Water dispenser energy saving and water drinking reminding method and system based on AI

Abstract

The invention provides an AI-based water dispenser energy-saving and water drinking reminding method and system, and the method comprises the steps: collecting water drinking related data which comprise equipment operation parameters, environment parameters and user health data; generating a personalized energy-saving program rule and a personalized water drinking reminding rule based on the water drinking related data; executing energy-saving operation according to the energy-saving program rule, wherein the energy-saving operation comprises closing or starting a heating and refrigerating function; pushing water drinking reminding according to the water drinking reminding rule; and collecting user feedback data, and optimizing the rule generation process based on the feedback data. Energy is saved through data driving, the equipment running state is dynamically adjusted according to the environment electricity price and user habits, and energy consumption is remarkably reduced; and accurate reminding is pushed in combination with the health data and the position information, so that the standard reaching rate of the daily average water intake of the user is remarkably improved. The model is continuously improved through user feedback, the user satisfaction is stabilized at a high level after operation for a period of time, and long-term balance between energy conservation and user experience is formed.

Description

Technical Field

[0001] This application relates to the field of smart home appliance technology, and in particular to an AI-based method and system for energy saving and drinking reminders for water dispensers. Background Technology

[0002] Water dispensers, as frequently used devices powered 24 hours a day, consume approximately 40% of their total annual electricity in standby mode, with energy waste being particularly significant during non-drinking periods such as nighttime due to continuous heating / cooling. Current energy-saving technologies for water dispensers face three main challenges: first, significant differences in user habits mean that fixed temperature control modes cannot meet individual needs; second, a lack of intelligent predictive capabilities leads to repeated heating / cooling and ineffective energy consumption; and third, balancing energy saving with user experience is difficult, with low compliance to manual adjustments.

[0003] Against this backdrop, the industry has introduced the "timed energy saving" function, which allows users to actively configure energy-saving periods and start the energy-saving mode on their mobile phones / devices. However, this one-size-fits-all energy-saving mode obviously does not automatically match more reasonable energy-saving operation based on the actual water needs of users' households, such as changes in ambient temperature and humidity, users' physical conditions, and differences in drinking water needs on weekdays or holidays. It sacrifices user experience and requires users to make complicated settings.

[0004] In addition, traditional drinking water reminders usually set a fixed daily water intake target, ignoring the differences in the user's environment, weekdays or holidays, and the total amount of water consumed at home each day. Summary of the Invention

[0005] To address the issue that existing water dispenser energy-saving modes do not automatically match more reasonable energy-saving operation based on the actual water demand of users' households, and still require cumbersome settings by users.

[0006] The first aspect of this application provides an AI-based method for energy saving and drinking reminders in water dispensers, including the following steps:

[0007] Collect drinking water-related data, including equipment operating parameters, environmental parameters, and user health data;

[0008] Personalized energy-saving program rules and personalized drinking water reminder rules are generated based on the drinking water-related data.

[0009] Energy-saving operations are performed according to the energy-saving procedure rules, including turning off or starting the heating and cooling functions;

[0010] Drinking reminders will be sent according to the aforementioned drinking reminder rules;

[0011] Collect user feedback data and optimize the rule generation process based on the feedback data.

[0012] In one feasible implementation, the equipment operating parameters include water intake time, water intake volume, water intake temperature, and equipment on / off status; the environmental parameters include real-time temperature, humidity, and time-of-use electricity price data.

[0013] In one feasible implementation, the personalized energy-saving program rules include:

[0014] Predict future water demand and dynamically adjust preheating periods or precooling temperatures.

[0015] In one feasible implementation, the personalized hydration reminder rules include:

[0016] Analyze the progress of daily water intake and generate tiered reminders based on user habits.

[0017] In one feasible implementation, the process of generating optimization rules based on the feedback data includes:

[0018] When the water intake interval exceeds the set threshold, a correction mechanism is triggered, and the feature weights are adjusted in conjunction with user rating data.

