An integrated intelligent adjustment method and system for a coffee machine and water dispenser

Abstract

The present invention provides an integrated intelligent adjustment method and system for a coffee machine and water dispenser, which relates to the field of intelligent automatic adjustment technology, including using a graph neural network to capture the complex associations between data, and constructing a user health status model that reflects the user's health status and long-term health trends. An environmental comfort model is established to guide the adjustment of the integrated equipment of a coffee machine and water dispenser; an isolation forest algorithm is used to detect abnormal points in health data, identify potential health risks, and obtain health trend prediction results. Through a deep learning model, a dynamic health risk warning is generated; an environmental adaptability algorithm based on fuzzy logic is developed to obtain optimized equipment parameters; and then the integrated intelligent adjustment of a coffee machine and water dispenser is realized. Users of the present invention can enjoy smart home appliance services that are automatically adjusted according to personal health status and environmental comfort, which greatly improves the intelligence level of smart devices and user satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent automatic adjustment, and in particular to an integrated intelligent adjustment method and system for a coffee machine and a water dispenser. Background Art

[0002] In contemporary society, intelligent regulation technology is rapidly penetrating into all aspects of daily life, with the core goal of improving living comfort and convenience through technical means. As an important part of the intelligent ecosystem, the intelligence level of the integrated coffee and water dispenser directly affects the daily quality of users. Although the intelligent integrated coffee and water dispenser on the market are already able to perform some basic automated tasks, such as brewing coffee on time or adjusting water temperature, these functions are often based on manual settings by users and lack flexibility and adaptability. The limitation of existing technologies is that they usually use a single sensor and a fixed control algorithm, which limits the device's ability to respond to complex environmental changes and personalized user needs. For example, most integrated coffee and water dispensers cannot automatically adjust their working mode according to changes in indoor and outdoor temperatures, user activity levels or health status. In addition, the user interface is often not intuitive enough, making it difficult for users to fully utilize the functions provided by the device. These problems not only reduce user satisfaction, but also limit the potential of smart home appliances in improving the quality of life.

[0003] With the development of advanced technologies such as big data, artificial intelligence and machine learning, the market has put forward higher requirements for all-in-one coffee and water dispensers. Users expect these devices to understand and predict their needs more intelligently and provide customized services. However, existing technologies have not yet been able to fully utilize these advanced technologies to achieve this goal. For example, although some devices try to use simple algorithms to analyze user behavior, they usually lack the ability to deeply analyze data and update in real time, and cannot achieve truly personalized services. In addition, existing devices also have shortcomings in network security and data protection, which is particularly important today when smart home devices are increasingly connected. Users are increasingly concerned about the privacy and security issues of smart devices, but many device manufacturers still lack investment and innovation in this regard. Therefore, the market urgently needs a new intelligent adjustment method and system for all-in-one coffee and water dispensers that can overcome the limitations of existing technologies and provide comprehensive intelligent solutions. Summary of the invention

[0004] The purpose of the present invention is to provide an integrated intelligent adjustment method and system for a coffee machine and a water dispenser to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides an integrated intelligent adjustment method for a coffee machine and a water dispenser, comprising:

[0006] Obtain the user's health data and environmental data, use graph neural networks to capture the complex relationships between data, and build a user health status model that reflects the user's health status and long-term health trends; and based on the user's historical preferences and environmental data, establish an environmental comfort model to guide the adjustment of the integrated coffee machine and water dispenser equipment, use grey correlation analysis to evaluate the correlation between user preferences and real-time environmental data, and obtain an optimized environmental comfort model;

[0007] Based on the user health status model and the optimized environmental comfort model, the adaptive resonance theory is used to combine the user's historical preferences and real-time feedback to perform multi-source data fusion. The environmental data includes indoor and outdoor temperature, humidity and air quality, and the health data includes blood sugar, heart rate and blood pressure. The user's historical preferences include beverage type and temperature preference, and the real-time feedback includes real-time heart rate changes and environmental comfort evaluation.

[0008] Based on the user's health status model and health data, the isolation forest algorithm is used to detect abnormal points in the health data, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain health trend prediction results; the health trend prediction results are analyzed through a deep learning model to generate dynamic health risk warnings;

[0009] According to the environmental comfort model and environmental data, an environmental adaptability algorithm based on fuzzy logic is developed to automatically adjust the working parameters of the integrated coffee machine and water dispenser equipment to obtain optimized equipment parameters to ensure the best beverage experience for users in different environments. The working parameters include water temperature and coffee concentration.

[0010] Based on health risk warnings, health trend prediction results and optimized equipment parameters, create smart scenarios to achieve one-click collaborative work between coffee machines and water dispensers. Collect user feedback and equipment performance data, combine with smart scenarios, and use reinforcement learning algorithms to optimize the recommendation system and equipment adjustment parameters in real time to obtain the optimized recommendation system and equipment adjustment strategy, thereby achieving integrated intelligent adjustment of coffee machines and water dispensers.

[0011] Preferably, the user's health data and environmental data are obtained, and a graph neural network is used to capture the complex relationship between the data to build a user health status model that reflects the user's health status and long-term health trend, including:

[0012] Extract the acquired user's health data and environmental data to obtain the user's physiological indicators and environmental parameters. After wavelet transform and empirical mode decomposition processing, obtain a set of key features reflecting the user's health status.

[0013] Based on the key feature set, a graph representation of the user's health status is constructed. The nodes represent health parameters, and the edges represent the correlation between two health parameters. After being processed by the graph convolutional network, the association mapping between data nodes is obtained.

[0014] Based on the association mapping and combined with the long short-term memory network for time series analysis, a user health status model that reflects the user's health status and long-term health trend is obtained.

