Intelligent monitoring method and system

Through the intelligent monitoring system, the food temperature and meal frequency data are collected and analyzed in real time, and the dietary plan is generated using machine learning, which solves the problem that traditional methods cannot scientifically monitor food temperature and meal frequency, and provides effective healthy diet suggestions to prevent health such as esophageal cancer. risk.

CN118969322APending Publication Date: 2024-11-15CHONGQING COLLEGE OF ELECTRONICS ENG +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410920813.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In traditional eating habits, the monitoring methods of food temperature and consumption frequency are not scientific enough to achieve real-time and continuous monitoring, which makes it difficult to prevent health problems such as esophageal cancer.

Method used

Intelligent monitoring methods and systems are adopted to obtain food temperature and meal frequency data through temperature sensors and frequency measurement devices, perform preprocessing and machine learning analysis, generate diet plans, and provide scientific health advice.

Benefits of technology

Real-time monitoring and data analysis of food temperature and meal frequency are achieved, warning reports are pushed, personalized healthy diet suggestions are provided, and risks such as esophageal cancer are prevented.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118969322A_ABST
    Figure CN118969322A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of food intelligent monitoring, and discloses an intelligent monitoring method and system, and the method comprises the steps: obtaining food temperature data and eating frequency data; preprocessing the food temperature data and the eating frequency data to obtain a preprocessing result; training the preprocessing result by adopting machine learning to obtain a training result; and determining a diet scheme according to a training result. According to the intelligent monitoring method and system, the detector, the temperature sensor and the frequency measuring device are arranged, and meanwhile the related terminal is arranged; according to the system, the temperature and the eating frequency of food eaten by a user can be monitored in real time, then the monitoring data is processed and analyzed through the controller and sent to the terminal, and therefore a warning report and a safe diet report are pushed, healthy supervision diet suggestions can be provided more scientifically, and risks such as esophageal cancer in the diet process can be prevented to a certain extent.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method and system. Background Art

[0002] As the pace of modern life accelerates, people pay more and more attention to the health and safety of their diet. However, in traditional eating habits, the temperature and frequency of food consumption are often overlooked. These two factors are closely related to a variety of health problems, especially digestive tract diseases such as esophageal cancer. Food that is too hot can burn the esophageal mucosa, which may induce esophageal cancer in the long term; while eating too fast may lead to health problems such as indigestion and obesity.

[0003] Traditional food temperature monitoring methods mainly rely on people's subjective feelings or use tools such as thermometers for measurement. These methods are not only cumbersome to operate, but also cannot achieve continuous and real-time monitoring of food temperature. At the same time, the monitoring of meal frequency also mainly relies on personal self-observation and recording. This method is not only time-consuming and laborious, but also easily affected by subjective factors, resulting in inaccurate data.

[0004] With the development of sensor technology and information technology, it has become possible to monitor food temperature and eating frequency in real time. By integrating temperature sensors and frequency measurement devices on tableware, real-time and continuous monitoring of food temperature and eating frequency can be achieved. However, how to effectively process and analyze the acquired data to provide scientific dietary advice is still a problem that needs to be solved. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention proposes an intelligent monitoring method and system to solve the above technical problems.

[0006] In a first aspect, an intelligent monitoring method and system are provided, including obtaining food temperature data and meal frequency data; preprocessing the food temperature data and the meal frequency data to obtain preprocessing results; training the preprocessing results using machine learning to obtain training results; and determining a diet plan based on the training results.

[0007] Furthermore, food temperature data and meal frequency data are obtained, including:

[0008] A temperature sensor and a frequency measuring device are used to collect food temperature and eating frequency respectively, so as to obtain food temperature data and eating frequency data.

[0009] Further, the food temperature data and the meal frequency data are preprocessed to obtain preprocessing results, including:

[0010] Performing data cleaning on the food temperature data and the eating frequency data to obtain a data cleaning result;

[0011] The data cleaning result is normalized to obtain a preprocessing result.

[0012] Furthermore, the preprocessing result is trained using machine learning to obtain a training result, including:

[0013] Performing feature extraction on the preprocessing result to obtain an extraction result;

[0014] Constructing a feature set according to the extraction results;

[0015] The feature set is trained using a linear regression algorithm to obtain a training result.

