Intelligent energy cup food intake monitoring system and method thereof

Abstract

The invention relates to the technical field of food intake monitoring systems, in particular to an intelligent energy cup food intake monitoring system and method. The data preprocessing module is electrically connected with the multi-sensor data acquisition module; the AI analysis module is in data connection with the data preprocessing module; calculating the real-time food intake of the user according to the liquid type and the food intake behavior in combination with a preset health standard; predicting a blood glucose curve of the user based on the real-time food intake and historical data of the user; the intelligent intervention module is in signal connection with the AI analysis module and is used for judging whether a preset health threshold value is exceeded or not; when the judgment result exceeds the health threshold value, generating a corresponding intervention instruction; the feedback execution module is in control connection with the intelligent intervention module, and the data storage and communication module is in data connection with the multi-sensor data acquisition module, the AI analysis module and the intelligent intervention module; and the data are uploaded to a remote server through a wireless network, so that cloud backup and analysis of the data are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of food intake monitoring systems, in particular to an intelligent energy cup food intake monitoring system and its method. Background Art

[0002] With the increasing emphasis on a healthy lifestyle, intelligent drinking cups, as emerging health management tools, have gradually entered the public eye. Traditional intelligent drinking cups mainly focus on reminding users to drink water regularly or simply recording the amount of water consumed. However, these products still have many deficiencies in terms of function and intelligence level, and are difficult to meet the needs of users for precise health management.

[0003] Currently, the more advanced intelligent drinking cups on the market usually use a single liquid level sensor or weight sensor to monitor the amount of water consumed. Although this method can generally record the user's water intake situation, it has limitations in many aspects. First, the measurement accuracy of a single sensor is limited and is easily affected by external factors such as the tilt of the cup body and temperature changes, resulting in inaccurate data. Second, such products cannot distinguish different types of liquids, so they cannot provide personalized suggestions for different beverages to users. Moreover, existing products generally lack the ability to deeply analyze the user's drinking behavior and are difficult to identify subtle behavior patterns such as rapid drinking and intermittent drinking, thus unable to provide truly personalized health guidance.

[0004] In terms of data processing and analysis, existing technologies mostly use simple statistical methods or preset fixed thresholds to judge the user's drinking situation. This method ignores individual differences and cannot adapt to the physical characteristics and living habits of different users. At the same time, due to the lack of support from advanced artificial intelligence algorithms, existing products are difficult to learn and predict the user's long-term drinking pattern, and are even less able to correlate the drinking behavior with other health indicators (such as blood sugar level) for comprehensive analysis.

[0005] In addition, in terms of user interaction and intervention, most intelligent drinking cups only provide a simple drinking reminder function, lacking pertinence and flexibility. This single interaction method is easily ignored by users or generates resistance, and it is difficult to continuously and effectively improve the user's drinking habits. At the same time, existing products generally lack effective protection of user privacy, and there are security risks in the process of data transmission and storage.

[0006] In view of the above problems, there is an urgent need for an intelligent energy cup system that can accurately monitor drinking behavior, intelligently analyze health status, and provide personalized intervention. Summary of the Invention

[0007] In response to this need, the present invention proposes an innovative intelligent energy cup food intake monitoring system and method. The intelligent energy cup food intake monitoring system of the present invention effectively solves many problems existing in the prior art through innovative methods such as multi-sensor fusion technology, deep learning algorithms, and personalized intervention strategies, providing users with a comprehensive, accurate, and intelligent health management solution.

[0008] The present invention proposes an intelligent energy cup food intake monitoring system, including:

[0009] A multi-sensor data acquisition module, used for:

[0010] Collecting the liquid level information and weight information of the liquid in the cup body;

[0011] Obtaining the RFID identification information of the cup body;

[0012] Collecting the geographical location information and environmental data of the user;

[0013] A data preprocessing module, electrically connected to the multi-sensor data acquisition module, used for:

[0014] Receiving various sensor data sent by the multi-sensor data acquisition module;

[0015] Performing noise reduction, normalization, and feature extraction processing on the sensor data;

[0016] An AI analysis module, data-connected to the data preprocessing module, used for:

[0017] Based on the preprocessed sensor data, using deep learning algorithms to identify the liquid type and eating behavior;

[0018] According to the liquid type and eating behavior, combined with the preset health standards, calculating the user's real-time food intake;

[0019] Based on the real-time food intake and the user's historical data, predicting the user's blood glucose curve;

[0020] An intelligent intervention module, signal-connected to the AI analysis module, used for:

[0021] Receiving the food intake data and blood glucose prediction data sent by the AI analysis module;

[0022] According to the food intake data and blood glucose prediction data, determining whether it exceeds the preset health threshold;

[0023] When the judgment result exceeds the health threshold, generating a corresponding intervention instruction;

[0024] A feedback execution module, control-connected to the intelligent intervention module, used for:

[0025] Receive the intervention instruction sent by the intelligent intervention module;

[0026] Selectively perform sound reminder, vibration warning or heating intervention operation according to the intervention instruction;

[0027] The data storage and communication module is respectively connected to the multi-sensor data acquisition module, the AI analysis module and the intelligent intervention module for:

[0028] Store the user's historical eating data, health indicators and intervention records;

[0029] Upload the data to a remote server through a wireless network to achieve cloud backup and analysis of the data.