[0015] Preferably, the user's physiological indicators and environmental parameters are processed by wavelet transform and empirical mode decomposition to obtain a set of key features reflecting the user's health status, including:

[0016] According to the physiological index data, the characteristics of different time scales are obtained through wavelet transformation;

[0017] The environmental parameters are extracted by Fourier transform to obtain the characteristics of the environmental data, wherein the characteristics include periodic characteristics or statistical characteristics;

[0018] Performing empirical mode decomposition on the characteristics of different time scales and the characteristics of environmental data to obtain decomposition results, wherein the decomposition results include the behavior of the data at different time scales;

[0019] Based on the decomposition results and combined with the wavelet transform coefficients and modal functions, a comprehensive feature set is constructed, where the comprehensive feature set is used to provide input items for graph neural network modeling.

[0020] Preferably, the method uses an isolation forest algorithm to detect abnormal points in the health data based on the user's health status model and health data, identifies potential health risks, and predicts the user's short-term health trend through time series analysis to obtain a health trend prediction result, which includes:

[0021] The user health status model and health data are input into the isolation forest algorithm, data features and split points are randomly selected, and the average path length from the data point to the nearest boundary is measured to generate an anomaly score for each data point. The isolation forest algorithm evaluates the abnormality of each data point by constructing multiple isolation trees. The anomaly score is used to reflect the degree of isolation of the data point in multidimensional space and the degree of deviation from the normal data distribution.

[0022] Based on the anomaly score, by presetting the threshold based on the historical health data distribution, the anomaly points beyond the normal range are identified to obtain a set of data points with potential health risks;

[0023] According to the time series characteristics of user health data and the data point set of potential health risks, the autoregressive integrated moving average model is used to perform time series analysis, the order of the model is determined, and the model parameters are estimated by the maximum likelihood method to obtain the parameter estimation results of the time series model.

[0024] Preferably, the process of developing an environmental adaptability algorithm based on fuzzy logic includes:

[0025] Define fuzzy sets related to environmental parameters, where the fuzzy sets include temperature and humidity;

[0026] Based on expert experience and user preference data, combined with fuzzy sets, a fuzzy rule base is constructed through a rule-making process, where the fuzzy rule base includes the logical relationship between environmental status and equipment regulation;

[0027] According to the current environmental parameters and the fuzzy rule base, the first conclusion of equipment adjustment is obtained through the implementation of the reasoning mechanism. After the automated design process, the adaptive adjustment mechanism is obtained. The first conclusion is used to guide the adjustment direction of the coffee and water dispenser. The adaptive adjustment mechanism can adjust the working parameters of the coffee machine and water dispenser in real time.

[0028] Preferably, the health trend prediction results are analyzed by a deep learning model to generate a dynamic health risk warning, which includes:

[0029] A deep learning model is constructed using a long short-term memory network. The deep learning model captures potential health trends by learning the time series characteristics of health data and integrates time series characteristics and historical health status to obtain a trained deep learning model.

[0030] Real-time health data is input into the trained deep learning model for forward propagation calculation to predict health indicators in future time periods. Combining the output of the deep learning model with the preset risk threshold, classification algorithms or anomaly detection techniques are used to identify deviations between the predicted values ​​and the normal range to generate health risk warnings.

[0031] In a second aspect, the present application also provides an integrated intelligent adjustment system for a coffee machine and a water dispenser, comprising:

[0032] Model building module: used to obtain the user's health data and environmental data, use graph neural network to capture the complex relationship between data, and build a user health status model that reflects the user's health status and long-term health trend; and based on the user's historical preferences and environmental data, build an environmental comfort model to guide the adjustment of the integrated coffee machine and water dispenser equipment, and use grey correlation analysis to evaluate the correlation between user preferences and real-time environmental data to obtain an optimized environmental comfort model;

[0033] Fusion module: It is used to fuse multi-source data based on the user health status model and the optimized environmental comfort model, using adaptive resonance theory, combined with the user's historical preferences and real-time feedback. The environmental data includes indoor and outdoor temperature, humidity and air quality, and the health data includes blood sugar, heart rate and blood pressure. The user's historical preferences include beverage type and temperature preference, and the real-time feedback includes real-time heart rate changes and environmental comfort evaluation.

[0034] Prediction and analysis module: It is used to detect abnormal points in health data based on the user's health status model and health data using the isolation forest algorithm, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain health trend prediction results; through the deep learning model, the health trend prediction results are analyzed to generate dynamic health risk warnings;

[0035] Adjustment module: used to develop an environmental adaptability algorithm based on fuzzy logic according to the environmental comfort model and environmental data, automatically adjust the working parameters of the integrated coffee machine and water dispenser equipment, obtain optimized equipment parameters, and ensure the best beverage experience for users in different environments. The working parameters include water temperature and coffee concentration;

[0036] Optimization module: used to create intelligent scenarios to achieve one-click collaborative work of coffee machines and water dispensers based on health risk warnings, health trend prediction results and optimized equipment parameters; collect user feedback and equipment performance data, combine intelligent scenarios, and use reinforcement learning algorithms to optimize the recommendation system and equipment adjustment parameters in real time, obtain the optimized recommendation system and equipment adjustment strategy, and then realize the integrated intelligent adjustment of coffee machines and water dispensers.

[0037] In a third aspect, the present application also provides an integrated intelligent adjustment device for a coffee machine and a water dispenser, comprising:

[0038] Memory for storing computer programs;

[0039] A processor is used to implement the steps of the integrated intelligent adjustment method for the coffee machine and water dispenser when executing the computer program.

[0040] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent adjustment method based on the integration of a coffee machine and a water dispenser are implemented.