[0019] This application also provides an AI-based water dispenser energy-saving and drinking reminder system, which is used to implement the AI-based water dispenser energy-saving and drinking reminder method described in any of the above claims, and includes: a data acquisition module, a cloud AI decision-making module, a rule execution module, and a feedback optimization module;

[0020] The data acquisition module connects the water dispenser terminal to the environmental sensor and is used to collect equipment operation data and environmental parameters;

[0021] The input end of the cloud-based AI decision-making module is connected to the output end of the data acquisition module, and is used to generate energy-saving program rules and drinking water reminder rules;

[0022] The input end of the rule execution module is connected to the output end of the cloud AI decision module, and the output end of the rule execution module is connected to the water dispenser controller and the user terminal respectively, for performing energy-saving operations and pushing drinking reminders;

[0023] The input end of the feedback optimization module is connected to the user terminal, and the output end of the feedback optimization module is connected to the cloud AI decision module, which is used to optimize the model parameters based on user feedback data.

[0024] In one feasible implementation, the data acquisition module includes: an Internet of Things communication unit, an environmental sensing unit, and a health data interface unit;

[0025] The IoT communication unit supports at least one of the following communication protocols: Wi-Fi, NB-IoT, and Zigbee.

[0026] The environmental sensing unit is used to acquire temperature, humidity, and electricity price data of the location area;

[0027] The health data interface unit is used to access the user's fitness and health data from their wristband or watch.

[0028] In one feasible implementation, the cloud-based AI decision-making module includes: a habit analysis unit, a demand prediction unit, and a rule generation unit;

[0029] The habit analysis unit is used to learn the distribution of users' drinking time and water temperature preferences;

[0030] The demand forecasting unit is used to forecast water demand for the next 24 hours based on historical data;

[0031] The rule generation unit is used to dynamically generate energy-saving program rules and drinking water reminder rules by integrating environmental parameters and health data.

[0032] In one feasible implementation, the rule execution module includes: an energy-saving control unit and an reminder push unit;

[0033] The energy-saving control unit is used to turn off the heating and cooling functions of the hot tank / ice water box during non-water usage periods, and to start preheating or precooling before the predicted water usage period.

[0034] The reminder push unit is used to push tiered reminders to the user terminal based on the progress of achieving the drinking water target.

[0035] In one feasible implementation, the feedback optimization module includes: an evaluation analysis unit and a model tuning unit;

[0036] The evaluation and analysis unit is used to analyze user ratings for energy-saving effects and drinking water reminders;

[0037] The model tuning unit is used to automatically correct the rule generation strategy when the user's water intake interval exceeds the threshold, and to adjust the model feature weights in combination with the scoring data.

[0038] The AI-based energy-saving and hydration reminder method and system for water dispensers provided in this application achieves dual optimization goals of energy saving and health through a data-driven approach. On one hand, by collecting equipment operating parameters, environmental parameters, and user health data, the system can generate personalized energy-saving program rules and hydration reminder rules, effectively reducing unnecessary idling energy consumption and achieving power savings. On the other hand, the system can dynamically adjust the frequency and content of reminders based on users' drinking habits and health data, improving user response rates and promoting hydration compliance, thus ensuring user health. Furthermore, through a closed-loop optimization mechanism, the system can continuously adapt to changes in user lifestyles, improving the model's predictive accuracy and providing users with a more intelligent and personalized service experience. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the implementation of the invention and, together with the description, serve to explain the principles of the embodiments of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0040] Figure 1 This is a schematic flowchart illustrating an AI-based water dispenser energy-saving and drinking reminder method according to an exemplary embodiment of this application;

[0041] Figure 2 This is an exemplary embodiment of the present application illustrating the architecture of an AI-based water dispenser energy-saving and drinking reminder system. Detailed Implementation

[0042] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the embodiments of the invention will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of how embodiments of the invention are carried out.

