Intelligent electric cooker boiling control method and system based on multi-sensor fusion

Abstract

The embodiment of the invention discloses an intelligent electric cooker boiling control method and system based on multi-sensor fusion, and the control method comprises the steps: adjusting the initial heating power according to a first top temperature, a first bottom temperature and a first heating duration, and controlling the electric cooker to heat according to the adjusted first heating power; establishing a risk assessment system, obtaining a risk score output by the risk assessment system, and comparing the risk score with a preset risk level to obtain a response strategy; and controlling the electric cooker to work according to the response strategy. According to the method, temperature, humidity, sound and other data of different physical sensors are combined, the heating intensity is intelligently adjusted, control is more accurate and intelligent, and the stability of the heating process and the rice quality can be guaranteed.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of smart rice cookers, and in particular to a boiling control method and system for a smart rice cooker based on multi-sensor fusion, an electronic device, and a storage medium. Background Art

[0002] With the continuous advancement of rice cooker technology, traditional rice cooker control methods are becoming increasingly inadequate to meet users' growing demands for precision, intelligence, and high performance. To better control the heating process and improve rice quality, especially during the boiling stage, which is crucial for rice gelatinization, overflow risk, and energy consumption, intelligent control technologies are becoming mainstream.

[0003] Traditional rice cookers typically monitor the temperature inside the pot using simple temperature sensors, controlling heating power based on set temperature thresholds or simply by temperature changes at the top or bottom. This ignores other important factors, such as humidity and sound, and fails to address the varying heating requirements of different rice types and environmental conditions. This approach is prone to several issues: uneven temperature distribution, with significant differences between the bottom and top temperatures, leading to uneven heating within the rice cooker, impacting rice quality, overheating or underheating. Alternatively, the rice cooker may fail to accurately assess actual heating conditions, potentially leading to overheating, resulting in overflow or burning, or uneven heating, resulting in unevenly cooked rice.

[0004] Therefore, the traditional rice cooker control method is in urgent need of improvement, especially the control of the rice cooker during the boiling stage. Summary of the Invention

[0005] In order to overcome the shortcomings of the existing technology, the purpose of the embodiments of the present invention is to provide an intelligent rice cooker boiling control method and system, and electronic equipment based on multi-sensor fusion, which can combine temperature, humidity, sound and other data from different physical sensors to intelligently adjust the heating intensity, making the control more precise and intelligent. By comprehensively analyzing various sensor data to evaluate the current working risk of the rice cooker, the stability of the heating process and the quality of the rice can be guaranteed.

[0006] To solve the above problems, a first aspect of an embodiment of the present invention discloses a boiling control method for an intelligent rice cooker based on multi-sensor fusion, which includes the following steps: When the rice cooker switches from the heating stage to the boiling stage, the rice cooker is heated by a preset initial heating power control, and the first top temperature, the first bottom temperature, the humidity in the pot, the heating time and the sound signal score of the rice cooker are obtained in real time; Adjusting the initial heating power according to the first top temperature, the first bottom temperature, and the first heating time, and controlling the electric rice cooker to heat according to the adjusted first heating power; Establishing a risk assessment system, inputting the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score into the risk assessment system, obtaining a risk score output by the risk assessment system, comparing the risk score with a preset risk level, and obtaining a response strategy; According to the response strategy, the operation of the rice cooker is controlled, and the response strategy includes: maintaining the first heating power, reducing the first heating power to the second heating power, and stopping heating.

[0007] Preferably, the initial heating power is adjusted according to the first top temperature, the first bottom temperature, and the first heating duration, and the electric rice cooker is controlled to heat according to the adjusted first heating power; comprising: Calculate in real time the difference between the top temperature of the rice cooker and the top reference temperature, and the duration of the difference, based on the first top temperature, the first bottom temperature, and the first heating duration; the top reference temperature is the highest value of the top temperature detected in real time during the heating stage of the rice cooker, and the bottom reference temperature is the bottom temperature of the rice cooker at the end of the heating stage; According to the difference between the top temperature and the top reference temperature, the bottom reference temperature is dynamically adjusted, and the difference between the adjusted bottom reference temperature and the current bottom temperature is used as the input of a PID closed-loop controller. The PID closed-loop controller outputs a first heating power, and the rice cooker is controlled to heat according to the first heating power.