[0041] The beneficial effects of the present invention are:

[0042] The present invention proposes an innovative integrated intelligent adjustment method and system for coffee machines and water dispensers, aiming to address the limitations of the prior art. The method collects the user's physiological health data and environmental parameters in real time through advanced sensor technology, and uses graph neural networks and machine learning algorithms to conduct in-depth analysis of the data to build a personalized user health status model and environmental comfort model; the empirical mode decomposition and wavelet transform signal processing technology adopted by the present invention extract key features and perform anomaly detection to predict the user's health trends and environmental adaptability needs; in addition, the present invention also introduces fuzzy logic control and reinforcement learning algorithms to achieve adaptive adjustment and continuous optimization of the equipment, thereby providing a more accurate and personalized beverage making experience. Therefore, through the technology of the present invention, users can enjoy intelligent services that are automatically adjusted according to personal health status and environmental comfort, which greatly improves the intelligence level and user satisfaction of intelligent adjustment equipment.

[0043] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 It is a schematic diagram of the process of the integrated intelligent adjustment method of the coffee machine and water dispenser described in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of the integrated intelligent adjustment system for a coffee machine and water dispenser according to an embodiment of the present invention;

[0047] Figure 3 It is a schematic diagram of the structure of the integrated intelligent adjustment device for a coffee machine and a water dispenser described in an embodiment of the present invention.

[0048] In the figure: 701, model building module; 702, fusion module; 703, prediction and analysis module; 704, adjustment module; 705, optimization module; 800, integrated intelligent adjustment device for coffee machine and water dispenser; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. Example 1

[0051] This embodiment provides an integrated intelligent adjustment method for a coffee machine and a water dispenser.

[0052] See also Figure 1 , the figure shows that the method includes step S100, step S200, step S300, step S400 and step S500.

[0053] S100. Obtain the user's health data and environmental data, use graph neural networks to capture the complex relationships between the data, and build a user health status model that reflects the user's health status and long-term health trends; and based on the user's historical preferences and combined with environmental data, establish an environmental comfort model to guide the adjustment of the integrated coffee machine and water dispenser equipment, use grey correlation analysis to evaluate the correlation between user preferences and real-time environmental data, and obtain an optimized environmental comfort model.

[0054] It can be understood that step S100 includes S101, S102 and S103, wherein:

[0055] S101, extracting the acquired health data and environmental data of the user to obtain the user's physiological indicators and environmental parameters, and obtaining a key feature set reflecting the user's health status through wavelet transform and empirical mode decomposition processing;

[0056] Wherein, step S101 includes S1011, S1012, S1013 and S1014, wherein:

[0057] S1011. Based on the physiological index data, the characteristics of different time scales are obtained through wavelet transformation. The calculation formula is as follows:

[0058]

[0059] In the formula, W ( x ) is the coefficient after wavelet transformation, x ( t ) is the original signal, ψ is the wavelet function, x 0 and s are the translation and scaling parameters, t is the time variable, and dt is the sampling interval;

[0060] S1012, extracting environmental parameters by Fourier transform to obtain characteristics of environmental data, wherein the characteristics include periodic characteristics or statistical characteristics;

[0061] S1013, performing empirical mode decomposition on the features of different time scales and the features of the environmental data to obtain decomposition results, wherein the decomposition results include behaviors of the data at different time scales;

[0062] It should be noted that complex time series data can be converted into a frequency domain representation that is easier to analyze, making it easier to identify repetitive patterns and potential periodic changes in the environment. For example, the periodic characteristics of diurnal changes can be identified from environmental temperature records through Fourier transforms. Through Fourier transforms, the technical effect of this step is to decompose the environmental parameter data into multiple IMFs, each IMF representing a single frequency component in the data, so that a more detailed understanding of the behavior of the data at different time scales can be achieved. For example, one IMF may represent a sharp change in temperature over a short period of time, while another may represent a longer-term temperature trend.

[0063] S1014. Based on the decomposition results and in combination with the wavelet transform coefficients and modal functions, a comprehensive feature set is constructed, wherein the comprehensive feature set is used to provide input items for graph neural network modeling.

[0064] It should be noted that the behavior of data at different time scales refers to the characteristics expressed by the intrinsic mode function obtained after the original time series data is decomposed. Among them, the original time series data refers to the collected continuous or discrete user health status data and environmental parameter data, such as the user's heart rate, blood sugar level, or the temperature and humidity of the environment; a series of functions decomposed from the original data by the EMD method. Each IMF satisfies two conditions: within the range of the entire data set, the number of local maxima and local minima is equal or at most one different, and for any point, the average of the local maximum envelope (the curve composed of local maximum points) and the local minimum envelope of the IMF is zero or close to zero. Each IMF represents a specific oscillation mode in the data and can be regarded as the behavior of the original data at a specific time scale. For example, one IMF may represent a rapid fluctuation in the user's heart rate, while another IMF may represent a slow change trend in the heart rate. Therefore, the EMD method can decompose complex time series data into several simple IMFs, which are arranged from high to low in frequency, reflecting the characteristics of the data at different time scales.

[0065] S102, based on the key feature set, construct a graph representation of the user's health status, where nodes represent health parameters and edges represent the correlation between two health parameters, and after being processed by a graph convolutional network, obtain an association map between data nodes;

[0066] S103. Perform time series analysis based on the association mapping and the long short-term memory network to obtain a user health status model that reflects the user's health status and long-term health trend.

[0067] It should be noted that the long short-term memory network (LSTM) is used to conduct in-depth analysis of time series data. LSTM can remember long-term dependent information and ignore unimportant changes, which is suitable for the prediction of health trends. Combining the node feature representation obtained by the graph neural network and the time series analysis ability of LSTM, a fusion model is constructed, which can predict the user's health status and identify patterns of health changes.

[0068] It can be understood that this model can identify the evolution patterns of health status and predict long-term trends, providing a scientific basis for personalized device adjustment. It not only realizes in-depth analysis of user health data, but also builds an intelligent model that can predict health trends and guide device adjustment.

