has the characteristics of digitalization and automation. Attached Figure Description

[0067] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1 This is a flowchart of a dietary assessment system based on condiment health monitoring, as proposed in an embodiment of the present invention.

[0069] Figure 2 This is a hardware principle block diagram of a dietary assessment system based on condiment health monitoring proposed in an embodiment of the present invention;

[0070] Figure 3This is a schematic diagram of a terminal device for a dietary assessment system based on condiment health monitoring, as proposed in an embodiment of the present invention.

[0071] Figure 4 This is a schematic diagram of the storage medium for a dietary assessment system based on condiment health monitoring, as proposed in an embodiment of the present invention. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0073] Example 1

[0074] This embodiment proposes a specific implementation process for a dietary assessment system based on condiment health monitoring, as follows:

[0075] like Figure 1 As shown, users connect this invention to their home Wi-Fi. Upon first use, users need to complete a questionnaire on the app to set dietary preferences. The weighing module automatically measures the weight of various condiment bottles (containing seasonings) at midnight each day, then uploads the data to the Bafa Maker Cloud Platform via Wi-Fi. The app automatically retrieves the data from the cloud platform, compares it with the previous day's data, and calculates the daily usage. Based on the user's set dietary preferences, the daily intake is calculated. According to the standards of the World Health Organization and the Chinese Dietary Guidelines, the health level of today's intake is comprehensively assessed, providing recommendations for the amount of seasoning to use the next day, along with personalized recommendations for dishes and their cooking methods.

[0076] Example 2

[0077] Based on Example 1, and preferably, this example proposes a dish clustering implementation method based on the k-means clustering algorithm. This algorithm has the following two functions in this invention: ① Clustering all dishes to find representative dishes, i.e., cluster centers, for designing a dietary preference questionnaire. ② Calculating the user's intake of various seasonings. First, data on the amount of various seasonings used in different dishes are collected based on user preferences. Then, cluster centers are determined according to the clustering algorithm, and the amount of various seasonings used per 100 grams of dish is calculated for each cluster center, thereby calculating the user's intake of various seasonings.

[0078] Once users start using the app, they will select whether to accept the recommended dishes in the "Daily Recommended Dishes" module. By judging the user's actual intake, new dish data will be added to the cluster, allowing the algorithm to iterate continuously to achieve accurate calculations.

[0079] Example 3

[0080] Based on Example 1, and preferably, this example proposes a health assessment implementation method based on fuzzy comprehensive evaluation, establishing the relationship between condiment intake and human health. In this example, the indicator set to be evaluated is the intake of each condiment the previous day, and the evaluation set is created based on the condiment classification obtained through clustering. Establishing the membership function is equivalent to establishing the relationship between the indicator set and the evaluation set; the Euclidean distance between the intake and the standard intake in the condiment classification is used as the basis for establishing the membership function. After obtaining the evaluation matrix through the membership function, the weight of each condiment's impact on human health is determined using the analytic hierarchy process (AHP). The evaluation matrix is ​​multiplied by the weight vector to obtain the fuzzy evaluation matrix, which can be used to assess the degree of influence of condiment intake on human health. The membership function is mainly calculated using Euclidean distance, normalized to obtain the evaluation matrix, and the weight vector is determined using the AHP to comprehensively evaluate the health status of condiment intake.

[0081] Example 4

[0082] Building upon Example 1, this embodiment proposes a preferred implementation method that uses a user-based collaborative filtering (UserCF) algorithm for food recommendation. The collaborative filtering algorithm primarily considers the similarity between users. Its application scenario is: when a user requires personalized recommendations, other users similar to them can be found first (through interests, hobbies, or behavioral habits), and then items that the user likes but is unaware of can be recommended to them. For example, to recommend items to user A, user B, who is most similar to A, can be found first. Then, user B's favorite items that user A has not heard of can be obtained, and user A's ratings for these items can be predicted. The items with the highest ratings can then be selected and recommended to user A.

[0083] This embodiment defines users differently from traditional collaborative filtering algorithms. Each type of dish can be considered a special "user," and each is compared with the app's users. In one specific implementation, information is first collected based on dish information and user preferences to create a data table, as shown in Table 1, a similarity matrix between user preferences and dish information. To better measure the relationship between dishes and user preferences, ingredients are divided into three categories: those liked by the user, those disliked, and ordinary ingredients. To quantify the relationship between dishes and user preferences, three weights are set: 1 for liked ingredients, -1 for disliked ingredients, and 0 for all other ingredients. The presence of a corresponding ingredient in any dish is also marked as 1, with the rest defaulting to 0. Then, the formula is used... We calculate the cosine similarity (K=10) to obtain the user's top 10 favorite dishes, sorting them from largest to smallest. Then, we rank these top 10 dishes by their salt content, from highest to lowest. Finally, we match recipes to these dishes based on recommended intake levels.