[0043] Water dispensers require 24-hour power and are used frequently. Statistics show that their standby power consumption accounts for approximately 40% of their total annual power consumption, with significant energy waste occurring at night and during non-drinking periods. Currently, energy-saving technology for water dispensers faces three major challenges: first, users have diverse usage habits, and fixed temperature control modes cannot meet individual needs; second, there is a lack of intelligent predictive capabilities, resulting in repeated heating or cooling leading to ineffective energy consumption; and third, balancing energy saving with user experience is difficult, with low compliance to manual adjustments. To address this, the industry has introduced a "timed energy-saving" function, allowing users to actively configure energy-saving periods and activate energy-saving modes. However, this mode does not automatically match a reasonable energy-saving operating mode based on the user's actual household water demand, sacrificing user experience and requiring cumbersome settings.

[0044] To solve the above problems, refer to Figure 1 As shown, this application provides an AI-based method for energy saving and drinking reminders in water dispensers, including the following steps:

[0045] S100: Collects drinking water-related data, including equipment operating parameters, environmental parameters, and user health data.

[0046] In practice, the water dispenser's built-in IoT module collects real-time data on operating parameters such as water dispensing time, water volume, and set water temperature. Simultaneously, it acquires temperature and humidity data from environmental sensors and time-of-use electricity pricing information from the power company. Furthermore, with user authorization, it connects to a smart bracelet via Bluetooth or Wi-Fi to obtain daily step counts, heart rate, and other health data. This step provides the system with multi-dimensional data sources, ensuring a comprehensive foundation for subsequent analysis.

[0047] S200: Generates personalized energy-saving program rules and personalized drinking water reminder rules based on drinking water-related data.

[0048] The cloud-based AI decision-making module uses machine learning algorithms to build user profiles, identifies peak drinking times through time series analysis, predicts daily water needs based on ambient temperature and humidity, and adjusts daily drinking targets according to metabolic indicators from health data. Energy-saving rules prioritize time-of-use electricity pricing data, initiating preheating / precooling programs during low-price periods. Drinking reminder rules dynamically adjust reminder frequency based on the gap between the user's current drinking progress and the target value. This process transforms data into strategy, solving the energy waste problem caused by fixed programs in traditional water dispensers.

[0049] S300: Performs energy-saving operations according to energy-saving program rules, including turning off or starting heating and cooling functions.

[0050] By managing the power supply to the water dispenser's heating element and compressor, it automatically switches to standby mode during unpredictable water usage periods. When it detects that the user's usual water usage time is approaching, it initiates a preheating program in advance. This effectively reduces unnecessary idling energy consumption, thus achieving energy savings.

[0051] S400: Pushes drinking reminders based on drinking reminder rules.

[0052] Based on the gap between the user's drinking progress and the target value, reminders are sent through various means, including app notifications, flashing water dispenser displays, and smartwatch vibrations, with personalized elements incorporated into the reminders. This multimodal interaction helps improve user response rates to reminders, thereby encouraging users to meet their drinking goals.

[0053] S500: Collects user feedback data and optimizes the rule generation process based on the feedback data.

[0054] Users can rate each alert via the water dispenser's touchscreen. The system also records the deviation between the actual water dispensing volume and the predicted value. When consecutive abnormal water dispensing intervals occur, the model optimization process is automatically triggered, adjusting the feature weight parameters. This closed-loop optimization mechanism allows the system to better adapt to changes in users' lifestyles and continuously improve the model's prediction accuracy.

[0055] The AI-based energy-saving and drinking reminder method for water dispensers provided in this application operates as follows: First, the system collects real-time operating parameters of the equipment, including water dispensing time, water volume, and water temperature setpoint, while simultaneously acquiring temperature and humidity data transmitted from environmental sensors. Based on this data, the system learns and constructs a user profile, generating personalized energy-saving program rules and drinking reminder rules. Preheating or precooling programs are initiated according to the energy-saving rules; the drinking reminder rules dynamically adjust the reminder frequency based on the difference between the user's current drinking progress and the target value. Subsequently, the system executes energy-saving operations according to the energy-saving program rules, such as turning off or starting the heating and cooling functions to reduce unnecessary energy consumption. Simultaneously, according to the drinking reminder rules, the system pushes drinking reminders to the user through various means, including APP notifications, water dispenser display flashing, and smartwatch vibration. Finally, the system collects user feedback data and adjusts the feature weight parameters to optimize the rule generation process, forming a closed-loop optimization mechanism.