[0069] S200, based on the user health status model and the optimized environmental comfort model, using adaptive resonance theory, combined with the user's historical preferences and real-time feedback, multi-source data fusion is performed, where the environmental data includes indoor and outdoor temperature, humidity and air quality, and the health data includes blood sugar, heart rate and blood pressure. The user's historical preferences include beverage type and temperature preferences, and the real-time feedback includes real-time heart rate changes and environmental comfort evaluation.

[0070] It can be understood that in this step S200, both the user health status model and the optimized environmental comfort model provide the system with basic information on the user's health status and environmental adaptability, wherein the user health status model may be constructed based on historical health data and time series analysis, and the environmental comfort model may be set according to environmental data and user preferences. The use of adaptive resonance theory is to be able to handle the dynamic changes of input data and classify the data. In this scenario, ART is used to process and integrate data from different sources, including health data and environmental data. The system then stores the user's historical preferences, such as beverage type and temperature preferences. These data provide the basis for personalized services for the system, and then real-time feedback, such as real-time heart rate changes and environmental comfort evaluation, provides immediate user status and needs. When performing multi-source data fusion, the collected health data and environmental data are standardized and normalized to eliminate the dimensional effects of different data sources, and then features are extracted from the health data, such as the fluctuation range of blood sugar levels, heart rate variability, etc.; features are extracted from the environmental data, such as the daily range of temperature, the long-term trend of humidity, etc.; the pre-processed data is input into the ART network, and the network classifies the data through competition and cooperation mechanisms, and adaptively adjusts its parameters to adapt to new data patterns. The output of the ART network is combined with the user's historical preferences to form a comprehensive data representation that can reflect the user's immediate health status and environmental adaptability. Among them, the core of the adaptive resonance theory is its resonance mechanism, which can be expressed by the following simplified formula:

[0071]

[0072] In the formula, Vij It is i Features and j The connection weights of the class nodes, α and β are the learning rate and inhibition rate, Rj It is j The response vector of the categories , Wij is the input vector.

[0073] S300. Based on the user's health status model and health data, the isolation forest algorithm is used to detect anomalies in the health data, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain health trend prediction results; the health trend prediction results are analyzed through a deep learning model to generate dynamic health risk warnings.

[0074] It can be understood that in this step, the isolation forest algorithm "isolates" observations by randomly selecting features and randomly selecting the cut values ​​of the features. If an observation is easily isolated, it may be an anomaly, and health risks include abnormal fluctuations in blood sugar or abnormally increased heart rate.

[0075] It should be noted that step S300 includes S301, S302 and S303, wherein:

[0076] S301, input the user health status model and health data into the isolation forest algorithm, randomly select data features and split points, measure the average path length from the data point to the nearest boundary, and generate an anomaly score for each data point, wherein the isolation forest algorithm evaluates the abnormality of each data point by constructing multiple isolation trees, and the anomaly score is used to reflect the degree of isolation of the data point in the multidimensional space and the degree of deviation from the normal data distribution;

[0077] S302, based on the abnormal score, by presetting a threshold based on the historical health data distribution, identifying abnormal points beyond the normal range, and obtaining a data point set of potential health risks;

[0078] S303. Based on the time series characteristics of the user's health data and the data point set of potential health risks obtained, an autoregressive integrated moving average model is used to perform time series analysis, the order of the model is determined, and the model parameters are estimated by the maximum likelihood method to obtain the parameter estimation results of the time series model.

[0079] It should be noted that in step S301, the user's health status model and health data collected in real time are input into the isolation forest algorithm. The working principle of the algorithm is to construct decision trees by randomly selecting features and split points in the data set. These decision trees are called isolation trees. For each data point, the algorithm measures the average path length to the nearest boundary (i.e., the minimum or maximum value in the data set), where a shorter path length means that the data point is more likely to be isolated, thereby obtaining a higher anomaly score. This process is repeated on multiple trees to improve the accuracy and robustness of the assessment. This step can quantify the abnormality of each data point and provide a numerical anomaly score for subsequent health risk assessment. These scores reflect the location and degree of deviation of the data point relative to the normal data distribution.

[0080] It is understood that step S302 involves using the anomaly score generated in step S301 to identify potential health risks. By comparing with a threshold value based on the distribution of historical health data, data points whose anomaly scores exceed a preset threshold value can be identified, and these data points are considered abnormal and may indicate health risks. This step reveals potential health risks by identifying abnormal data points, making early diagnosis and intervention possible.

[0081] In step S303, the autoregressive integrated moving average model is used to perform time series analysis on the user's health data. First, the order of the ARIMA model needs to be determined, which includes the order of the autoregressive (AR) part, the number of differences (I), and the order of the moving average (MA) part. The selection of these orders is based on the analysis of the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the data; then, the maximum likelihood method or other optimization algorithms are used to estimate the model parameters to obtain the best model fit. This step captures the trend and seasonal changes of health data through the time series model, providing a mathematical basis for short-term health trend prediction.

[0082] It should be noted that step S300 also includes S304 and S305, wherein:

[0083] S304, constructing a deep learning model using a long short-term memory network, wherein the deep learning model captures potential health trends by learning the time series characteristics of health data, and integrates the time series characteristics and historical health status to obtain a trained deep learning model;

[0084] S305. Input the real-time health data into the trained deep learning model and perform forward propagation calculations to predict health indicators in the future time period. Combine the output of the deep learning model with the preset risk threshold, use classification algorithms or anomaly detection technology to identify deviations between the predicted values ​​and the normal range, and generate health risk warnings.