[0030] Preferably, the multi-sensor data acquisition module includes:

[0031] A liquid level sensor for real-time detection of the height change of the liquid in the cup body;

[0032] A weight sensor for accurately measuring the weight of the liquid in the cup body;

[0033] An RFID reader for identifying the unique identifier of the cup body and obtaining the cup body capacity information associated with the identifier;

[0034] A GPS module for obtaining the user's real-time geographical location information;

[0035] An environment sensor for collecting environmental parameters such as ambient temperature, humidity and light intensity;

[0036] Among them, the data of the liquid level sensor and the weight sensor are used for cross-verification to improve the accuracy of liquid volume measurement.

[0037] Preferably, the data preprocessing module includes:

[0038] A data cleaning unit for removing outliers and noise in the sensor data;

[0039] A data standardization unit for converting different types of sensor data into a unified numerical range;

[0040] A feature extraction unit for extracting time series features, statistical features and frequency domain features from the original sensor data;

[0041] A data fusion unit for time-aligning and comprehensively analyzing the data of multiple sensors to generate a multi-dimensional feature vector.

[0042] Preferably, the AI analysis module adopts a multi-layer convolutional neural network structure, including:

[0043] An input layer for receiving the preprocessed multi-dimensional feature vectors;

[0044] Multiple convolutional layers and pooling layers for automatically extracting high-level features of liquid types and eating behaviors;

[0045] A fully connected layer for comprehensively analyzing the extracted features and outputting liquid type recognition results and eating behavior classifications;

[0046] A regression output layer for predicting real-time food intake and blood glucose curves based on the recognized liquid types and eating behaviors, combined with the user's personal information.

[0047] Preferably, the intelligent intervention module includes:

[0048] A threshold judgment unit for comparing the food intake data and blood glucose prediction data with preset health thresholds;

[0049] A personalized parameter adjustment unit for dynamically adjusting the health thresholds according to the user's age, gender, weight, and health status;

[0050] An intervention strategy generation unit for formulating graded intervention strategies according to the degree and duration of exceeding the thresholds;

[0051] A learning optimization unit for recording the user's responses to different intervention strategies and continuously optimizing the intervention effects through reinforcement learning algorithms.

[0052] Preferably, the feedback execution module includes:

[0053] A sound reminder unit for emitting gentle sound prompts in case of mild overconsumption;

[0054] A vibration warning unit for generating obvious vibration warnings in case of moderate overconsumption;

[0055] A heating intervention unit for preventing continued drinking by heating the liquid when there is severe overconsumption and the user does not respond to the first two levels of reminders;

[0056] An LED display unit for intuitively displaying the current food intake status and health suggestions;

[0057] Among them, the heating intervention unit also has a heat preservation function and can automatically adjust the optimal heat preservation temperature according to the liquid type.

[0058] Preferably, the data storage and communication module includes:

[0059] A local storage unit for temporarily storing the collected data in an offline state;

[0060] A data encryption unit for encrypting the user's sensitive health data;

[0061] A wireless communication unit that supports multiple communication methods such as Wi-Fi, Bluetooth, and 4G / 5G, and is used to achieve real-time data upload;

[0062] A data synchronization unit that is used to ensure the consistency of local data and cloud data, and automatically synchronize offline data after the network is restored.

[0063] Preferably, it further includes:

[0064] A power management module that is used to:

[0065] Monitor the energy consumption status of each module of the system;

[0066] Automatically adjust the power consumption mode according to the usage scenario;

[0067] Support wireless charging and fast charging technologies;

[0068] Among them, the power management module further includes an energy recovery unit that can convert the kinetic energy generated by the user's drinking behavior into electrical energy to extend the usage time of the system.

[0069] Preferably, it further includes:

[0070] A self-cleaning module that is used to:

[0071] Detect the degree of stains on the inner wall of the cup;

[0072] When it detects that the stains exceed the preset threshold, start the automatic cleaning program;

[0073] Utilize ultrasonic technology and special coating materials to achieve deep cleaning of the cup;

[0074] Among them, the self-cleaning module is data-connected to the AI analysis module and can automatically adjust the cleaning intensity and method according to the recognized liquid type.

[0075] An intelligent energy cup food intake monitoring method based on the system includes the following steps:

[0076] S1. Through the multi-sensor data acquisition module, collect the liquid level information, weight information of the liquid in the cup, as well as the RFID identification information of the cup, the geographical location information of the user, and the environmental data;

[0077] S2. Use the data preprocessing module to perform noise reduction, normalization, and feature extraction processing on the collected sensor data;

[0078] S3. In the AI analysis module, based on the preprocessed sensor data, use deep learning algorithms to identify the liquid type and eating behavior, and calculate the user's real-time food intake;

[0079] S4. Predict the user's blood glucose curve in the AI analysis module based on the real-time food intake and the user's historical data;

[0080] S5. In the intelligent intervention module, receive the food intake data and blood glucose prediction data sent by the AI analysis module, and compare them with the preset health thresholds;

[0081] S6. When the comparison result shows that the health threshold is exceeded, the intelligent intervention module generates corresponding intervention instructions;

[0082] S7. The feedback execution module selectively performs voice reminders, vibration warnings, or heating intervention operations according to the intervention instructions;

[0083] S8. Through the data storage and communication module, store the user's food intake data, health indicators, and intervention records locally and upload them to the remote server;

[0084] S9. Regularly analyze the user's long-term food intake data to generate personalized health reports and improvement suggestions;

[0085] S10. Based on the user's feedback and the long-term data analysis results, continuously optimize the system's recognition algorithm, prediction model, and intervention strategy.