[0016] Furthermore, the extraction results include: food temperature change rate, meal frequency, special dates, seasons and temperature changes.

[0017] Furthermore, the calculation formula of the linear regression algorithm includes:

[0018] [y=\beta_0+\beta_1x_1+\beta_2x_2+\ldots+\beta_n x_n],

[0019] Where (y) is the target variable (number of meals or calorie intake), (\beta_0) is the intercept, and (\beta_1,\beta_2,\ldots,\beta_n) are regression coefficients corresponding to each feature (x_1,x_2,\ldots,x_n).

[0020] Furthermore, a diet plan is generated according to the training results, including:

[0021] Performing cluster analysis on the training results using a clustering algorithm to obtain a dietary behavior pattern;

[0022] A diet plan is determined based on the dietary behavior pattern.

[0023] In a second aspect, an intelligent monitoring system is provided, characterized in that, based on an intelligent monitoring method described in any one of the above, it includes:

[0024] Detectors, temperature sensors, frequency measuring devices, time monitoring devices, controllers, Bluetooth modules and terminals;

[0025] The temperature sensor, frequency measuring device, time monitoring device, controller and Bluetooth module are all arranged in the detector;

[0026] The controller is electrically connected to the detector, the temperature sensor, the frequency measuring device, the time monitoring device and the Bluetooth module respectively;

[0027] The detector is used to detect contact objects;

[0028] The temperature sensor is used to monitor the temperature of the object contacted by the detector in real time and send the temperature data to the controller;

[0029] The frequency measuring device is used to monitor the user's eating frequency and send the frequency data to the controller;

[0030] The time monitoring device is used to record the user's meal time and send the time data to the controller;

[0031] The controller receives data from the temperature sensor, the frequency measuring device and the time monitoring device, and analyzes and processes the data;

[0032] The terminal is connected to the controller signal via a Bluetooth module.

[0033] Furthermore, it also includes:

[0034] A power module is arranged in the detector and is electrically connected to the detector, the temperature sensor, the frequency measuring device, the controller, the display and the Bluetooth module respectively.

[0035] The invention adopting the above technical solution has the following advantages:

[0036] The present invention is equipped with detectors, temperature sensors and frequency measuring devices, and is also equipped with relevant terminals; it can monitor the temperature and frequency of food consumed by users in real time, and then process and analyze the monitoring data through a controller and send it to the terminal, so as to push warning reports and safe eating reports, and can provide more scientific health supervision diet recommendations, and to a certain extent prevent risks such as esophageal cancer during the eating process. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific implementation of the present invention, the following will briefly introduce the drawings required for use in the specific implementation. In all the drawings, each element or part is not necessarily drawn according to the actual scale.

[0038] Figure 1 A flow chart of an intelligent monitoring method of the present invention;

[0039] Figure 2 The present invention is a flowchart of an intelligent monitoring system. DETAILED DESCRIPTION

[0040] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0041] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should be the common meanings understood by technicians in the field to which the present invention belongs. The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to implement the embodiments of the present disclosure described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. Unless otherwise specified, the term "multiple" means two or more. In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B. The term "and / or" is a description of the association relationship of objects, indicating that there can be three relationships. For example, A and / or B means: A or B, or, A and B. The term "corresponding" can refer to an association relationship or a binding relationship, and A and B correspondingly refer to an association relationship or a binding relationship between A and B.

[0042] like Figure 1-2 As shown, an intelligent monitoring method of the present invention includes:

[0043] Step S01, obtaining food temperature data and meal frequency data;

[0044] Step S02: pre-processing the food temperature data and the eating frequency data to obtain pre-processing results;

[0045] Step S03: training the preprocessing results using machine learning to obtain training results;

[0046] Step S04: Determine a diet plan based on the training results.

[0047] In some embodiments, by setting up detectors, temperature sensors and frequency measuring devices, and at the same time equipping with relevant terminals, the temperature and frequency of food consumed by the user can be monitored in real time, and the monitoring data can be processed and analyzed by the controller and sent to the terminal, so as to push warning reports and safe eating reports, and provide more scientific health supervision diet recommendations, which can prevent risks such as esophageal cancer during the eating process to a certain extent.