[0056] The AI-based energy-saving and hydration reminder method for water dispensers provided in this application achieves dual optimization goals of energy conservation and health through a data-driven approach. On one hand, by collecting equipment operating parameters, environmental parameters, and user health data, the system can generate personalized energy-saving program rules and hydration reminder rules, effectively reducing unnecessary idling energy consumption and achieving power savings. On the other hand, the system can dynamically adjust the frequency and content of reminders based on users' drinking habits and health data, improving user response rates and promoting hydration compliance to ensure user health. Furthermore, through a closed-loop optimization mechanism, the system can continuously adapt to changes in user lifestyles, improving the model's prediction accuracy and providing users with a more intelligent and personalized service experience. In summary, this method not only solves the energy waste problem caused by fixed programs in traditional water dispensers but also overcomes the shortcomings of generic reminder schemes that ignore individual differences, constructing a dynamically balanced intelligent adjustment system.

[0057] In some embodiments of this application, the equipment operating parameters include water intake time, water intake volume, water intake temperature, and equipment on / off status; environmental parameters include real-time temperature, humidity, and time-of-use electricity price data.

[0058] In practice, a flow sensor can be installed at the water dispenser's outlet to record the time and flow rate of water dispensing, a water temperature sensor can monitor the water temperature in real time, and the switch status can be obtained through the relay contact status. The environmental sensing unit will periodically upload temperature and humidity data, while time-of-use electricity price data will be obtained from the power company's system via an API interface.

[0059] These parameters provide the system with multi-dimensional decision-making support. For example, the distribution of water collection time helps identify users' daily routines; water collection volume data can be used to train a drinking water demand prediction model; ambient temperature and humidity affect the calculation of the total daily water consumption; and time-of-use electricity pricing can guide the development of energy-saving programs. Compared to traditional water dispensers that only record on / off status, this solution greatly enriches the parameter dimensions and significantly improves the completeness of the input features for the AI ​​model.

[0060] In some embodiments of this application, in step S200, the personalized energy-saving program rules include:

[0061] S210: Predict future water demand and dynamically adjust the preheating period or precooling temperature.

[0062] Specifically, historical water intake and environmental data can be combined to predict water demand for the next 24 hours. Based on the prediction results, the energy-saving control unit initiates the preheating program during periods of low electricity prices to maintain the water temperature within a suitable range. Compared to fixed-time preheating, this dynamic adjustment method can shorten the heat tank's heat preservation time, reduce the number of compressor start-stop cycles, and reduce standby energy consumption while ensuring a good water experience, thus solving the energy waste problem caused by fixed preheating periods in traditional water dispensers.

[0063] For example, by analyzing users' typical hot water usage habits around 8 AM, 12 PM, and 7 PM over the past week, and combining this with the day's weather conditions, the system predicts that users will have higher hot water demand around these times the following day. Therefore, the water dispenser can choose to start the preheating program during the low electricity price period before these peak times, heating the water to a suitable temperature and maintaining it briefly. During off-peak hours, it can appropriately lower the heat preservation temperature or stop preheating.

[0064] This embodiment utilizes personalized energy-saving program rules to accurately predict users' actual water needs, achieving on-demand energy supply and avoiding the energy waste caused by traditional fixed-period preheating. It effectively shortens the ineffective heat preservation time of the heating tank and reduces unnecessary compressor start-stop cycles, thus ensuring users can obtain water at the appropriate temperature immediately when needed, guaranteeing a good water experience while significantly reducing the water dispenser's standby energy consumption. This function solves the energy waste problem caused by the fixed preheating period of traditional water dispensers, achieving on-demand energy supply through accurate demand prediction, ensuring an immediate water experience while reducing standby energy consumption.

[0065] In some embodiments of this application, in step S200, the personalized drinking water reminder rules include:

[0066] S220: Analyze the progress of daily water intake and generate tiered reminders based on user habits.