[0084] Ingredients user Cabbage stew with tofu Winter melon and pork rib soup Lotus root tofu Fish-flavored shredded pork Cola Chicken Wings Braised pork belly pork 1 1 1 chicken 1 1 Chinese cabbage 1 1 fungus -1 1 Ribs 1 1 eggplant -1 carrot 0 1 winter melon -1 1 Tofu 0 1 1 lotus root 1 1 …… N(1) N(2) N(3) N(4) N(5) N(6) N(7)

[0085] Table 1. Similarity Matrix Between User Preferences and Menu Information

[0086] Example 5

[0087] This embodiment proposes a hardware and software implementation method for a dietary assessment system based on condiment health monitoring.

[0088] Hardware: An Arduino microcontroller equipped with a WIFI module and a high-precision pressure sensor, such as... Figure 2 .

[0089] software:

[0090] cloud platform

[0091] i. K-means clustering algorithm;

[0092] ii. Fuzzy comprehensive evaluation algorithm;

[0093] iii. User-based collaborative filtering algorithm;

[0094] The hardware consists of an Arduino Mega2560 as the core circuit board, connected to an ESP8266 Wi-Fi module and an HX711 A / D converter chip. The chip transmits data from the balance beam strain gauge load cell to the Arduino. Weighing data is sampled 10 times daily at midnight and averaged, achieving a weighing accuracy of 0.1g. The data is then uploaded to a cloud platform via the Wi-Fi module. The software utilizes cloud computing, K-means clustering, fuzzy comprehensive evaluation, and user-based collaborative filtering to analyze user seasoning usage, providing reasonable suggestions and personalized dish recommendations.

[0095] Through this embodiment, the product has multiple application programming interfaces (APIs) that are compatible with TCP, MQTT, Airkiss, SmartConfig, and SoftAp protocols, and can be connected to other smart home devices, currently including Tmall Genie, Mi Home Xiao Ai, and Baidu Smart Speaker.

[0096] Example 6

[0097] like Figure 3 This embodiment proposes a terminal device for a dietary assessment system based on condiment health monitoring. The terminal device 200 includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0098] The memory 210 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 211 and / or cache memory 212, and may further include read-only memory (ROM) 213.

[0099] The memory 210 also stores a computer program, which can be executed by the processor 220, causing the processor 220 to execute any of the above-described dietary assessment systems based on condiment health monitoring in this application embodiment. The specific implementation method and the achieved technical effects are consistent with the implementation methods and technical effects described in the above embodiments, and some details will not be repeated. The memory 210 may also include a program / utility 214 having a set (at least one) of program modules 215. Such program modules include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0100] Accordingly, processor 220 can execute the aforementioned computer program, as well as executable program / utility 214.

[0101] Bus 230 can represent one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any of the various bus structures.

[0102] Terminal device 200 can also communicate with one or more external devices 240, such as keyboards, pointing devices, Bluetooth devices, etc., and with one or more devices capable of interacting with it, and / or with any device that enables it to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed via input / output (I / O) interface 250. Furthermore, terminal device 200 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 260. Network adapter 260 can communicate with other modules of terminal device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with terminal device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0103] Example 7

[0104] like Figure 4 This embodiment proposes a computer-readable storage medium for a dietary assessment system based on condiment health monitoring. The computer-readable storage medium stores instructions that, when executed by a processor, implement any of the aforementioned dietary assessment systems based on condiment health monitoring. The specific implementation method and the achieved technical effects are consistent with those described in the above embodiments, and some details will not be repeated.

[0105] Figure 4 The present embodiment illustrates a program product 300 for implementing the above-described method, which may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product 300 of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. The program product 300 may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0106] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. Program code for performing operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0107] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A dietary assessment method based on health monitoring of condiments, characterized in that, Includes the following steps: Extract and analyze user dietary information. The analysis of user dietary information specifically includes: A. Cluster all the dishes in the recipes and analyze them to obtain representative dishes, i.e., cluster centers, in order to design a dietary preference questionnaire; B. Calculate the intake of various condiments by users, establish an evaluation matrix based on the membership function, and use the analytic hierarchy process (AHP) to assess the health impact of condiments. Based on dietary preference questionnaires and health assessment results, a user-based collaborative filtering algorithm is used to recommend personalized recipes. The specific steps of clustering all the dishes in the recipe are as follows: A1. Randomly select k initial samples as initial cluster centers. The k represents the number of samples. This indicates the amount of a certain seasoning used in the dish in the initial cluster center; A2. For each sample in the dataset , This represents the amount of a certain seasoning used in any dish. It calculates the distance of the sample to the k cluster centers and assigns it to the cluster corresponding to the cluster center with the smallest distance. A3. For each category , For the clusters obtained in step A2, recalculate the cluster centers of the clusters. ; A4. Repeat steps A2 and A3 until the termination condition is met, which is the minimum error change.

