Artificial intelligence-based warming cup liquid temperature self-adaptive control method and system

Abstract

The application discloses a temperature increasing cup liquid temperature self-adaptive control method and system based on artificial intelligence. The temperature increasing cup comprises a smart liquid container. The method comprises the following steps: acquiring and analyzing digital schedule data of a user to predict a drinking window and a non-drinking window; by monitoring the temperature change rate of the liquid in the smart liquid container, the thermal inertia characteristics are calculated to identify the liquid type; based on the predicted window and the identified liquid type, a dynamic temperature control logic is generated and executed, the heating circuit is controlled to enter a low-power mode during the non-drinking window, and the liquid temperature is adjusted to a target drinking temperature matched with the liquid type before the drinking window arrives. The application can realize temperature non-susceptible self-adaptive control according to the user schedule and the liquid type, improve the user experience, optimize the device energy efficiency and enhance the use safety.

Description

Technical Field

[0001] This application relates to the field of data processing and automation control, and more specifically, to an artificial intelligence-based adaptive temperature control method and system for heating cups, applicable to office and health management scenarios. Background Technology

[0002] In today's fast-paced office environment, users' drinking habits are often highly fragmented and unpredictable. Existing smart liquid containers, such as smart water cups, typically employ a "fixed setpoint constant temperature" operating mode, for example, preset and maintaining the temperature at a constant 55°C. However, this mode has significant drawbacks.

[0003] First, this model ignores the user's specific schedule. When the user is in a meeting or out and about and cannot drink water, the cup will continue to heat and keep the liquid inside warm. This not only causes unnecessary power consumption, but also shortens the battery life of portable devices that rely on battery power.

[0004] Secondly, this mode lacks the ability to sense the properties of the liquid inside the container. Users may add different types of beverages to the container, such as instant coffee that needs to be brewed with 85°C hot water, or tea that needs to be enjoyed at a specific temperature. Traditional constant temperature modes cannot identify the type of liquid and match the optimal temperature. If the system still maintains the temperature at the preset 55°C, it may result in the beverage not being brewed sufficiently, seriously affecting the taste and drinking experience.

[0005] Current technologies typically rely on users manually adjusting the temperature via smartphone apps or physical buttons on the container itself. This "human-adapted-to-device" interaction increases the user's operational burden and cognitive load, contradicting the trend towards automation and seamless operation in smart devices. Furthermore, traditional temperature control algorithms, such as proportional-integral-derivative (PID) control, adjust based solely on the difference between the current liquid temperature and the target temperature, lacking the ability to predict future user behavior. This results in a significant time lag between the user's immediate needs and the system's response, failing to achieve "predictive" intelligent service.

[0006] Therefore, how to solve the problem of low energy efficiency and poor drinking experience caused by the inability of existing smart liquid containers to dynamically adjust temperature control according to the user's schedule and liquid characteristics is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0007] The main objective of this invention is to provide an artificial intelligence-based adaptive temperature control method and system for heated cups, which solves the problem that existing smart cups cannot dynamically adjust the temperature control method according to the user's schedule and the characteristics of the liquid, resulting in low energy efficiency and poor drinking experience.

[0008] To achieve the above objectives, this invention provides an artificial intelligence-based adaptive temperature control method for a heated cup, comprising: obtaining a predicted drinking window and a predicted non-drinking window based on the user's digital schedule data; monitoring the rate of temperature change of the liquid when a preset power is applied to the liquid in the intelligent liquid container using a temperature sensor and a heating circuit installed inside the container; calculating the thermal inertia characteristics of the liquid based on the rate of temperature change, and identifying the liquid type based on the thermal inertia characteristics; generating and executing dynamic temperature control logic by combining the predicted drinking window, the non-drinking window, and the identified liquid type, wherein the dynamic temperature control logic includes: controlling the heating circuit to enter a low-power mode during the non-drinking window; and driving the heating circuit to adjust the temperature of the liquid to a target drinking temperature matching the liquid type within a preset advance time before the drinking window arrives.