[0086] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0087] First of all, the present invention adopts multi-sensor fusion technology, significantly improving the accuracy and comprehensiveness of data collection. Through the collaborative work of the liquid level sensor, weight sensor, RFID reader, GPS module, and environmental sensor, the system can not only accurately measure the liquid volume but also identify the liquid type, monitor the user's location, and environmental factors. This multi-dimensional data collection lays a solid foundation for subsequent intelligent analysis, enabling the system to comprehensively understand the user's drinking behavior and environmental background.

[0088] Secondly, the present invention utilizes advanced AI analysis technology to achieve a deep understanding and prediction of the user's drinking behavior. By adopting a multi-layer convolutional neural network structure, the system can automatically extract the high-level features of the liquid type and eating behavior, accurately identifying different drinking patterns. This intelligent analysis not only improves the monitoring accuracy but also can predict the user's blood glucose curve, providing a valuable health management tool for patients with chronic diseases such as diabetes.

[0089] Furthermore, the intelligent intervention module of the present invention dynamically adjusts the health threshold based on personalized parameters and adopts a hierarchical intervention strategy. This method takes into account the individual differences of users and can provide more accurate and effective health suggestions. By continuously adjusting the intervention strategy through the learning and optimization unit, the system can gradually adapt to the user's preferences and habits, improving the acceptance and effectiveness of the intervention.

[0090] In addition, the feedback execution module of the present invention adopts a multi-modal interaction method, including voice reminder, vibration warning, heating intervention, LED display, etc. This diverse feedback method can adapt to different usage scenarios, enhance the user experience, and improve the persistence and effectiveness of health management.

[0091] In terms of data security, the present invention effectively protects the user's privacy information through advanced encryption algorithms and data synchronization mechanisms. At the same time, the innovative power management technology and self-cleaning function greatly improve the practicality and user-friendliness of the product.

[0092] In summary, the intelligent energy cup food intake monitoring system and method of the present invention have achieved significant breakthroughs in multiple aspects such as data acquisition accuracy, intelligent analysis ability, personalized intervention, user interaction, and data security. These innovations not only solve many problems in the prior art but also provide users with a comprehensive, accurate, and intelligent health management tool. Through the present invention, users can better understand their eating habits, obtain personalized health advice, thereby effectively preventing overeating, controlling calorie intake, managing chronic diseases, and ultimately achieving the goal of improving the overall health status. The implementation of the present invention will bring revolutionary progress to the field of intelligent health management, with broad application prospects and significant social benefits. Brief Description of the Drawings

[0093] Figure 1 It is the logical block diagram of the overall system of the present invention.

[0094] Figure 2 It is the logical block diagram of the multi-sensor data acquisition module of the present invention.

[0095] Figure 3 It is the logical block diagram of the data preprocessing module of the present invention.

[0096] Figure 4 It is the logical block diagram of the AI analysis module of the present invention.

[0097] Figure 5 It is the logical block diagram of the intelligent intervention module of the present invention.

[0098] Figure 6 It is the logical block diagram of the feedback execution module of the present invention.

[0099] Figure 7 It is the logical block diagram of the data storage and communication module of the present invention.

[0100] Figure 8 It is the logical block diagram of the power management module of the present invention.

[0101] Figure 9This is the logic block diagram of the self-cleaning module of the present invention. Detailed implementation manners

[0102] Refer to Figures 1-9 , the present invention provides an intelligent energy cup food intake monitoring system and its method. Through multi-sensor fusion technology, artificial intelligence algorithms, and intelligent feedback mechanisms, this system realizes precise monitoring of users' eating behaviors and personalized health management. The technical solutions of the present invention will be described in detail below.

[0103] The intelligent energy cup food intake monitoring system includes a multi-sensor data acquisition module 1, a data preprocessing module 2, an AI analysis module 3, an intelligent intervention module 4, a feedback execution module 5, and a data storage and communication module 6. These modules work together to form a complete intelligent monitoring and intervention system.

[0104] The multi-sensor data acquisition module 1 is used to collect the liquid level information and weight information of the liquid in the cup body, obtain the RFID identification information of the cup body, and collect the geographical location information and environmental data of the user. Through the collaborative work of multiple sensors, this module provides comprehensive and accurate raw data for the system. Preferably, the acquisition frequency of the liquid level information can be set to 10 times per second to capture rapid drinking behaviors; while the acquisition frequency of the weight information can be set to 5 times per second to balance accuracy and power consumption.

[0105] The data preprocessing module 2 is electrically connected to the multi-sensor data acquisition module 1 and is used to receive various sensor data and perform preprocessing. The preprocessing process includes noise reduction, normalization, and feature extraction. For example, for the liquid level data, a moving average filtering algorithm can be used for noise reduction, and the filter window size can be selected as 5 sampling points, which can effectively remove short-term fluctuations while retaining the true drinking trend.