[0008] Preferably, the control method further includes: When the electric rice cooker is heated according to the first heating power control, if it is detected that the real-time top temperature is lower than the top reference temperature, and the first duration for which the top temperature is lower than the top reference temperature reaches a first time threshold, an operation of increasing the current heating power is triggered; If it is detected that the top temperature is higher than the top reference temperature, and a second duration of the top temperature being higher than the top reference temperature reaches a second time threshold, an operation of reducing the current heating power is triggered.

[0009] Preferably, the triggering operation of increasing the current heating power or triggering the reduction of the current heating power includes: processing the first heating power through the EMA algorithm to obtain a third heating power, triggering an increase in the third heating power or triggering a reduction in the third heating power, and making the difference between the third heating power after the triggering change and the first heating power within a preset limit.

[0010] Preferably, the control method also includes: setting an initial first time threshold and a second time threshold according to rice characteristics and user preference data, and automatically optimizing the first time threshold and the second time threshold through a DQN model based on the initial first time threshold and the second time threshold, as well as user feedback data.

[0011] Preferably, the risk assessment system is established, the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score are input into the risk assessment system, a risk score is output by the risk assessment system, and the risk score is compared with a preset risk level to obtain a response strategy, including: A risk assessment system is established, which converts the current top temperature, bottom temperature, pot humidity and pot sound signal scores into a top temperature factor, a bottom temperature factor, a pot humidity factor and a sound factor respectively; performs a weighted summation of the top temperature factor, the bottom temperature factor, the pot humidity factor and the sound factor to obtain a risk score; and compares the risk score with a preset risk level to obtain a response strategy.

[0012] Preferably, the sound signal score is obtained by the following steps: The internal sound signals of the rice cooker during the boiling stage are collected in real time, the collected sound signals are framed and windowed, and MFCC feature data is extracted. The MFCC feature data is input into a pre-trained sound recognition model using a convolutional neural network to obtain a sound signal score. The sound signal score is a numerical value between 0 and 1.

[0013] A second aspect of an embodiment of the present invention discloses an intelligent rice cooker boiling control system based on multi-sensor fusion, which includes: an initial unit, configured to control the heating of the rice cooker by using a preset initial heating power when the rice cooker switches from a heating stage to a boiling stage, and to obtain in real time a first top temperature, a first bottom temperature, and a heating time of the rice cooker; an adjusting unit, configured to adjust an initial heating power according to the first top temperature, the first bottom temperature, and the first heating duration, and control heating of the rice cooker according to the adjusted first heating power; an evaluation unit, configured to establish a risk evaluation system, input the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score into the risk evaluation system, obtain a risk score output by the risk evaluation system, compare the risk score with a preset risk level, and obtain a response strategy; The response unit is used to control the operation of the rice cooker according to the response strategy, wherein the response strategy includes: maintaining the first heating power, reducing the first heating power to the second heating power, and stopping heating.

[0014] A third aspect of an embodiment of the present invention discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the intelligent rice cooker boiling control method based on multi-sensor fusion disclosed in the first aspect of the embodiment of the present invention.

[0015] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the intelligent rice cooker boiling control method based on multi-sensor fusion disclosed in the first aspect of an embodiment of the present invention.

[0016] Compared with the prior art, the embodiments of the present invention have the following advantages: When the electric rice cooker switches from the heating stage to the boiling stage, the present invention controls the heating of the electric rice cooker through a preset initial heating power, and obtains in real time a first top temperature, a first bottom temperature, humidity in the pot, a heating time, and a sound signal score of the electric rice cooker; the initial heating power is adjusted according to the first top temperature, the first bottom temperature, and the first heating time, and the heating of the electric rice cooker is controlled according to the adjusted first heating power. The heating power can be automatically adjusted according to the actual working state, and rice quality problems caused by uneven temperature or overheating can be avoided. By integrating data from multiple sensors, the system can more comprehensively evaluate the working state of the electric rice cooker, avoid misjudgment that may be caused by a single data source, and can more accurately control the heating process of the electric rice cooker through comprehensive analysis of data from multiple sensors such as temperature, humidity, and sound. A risk assessment system is established, and the first top temperature, the first bottom temperature, the humidity in the pot and the sound signal score are input into the risk assessment system to obtain a risk score output by the risk assessment system. The risk score is compared with a preset risk level to obtain a response strategy; according to the response strategy, the operation of the rice cooker is controlled, and by real-time monitoring of the status in the pot, safety issues such as overflowing and sticking can be automatically predicted and avoided, thereby improving cooking safety and ensuring the stability of the heating process and the quality of rice.