[0009] Furthermore, the present invention also provides an artificial intelligence-based adaptive control system for the temperature of a heated cup liquid, comprising: a cloud server, wherein the cloud server has a built-in schedule parsing module for acquiring and parsing the user's digital schedule data to predict future drinking and non-drinking windows; a smart liquid container, wherein the smart liquid container includes: a communication module for communicating with the cloud server; a temperature sensor for monitoring the temperature of the liquid inside the container; a heating circuit for heating the liquid; and a processor electrically connected to the communication module, the temperature sensor, and the heating circuit, wherein the processor is configured to: receive drinking and non-drinking window information sent by the cloud server; control the heating circuit to apply power and calculate the thermal inertia characteristics of the liquid based on the temperature data fed back by the temperature sensor to identify the liquid type; and, considering the drinking window, the non-drinking window, and the identified liquid type, control the heating circuit to enter a low-power mode during the non-drinking window and drive the heating circuit to adjust the liquid temperature to a target drinking temperature matching the liquid type before the drinking window is reached.

[0010] Compared with existing technologies, the advantages of this invention are as follows: By analyzing the user's digital schedule, this invention can predict the user's available drinking time. Without manual intervention from the user, the system can automatically adjust the liquid temperature to the optimal drinking temperature in advance based on scheduled events such as meeting end times, significantly improving the automation and intelligence level of the user experience. By measuring the thermal response characteristics of liquids during the heating process, this invention can automatically distinguish between different liquids such as water, tea, and coffee in a low-cost manner and match them with differentiated and more suitable heat preservation methods, thereby improving the taste of various beverages. This invention can accurately identify the user's non-drinking time and automatically control the device to enter low-power or sleep mode, avoiding ineffective continuous heating, thus significantly extending the battery life of portable devices. By using the signal from the liquid level sensor as a necessary prerequisite for executing the heating command, this invention effectively avoids the risk of dry burning that may occur when heating when there is too little or no liquid in the container, improving product safety. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of the overall architecture of a liquid temperature adaptive control system provided in an embodiment of the present invention; Figure 2 This is a hardware structure block diagram of the intelligent liquid container provided in an embodiment of the present invention; Figure 3 This is a main flowchart of a liquid temperature adaptive control method provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the state switching of the dynamic temperature control model provided in the embodiment of the present invention.

[0013] In the diagram: 101-Cloud server, 102-User mobile terminal, 103-Smart liquid container, 201-Processor, 202-Communication module, 203-Temperature sensor, 204-Heating circuit, 205-Liquid level sensor, 206-Inertial measurement unit, 207-Status indication module, 208-Power module, 401-Sleep state, 402-Ready state, 403-Insulation state, S301-Acquire and parse digital schedule data, S302-Identify liquid type, S303-Execute dynamic temperature control logic, S304-Execute safety monitoring logic. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0016] Example 1

[0017] This embodiment provides a liquid temperature adaptive control system. (Refer to...) Figure 1 The system adopts an edge-cloud collaborative architecture, and its overall architecture includes a cloud server 101, a user mobile terminal 102, and an intelligent liquid container 103.

[0018] Cloud server 101 is responsible for core data analysis and decision-making. Internally, it runs a behavior prediction engine, which includes a schedule parsing module and a habit learning module. The schedule parsing module securely acquires the user's digital schedule data through an application programming interface (API), such as an authorized third-party electronic calendar service interface. This data includes, but is not limited to, event text descriptions, time intervals, and location tags. The server parses this data, extracting the event text, time intervals, and location tags from the digital schedule data; a pre-built natural language processing module maps the event text to the event's activity intensity and disturbance index; combining the current time and the user's historical drinking frequency for similar events, as well as the location change status calculated based on the location tags, a multi-dimensional feature vector is constructed: [current time, event duration, activity intensity, disturbance index, location change distance, historical drinking frequency for similar events]. This multi-dimensional feature vector is input into a pre-trained time series prediction model (such as a Long Short-Term Memory network), which outputs predicted drinking probabilities for each future time slice, thereby accurately predicting the user's "drinking window" and "non-drinking window" in the future. .

[0019] User mobile terminal 102, such as a smartphone, acts as a data relay and a bridge for user interaction. It establishes a communication connection with the smart liquid container 103 via Bluetooth Low Energy and forwards sensor data collected by the smart liquid container 103 to the cloud server 101. Simultaneously, it also receives control commands from the cloud server 101 and sends them to the smart liquid container 103. Furthermore, the application on the user mobile terminal 102 can also be used for auxiliary functions such as initial user account binding, calendar access authorization, and device pairing.