[0106] The AI analysis module 3 is data-connected to the data preprocessing module 2 and is the core part of the system. This module uses deep learning algorithms to identify the liquid type and eating behaviors, calculate the real-time food intake, and predict the user's blood glucose curve. The present invention adopts an improved convolutional neural network model, and its structure can be expressed as:

[0107] f(x) = softmax(W 2 ·ReLU(W 1 ·Conv(x) + b 1 ) + b 2 ),

[0108] where x is the input multi-dimensional sensor data, Conv represents the convolution operation, W 1 and W 2 are weight matrices, b 1 and b 2is the bias vector, ReLU is the activation function, and softmax is used to output classification probabilities. The intelligent intervention module 4 is signal-connected to the Al analysis module 3 and is responsible for determining whether intervention is needed based on the analysis results. The present invention adopts an adaptive threshold algorithm, which can dynamically adjust the intervention threshold according to the user's personal characteristics. The threshold adjustment formula is as follows:

[0109] T = T 0 + k 1 ·BMI + k 2 ·Age + k 3 ·ActivityLevel,

[0110] where T is the adjusted threshold, T 0 is the reference threshold (for example, for water intake, it can be set to 500 ml per hour), BMI is the body mass index, Age is the age, Activity Level is the activity level, and k 1 , k 2 , k 3 are adjustment coefficients. The empirical values can be set as: k 1 = 10, k 2 = -0.5, k 3 = 50.

[0111] The feedback execution module 5 is control-connected to the intelligent intervention module 4 and is used to execute specific intervention operations. The present invention designs a set of progressive intervention strategies, including voice reminders, vibration warnings, and heating interventions. For example, when a mild overage (within 10% of the threshold) is detected, the system will emit a soft reminder sound; when a moderate overage (exceeding 10% - 30%) occurs, a vibration warning will be triggered; when a severe overage (exceeding 30% or more) and the user does not respond to the first two levels of reminders, the system will activate the heating function to heat the liquid to about 40°C to prevent the user from continuing to drink.

[0112] The data storage and communication module 6 is responsible for local storage and cloud synchronization of data. This module uses the AES-256 encryption algorithm to protect user privacy and supports an incremental synchronization strategy, only uploading the changed data, thereby improving the synchronization efficiency and saving traffic.

[0113] The intelligent energy cup food intake monitoring system of the present invention realizes the comprehensive monitoring and intelligent intervention of the user's diet behavior through the collaborative work of the above modules. This system can not only accurately record the user's food intake but also provide personalized health advice according to personal characteristics, which is of great significance for preventing overeating, controlling calorie intake, and managing chronic diseases.

[0114] Furthermore, the multi-sensor data acquisition module 1 of the present invention includes a liquid level sensor 11, a weight sensor 12, an RFID reader 13, a GPS module 14, and an environmental sensor 15. The collaborative work of these sensors ensures the comprehensiveness and accuracy of data acquisition.

[0115] The liquid level sensor 11 uses ultrasonic ranging technology, and the measurement accuracy can reach ±1 mm. The weight sensor 12 selects a high-precision strain gauge sensor, and the accuracy can reach ±0.1 g. The RFID reader 13 supports the ISO15693 protocol, and the reading distance can reach 5 cm. The GPS module 14 adopts a low-power design, and the positioning accuracy can reach ±3 m in open areas. The environmental sensor 15 integrates temperature, humidity, and light sensors, with measurement accuracies of ±0.5 °C, ±3% RH, and ±5% respectively.

[0116] The data cross-verification mechanism of these sensors greatly improves the reliability of the system. For example, by comparing the liquid level change and the weight change, the system can accurately determine whether an actual drinking behavior has occurred, thus avoiding misjudgment caused by factors such as the tilting of the cup body.

[0117] The data preprocessing module 2 includes a data cleaning unit 21, a data standardization unit 22, a feature extraction unit 23, and a data fusion unit 24. The design of these units aims to improve the efficiency and accuracy of subsequent AI analysis.

[0118] The data cleaning unit 21 uses a median filtering algorithm to remove outliers, and the filter window size can be set to 7 sampling points. The data standardization unit 22 uses the Z-score standardization method to convert different types of data into a distribution with a mean of 0 and a standard deviation of 1. The feature extraction unit 23 not only extracts time-domain features (such as mean, variance, kurtosis, etc.), but also extracts frequency-domain features through fast Fourier transform (FFT) to capture periodic drinking patterns. The data fusion unit 24 uses the Kalman filtering algorithm to achieve the optimal fusion of multi-sensor data.

[0119] This multi-level data preprocessing scheme of the present invention can effectively improve the quality of the original data, laying a solid foundation for subsequent AI analysis. By removing noise, unifying the data scale, and extracting key features, the system can more accurately identify the user's drinking behavior and liquid type, thereby providing more accurate health advice. The AI analysis module 3 of the present invention adopts a multi-layer convolutional neural network structure, including an input layer 31, multiple convolutional layers and pooling layers 32, a fully connected layer 33, and a regression output layer 34. This deep learning architecture can automatically extract high-level features of liquid types and eating behaviors, achieving accurate identification and prediction.

[0120] The input layer 31 is responsible for receiving the preprocessed multi-dimensional feature vectors. In an embodiment of the present invention, the input vector contains 128 features, covering the time domain, frequency domain, and statistical features. These features are normalized to ensure the training stability of the network.

[0121] Multiple convolutional layers and pooling layers 32 are the core part of the network, used to automatically extract high-level features of liquid types and eating behaviors. The present invention adopts an innovative residual connection structure, which can be expressed as:

[0122] H l =F(H l-1 )+H l-1 ,

[0123] where H l represents the output of the l-th layer, and F represents the convolution operation. This structure effectively alleviates the gradient vanishing problem of deep networks and improves the performance of the model. Preferably, the present invention uses 3 convolutional blocks, each block containing 2 convolutional layers and 1 max pooling layer. The convolutional kernel size is 3x3, the initial number of channels is 32, and it doubles after each block.