[0017] Furthermore, the present invention sets an initial first time threshold and a second time threshold according to the characteristics of the rice type and the user preference data. Based on the initial first time threshold and the second time threshold, as well as the user feedback data, the first time threshold and the second time threshold are automatically optimized through the DQN model. The control strategy can be automatically adjusted according to different cooking requirements, rice types, user preferences and user feedback to meet the needs of different users. The continuous dynamic adjustment based on the scoring data of user feedback can improve the taste control accuracy and reduce the risk of overflowing, thereby meeting the cooking needs of users and realizing intelligent control. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 11 is a flow chart of a method for controlling boiling of an intelligent rice cooker based on multi-sensor fusion provided by one embodiment of the present invention; Figure 2 This is a schematic structural diagram of an intelligent rice cooker boiling control system based on multi-sensor fusion provided by one embodiment of the present invention; Figure 3 It is a structural diagram of an electronic device disclosed in one embodiment of the present invention. DETAILED DESCRIPTION

[0019] This specific implementation manner is merely an explanation of an embodiment of the present invention, and it is not a limitation of the embodiment of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the embodiment as needed, but as long as it is within the scope of the claims of the embodiment of the present invention, it is protected by patent law.

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the embodiments of the present invention.

[0021] The term "comprise" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units expressly listed, but may include other steps or units not expressly listed or inherent to such process, method, product or apparatus.

[0022] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0023] Embodiment 1 of the present invention

[0024] Please refer to Figure 1-3 As shown in FIG, a control method of an intelligent rice cooker boiling control system based on multi-sensor fusion is shown. Figure 1 As shown, it includes the following steps: Step S110: When the rice cooker switches from the heating stage to the boiling stage, the rice cooker is heated by controlling the preset initial heating power, and a first top temperature, a first bottom temperature, humidity in the pot, heating time, and a sound signal score of the rice cooker are obtained in real time; In this step, the preset initial heating power can be set to a suitable initial heating power based on experience or factors such as the type of ingredients and the amount of water, such as 600W~800W, as the starting control intensity of the boiling stage. Heating through the initial heating power can ensure that the heat input required for continuous boiling in the pot is quickly reached.

[0025] In this step, data is collected through multi-source sensors, including temperature sensors, humidity sensors, microphones and other sensors.

[0026] In specific implementation, the first top temperature is the temperature of the gas phase area under the lid, the first bottom temperature is the temperature of the contact area of the heating plate, the humidity in the pot is the steam concentration in the rice steaming environment, the heating time refers to the cumulative heating time from switching to the boiling stage, and the sound signal score is the score of the real-time evaluation of the bubble sound through the sound recognition model.

[0027] In this step, by collecting data in real time when the rice cooker switches from the heating stage to the boiling stage, it is possible to quickly respond to changes in the pot and provide a data basis for subsequent intelligent control such as dynamic adjustment of heating power and response strategy.

[0028] Step S120: adjusting the initial heating power according to the first top temperature, the first bottom temperature, and the first heating duration, and controlling the rice cooker to heat according to the adjusted first heating power; In this step, since the first top temperature (T_top) reflects the degree of steam accumulation and indirectly determines whether sufficient boiling is achieved, the first bottom temperature (T_bot) reflects the heating intensity and the risk of sticking the pot, and the first heating time (t) is the accumulated heating time in the boiling stage, which may lead to overheating or water exhaustion if it is too long, the initial heating power can be dynamically corrected by the first top temperature, the first bottom temperature, and the first heating time.

[0029] For example, if the top temperature is continuously lower than the boiling reference temperature (such as 95°C), it means that the boiling is insufficient → increase the power; if the top temperature is continuously high and the bottom temperature is also high for a long time → reduce the power to avoid overflowing or sticking; if it is in the normal range → maintain the current heating power.