[0020] The intelligent liquid container 103 is the final execution terminal of the technical solution. (Refer to...) Figure 2 Its hardware structure mainly includes a processor 201, a communication module 202, a temperature sensor 203, a heating circuit 204, a liquid level sensor 205, an inertial measurement unit 206, a status indication module 207, and a power supply module 208.

[0021] The processor 201, such as an embedded microcontroller, is the control core of the intelligent liquid container 103. It is electrically connected to all other modules and is responsible for performing local sensor data acquisition, data preprocessing, instruction parsing, and drive control.

[0022] The communication module 202, in this embodiment, is a low-power Bluetooth module, which is responsible for wireless data exchange with the user's mobile terminal 102.

[0023] The perception layer module includes: Temperature sensor 203, such as a negative temperature coefficient thermistor, is disposed on the inner wall of the container for real-time, high-precision monitoring of the temperature of the liquid inside the container.

[0024] The liquid level sensor 205, in this embodiment, is preferably a non-contact capacitive array sensor disposed on the outer wall of the container, used to monitor the percentage of liquid volume in the container in real time. Its non-contact nature avoids contamination of the liquid itself.

[0025] An inertial measurement unit 206, such as a MEMS six-axis accelerometer, is used to monitor the container's attitude and micro-vibrations to identify the user's "drinking action." For example, if a container tilt angle exceeding 30 degrees is detected for more than 2 seconds, it can be considered a valid drinking action.

[0026] The execution layer module includes: Heating circuit 204, such as a thick-film heating circuit disposed at the bottom and lower sidewall of the container, is used to heat the liquid according to instructions from processor 201.

[0027] The status indicator module 207, such as a ring of light-emitting diodes, can intuitively indicate the current working status to the user through different colors or flashing patterns.

[0028] The power module 208 includes a rechargeable lithium battery, a charging interface, and a power management chip, providing stable and reliable power to all electronic components of the entire intelligent liquid container 103.

[0029] In this embodiment, the data interaction process for the collaborative operation of each component is as follows: The processor 201 of the intelligent liquid container 103 collects raw data from the temperature sensor 203, the liquid level sensor 205, and the inertial measurement unit 206 at a preset frequency. The data is preprocessed using algorithms such as Kalman filtering to eliminate noise. Subsequently, the data is packaged into data frames at preset time intervals or when a specific event is detected, and sent to the user mobile terminal 102 via the communication module 202, and finally uploaded to the cloud server 101. The cloud server 101 calculates the target temperature control method for the next time period based on the received terminal status data and the predicted schedule window, and issues specific control commands. The processor 201 of the intelligent liquid container 103 receives and parses the command, and finally drives the heating circuit 204 to perform the corresponding heating or heat preservation actions.

[0030] The semantic mapping execution logic for the specific event is as follows: the semantic analysis algorithm is used to classify the text description of the event, and text features such as "meeting", "report" and "driving" are mapped to a higher disturbance index, while "independent office" and "lunch break" are mapped to a lower disturbance index. Then, the time series prediction model is combined to divide the event into "drinking water window" and "non-drinking water window".

[0031] To ensure real-time data transmission and low power consumption, this embodiment defines a Bluetooth transparent data frame format. The data frame begins with a frame header of 0xAA and ends with a frame tail of 0x55. Its payload includes, in sequence: a 4-byte timestamp, 2 bytes of current water temperature data, 1 byte of liquid level percentage, and 1 byte of IMU activity score. To ensure data integrity, the data frame also includes a cyclic redundancy check (CRC) code.

[0032] Example 2

[0033] This embodiment, based on the system of Embodiment 1, elaborates in detail a liquid temperature adaptive control method. (Refer to...) Figure 3 The main steps of this method are as follows: Step S301: Obtain and parse digital schedule data.

[0034] The schedule parsing module of cloud server 101 continuously obtains schedule data from the user-authorized calendar service. To achieve high-precision prediction, the system specifically executes the following sub-steps: First, it extracts the event text description, time interval, and location tags from the digital schedule data; second, it uses a semantic analysis algorithm to classify the event text description, mapping text features such as "meeting," "report," and "driving" to a higher disturbance index, and mapping "working alone" and "lunch break" to a lower disturbance index; next, it combines the user's drinking frequency under similar historical events stored in the system, and the location change status calculated based on the previous and subsequent schedule location tags (such as whether commuting), to construct a multi-dimensional feature vector; subsequently, it inputs the multi-dimensional feature vector into a time series prediction model based on a long short-term memory network, which outputs corresponding drinking probability prediction values ​​for a series of future time slices; finally, when the drinking probability prediction value of a consecutive time slice is lower than a preset available probability threshold, the consecutive time period is defined as a non-drinking window; conversely, when the drinking probability prediction value of a consecutive time slice is higher than or equal to the available probability threshold, it is defined as a drinking window.