[0085] In this embodiment, a long short-term memory network (LSTM) is used to build a deep learning model specifically for analyzing and predicting the health trends of users. By learning the time series characteristics of the user's health data, such as the history of heart rate, blood pressure and blood sugar levels, potential health trends can be identified and predicted. During the model training process, the time series characteristics and historical health status are used as input, and the network weights are continuously adjusted through the back propagation algorithm to minimize the difference between the predicted value and the actual value. After the training is completed, we obtain a deep learning model that can accurately reflect the changes in the user's health status. Among them, the model can predict future health trends based on the user's historical health data, and provide a basis for personalized adjustment for the integrated coffee machine and water dispenser equipment.

[0086] It should be noted that in step S305, the user's real-time health data is input into the LSTM model trained in step S304. The model performs forward propagation calculations on these data to predict key health indicators in the future time period. These prediction results are compared with the preset health risk threshold to determine whether there are potential health risks, and use classification algorithms or anomaly detection techniques, such as support vector machines (SVM) or one-class support vector machines (One-Class SVM), to identify the deviation between the predicted values ​​output by the model and the normal health range. When the predicted health indicators exceed the normal range, the system will automatically issue an early warning to prompt the user of possible health problems. These early warning information can be used by the integrated coffee machine and water dispenser device to trigger corresponding adjustment measures, such as adjusting the water temperature, reminding the user to rest or drink specific drinks, thereby improving the user's quality of life and health level.

[0087] S400. According to the environmental comfort model and environmental data, an environmental adaptability algorithm based on fuzzy logic is developed to automatically adjust the working parameters of the integrated coffee machine and water dispenser equipment to obtain optimized equipment parameters to ensure the user's best beverage experience in different environments. The working parameters include water temperature and coffee concentration.

[0088] It can be understood that the development process of the environment adaptability algorithm based on fuzzy logic in step S400 includes:

[0089] A fuzzy set about environmental parameters is defined, wherein the fuzzy set includes temperature and humidity; wherein "warm", "cool", "dry" and "humid" are not included in the fuzzy set;

[0090] Based on expert experience and user preference data, combined with fuzzy sets, a fuzzy rule base is constructed through a rule-making process, where the fuzzy rule base includes the logical relationship between environmental status and equipment regulation;

[0091] It is understood that, for example, "if the indoor temperature is "warm" and the outdoor temperature is "cool", adjust the water temperature to "moderate".

[0092] According to the current environmental parameters and the fuzzy rule base, the first conclusion of equipment adjustment is obtained through the implementation of the reasoning mechanism. After the automated design process, the adaptive adjustment mechanism is obtained. The first conclusion is used to guide the adjustment direction of the coffee and water dispenser. The adaptive adjustment mechanism can adjust the working parameters of the coffee machine and water dispenser in real time.

[0093] It should be noted that according to the response of the adaptive adjustment mechanism, after real-time monitoring and automatic adjustment, the optimized equipment operating parameters are obtained to ensure that the coffee machine and water dispenser can provide the best beverage experience under different environmental conditions. Through these steps, the developed environmental adaptability algorithm can ensure that the coffee machine and water dispenser can be intelligently adjusted according to real-time environmental parameters and user preferences, improving user satisfaction and equipment efficiency.

[0094] In this embodiment, in practical applications, the adaptive adjustment mechanism can be implemented by integrating into the microcontroller or cloud platform of the coffee machine and water dispenser, and remote monitoring and control can be performed using the Internet of Things technology. The combination of fuzzy logic and other intelligent algorithms, such as neural networks or deep learning, can be further explored to improve the accuracy and robustness of the environmental adaptability algorithm. In addition, the research can be extended to the use of reinforcement learning algorithms, so that the system can self-optimize based on the long-term feedback of users, further improve the quality of personalized services and the intelligence level of the system, and through these studies, the field of smart home appliances can be promoted to a more intelligent and personalized direction.

[0095] S500. Create smart scenarios based on health risk warnings, health trend prediction results and optimized equipment parameters to achieve one-click collaboration between coffee machines and water dispensers. Collect user feedback and equipment performance data, combine smart scenarios, and use reinforcement learning algorithms to optimize the recommendation system and equipment adjustment parameters in real time to obtain the optimized recommendation system and equipment adjustment strategy, thereby achieving integrated intelligent adjustment of coffee machines and water dispensers.

[0096] It can be understood that in this step, drinks with suitable temperature are automatically prepared according to the user's waking time, and user feedback and equipment performance data are collected. Example 2

[0097] like Figure 2 As shown, this embodiment provides an integrated intelligent adjustment system for a coffee machine and a water dispenser, see Figure 2 The system comprises:

[0098] Model building module 701: used to obtain the user's health data and the environment data in which he is located, use graph neural network to capture the complex relationship between the data, and build a user health status model that reflects the user's health status and long-term health trend; and according to the user's historical preferences, combined with environmental data, build an environmental comfort model for guiding the adjustment of the integrated coffee machine and water dispenser equipment, use grey correlation analysis to evaluate the correlation between user preferences and real-time environmental data, and obtain an optimized environmental comfort model;

[0099] Fusion module 702: for performing multi-source data fusion based on the user health status model and the optimized environmental comfort model, using adaptive resonance theory, combined with the user's historical preferences and real-time feedback, wherein the environmental data includes indoor and outdoor temperature, humidity and air quality, the health data includes blood sugar, heart rate and blood pressure, wherein the user's historical preferences include beverage type and temperature preference, and the real-time feedback includes real-time heart rate changes and environmental comfort evaluation;

[0100] Prediction and analysis module 703: used to detect abnormal points in health data based on the user's health status model and health data using the isolation forest algorithm, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain health trend prediction results; analyze the health trend prediction results through a deep learning model to generate dynamic health risk warnings;

[0101] Adjustment module 704: used to develop an environmental adaptability algorithm based on fuzzy logic according to the environmental comfort model and environmental data, automatically adjust the working parameters of the integrated coffee machine and water dispenser device, obtain optimized device parameters, and ensure the best beverage experience for users in different environments, wherein the working parameters include water temperature and coffee concentration;

[0102] Optimization module 705: used to create intelligent scenarios to achieve one-click collaborative work of coffee machines and water dispensers based on health risk warnings, health trend prediction results and optimized equipment parameters; collect user feedback and equipment performance data, combine intelligent scenarios, and use reinforcement learning algorithms to optimize the recommendation system and equipment adjustment parameters in real time, obtain the optimized recommendation system and equipment adjustment strategy, and then realize the integrated intelligent adjustment of coffee machines and water dispensers.