[0067] By identifying users' primary water-drinking periods, the water-reminder rules determine the reminder level based on the interval between the current time and the most recent water intake, as well as the proportion of water consumed that day. This tiered reminder strategy accurately controls the timing of reminders, improving user response rates while avoiding frequent interruptions.

[0068] For example, the system learns that users typically drink water during work breaks around 10 AM and 3 PM, and sets a daily target water intake of 1500 ml. If, by 2 PM, the system detects that the user has only consumed 30% of the target for the day, and more than 2 hours have passed since the last drink, a Level 1 reminder will be issued, such as a gentle pop-up notification on the user's computer screen. If, by 4 PM, the user's water intake has still not reached 60% of the target, and some time has passed since the last drink, a slightly stronger Level 2 reminder may be issued, such as a push notification on a mobile app accompanied by a soft ringtone. If the user's water intake is close to the target near the end of the workday, only an encouraging reminder may be issued, or no further reminders may be given.

[0069] This tiered reminder strategy can precisely control the timing and intensity of reminders based on the user's daily drinking rhythm and water intake that day. This embodiment avoids the frequent disturbances that simple, timed reminders might cause, making the reminders more user-friendly and effectively improving the user's response rate to drinking reminders, thus helping users better develop a regular drinking habit.

[0070] In some embodiments of this application, step S500, the process of optimizing rule generation based on feedback data, includes:

[0071] S510: When the water intake interval exceeds the set threshold, a correction mechanism is triggered, and the feature weights are adjusted in conjunction with user rating data.

[0072] By using dynamic thresholds, a correction process is initiated when abnormal water withdrawal intervals are detected. The model tuning unit adjusts the feature weight parameters based on the user's rating of the alert. This mechanism enables the system to be adaptive, maintaining high prediction accuracy through model retraining even when user lifestyles change.

[0073] In actual use, the system might initially consider 3 PM as a potential time when a user has a need for drinking water based on historical user data and set reminders accordingly. However, if a user fails to collect water after the 3 PM reminder for several consecutive days, and the interval between water collections significantly exceeds the usual average, the system will trigger a correction mechanism. Simultaneously, if the user gives a low rating to these time reminders, indicating that they feel the reminders are inappropriate, the model tuning unit will reduce the weight of the "3 PM" time feature in the prediction model based on this feedback, no longer using it as the primary reminder reference time. Instead, it will focus on the user's recent actual water collection patterns, such as discovering that the user may have recently become accustomed to collecting water around 2:30 PM, and adjust the reminder strategy to adapt to this change.

[0074] This embodiment endows the system with strong adaptive capabilities through a correction mechanism, enabling it to keenly perceive changes in users' lifestyles. By combining direct user rating feedback, it dynamically adjusts the feature weights in the model and retrains the model, allowing the rules generated by the system to continuously optimize as user habits evolve. This maintains high prediction accuracy and alert effectiveness over the long term, better adapting to users' ever-changing needs.

[0075] This application also provides an AI-based energy-saving and drinking reminder system for water dispensers. The system is used to implement the AI-based energy-saving and drinking reminder methods for water dispensers provided in any embodiment, as described above. Figure 2 As shown, it includes: a data acquisition module, a cloud-based AI decision-making module, a rule execution module, and a feedback optimization module.

[0076] The system comprises the following modules: a data acquisition module, which connects the water dispenser terminal to an environmental sensor to collect equipment operation data and environmental parameters; a cloud-based AI decision-making module, whose input is connected to the data acquisition module's output, which generates energy-saving program rules and drinking water reminder rules; a rule execution module, whose input is connected to the cloud-based AI decision-making module's output, which in turn connects to the water dispenser controller and the user terminal, for executing energy-saving operations and pushing drinking water reminders; and a feedback optimization module, whose input is connected to the user terminal and whose output is connected to the cloud-based AI decision-making module, for optimizing model parameters based on user feedback data.