[0035] Step S302: Identify the liquid type.

[0036] This step is a core technical point of the present invention, used to indirectly identify the type of liquid through physical methods. The triggering condition for this step can be that the system detects a liquid refill event; for example, the temperature sensor 203 detects that the liquid temperature drops more than a preset temperature drop threshold within a short time window. Alternatively, the level sensor 205 may detect a significant change in the liquid level that exceeds a preset filling threshold.

[0037] Upon triggering, processor 201 executes liquid identification logic. Specifically, processor 201 controls heating circuit 204 to operate at a constant test power. The liquid inside the container is heated and the heating continues for a preset test duration. During this period, the processor 201 obtains the initial temperature at the start of heating via the temperature sensor 203. and the termination temperature at the end of heating .

[0038] Subsequently, the system calculates the rate of temperature change, that is, it calculates the amount of temperature change. And the rate of temperature change is defined as This rate reflects how quickly a liquid heats up when it absorbs the same amount of heat, and is an important characteristic of the liquid's thermal inertia.

[0039] In a preferred embodiment, the above calculation logic can be implemented based on thermodynamic formulas: in, It is the heat absorbed by the liquid, which can be... Calculated; It is the mass of the liquid, which can be estimated by combining the volume measured by the liquid level sensor 205 with the liquid density; This is the measured temperature rise. From this, the specific heat capacity coefficient of the liquid can be estimated. .

[0040] The system compares the calculated rate of temperature change with a pre-set mapping database stored in local memory. This mapping database stores various common liquid types and their corresponding temperature change rate threshold ranges. In the embodiments of this specification, common liquid types in this mapping database include, but are not limited to: pure water, coffee or sugary beverages, and high-concentration fluids. For example, if the estimated specific heat capacity... Approximately equal to If the thermal response is slow, meaning the rate of temperature change is low, the system determines the liquid type as "water"; if the thermal response is slow, meaning the rate of temperature change is low, it may be determined as "concentrated liquid / coffee" containing a large amount of solute. By judging the range in which the calculated rate value falls, the type of liquid can be determined.

[0041] To improve recognition accuracy, the temperature change rate threshold range in the mapping database can be dynamic. Specifically, its specific value is related to the current ambient temperature measured by temperature sensor 203 before the recognition step is executed. This is because ambient temperature affects the rate of heat dissipation, thus affecting the net rate of temperature rise. A dynamic lookup table related to ambient temperature can be used to adjust the threshold range and eliminate the interference from changes in ambient temperature.

[0042] The mapping database contains specific decision intervals. For example, when the test power is constant at 30W and the test liquid volume is 200ml: If the temperature change characteristic value is in Between these values, it is determined to be pure water, matching the target temperature of 45℃; If the temperature change characteristic value is in Between these values, it is determined to be coffee or a sugary beverage (which heats up faster due to differences in density and specific heat capacity), and the target temperature is matched to 60℃; If the temperature change characteristic value is greater than It is determined to be a high-concentration fluid (such as a thick soup containing a large amount of solute and with high viscosity, which limits heat convection), and the target temperature is matched to 55℃.

[0043] Step S303: Execute dynamic temperature control logic.

[0044] The processor 201 integrates the drinking window information received from the cloud server 101 and the locally identified liquid type information to execute a state machine-based dynamic temperature control logic. (Refer to...) Figure 4 This logic classifies the operating states of the intelligent liquid container 103 into at least the following three categories: Sleep mode 401: When the system determines that it is currently in a user's "non-drinking window," it enters sleep mode. In this state, the processor 201 controls the heating circuit 204 to enter a low-power mode, and its average operating power is controlled at a preset sleep power threshold. The following describes how entering a sleep state can maximize energy savings.