[0103] Specifically, the model building module 701 includes:

[0104] The first decomposition unit is used to extract the acquired health data of the user and the environmental data to obtain the user's physiological indicators and environmental parameters, and obtain a key feature set reflecting the user's health status through wavelet transform and empirical mode decomposition processing;

[0105] The first processing unit is used to construct a graph representation of the user's health status based on the key feature set, where nodes represent health parameters and edges represent the correlation between two health parameters. After being processed by the graph convolutional network, an association map between data nodes is obtained;

[0106] The first analysis unit is used to perform time series analysis based on association mapping in combination with a long short-term memory network to obtain a user health status model that reflects the user's health status and long-term health trend.

[0107] Specifically, the first decomposition unit includes:

[0108] The second processing unit is used to obtain the characteristics of different time scales based on the physiological index data through wavelet transformation. The calculation formula is as follows:

[0109]

[0110] In the formula, W ( x ) is the coefficient after wavelet transformation, x ( t ) is the original signal, ψ is the wavelet function, x 0 and s are the translation and scaling parameters, t is the time variable, and dt is the sampling interval;

[0111] Extraction unit: used to extract environmental parameters by Fourier transform to obtain characteristics of environmental data, wherein the characteristics include periodic characteristics or statistical characteristics;

[0112] The second decomposition unit is used to perform empirical mode decomposition on the features of different time scales and the features of environmental data to obtain decomposition results, wherein the decomposition results include the behaviors of the data at different time scales;

[0113] The first construction unit is used to construct a comprehensive feature set based on the decomposition results and in combination with the wavelet transform coefficients and the modal function, wherein the comprehensive feature set is used to provide input items for graph neural network modeling.

[0114] Specifically, the prediction analysis module 703 includes:

[0115] Input unit: used to input the user health status model and health data into the isolation forest algorithm, randomly select data features and split points, measure the average path length from the data point to the nearest boundary, and generate an anomaly score for each data point. The isolation forest algorithm evaluates the abnormality of each data point by constructing multiple isolation trees. The anomaly score is used to reflect the degree of isolation of the data point in the multidimensional space and the degree of deviation from the normal data distribution.

[0116] Identification unit: used to identify abnormal points beyond the normal range based on the abnormal score and obtain a data point set of potential health risks by presetting a threshold based on the distribution of historical health data;

[0117] The second analysis unit is used to perform time series analysis using an autoregressive integrated moving average model based on the time series characteristics of the user's health data and the data point set of potential health risks obtained, determine the order of the model, and estimate the model parameters through the maximum likelihood method to obtain the parameter estimation results of the time series model.

[0118] Specifically, the adjustment module 704 includes:

[0119] Definition unit: used to define fuzzy sets related to environmental parameters, where the fuzzy sets include temperature and humidity;

[0120] Formulating unit: used to build a fuzzy rule base based on expert experience and user preference data, combined with fuzzy sets, through a rule formulation process, where the fuzzy rule base includes the logical relationship between environmental status and equipment adjustment;

[0121] Adaptive unit: It is used to obtain the first conclusion of equipment adjustment according to the current environmental parameters and fuzzy rule base through the implementation of the reasoning mechanism. After the automated design process, an adaptive adjustment mechanism is obtained, in which the first conclusion is used to guide the adjustment direction of the coffee and water dispenser. The adaptive adjustment mechanism can adjust the working parameters of the coffee machine and water dispenser in real time.

[0122] Specifically, the prediction analysis module 703 further includes:

[0123] The second construction unit is used to construct a deep learning model using a long short-term memory network, wherein the deep learning model captures potential health trends by learning the time series characteristics of health data, and integrates the time series characteristics and historical health status to obtain a trained deep learning model;

[0124] Generation unit: used to input real-time health data into the trained deep learning model, perform forward propagation calculations to predict health indicators in the future time period, combine the output of the deep learning model with the preset risk threshold, use classification algorithms or anomaly detection technology to identify deviations between the predicted value and the normal range, and generate health risk warnings.

[0125] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here. Example 3

[0126] Corresponding to the above method embodiment, this embodiment also provides an integrated intelligent adjustment device for a coffee machine and water dispenser. The integrated intelligent adjustment device for a coffee machine and water dispenser described below and the integrated intelligent adjustment method for a coffee machine and water dispenser described above can refer to each other.

[0127] Figure 3 FIG. 8 is a block diagram of an integrated intelligent adjustment device 800 for a coffee machine and a water dispenser according to an exemplary embodiment. Figure 3As shown, the integrated intelligent adjustment device 800 for a coffee machine and a water dispenser includes: a processor 801 and a memory 802. The integrated intelligent adjustment device 800 for a coffee machine and a water dispenser also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0128] The processor 801 is used to control the overall operation of the integrated intelligent adjustment device 800 of the coffee machine and water dispenser to complete all or part of the steps in the integrated intelligent adjustment method of the coffee machine and water dispenser. The memory 802 is used to store various types of data to support the operation of the integrated intelligent adjustment device 800 of the coffee machine and water dispenser. For example, these data may include instructions for any application or method operating on the integrated intelligent adjustment device 800 of the coffee machine and water dispenser, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse or buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the integrated intelligent adjustment device 800 of the coffee machine and water dispenser and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: a Wi-Fi module, a Bluetooth module or an NFC module.