[0124] The fully connected layer 33 is used to comprehensively analyze the extracted features and output the liquid type recognition result and eating behavior classification. The present invention introduces the Dropout technique in the fully connected layer, and the dropout rate is set to 0.5, effectively preventing the overfitting problem. The liquid type recognition uses a softmax classifier, which can recognize 10 common beverages such as water, tea, coffee, carbonated drinks, etc. The eating behavior classification uses a multi-label classification method, which can simultaneously recognize multiple behavior patterns such as rapid drinking, slow sipping, and intermittent drinking.

[0125] The regression output layer 34 predicts the real-time food intake and blood glucose curve based on the recognized liquid type and eating behavior, combined with the user's personal information. The present invention adopts an innovative multi-task learning framework to simultaneously optimize the two tasks of food intake prediction and blood glucose curve prediction. Its loss function can be expressed as:

[0126] L=αL intake +βL glucose +λΩ(W),

[0127] where L intake and L glucose respectively represent the losses of food intake prediction and blood glucose curve prediction, Ω(W) is the regularization term, and α, β, and λ are weight coefficients. The empirical values can be set as: α = 0.6, β = 0.3, λ = 0.1.

[0128] The intelligent intervention module 4 of the present invention includes a threshold judgment unit 41, a personalized parameter adjustment unit 42, an intervention strategy generation unit 43, and a learning optimization unit 44. These units work together to achieve an intelligent and personalized intervention mechanism.

[0129] The threshold judgment unit 41 is responsible for comparing the food intake data and blood glucose prediction data with the preset health thresholds. The present invention adopts a fuzzy logic system to divide the food intake and blood glucose levels into three levels: low, normal, and high. For example, for water intake, an intake of less than 200 ml per hour can be defined as low, 200 - 800 ml as normal, and more than 800 ml as high. This fuzzy classification method is more in line with the continuous changes of human physiological characteristics than a simple fixed threshold.

[0130] The personalized parameter adjustment unit 42 dynamically adjusts the health thresholds according to the user's age, gender, weight, and health status. The present invention proposes a threshold adjustment algorithm based on the user profile:

[0131] T adjusted =T base ·(1 + k 1 ·Age + k 2 ·BMI + k 3 ·HealthScore),

[0132] where T adjusted is the adjusted threshold, T b ase is the reference threshold, Age is the standardized age value, BMI is the standardized body mass index value, and HealthScore is the health score (a floating-point number between 0 and 1). The coefficients k 1 、k 2 、k 3 can be dynamically optimized by machine learning methods.

[0133] The intervention strategy generation unit 43 formulates a hierarchical intervention strategy according to the degree and duration of exceeding the threshold. The present invention designs a three-level intervention mechanism: mild intervention (such as gentle reminder), moderate intervention (such as strong warning), and strong intervention (such as physical prevention). The selection of the intervention level is based on the following formula:

[0134]

[0135] where I is the intervention level (1 - 3), E is the amount exceeding the threshold, T is the threshold, S is the sensitivity parameter (which can be adjusted according to user preferences), and the clip function limits the result between 1 and 3.

[0136] The learning optimization unit 44 records the user's responses to different intervention strategies and continuously optimizes the intervention effect through a reinforcement learning algorithm. The present invention uses the Q-learning algorithm, and its update formula is:

[0137]

[0138] Among them, Q(s t ,a t ) represents the value of taking action a t in state s t , r t +1 is the immediate reward, α is the learning rate, and γ is the discount factor. This adaptive learning mechanism enables the system to gradually adjust the intervention strategy to achieve the best user response effect.

[0139] The feedback execution module 5 of the present invention includes a sound reminder unit 51, a vibration warning unit 52, a heating intervention unit 53, and an LED display unit 54. These units provide multimodal feedback methods to ensure that users can receive the system's intervention information in a timely manner.

[0140] The sound reminder unit 51 emits a gentle sound prompt in case of mild overage. The present invention designs a progressive sound reminder mechanism. The initial volume is set to 1.2 times the ambient noise level. If the user does not respond within 30 seconds, the volume increases by 5 decibels every 10 seconds until the preset maximum volume (usually 2 times the ambient noise) is reached. This design can attract the user's attention without causing excessive disturbance.

[0141] The vibration warning unit 52 generates an obvious vibration warning in case of moderate overage. The vibration mode adopts an innovative rhythm design, which can be expressed as:

[0142] V(t) = A·sin(2πft)·e -λt ,

[0143] Among them, A is the amplitude, f is the frequency, and λ is the attenuation coefficient. The present invention sets f to 200 Hz, which is the frequency range where the human body is most sensitive to touch. The vibration duration is 0.5 seconds, with an interval of 1.5 seconds, forming a rhythm that is easy to recognize but not annoying.

[0144] The heating intervention unit 53 is activated in case of severe overage and when the user does not respond to the first two levels of reminders. This unit uses a PID control algorithm to precisely control the heating process:

[0145]

[0146] Among them, u(t) is the control output, e(t) is the error between the target temperature and the current temperature, K p , K i , Kd They are the proportional, integral, and derivative coefficients respectively. In the present invention, the target temperature is set to 40 °C, which is sufficient to make most beverages less palatable but not hot enough to cause burns.

[0147] The LED display unit 54 is used to visually display the current food intake status and health advice. The present invention adopts a color-coding system: green indicates normal, yellow indicates approaching the threshold, and red indicates exceeding the threshold. The brightness of the color is proportional to the degree of exceeding, which can be expressed by the following formula:

[0148]

[0149] where B is the brightness, B 0 is the base brightness, B max is the maximum brightness, E is the amount exceeding the threshold, and T is the threshold.