[0045] Ready state 402: When the system clock detects that there is only a preset advance time remaining before the start time of the next "drinking window". When the system is in a standby state, it automatically switches from a hibernation state or other states to a ready state. In this state, the processor 201 activates the heating circuit 204 to provide rated heating power. Works to change the liquid temperature from the current temperature Heat to the target drinking temperature that matches the identified liquid type. .

[0046] In a preferred embodiment, the preset advance time It is not a fixed value, but rather dynamically calculated based on the current equipment status. This dynamic calculation allows for more precise control over the timing of heating initiation. Specifically, the system performs a lead time calculation, determining the required heating duration based on the current liquid mass, specific heat capacity, temperature difference, and heating power. The calculation logic is implemented through the following formula: in, The target drinking temperature; It is the current liquid temperature measured by temperature sensor 203 when entering the preparatory state; This is the rated heating power of heating circuit 204; The current liquid mass is estimated based on the reading of the liquid level sensor 205; It is the specific heat capacity coefficient value corresponding to the liquid type identified in step S302; This is a preset buffer time. Using this formula, the system can dynamically adjust the start-up time of the preparatory state based on the type and volume of liquid, achieving refined energy efficiency management.

[0047] Insulated state 403: When the temperature sensor 203 detects that the liquid temperature has reached the target drinking temperature. During the designated drinking window, the system enters a heat preservation state. In this state, the processor 201 uses a high-precision PID control algorithm to drive the heating circuit 204 via pulses or variable power to precisely maintain the liquid temperature at the target drinking temperature. Within a preset temperature fluctuation range in the vicinity.

[0048] Step S304: Execute security monitoring logic.

[0049] Throughout the entire workflow, safety logic always has the highest priority. Before executing any instruction to drive the heating circuit 204, the processor 201 first queries the reading of the liquid level sensor 205. Only when the reading indicates that the current liquid level is higher than a preset minimum safe liquid level threshold will the processor 201 execute the instruction to drive the heating circuit 204. This AND logic mechanism ensures that the heating circuit will not start when the liquid in the container is insufficient or the cup is empty, thus fundamentally eliminating the risk of dry burning.

[0050] Furthermore, to accommodate the different physical properties of liquids, the minimum safe liquid level threshold is variable. After identifying the liquid type, the processor 201 retrieves the corresponding safe liquid level threshold from a lookup table. For example, for liquids identified as highly volatile or with low boiling points, the processor 201 will retrieve a relatively high safe liquid level threshold. This allows for a larger safety margin at the top of the container to accommodate the pressure generated by boiling or evaporation, further enhancing safety during use.

[0051] In summary, this invention constructs a collaborative control system combining cloud-based behavioral prediction and terminal physical sensing, deeply integrating time-dimensional information obtained from schedule analysis with physical-dimensional information obtained through thermal inertia identification. The signal from the liquid level sensor constitutes a "safety lock" for the execution of heating commands, while the liquid identification results dynamically correct key parameters in the temperature control logic. This cross-validation and parameter complementarity of hardware and software data achieves a balance between high energy efficiency and superior user experience, which is impossible to achieve with a single technology.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An AI-based adaptive temperature control method for a heated cup, wherein the heated cup includes an intelligent liquid container, characterized in that, include: Based on the user's digital schedule data, predict the drinking window and the non-drinking window are obtained; Specifically, this includes: extracting event text descriptions, time intervals, and location tags from the digital schedule data; classifying the event text descriptions using semantic analysis algorithms; and mapping the event texts to an event disturbance index. By combining the frequency of the user's drinking under similar historical events stored in the system, and the location change status calculated based on the location tags of the previous and subsequent schedules, a multi-dimensional feature vector is constructed. The multidimensional feature vector is input into a time series prediction model built on a long short-term memory network. The model outputs corresponding drinking probability prediction values ​​for a series of future time slices. When the predicted drinking probability value of a continuous time slice is lower than the preset available probability threshold, the continuous time slice is defined as a non-drinking window; conversely, when the predicted drinking probability value of a continuous time slice is higher than or equal to the available probability threshold, it is defined as a drinking window. By using a temperature sensor and heating circuit installed inside the smart liquid container, the rate of temperature change of the target liquid is monitored when a preset power is applied to heat the target liquid inside the smart liquid container. The thermal inertia characteristics of the target liquid are calculated based on the temperature change rate, and the liquid type of the target liquid is identified based on the thermal inertia characteristics to obtain the identified liquid type. Specifically, this includes: controlling the heating circuit to maintain a constant test power. The target liquid is heated and the test is continued for a preset duration. ; The initial temperature at the start of heating is obtained through the temperature sensor. and the termination temperature at the end of heating ; Calculate the temperature change And the rate of temperature change is defined as ; The calculated rate of temperature change is compared with a preset mapping database, which stores various liquid types and their corresponding temperature change rate threshold ranges. The liquid type of the target liquid is determined by judging the range in which the temperature change rate falls. Based on the predicted drinking window, the predicted non-drinking window, and the identified liquid type, dynamic temperature control logic is generated and executed. The dynamic temperature control logic includes: During the predicted non-drinking window, the heating circuit is controlled to enter a low-power mode; Within a preset lead time before the predicted drinking window is reached, the heating circuit is activated to adjust the temperature of the liquid to a target drinking temperature that matches the type of liquid.