[0077] Specifically, the data acquisition module collects real-time data on the temperature of the hot water tank, the temperature of the ice water box, the amount of water dispensed, and the energy consumption of the equipment through the water dispenser's built-in temperature sensor, flow meter, and water pump status monitoring unit. At the same time, it connects to external data sources through the IoT communication unit to obtain information on the temperature and humidity of the location area, peak and off-peak electricity prices, and exercise step count and heart rate data transmitted by the user-authorized health bracelet / watch.

[0078] The cloud-based AI decision-making module uses simulated data to train a basic model, learning the correlation between water demand and equipment energy consumption. It optimizes parameters using real user data to improve personalized decision-making capabilities and continuously adjusts model weights through enhanced learning. The rule execution module receives rules from the AI ​​model and controls the water dispenser to turn off heating and cooling functions during non-water usage periods, and to start preheating or precooling before predicted water usage periods. Simultaneously, based on the user's daily activity level, ambient temperature and humidity, and historical drinking habits, it generates time-segmented water consumption targets, sending text reminders via the app or flashing prompts on the water dispenser screen.

[0079] The feedback optimization module automatically collects user ratings on reminder timeliness and water temperature comfort every morning at midnight. Based on user water-taking patterns, it triggers a model self-correction mechanism, reducing the weight of environmental data and increasing the weight of user habit data, and updates the model parameters through incremental training.

[0080] The AI-based water dispenser energy-saving and drinking reminder system provided in this embodiment collects multi-dimensional data on equipment operation, environmental parameters, and user health through a data acquisition module. Combined with the intelligent analysis and learning capabilities of the cloud-based AI decision-making module, it can more accurately generate energy-saving program rules and personalized drinking reminder rules. The rule execution module then intelligently starts and stops the water dispenser during non-water usage periods, effectively reducing unnecessary energy consumption. Simultaneously, it pushes drinking reminders adapted to the user's daily status across multiple terminals, improving the effectiveness of the reminders. The feedback optimization module continuously collects user feedback and actual water consumption patterns, constantly adjusting model parameters and the weights of various influencing factors. This allows the system to better adapt to the ever-changing needs and habits of users, thereby achieving energy-saving goals while providing users with more considerate and precise drinking health management services.

[0081] In some embodiments of this application, the data acquisition module includes: an IoT communication unit, an environmental sensing unit, and a health data interface unit. The IoT communication unit supports multiple protocols such as Wi-Fi, NB-IoT, and Zigbee, ensuring that the water dispenser terminal can stably access the IoT cloud platform in different scenarios such as home and office, and upload device operation data to the cloud-based AI decision-making module in real time.

[0082] The environmental sensing unit integrates temperature and humidity sensors with an electricity price data interface. By periodically collecting weather data and time-of-use electricity price information of the location area, it provides environmental constraints for the generation of energy-saving program rules.

[0083] The health data interface unit connects with the user's smart bracelet or watch to synchronously acquire health data such as steps, heart rate, and sleep quality. Combined with basic information such as the user's age and weight, it constructs a personalized drinking water demand model.

[0084] The three sub-modules in this embodiment integrate device status, environmental parameters, and user health data into a structured data package through a data fusion mechanism, providing multi-dimensional decision-making support for the AI ​​model. The data acquisition module, through collaborative acquisition of multi-source data, makes energy-saving decisions more aligned with actual user needs, improving the accuracy and adaptability of rule generation.

[0085] In some embodiments of this application, the cloud-based AI decision-making module includes three functional components: a habit analysis unit, a demand prediction unit, and a rule generation unit.

[0086] The habit analysis unit uses an LSTM neural network model, taking users' historical water intake records as input, and identifies the distribution pattern of users' drinking time and water temperature preferences through time-series feature extraction.

[0087] The demand forecasting unit builds a forecasting model based on the Transformer architecture. It takes temperature and humidity data provided by the environmental sensing unit, electricity price information, and exercise intensity data obtained by the health data interface unit as inputs, and outputs water consumption forecasts for different time periods in the next 24 hours, thus reducing the forecast error rate.

[0088] The rule generation unit uses a multi-objective optimization algorithm to dynamically generate energy-saving program rules and drinking water reminder rules by comprehensively considering equipment energy consumption characteristics, environmental constraints such as peak electricity prices during high-temperature periods, and user demand prediction results.