[0150] This multi-modal feedback system of the present invention can adapt to different usage scenarios and user preferences, effectively improving the success rate of intervention. For example, in a quiet office environment, the system will preferentially select vibration and LED display modes; while in a noisy outdoor environment, it will increase the frequency and intensity of sound reminders.

[0151] Through the above detailed description, the intelligent energy cup food intake monitoring system of the present invention demonstrates its innovation in aspects such as multi-sensor fusion, deep learning analysis, personalized intervention strategies, and human-computer interaction. The organic combination of these technologies not only realizes the accurate monitoring of users' dietary behaviors but also provides timely and effective health interventions, offering a new solution for users' health management. The data storage and communication module 6 of the present invention includes a local storage unit 61, a data encryption unit 62, a wireless communication unit 63, and a data synchronization unit 64. The coordinated work of these units ensures the security, integrity, and accessibility of user data.

[0152] The local storage unit 61 adopts an innovative hierarchical storage structure. In this structure, short-term data with high-frequency access (such as daily dietary records) is stored in fast-access flash memory, while long-term statistical data is stored in EEPROM with lower energy consumption. This design not only ensures the data read and write speed but also optimizes energy consumption. Preferably, the present invention adopts an adaptive data compression algorithm, which can dynamically adjust the compression ratio according to the usage of the storage space. The compression ratio R can be expressed as:

[0153]

[0154] where R min and R max are the minimum and maximum compression ratios respectively, S used is the used storage space, S totalis the total storage space. This method can maximize storage efficiency while ensuring data integrity. The data encryption unit 62 is responsible for encrypting the user's sensitive health data. The present invention adopts a lightweight encryption scheme based on elliptic curve cryptography, and its encryption process can be expressed as:

[0155] C = E k (M) = {kG, M + kH(P)},

[0156] where C is the ciphertext, M is the plaintext, k is a randomly selected private key, G is the base point on the elliptic curve, P is the user's public key, and H is the hash function. This encryption scheme has a low computational complexity while ensuring security and is suitable for use in resource-constrained embedded devices.

[0157] The wireless communication unit 63 supports multiple communication methods such as Wi-Fi, Bluetooth, and 4G / 5G for real-time data upload. The present invention designs an intelligent communication mode switching algorithm that can automatically select the optimal communication method according to signal strength, data volume, and battery status. The decision function of this algorithm can be expressed as:

[0158]

[0159] where S is the selected communication method, W, B, and G represent Wi-Fi, Bluetooth, and 4G / 5G respectively, Q i is the signal quality, E i is the energy consumption per unit data transmission, T i is the estimated transmission time, w 1 、w 2 、w 3 are the weight coefficients. This adaptive communication strategy can maximize battery life while ensuring data transmission efficiency.

[0160] The data synchronization unit 64 is responsible for ensuring the consistency between local data and cloud data and automatically synchronizing offline data after the network is restored. The present invention adopts a data synchronization algorithm based on version vectors, which can effectively solve the data consistency problem in distributed systems. Each data record is attached with a version vector V, and its update rule is:

[0161] V i [i] = V i [i] + 1,

[0162]

[0163] where V i represents the version vector of device i, V i[j] represents the latest version number of device j known to device i. By comparing the version vectors, the system can efficiently identify the data that needs to be synchronized, reducing unnecessary data transmission.

[0164] The intelligent energy cup food intake monitoring system of the present invention further includes a power management module 7, which is used to monitor the energy consumption status of each module of the system, automatically adjust the power consumption mode according to the usage scenario, and support wireless charging and fast charging technologies.

[0165] The power management module 7 adopts an innovative dynamic power consumption adjustment algorithm. This algorithm dynamically adjusts the working frequency and voltage of each functional module according to the user's usage pattern and remaining battery power. Its core idea can be expressed by the following formula:

[0166] P = α·f 3 +β·V 2 ·f,

[0167] where P is the power consumption, f is the working frequency, V is the working voltage, and α and β are constants related to the hardware. By optimizing f and V, the system can minimize the energy consumption while ensuring performance. For example, when the user has not used the cup for a long time, the system will automatically enter the low-power mode, reduce the frequency of the main processor to the minimum value, and turn off the unnecessary sensors. The power management module 7 of the present invention also includes an energy recovery unit 71, which can convert the kinetic energy generated by the user's drinking behavior into electrical energy, extending the usage time of the system. The energy recovery unit 71 uses piezoelectric materials and can convert the vibration of the cup body into electrical energy. Its output power P out can be expressed as 20

[0168]

[0169] where k is the electromechanical coupling coefficient, Q m is the mechanical quality factor, P in is the input mechanical power. By optimizing the geometric structure of the piezoelectric material and the circuit parameters, the present invention achieves an energy conversion efficiency of up to 30%, significantly extending the usage time of the system.

[0170] In addition, the present invention also includes a self-cleaning module 8, which is used to detect the degree of stains on the inner wall of the cup, start the automatic cleaning program when the stains exceed the preset threshold, and use ultrasonic technology and special coating materials to achieve deep cleaning of the cup body.