2. The method as described in claim 1, characterized in that, The temperature change rate threshold range in the mapping database is dynamic, and its specific value is related to the current ambient temperature measured by the temperature sensor before the method is executed. Related; Furthermore, the triggering condition for the step of identifying the liquid type is: the temperature sensor detects that the temperature of the target liquid drops by more than a preset temperature drop threshold within a specified time window. Alternatively, a liquid level sensor built into the intelligent liquid container detects a change in the liquid level exceeding a preset filling threshold, thereby determining that a target liquid refill event has occurred.

3. The method as described in claim 1, characterized in that, The dynamic temperature control logic classifies the working state of the intelligent liquid container into at least three types: In the dormant state, during the non-drinking window, the smart liquid container enters the dormant state, and the average operating power of the heating circuit is controlled at a preset dormant power threshold. the following; In the ready state, within the preset advance time before the drinking window is reached, the smart liquid container enters the ready state, and the heating circuit is activated to heat the liquid temperature from the current temperature to the target drinking temperature. During the drinking window, the smart liquid container enters the heat preservation state, and the heating circuit operates in a pulsed or variable power mode to maintain the liquid temperature within a preset temperature fluctuation range near the target drinking temperature.

4. The method as described in claim 3, characterized in that, The preset advance time in the ready state It is dynamically calculated based on the current device status, and the calculation method is as follows: ;in, The target drinking temperature, The current liquid temperature measured by the temperature sensor when entering the preparatory state. The rated heating power of the heating circuit; The current liquid mass is estimated based on a reading from a level sensor inside the smart liquid container; The specific heat capacity coefficient value corresponding to the identified liquid type; This is the preset buffer time.

5. The method as described in claim 1, characterized in that, The method further includes: querying the reading of a liquid level sensor installed in the smart liquid container before executing the instruction to drive the heating circuit, and only executing the instruction to drive the heating circuit when the reading of the liquid level sensor indicates that the current liquid level is higher than a preset minimum safe liquid level threshold.

6. The method as described in claim 1, characterized in that, The method further includes: monitoring the attitude and micro-vibrations of the container by an inertial measurement unit installed in the smart liquid container to identify the user's drinking action; when the container tilt angle is detected to exceed a preset tilt angle threshold and lasts for more than a preset time, it is determined to be a valid drinking action.

7. An AI-based adaptive temperature control system for a heated cup, comprising an intelligent liquid container, for executing the method according to any one of claims 1-6, characterized in that, The system includes: A cloud server, which has a built-in schedule parsing module, is used to acquire and parse the user's digital schedule data to predict future drinking and non-drinking windows. The intelligent liquid container includes: A communication module for communicating with the cloud server; Temperature sensor used to monitor the temperature of liquid inside a container; A heating circuit for heating the liquid; The processor is electrically connected to the communication module, the temperature sensor, and the heating circuit, and is configured to... Receive information about the drinking window and non-drinking window sent by the cloud server; The heating circuit is controlled to apply power, and the thermal inertia characteristics of the liquid are calculated based on the temperature data fed back by the temperature sensor to identify the type of liquid. Based on the drinking window, non-drinking window, and identified liquid type, the heating circuit is controlled to enter a low-power mode during the non-drinking window, and before the drinking window is reached, the heating circuit is driven to adjust the liquid temperature to a target drinking temperature that matches the liquid type.

Images