2. The dietary assessment method based on condiment health monitoring according to claim 1, characterized in that, The assessment of the health impact specifically involves: B1. Establish a comprehensive evaluation index set: ; Wherein, U represents the index set, which is a general set composed of factors influencing the evaluation object. The i-th factor representing the object of evaluation, i.e., different seasonings; B2. Establish a comprehensive evaluation set: ; Wherein, V represents the evaluation set, which is the set of all possible outcomes that the evaluator will make regarding the evaluated object. This represents the j-th evaluation result, i.e., the evaluation index set for different amounts of seasonings. B3. Create a membership function to obtain the evaluation matrix; When the membership degree of the i-th element in the index set U to the j-th element in the evaluation set V is The result of the single-factor evaluation of the i-th element is represented by a fuzzy set as follows: The evaluation matrix represents an evaluation set of n single indicators. Composition matrix; B4. Determine the weight vector; In the evaluation process, each indicator Assign a weight That is, assigning weights to the importance of different seasonings. Then we obtain the weight vector: ; Where B represents the weight vector of the weight set of each indicator; B5. Establish a comprehensive evaluation model.

3. The dietary assessment method based on condiment health monitoring according to claim 1, characterized in that, The specific collaborative filtering algorithm for the user Includes the following steps: Collect user information; Construct a user similarity calculation function; Calculate the user similarity matrix; Find the K users most similar to each user, and recommend dishes to the target users based on the preferences of the K users.

4. The dietary assessment method based on condiment health monitoring according to claim 1, characterized in that, The user's dietary information specifically includes: user dietary preferences and the amount of condiments consumed by the user on that day.

5. A dietary assessment method based on condiment health monitoring according to claim 4, characterized in that, The user's condiment intake is specifically the difference between the weight of the condiment bottle on the current day and the weight of the condiment bottle on the previous day.

6. A dietary assessment system based on condiment health monitoring, characterized in that, include: The user diet information recording module is used to record dietary preference information and the amount of condiments consumed by users on the same day, and upload the user diet information to the cloud platform; The recipe clustering and classification module is used to cluster all the dishes in the recipe and analyze them to obtain representative dishes, i.e., cluster centers, in order to design a dietary preference questionnaire. The condiment health impact calculation module is used to calculate the user's intake of various condiments, establish an evaluation matrix based on the membership function, and use the analytic hierarchy process to evaluate the health impact of condiments. The personalized recipe recommendation module uses a user-based collaborative filtering algorithm to recommend personalized recipes based on the dietary preference questionnaire obtained from the recipe clustering and classification module and the health assessment results obtained from the condiment health impact calculation module. The health impact calculation module for condiments also includes: The user's condiment weighing unit is used to automatically detect the weight of the condiment bottles for the day; The user condiment intake calculation unit is used to calculate the difference between the weight of the condiment bottle on the current day and the weight of the condiment bottle on the previous day, and to obtain the user's condiment intake on the current day. The recipe clustering and classification module specifically includes: Randomly select k samples as initial cluster centers The number of samples is represented by k. For each sample in the dataset Calculate the distance of a sample to k cluster centers and assign it to the cluster center with the smallest distance. For each category Recalculate the cluster centers of the categories ; The steps of repeatedly calculating the distance from the sample to the k cluster centers and classifying the samples, as well as recalculating the cluster centers, are repeated until a termination condition is met, which is the minimum error change.

7. A dietary assessment system based on condiment health monitoring according to claim 6, characterized in that, The module for calculating the health impact of condiments specifically includes: Establish a comprehensive evaluation index set: ; Wherein, U represents the index set, which is a general set composed of factors influencing the evaluation object. The i-th factor represents the factor that affects the evaluation object; Establish a comprehensive evaluation set: ; Wherein, V represents the evaluation set, which is the set of all possible outcomes that the evaluator will make regarding the evaluated object. This represents the j-th evaluation result; Create a membership function to obtain the evaluation matrix; When the membership degree of the i-th element in the index set U to the j-th element in the evaluation set V is Then, the result of the single-factor evaluation of the i-th element is represented by a fuzzy set as follows: The evaluation matrix represents an evaluation set of n single indicators. Composition Matrix; Determine the weight vector; In the evaluation process, each indicator Assign a weight That is, assigning weights to the importance of different seasonings. Then we obtain the weight vector: ; Where B represents the weight vector of the weight set of each indicator; Establish a comprehensive evaluation model.

Citation Information

Patent Citations

  • Multi-feature-based healthy diet recommendation system and method

    CN115116582A