[0129] In an exemplary embodiment, the integrated intelligent adjustment device 800 of a coffee machine and a water dispenser may be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned integrated intelligent adjustment method of a coffee machine and a water dispenser.

[0130] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned coffee machine and water dispenser integrated intelligent adjustment method are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions may be executed by the processor 801 of the coffee machine and water dispenser integrated intelligent adjustment device 800 to complete the above-mentioned coffee machine and water dispenser integrated intelligent adjustment method. Example 4

[0131] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the integrated intelligent adjustment method for a coffee machine and water dispenser described above can refer to each other.

[0132] A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, the steps of the integrated intelligent adjustment method for the coffee machine and water dispenser of the above method embodiment are implemented.

[0133] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0134] 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.

[0135] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An integrated intelligent adjustment method for a coffee machine and a water dispenser, characterized in that: include: Obtain the user's health data and environmental data, use graph neural networks to capture the complex relationships between data, and build a user health status model that reflects the user's health status and long-term health trends; and based on the user's historical preferences and environmental data, establish an environmental comfort model to guide the adjustment of the integrated coffee machine and water dispenser equipment, use grey correlation analysis to evaluate the correlation between user preferences and real-time environmental data, and obtain an optimized environmental comfort model; Based on the user health status model and the optimized environmental comfort model, the adaptive resonance theory is used to combine the user's historical preferences and real-time feedback to perform multi-source data fusion. The environmental data includes indoor and outdoor temperature, humidity and air quality, and the health data includes blood sugar, heart rate and blood pressure. The user's historical preferences include beverage type and temperature preference, and the real-time feedback includes real-time heart rate changes and environmental comfort evaluation. Based on the user's health status model and health data, the isolation forest algorithm is used to detect abnormal points in the health data, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain the health trend prediction results; Through deep learning models, health trend prediction results are analyzed to generate dynamic health risk warnings; According to the environmental comfort model and environmental data, an environmental adaptability algorithm based on fuzzy logic is developed to automatically adjust the working parameters of the integrated coffee machine and water dispenser equipment to obtain optimized equipment parameters to ensure the best beverage experience for users in different environments. The working parameters include water temperature and coffee concentration. Based on health risk warnings, health trend prediction results and optimized equipment parameters, create smart scenarios to achieve one-click collaboration between coffee machines and water dispensers; Collect user feedback and equipment performance data, combine with intelligent scenarios, and use reinforcement learning algorithms to optimize the recommendation system and equipment adjustment parameters in real time, obtain the optimized recommendation system and equipment adjustment strategy, and then realize the integrated intelligent adjustment of coffee machines and water dispensers; The user's health data and environmental data are obtained, and a graph neural network is used to capture the complex relationship between the data to build a user health status model that reflects the user's health status and long-term health trend, including: Extract the acquired user's health data and environmental data to obtain the user's physiological indicators and environmental parameters. After wavelet transform and empirical mode decomposition processing, obtain a set of key features reflecting the user's health status; Based on the key feature set, a graph representation of the user's health status is constructed, where nodes represent health parameters and edges represent the correlation between two health parameters. After being processed by a graph convolutional network, the association mapping between data nodes is obtained; Based on the association mapping, combined with the long short-term memory network, time series analysis is performed to obtain a user health status model that reflects the user's health status and long-term health trend; The user's physiological indicators and environmental parameters are processed by wavelet transform and empirical mode decomposition to obtain a set of key features reflecting the user's health status, including: According to the physiological index data, after wavelet transform processing, the characteristics of different time scales are obtained, and the calculation formula is as follows: In the formula, W ( x ) is the coefficient after wavelet transformation, x ( t ) is the original signal, ψ is the wavelet function, x 0 and s are the translation and scaling parameters, t is the time variable, and dt is the sampling interval; The environmental parameters are extracted by Fourier transform to obtain the characteristics of the environmental data, wherein the characteristics include periodic characteristics or statistical characteristics; Performing empirical mode decomposition on the characteristics of different time scales and the characteristics of environmental data to obtain decomposition results, wherein the decomposition results include the behavior of the data at different time scales; Based on the decomposition results, combined with wavelet transform coefficients and modal functions, a comprehensive feature set is constructed, where the comprehensive feature set is used to provide input items for graph neural network modeling; According to the user health status model and health data, the isolation forest algorithm is used to detect abnormal points in the health data, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain the health trend prediction results, including: The user health status model and health data are input into the isolation forest algorithm, data features and split points are randomly selected, and the average path length from the data point to the nearest boundary is measured to generate an anomaly score for each data point. The isolation forest algorithm evaluates the abnormality of each data point by constructing multiple isolation trees. The anomaly score is used to reflect the degree of isolation of the data point in multidimensional space and the degree of deviation from the normal data distribution. Based on the anomaly score, by presetting the threshold based on the historical health data distribution, the anomaly points beyond the normal range are identified to obtain a set of data points with potential health risks; According to the time series characteristics of user health data and the data point set of potential health risks, the autoregressive integrated moving average model is used to perform time series analysis, the order of the model is determined, and the model parameters are estimated by the maximum likelihood method to obtain the parameter estimation results of the time series model.

2. The integrated intelligent adjustment method for a coffee machine and a water dispenser according to claim 1, characterized in that: The development process of the fuzzy logic based environment adaptability algorithm includes: Define fuzzy sets related to environmental parameters, where the fuzzy sets include temperature and humidity; Based on expert experience and user preference data, combined with fuzzy sets, a fuzzy rule base is constructed through a rule-making process, where the fuzzy rule base includes the logical relationship between environmental status and equipment regulation; According to the current environmental parameters and the fuzzy rule base, the first conclusion of equipment adjustment is obtained through the implementation of the reasoning mechanism. After the automated design process, the adaptive adjustment mechanism is obtained. The first conclusion is used to guide the adjustment direction of the coffee and water dispenser. The adaptive adjustment mechanism can adjust the working parameters of the coffee machine and water dispenser in real time.