[0089] The cloud-based AI decision-making module in this embodiment uses a layered AI architecture to achieve intelligent processing from habit learning to demand prediction to rule generation, solving the problem that traditional timed energy-saving modes cannot adapt to dynamic demands and enabling precise matching of energy-saving operations with users' actual water usage needs.

[0090] In some embodiments of this application, the rule execution module includes two execution components: an energy-saving control unit and an alert push unit.

[0091] The energy-saving control unit establishes two-way communication with the water dispenser controller through the Internet of Things protocol. After receiving the energy-saving program rules issued by the cloud AI decision module, it parses them into specific control instructions: automatically turn off the heating function of the hot tank and the cooling function of the ice water box during the user's non-water usage period to reduce standby energy consumption; and start the hot tank to preheat to the user's preferred temperature in advance during the predicted water usage period, or start the cooling function of the ice water box in advance based on the predicted ambient temperature.

[0092] The reminder push unit employs a tiered reminder strategy based on the user's progress towards their hydration goals: a basic reminder is sent when the achievement rate is low, a stronger reminder is triggered when the achievement rate is even lower, and an emergency reminder is activated when the achievement rate is close to the goal. Simultaneously, it incorporates user health data, prioritizing hydration reminders when continuous lack of water intake and elevated heart rate are detected.

[0093] The module rule execution module in this embodiment ensures that energy-saving operation does not affect user experience through hardware and software collaborative control. The hierarchical reminder mechanism improves user response rate and solves the problem that traditional single reminder methods are easily ignored, thus significantly improving the efficiency of improving users' drinking habits.

[0094] In some embodiments of this application, the feedback optimization module includes an evaluation analysis unit and a model tuning unit.

[0095] The evaluation and analysis unit collects rating data on energy-saving effects and drinking water reminders through user terminals, and uses sentiment analysis algorithms to analyze key improvement points in user feedback text. The model optimization unit establishes a dual closed-loop optimization mechanism: when it detects that the actual water collection interval of users exceeds the predicted value, it automatically triggers rule generation strategy correction and adjusts the user behavior weight parameters in the demand prediction model; combined with the rating data, it optimizes the feature weights of the AI ​​model and enhances the decision influence of high-rated features.

[0096] In this embodiment, the feedback optimization module drives model evolution through user feedback, continuously optimizes energy efficiency, and continuously improves the cycle, making the model output more in line with user preferences, improving user satisfaction and acceptance of energy-saving effects and drinking water reminder functions, thereby enhancing the overall system's intelligence level and user experience.

[0097] The AI-based water dispenser energy-saving and drinking water reminder system described in this application requires users to bind the water dispenser to an app and authorize a health data interface. The system automatically collects initial data to pre-train the AI ​​model. During daily use, the data acquisition module continuously acquires device operating data, environmental parameters, and health information. The cloud-based AI decision-making module generates energy-saving program rules and drinking water reminder rules in real time. The rule execution module controls the water dispenser to preheat / precool before the predicted water usage period and pushes tiered reminders through the app. Users can view real-time drinking water data, adjust target water consumption, and rate the energy-saving effect and reminder methods through the app. The feedback optimization module analyzes user feedback data, dynamically adjusts AI model parameters, and continuously optimizes the rule generation strategy.

[0098] The system utilizes multi-module collaboration and data-driven energy conservation, dynamically adjusting equipment operation based on environmental electricity prices and user habits to significantly reduce energy consumption. Furthermore, it combines health data and location information to push precise reminders, significantly improving the rate of users meeting daily water intake standards. Through continuous model improvement based on user feedback, user satisfaction has stabilized at a high level after a period of operation, achieving a long-term balance between energy conservation and user experience.

[0099] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the disclosure in the specification and the embodiments. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein.