[0048] Specifically, obtaining food temperature data and meal frequency data includes:

[0049] A temperature sensor and a frequency measuring device are used to collect food temperature and eating frequency respectively, so as to obtain food temperature data and eating frequency data.

[0050] Specifically, the food temperature data and the eating frequency data are preprocessed to obtain preprocessing results, including:

[0051] Perform data cleaning on food temperature data and meal frequency data to obtain data cleaning results;

[0052] Normalize the data cleaning results to obtain the preprocessing results.

[0053] In some embodiments, the terminal (such as a mobile phone) will pre-process the data internally, clean the existing data, remove erroneous data or monitor abnormal values ​​(food temperature data is not between 35°C-45°C), and normalize the data after cleaning to facilitate the establishment of a subsequent data model.

[0054] Specifically, the preprocessing results are trained using machine learning to obtain training results, including:

[0055] Perform feature extraction on the preprocessing result to obtain the extraction result;

[0056] According to the extraction results, construct a feature set;

[0057] The feature set is trained using a linear regression algorithm to obtain training results.

[0058] Specifically, the extracted results include: food temperature change rate, meal frequency, special dates, seasons, and temperature changes.

[0059] In some embodiments, an average change rate characteristic is created for the food temperature change rate data, and the average change rate of the temperature is calculated over a longer period of time to understand the overall change trend of the food temperature.

[0060] Calculate the temperature change in each time period: (\Delta T_{i}=T_{i+1}-T_{i})

[0061] Where (\Delta T_{i}) is the temperature change in the (i)th time period, (T_{i}) and (T_{i+1}) are the temperature values ​​at the (i)th and (i+1)th time points, respectively, to monitor the temperature change.

[0062] Calculate the average temperature change rate: (Average temperature change rate = \frac{\sum_{i=1}^{n-1}\Delta T_{i}}{n-1}), where (n) is the total number of data points.

[0063] Note that since we are calculating the change between adjacent points, the denominator is (n-1) to calculate the average temperature rate of change per hour, day, or week.

[0064] The maximum and minimum values ​​of the temperature change rate: (maximum value = \max(\Delta T_{1},\Delta T_{2},\ldots,\Delta T_{n-1}), (minimum value = \min(\Delta T_{1},\Delta T_{2},\ldots,\DeltaT_{n-1}).

[0065] These indicators can show the extremes of the rate of change of food temperature and can help detect abnormal temperature fluctuations or identify specific patterns.

[0066] Specifically, the calculation formula of the linear regression algorithm includes:

[0067] [y=\beta_0+\beta_1x_1+\beta_2x_2+\ldots+\beta_n x_n],

[0068] Where (y) is the target variable (number of meals or calorie intake), (\beta_0) is the intercept, and (\beta_1,\beta_2,\ldots,\beta_n) are regression coefficients corresponding to each feature (x_1,x_2,\ldots,x_n).

[0069] Specifically, based on the training results, a diet plan is generated, including:

[0070] Cluster analysis is performed on the training results using clustering algorithms to obtain dietary behavior patterns;

[0071] Determine a diet plan based on eating behavior patterns.

[0072] Specifically, clustering algorithms are used to perform cluster analysis on the training results to obtain dietary behavior patterns, including

[0073] In some embodiments, a K-means clustering algorithm is used to iteratively calculate

[0074] #Assume that X is the user's eating behavior data, and each row is a user's data point

[0075] X=np.array([...])#This needs to be replaced with actual data

[0076] #Choose the number of clusters

[0077] n_clusters=3

[0078] # Initialize K-means model

[0079] kmeans=KMeans(n_clusters=n_clusters,random_state=0)

[0080] #fit the model and predict the cluster label for each data point

[0081] labels=kmeans.fit_predict(X)

[0082] # Output the cluster label for each data point

[0083] print(labels)