[0171] The self-cleaning module 8 adopts an innovative stain detection algorithm. This algorithm judges the degree of stains by analyzing the light reflection characteristics of the inner wall of the cup. Specifically, the system will emit light of a specific wavelength and measure the intensity and spectral distribution of the reflected light. The degree of stains D can be calculated by the following formula:

[0172]

[0173] Among them, R(λ) is the reflection spectrum of the inner wall of the current cup, and R 0 (λ) is the standard reflection spectrum of the clean cup, λ 1 and λ 2 is the selected wavelength range. When D exceeds a preset threshold (e.g., 0.2), the system will start the automatic cleaning program.

[0174] During the self-cleaning process, the present invention adopts an innovative ultrasonic cleaning technology. This technology uses variable-frequency ultrasonic waves, which can generate a complex sound field distribution and effectively remove different types of stains. The change of the ultrasonic frequency f with time can be expressed as:

[0175] f(t) = f 0 +A·sin(2πωt),

[0176] Among them, f 0 is the center frequency (usually 40kHz), A is the frequency modulation amplitude, and ω is the modulation frequency. This variable-frequency technology can effectively avoid the standing wave of the sound field and ensure that each part of the inner wall of the cup can be evenly cleaned.

[0177] The intelligent energy cup food intake monitoring method of the present invention includes the following steps:

[0178] S1. Through the multi-sensor data acquisition module 1, collect the liquid level information, weight information of the liquid in the cup, as well as the RFID identification information of the cup, the geographical location information of the user, and the environmental data. Preferably, the acquisition frequency of the liquid level information and the weight information can be set to 10 times per second to capture rapid drinking behaviors.

[0179] S2. Use the data preprocessing module 2 to perform noise reduction, normalization, and feature extraction on the collected sensor data. The present invention uses wavelet transform for noise reduction, and its denoising function can be expressed as:

[0180]

[0181] Among them, is the denoised signal, d j ,k is the wavelet coefficient, λ is the threshold, ψ j ,k(t) is the wavelet basis function.

[0182] S3. In the AI analysis module 3, based on the preprocessed sensor data, use deep learning algorithms to identify the liquid type and eating behavior, and calculate the user's real-time food intake. The present invention adopts an innovative attention mechanism, which can automatically focus on the most relevant features. The calculation formula of the attention weight α is:

[0183] e i= v T tanh(Wh i + b),

[0184] where h i is the hidden state, and W, v, and b are learnable parameters.

[0185] S4. Based on the real-time food intake and the user's historical data, predict the user's blood glucose curve in the AI analysis module 3. The present invention adopts a blood glucose prediction model based on a recurrent neural network (RNN), and its core formula is:

[0186] h t = tanh(W xh x t + W hh h t-1 + b h ),

[0187] y t = W hy h t + b y ,

[0188] where h t is the hidden state, x t is the input feature, y t is the predicted blood glucose value, and W and b are model parameters.

[0189] S5 - S7. In the intelligent intervention module 4, receive the food intake data and blood glucose prediction data sent by the AI analysis module 3, and compare them with the preset health thresholds. When the comparison result shows that the health thresholds are exceeded, generate corresponding intervention instructions. The feedback execution module 5 selectively executes voice reminders, vibration warnings, or heating intervention operations according to the intervention instructions.

[0190] S8 - S10. Through the data storage and communication module 6, store the user's food intake data, health indicators, and intervention records locally and upload them to a remote server. Regularly analyze the user's long-term food intake data to generate personalized health reports and improvement suggestions. Based on the user's feedback and the long-term data analysis results, continuously optimize the system's recognition algorithm, prediction model, and intervention strategy.

[0191] The intelligent energy cup food intake monitoring system and method of the present invention realize the precise monitoring and intelligent intervention of the user's eating behavior through innovative technologies such as multi-sensor fusion, deep learning analysis, and personalized intervention strategies. This system can not only accurately record and analyze the user's eating situation, but also provide customized health suggestions according to personal characteristics, and has important practical application value in preventing overeating, controlling calorie intake, and managing chronic diseases.

[0192] It should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. Intelligent energy cup food intake monitoring system, characterized in that: include: Multi-sensor data acquisition module for: Collect the liquid level information and weight information of the liquid in the cup; Obtain RFID identification information of the cup body; Collect user's geographic location information and environmental data; The data preprocessing module is electrically connected to the multi-sensor data acquisition module and is used to: Receiving various sensor data sent by the multi-sensor data acquisition module; Performing noise reduction, standardization and feature extraction processing on the sensor data; The AI ​​analysis module is data-connected to the data preprocessing module and is used to: Based on the preprocessed sensor data, using a deep learning algorithm to identify liquid type and eating behavior; Calculate the user's real-time food intake based on the liquid type and eating behavior in combination with preset health standards; Predicting the user's blood sugar curve based on the real-time food intake and the user's historical data; The intelligent intervention module is connected to the AI ​​analysis module signal and is used to: Receiving food intake data and blood sugar prediction data sent by the AI ​​analysis module; Determine whether the food intake data and blood sugar prediction data exceed a preset health threshold; When the judgment result exceeds the health threshold, generating corresponding intervention instructions; The feedback execution module is connected to the intelligent intervention module for: receiving an intervention instruction sent by the intelligent intervention module; According to the intervention instruction, selectively performing a sound reminder, a vibration warning or a heating intervention operation; The data storage and communication module is respectively connected to the multi-sensor data acquisition module, the AI ​​analysis module and the intelligent intervention module for: Store users’ historical eating data, health indicators and intervention records; The data is uploaded to a remote server via a wireless network to achieve cloud backup and analysis of the data.