3. The integrated intelligent adjustment method for a coffee machine and a water dispenser according to claim 1, characterized in that: The deep learning model is used to analyze the health trend prediction results and generate dynamic health risk warnings, including: A deep learning model is constructed using a long short-term memory network. The deep learning model captures potential health trends by learning the time series characteristics of health data and integrates time series characteristics and historical health status to obtain a trained deep learning model. Real-time health data is input into the trained deep learning model for forward propagation calculation to predict health indicators in future time periods. Combining the output of the deep learning model with the preset risk threshold, classification algorithms or anomaly detection techniques are used to identify deviations between the predicted values ​​and the normal range to generate health risk warnings.

4. An integrated intelligent adjustment system for a coffee machine and a water dispenser, based on the integrated intelligent adjustment method for a coffee machine and a water dispenser according to claim 1, characterized in that: include: Model building module: used to obtain the user's health data and environmental data, use graph neural network to capture the complex relationship between data, and build a user health status model that reflects the user's health status and long-term health trend; and based on the user's historical preferences and environmental data, build an environmental comfort model to guide the adjustment of the integrated coffee machine and water dispenser equipment, and use grey correlation analysis to evaluate the correlation between user preferences and real-time environmental data to obtain an optimized environmental comfort model; Fusion module: It is used to fuse multi-source data based on the user health status model and the optimized environmental comfort model, using adaptive resonance theory, combined with the user's historical preferences and real-time feedback. The environmental data includes indoor and outdoor temperature, humidity and air quality, and the health data includes blood sugar, heart rate and blood pressure. The user's historical preferences include beverage type and temperature preference, and the real-time feedback includes real-time heart rate changes and environmental comfort evaluation. Prediction and analysis module: used to detect abnormal points in health data based on the user's health status model and health data using the isolation forest algorithm, identify potential health risks, and predict the user's short-term health trend through time series analysis to obtain health trend prediction results; Through deep learning models, health trend prediction results are analyzed to generate dynamic health risk warnings; Adjustment module: used to develop an environmental adaptability algorithm based on fuzzy logic according to the environmental comfort model and environmental data, automatically adjust the working parameters of the integrated coffee machine and water dispenser equipment, obtain optimized equipment parameters, and ensure the best beverage experience for users in different environments. The working parameters include water temperature and coffee concentration; Optimization module: used to create intelligent scenarios to achieve one-click collaboration between coffee machines and water dispensers based on health risk warnings, health trend prediction results, and optimized equipment parameters; Collect user feedback and equipment performance data, combine with intelligent scenarios, and use reinforcement learning algorithms to optimize the recommendation system and equipment adjustment parameters in real time to obtain the optimized recommendation system and equipment adjustment strategy, thereby realizing integrated intelligent adjustment of coffee machines and water dispensers.

5. The integrated intelligent adjustment system for coffee machine and water dispenser according to claim 4, characterized in that: The model building module includes: The first decomposition unit is used to extract the acquired health data of the user and the environmental data to obtain the user's physiological indicators and environmental parameters, and obtain a key feature set reflecting the user's health status through wavelet transform and empirical mode decomposition processing; The first processing unit is used to construct a graph representation of the user's health status based on the key feature set, where nodes represent health parameters and edges represent the correlation between two health parameters. After being processed by the graph convolutional network, an association map between data nodes is obtained; The first analysis unit is used to perform time series analysis based on association mapping in combination with a long short-term memory network to obtain a user health status model that reflects the user's health status and long-term health trend.

6. The integrated intelligent adjustment system for coffee machine and water dispenser according to claim 5, characterized in that: The first decomposition unit comprises: The second processing unit is used to obtain the characteristics of different time scales based on the physiological index data through wavelet transformation. The calculation formula is as follows: In the formula, W ( x ) is the coefficient after wavelet transformation, x ( t ) is the original signal, ψ is the wavelet function, x 0 and s are the translation and scaling parameters, t is the time variable, and dt is the sampling interval; Extraction unit: used to extract environmental parameters by Fourier transform to obtain characteristics of environmental data, wherein the characteristics include periodic characteristics or statistical characteristics; The second decomposition unit is used to perform empirical mode decomposition on the features of different time scales and the features of environmental data to obtain decomposition results, wherein the decomposition results include the behaviors of the data at different time scales; The first construction unit is used to construct a comprehensive feature set based on the decomposition results and in combination with the wavelet transform coefficients and the modal function, wherein the comprehensive feature set is used to provide input items for graph neural network modeling.

7. The integrated intelligent adjustment system for coffee machine and water dispenser according to claim 4, characterized in that: The prediction analysis module includes: Input unit: used to input the user health status model and health data into the isolation forest algorithm, randomly select data features and split points, measure the average path length from the data point to the nearest boundary, and generate an anomaly score for each data point. The isolation forest algorithm evaluates the abnormality of each data point by constructing multiple isolation trees. The anomaly score is used to reflect the degree of isolation of the data point in the multidimensional space and the degree of deviation from the normal data distribution. Identification unit: used to identify abnormal points beyond the normal range based on the abnormal score and obtain a data point set of potential health risks by presetting a threshold based on the distribution of historical health data; The second analysis unit is used to perform time series analysis using an autoregressive integrated moving average model based on the time series characteristics of the user's health data and the data point set of potential health risks obtained, determine the order of the model, and estimate the model parameters through the maximum likelihood method to obtain the parameter estimation results of the time series model.

Images