[0084] #If necessary, you can also get the updated center of mass position

[0085] centroids=kmeans.cluster_centers_

[0086] print(centroids)) process to determine the cluster to which each user belongs, (Cluster 1: Moderate temperature food for the elderly. Centroid characteristics: The centroid of this cluster may show a moderate value in "food temperature change rate", indicating that the elderly may tend to choose food with little temperature change to avoid irritation to the oral cavity and digestive system. Meal frequency: It may be low, reflecting that the elderly usually eat less but regularly. Cluster 2: Fast-paced diet for young people. Centroid characteristics: The centroid of this cluster may be high in "food temperature change rate", indicating that young people prefer food that is quickly heated or cooled, such as fast food, cold drinks, etc. Meal frequency: It may be high because young people are usually active and need more energy supplements. Cluster 3: Healthy eaters. Centroid characteristics: The centroid of this cluster may be low in "food temperature change rate", indicating that this group of people pay more attention to the natural temperature and cooking methods of food, and tend to choose healthy and mild food. Meal frequency: It may show a stable three meals a day pattern, reflecting the adherence to a healthy diet). Different eating behavior patterns are revealed.

[0087] In some embodiments, the terminal may provide the user with personalized dietary recommendations based on the user's real-time data and model predictions.

[0088] For example, it may recommend users to adjust the temperature of food, or remind users to eat within a precise time period (for example: the best time period for breakfast (7:00-8:30); the best time period for lunch (12:00-13:30); the best time period for dinner (18:30-20:00); the best time period for a morning snack (after 10:30). The time when you feel hungry between breakfast and lunch is after 10:30, and you can have a snack if conditions permit; the best time period for an afternoon snack (around 15:30). For afternoon tea, you can choose some fruits, nuts or dairy products to enhance your sense of fullness).

[0089] Finally, the terminal uses a pie chart to intuitively feedback the impact of different data on esophageal cancer. For example, if the frequency of food temperature exceeding 65°C is high, the proportion is relatively large, etc., allowing users to more easily understand the main risks that may affect esophageal cancer, so as to more accurately avoid and prevent risks.

[0090] In some other embodiments, an intelligent monitoring system is provided, characterized in that an intelligent monitoring method based on any one of the above items includes:

[0091] A detector (the detector includes a spoon and a detection needle, and the front end of the spoon is connected to the detection needle), a temperature sensor, a frequency measuring device, a time monitoring device, a controller, a Bluetooth module and a terminal;

[0092] The temperature sensor, frequency measuring device, time monitoring device, controller and Bluetooth module are all located inside the detector;

[0093] The controller is electrically connected to the detector, the temperature sensor, the frequency measuring device, the time monitoring device and the Bluetooth module respectively;

[0094] The detector is used to detect contact objects;

[0095] The temperature sensor is used to monitor the temperature of the object the detector contacts in real time and send the temperature data to the controller;

[0096] The frequency measuring device is used to monitor the user's eating frequency and send the frequency data to the controller;

[0097] The time monitoring device is used to record the user's meal time and send the time data to the controller;

[0098] The controller receives data from the temperature sensor, the frequency measuring device and the time monitoring device, and analyzes and processes the data;

[0099] The terminal is connected to the controller signal via the Bluetooth module.

[0100] Specifically, it also includes:

[0101] A power module is arranged in the detector and is electrically connected to the detector, the temperature sensor, the frequency measuring device, the controller, the display and the Bluetooth module respectively.

[0102] Specifically, it also includes:

[0103] A display (not shown in the figure), such as a liquid crystal, a digital tube or an LED matrix and an indicator light (not shown in the figure), are installed outside the detector, and the display and the indicator light are electrically connected to the controller and the power module.

[0104] In some embodiments, after the detector contacts the object, the temperature of the contacted object is monitored by a temperature sensor and sent to a controller. The controller receives the temperature data, analyzes and processes the data to determine whether the food temperature is within a preset range (for example, below 65°C, between 35°C and 45°C is considered appropriate).

[0105] If the food temperature is between 35℃ and 45℃, the controller will control the indicator light to show green, indicating that the food temperature is appropriate and eating food at this temperature is good for health.

[0106] If the food temperature exceeds 65°C or is lower than 35°C, the controller controls the indicator light to display a red light, indicating that the food temperature is too high or too low and may not be suitable for consumption.

[0107] When the food temperature exceeds the normal range, the controller sends the monitoring data to the terminal via the Bluetooth module. The terminal can preset the user groups, such as children, adults, etc., and generate different temperature reference tables accordingly. After the terminal is connected to the Bluetooth module, the data is detected and calibrated online to form a detailed measurement report.