[0030] As an embodiment, step 120 may specifically include: Step S1201: according to the first top temperature, the first bottom temperature, the first heating duration, the difference between the top temperature of the electric cooker and the top reference temperature is calculated in real time, and the duration of the difference is present in both; the top reference temperature is the maximum value of the top temperature detected in real time by the electric cooker during the heating stage, and the bottom reference temperature is the bottom temperature of the electric cooker when heating ends; In this step, the highest top temperature detected in real time during the heating stage of the rice cooker is used as the top reference temperature. This avoids dependence on a fixed temperature threshold (such as 95°C) and can adapt to different pots, rice types, water amounts, etc.

[0031] Step S1202: According to the difference between the top temperature and the top reference temperature, the bottom reference temperature is dynamically adjusted, and the difference between the adjusted bottom reference temperature and the current bottom temperature is used as the input of a PID closed-loop controller, and the PID closed-loop controller outputs a first heating power, and controls the rice cooker to heat according to the first heating power.

[0032] In this step, the bottom reference temperature (target value of the bottom temperature) is dynamically corrected by the difference between the top temperature and the top reference temperature, i.e., the top temperature deviation. The bottom reference temperature will change in real time due to the top steam state, making the control system more sensitive.

[0033] For example, if the top temperature is too low, the bottom reference temperature is increased to enhance heating; if the top temperature is too high, the bottom reference temperature is lowered to control heat flow.

[0034] In this step, the difference between the current bottom temperature and the dynamic reference value is used as the input of the PID controller. The PID output power adjusts the heating intensity in real time according to the difference between the actual bottom temperature and the dynamic target bottom reference temperature, thereby achieving precise power control of the rice cooker, avoiding boiling fluctuations and energy waste caused by a fixed temperature target, and avoiding timely power reduction when the top temperature is abnormally high to prevent violent boiling.

[0035] It should be noted that the output of the PID closed-loop controller may also be a heating power control instruction such as an electric heating power percentage, a PWM duty cycle, a current or voltage control value.

[0036] As another embodiment, during specific implementation, step 120 may specifically include: Step S12021: Control the heating of the rice cooker by the difference between the top temperature and the top reference temperature, and the duration of the difference.

[0037] Step S12022: The control strategy is obtained through an AI model, and the AI model adopts an LSTM neural network model. The input of the LSTM neural network model is a time series of the difference between the top temperature and the top reference temperature within a preset time (for example, 5S) (i.e., the top temperature deviation), and the output of the LSTM neural network model is an adjustment amount ΔP for the initial heating power.

[0038] For example, output regulation , .

[0039] The LSTM neural network model automatically learns the mapping between historical top temperature changes and optimal heating power adjustment range, enabling power prediction and adaptive control. During training, the top temperature history can be based on top temperature deviation data from temperature sensor curves collected during multiple cooking processes, while the optimal heating power adjustment range can be based on target power adjustment values set by experts during experiments or generated through empirical rules.

[0040] Preferably, the control method further includes: Step S121: when controlling the electric cooker to heat according to the first heating power, if it is detected that the real-time top temperature is lower than the top reference temperature, and the top temperature is lower than the first duration of the top reference temperature and reaches a first time threshold, then triggering the operation of improving the current heating power; Step S122: If it is detected that the top temperature is higher than the top reference temperature, and the second duration of the top temperature being higher than the top reference temperature reaches a second time threshold, an operation of reducing the current heating power is triggered.

[0041] Specifically, when it is detected that the real-time top temperature is lower than the top reference temperature, and the first duration that the top temperature is lower than the top reference temperature reaches a first time threshold, that is, when the risk of insufficient boiling is detected, power correction is performed; when it is detected that the top temperature is higher than the top reference temperature, and the second duration that the top temperature is higher than the top reference temperature reaches a second time threshold, the operation of reducing the current heating power is triggered to avoid overheating or overflowing in the pot.

[0042] In this step, by dynamically correcting the first heating power, real-time correction can be performed based on the actual state, and the current power can be dynamically adjusted. This can be triggered multiple times and can be executed repeatedly.