Claims

1. A method for energy saving and drinking reminders for water dispensers based on AI, characterized in that, Including the following steps: Collect drinking water-related data, including equipment operating parameters, environmental parameters, and user health data; Personalized energy-saving program rules and personalized drinking water reminder rules are generated based on the drinking water-related data. Energy-saving operations are performed according to the energy-saving procedure rules, including turning off or starting the heating and cooling functions; Drinking reminders will be sent according to the aforementioned drinking reminder rules; Collect user feedback data and optimize the rule generation process based on the feedback data.

2. The AI-based water dispenser energy-saving and drinking reminder method according to claim 1, characterized in that, The equipment operating parameters include water intake time, water intake volume, water intake temperature, and equipment on / off status; the environmental parameters include real-time temperature, humidity, and time-of-use electricity price data.

3. The AI-based water dispenser energy-saving and drinking reminder method according to claim 1, characterized in that, The personalized energy-saving program rules include: Predict future water demand and dynamically adjust preheating periods or precooling temperatures.

4. The AI-based water dispenser energy-saving and drinking reminder method according to claim 1, characterized in that, The personalized hydration reminder rules include: Analyze the progress of daily water intake and generate tiered reminders based on user habits.

5. The AI-based water dispenser energy-saving and drinking reminder method according to claim 1, characterized in that, The process of generating optimization rules based on the feedback data includes: When the water intake interval exceeds the set threshold, a correction mechanism is triggered, and the feature weights are adjusted in conjunction with user rating data.

6. An AI-based energy-saving and drinking reminder system for water dispensers, the system being used to implement the AI-based energy-saving and drinking reminder method for water dispensers as described in any one of claims 1-5, characterized in that, include: Data acquisition module, cloud AI decision-making module, rule execution module, and feedback optimization module; The data acquisition module connects the water dispenser terminal to the environmental sensor and is used to collect equipment operation data and environmental parameters; The input end of the cloud-based AI decision-making module is connected to the output end of the data acquisition module, and is used to generate energy-saving program rules and drinking water reminder rules; The input end of the rule execution module is connected to the output end of the cloud AI decision module, and the output end of the rule execution module is connected to the water dispenser controller and the user terminal respectively, for performing energy-saving operations and pushing drinking reminders; The input end of the feedback optimization module is connected to the user terminal, and the output end of the feedback optimization module is connected to the cloud AI decision module, which is used to optimize the model parameters based on user feedback data.

7. The AI-based water dispenser energy-saving and drinking reminder system according to claim 6, characterized in that, The data acquisition module includes: an Internet of Things communication unit, an environmental sensing unit, and a health data interface unit; The IoT communication unit supports at least one of the following communication protocols: Wi-Fi, NB-IoT, and Zigbee. The environmental sensing unit is used to acquire temperature, humidity, and electricity price data of the location area; The health data interface unit is used to access the user's fitness and health data from their wristband or watch.

8. The AI-based water dispenser energy-saving and drinking reminder system according to claim 6, characterized in that, The cloud-based AI decision-making module includes: a habit analysis unit, a demand prediction unit, and a rule generation unit; The habit analysis unit is used to learn the distribution of users' drinking time and water temperature preferences; The demand forecasting unit is used to forecast water demand for the next 24 hours based on historical data; The rule generation unit is used to dynamically generate energy-saving program rules and drinking water reminder rules by integrating environmental parameters and health data.

9. The AI-based water dispenser energy-saving and drinking reminder system according to claim 6, characterized in that, The rule execution module includes: an energy-saving control unit and an alert push unit; The energy-saving control unit is used to turn off the heating and cooling functions of the hot tank / ice water box during non-water usage periods, and to start preheating or precooling before the predicted water usage period. The reminder push unit is used to push tiered reminders to the user terminal based on the progress of achieving the drinking water target.

10. The AI-based water dispenser energy-saving and drinking reminder system according to claim 6, characterized in that, The feedback optimization module includes: an evaluation analysis unit and a model tuning unit; The evaluation and analysis unit is used to analyze user ratings for energy-saving effects and drinking water reminders; The model tuning unit is used to automatically correct the rule generation strategy when the user's water intake interval exceeds the threshold, and to adjust the model feature weights in combination with the scoring data.

Images