2. The smart energy cup food intake monitoring system according to claim 1, characterized in that: The multi-sensor data acquisition module comprises: Liquid level sensor, used to detect the height change of liquid in the cup in real time; Weight sensor, used to accurately measure the weight of the liquid in the cup; An RFID reader is used to identify the unique identification of the cup body and obtain the cup body capacity information associated with the identification; GPS module, used to obtain the user's real-time geographic location information; Environmental sensors are used to collect ambient parameters such as temperature, humidity, and light intensity; The data of the liquid level sensor and the weight sensor are used for cross-validation to improve the accuracy of liquid quantity measurement.

3. The smart energy cup food intake monitoring system according to claim 1, characterized in that: The data preprocessing module comprises: A data cleaning unit, used to remove outliers and noise from sensor data; A data normalization unit, which is used to convert different types of sensor data into a uniform numerical range; A feature extraction unit, used to extract time series features, statistical features and frequency domain features from the raw sensor data; The data fusion unit is used to time align and comprehensively analyze the data of multiple sensors to generate a multi-dimensional feature vector.

4. The smart energy cup food intake monitoring system according to claim 1, characterized in that: The AI ​​analysis module adopts a multi-layer convolutional neural network structure, including: An input layer, used for receiving the preprocessed multi-dimensional feature vector; Multiple convolutional and pooling layers to automatically extract high-level features of liquid type and eating behavior; The fully connected layer is used to comprehensively analyze the extracted features and output the liquid type recognition results and eating behavior classification; The regression output layer is used to predict the real-time food intake and blood glucose curve based on the identified liquid type and eating behavior combined with the user's personal information.

5. The smart energy cup food intake monitoring system according to claim 1, characterized in that: The intelligent intervention module comprises: A threshold judgment unit, used to compare the food intake data and blood sugar prediction data with a preset health threshold; A personalized parameter adjustment unit, used to dynamically adjust the health threshold according to the user's age, gender, weight and health condition; An intervention strategy generation unit, used to formulate a graded intervention strategy according to the degree and duration of exceeding the threshold; The learning optimization unit is used to record the user's response to different intervention strategies and continuously optimize the intervention effect through reinforcement learning algorithms.

6. The smart energy cup food intake monitoring system according to claim 1, characterized in that: The feedback execution module comprises: An audio reminder unit, which is used to issue a gentle audio reminder in case of a slight overdose; A vibration warning unit is used to generate a noticeable vibration warning in case of moderate overage; A heating intervention unit, which is used to prevent further drinking by heating the liquid when there is a serious overdose and the user does not respond to the first two levels of reminders; LED display unit, used to intuitively display the current food intake status and health advice; The heating intervention unit also has a heat preservation function and can automatically adjust the optimal heat preservation temperature according to the type of liquid.

7. The smart energy cup food intake monitoring system according to claim 1, characterized in that: The data storage and communication module includes: A local storage unit, used to temporarily store the collected data in an offline state; A data encryption unit, used to encrypt the user's sensitive health data; Wireless communication unit, supporting Wi-Fi, Bluetooth and 4G / 5G communication modes, used to achieve real-time data upload; The data synchronization unit is used to ensure the consistency of local data and cloud data, and automatically synchronize offline data after the network is restored.

8. The smart energy cup food intake monitoring system according to claim 1, characterized in that: Also includes: Power management module for: Monitor the energy consumption of each module in the system; Automatically adjust power consumption mode according to usage scenarios; Support wireless charging and fast charging technology; The power management module also includes an energy recovery unit, which can convert the kinetic energy generated by the user's drinking behavior into electrical energy, thereby extending the use time of the system.

9. The smart energy cup food intake monitoring system according to claim 1, characterized in that: Also includes: Self-cleaning modules for: Detect the degree of stains on the inner wall of the cup; When the dirt exceeds the preset threshold, the automatic cleaning program is started; Use ultrasonic technology and special coating materials to achieve deep cleaning of the cup body; Among them, the self-cleaning module is data-connected with the AI ​​analysis module, and can automatically adjust the cleaning intensity and method according to the identified liquid type.

10. A method for monitoring food intake of a smart energy cup based on the system according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Collect the liquid level information and weight information of the liquid in the cup body, as well as the RFID identification information of the cup body, the user's geographical location information and environmental data through the multi-sensor data acquisition module; S2. Using a data preprocessing module, the collected sensor data is subjected to noise reduction, standardization and feature extraction processing; S3. In the AI ​​analysis module, based on the preprocessed sensor data, a deep learning algorithm is used to identify the liquid type and eating behavior, and calculate the user's real-time food intake; S4. Predicting the user's blood sugar curve in the AI ​​analysis module based on the real-time food intake and the user's historical data; S5. In the intelligent intervention module, the food intake data and blood sugar prediction data sent by the AI ​​analysis module are received and compared with the preset health threshold; S6. When the comparison result shows that the health threshold is exceeded, the intelligent intervention module generates a corresponding intervention instruction; S7. The feedback execution module selectively executes a sound reminder, a vibration warning or a heating intervention operation according to the intervention instruction; S8. The user's eating data, health indicators and intervention records are stored locally and uploaded to a remote server through the data storage and communication module; S9. Regularly analyze users’ long-term eating data to generate personalized health reports and improvement suggestions; S10. Based on user feedback and long-term data analysis results, the system's recognition algorithms, prediction models, and intervention strategies are continuously optimized.

Images