[0108] Table 1

[0109]

[0110] If the user group is young children, a temperature reference table is generated, as shown in Table 1, and displayed on the display, which can record and read the highest value of the measured temperature, so that the user can intuitively see the food temperature and prompt the user whether to use it:

[0111] Temperatures below 39°C can easily damage the baby's gastric mucosa and cause inflammation. Temperatures above 50°C can easily burn the baby's oral and esophageal mucosa. Temperatures between 38°C and 45°C are the scientific feeding temperature and the best eating temperature.

[0112] If the frequency measurement device detects that the frequency of eating is too fast, the terminal will push a warning report, such as: eating too fast will cause:

[0113] 1. Reduced nutrient intake 2. Loss of blood sugar control 3. Damage to the stomach 4. Cause cardiovascular disease 5. Increased risk of cancer. At the same time, scientific and healthy eating suggestions are pushed to effectively help users prevent esophageal cancer.

[0114] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An intelligent monitoring method, characterized in that: include: Get food temperature data and eating frequency data; Preprocessing the food temperature data and the eating frequency data to obtain a preprocessing result; Using machine learning to train the preprocessing results to obtain training results; According to the training results, a diet plan is determined.

2. An intelligent monitoring method according to claim 1, characterized in that: Get food temperature data and meal frequency data, including: A temperature sensor and a frequency measuring device are used to collect food temperature and eating frequency respectively, so as to obtain food temperature data and eating frequency data.

3. The intelligent monitoring method according to claim 1, characterized in that: Preprocessing the food temperature data and the eating frequency data to obtain preprocessing results includes: Performing data cleaning on the food temperature data and the eating frequency data to obtain a data cleaning result; The data cleaning result is normalized to obtain a preprocessing result.

4. The intelligent monitoring method according to claim 1, characterized in that: The preprocessing result is trained using machine learning to obtain a training result, including: Performing feature extraction on the preprocessing result to obtain an extraction result; Constructing a feature set according to the extraction results; The feature set is trained using a linear regression algorithm to obtain a training result.

5. An intelligent monitoring method according to claim 4, characterized in that: The extraction results include: food temperature change rate, meal frequency, special dates, seasons and temperature changes.

6. An intelligent monitoring method according to claim 4, characterized in that: The calculation formula of the linear regression algorithm includes: [y=\beta_0+\beta_1x_1+\beta_2x_2+\ldots+\beta_n x_n], Where (y) is the target variable (number of meals or calorie intake), (\beta_0) is the intercept, and (\beta_1,\beta_2,\ldots,\beta_n) are regression coefficients corresponding to each feature (x_1,x_2,\ldots,x_n).

7. The intelligent monitoring method according to claim 1, characterized in that: According to the training results, a diet plan is generated, including: Performing cluster analysis on the training results using a clustering algorithm to obtain a dietary behavior pattern; A diet plan is determined based on the dietary behavior pattern.

8. An intelligent monitoring system, characterized in that: An intelligent monitoring method according to any one of claims 1 to 7, comprising: Detectors, temperature sensors, frequency measuring devices, time monitoring devices, controllers, Bluetooth modules and terminals; The temperature sensor, frequency measuring device, time monitoring device, controller and Bluetooth module are all arranged in the detector; The controller is electrically connected to the detector, the temperature sensor, the frequency measuring device, the time monitoring device and the Bluetooth module respectively; The detector is used to detect contact objects; The temperature sensor is used to monitor the temperature of the object contacted by the detector in real time and send the temperature data to the controller; The frequency measuring device is used to monitor the user's eating frequency and send the frequency data to the controller; The time monitoring device is used to record the user's meal time and send the time data to the controller; The controller receives data from the temperature sensor, the frequency measuring device and the time monitoring device, and analyzes and processes the data; The terminal is connected to the controller signal via a Bluetooth module.

9. An intelligent monitoring system according to claim 8, characterized in that: Also includes: A power module is arranged in the detector and is electrically connected to the detector, the temperature sensor, the frequency measuring device, the controller, the display and the Bluetooth module respectively.

Citation Information

Cited By

  • Auxiliary intervention method and system for nutrition plan of hypertensive gestational patient

    CN119580950A