[0043] As an embodiment, the triggering of increasing the current heating power operation or triggering of decreasing the current heating power operation includes: After the first heating power is processed by the EMA algorithm, a third heating power is obtained, which triggers an increase in the third heating power or a decrease in the third heating power, and ensures that the difference between the third heating power after the trigger change and the first heating power is within a preset limit.

[0044] In this step, the first heating power is processed by the EMA (Exponential Moving Average) algorithm and used as the actual control power, i.e., the third heating power. Then, when the trigger conditions of step S121 and step S122 are met, the change of the third heating power is triggered to avoid the PID control or judgment logic output changing too quickly, which causes the power to jump up and down frequently. At the same time, a preset limit constraint is set to trigger the difference between the third heating power and the first heating power after the change, to prevent overheating or burning of the pot due to excessive adjustment.

[0045] Step S130: Establish a risk assessment system, input the first top temperature, the first bottom temperature, the humidity in the pot and the sound signal score into the risk assessment system, obtain a risk score output by the risk assessment system, compare the risk score with the preset risk level, and obtain a response strategy.

[0046] In this step, by establishing a risk assessment system, a multi-sensor comprehensive assessment is conducted in real time during the operation of the rice cooker to assess abnormal risks in the pot, such as excessive boiling, overflowing, and dry burning. The risk score is then output, and a response strategy is obtained to enable control intervention in advance.

[0047] The risk assessment system converts the current top temperature, bottom temperature, pot humidity, and pot sound signal scores into risk contribution factors for assessing the risk of the rice cooker boiling over, burning dry, or otherwise abnormal. Specifically, the current top temperature, bottom temperature, pot humidity, and pot sound signal scores are mapped into a standardized score between 0 and 1 for use in risk assessment.

[0048] The risk contribution items include a top temperature factor, a bottom temperature factor, a pot humidity factor, and a sound factor; a weighted sum of the top temperature factor, the bottom temperature factor, the pot humidity factor, and the sound factor is performed to obtain a risk score.

[0049] Specifically, the top temperature factor ; Where T_top is the current top temperature measured in real time; T_top_thresh is the starting threshold of the top temperature score, below which no score is generated; T_top_range is the linear range of the temperature score, usually ; F_top is the normalized top temperature score, ranging from [0, 1], where T_top_thresh can be 95℃.

[0050] For example, the current top temperature is 96°C, the top temperature factor The current top temperature is 93℃, the top temperature factor .

[0051] Bottom temperature factor ; Where F_bot is the current bottom temperature measured in real time; T_bot_thresh is the bottom temperature threshold; T_bot_range is the denominator of the normalized temperature deviation, such as the maximum allowable overtemperature range of 10°C; and F_bot is the normalized top temperature score, ranging from [0 to 1].

[0052] For example, the current bottom temperature is 140, T_bot_thresh is 135, .

[0053] Humidity factor F_humid = dH / dt or humidity surge, where dH / dt is the rate of change of humidity.

[0054] The sound factor can be directly scored using sound signals.

[0055] Specifically, the sound signal score is obtained by the following steps: The internal sound signals of the rice cooker during the boiling stage are collected in real time, the collected sound signals are framed and windowed, and MFCC feature data is extracted. The MFCC feature data is input into a pre-trained sound recognition model using a convolutional neural network to obtain a sound signal score. The sound signal score is a numerical value between 0 and 1.

[0056] During data collection, a built-in microphone, such as a MEMS microphone or other highly sensitive audio sensor, can be used to capture real-time sound signals such as bubbling, popping, and steaming sounds inside the rice cooker. MFCC features effectively capture the audio signal's voice characteristics, timbre, pitch, and other information. In this embodiment, they can help distinguish different boiling sounds. For example, bubbling sounds indicate normal boiling; popping sounds indicate overboiling, potentially leading to overflowing; and silence indicates dry boiling, requiring immediate power reduction.

[0057] The sound recognition model uses a convolutional neural network (CNN) as input, with the extracted MFCC feature data. Each frame of MFCC data is fed into the CNN as a feature vector. During model training, different types of rice cooker sound data are collected and labeled, including normal bubbling sounds, overflowing sounds, and popping sounds. The training data labels are: 0 for normal and 1 for abnormal sounds (overflowing, dry cooking, etc.).

[0058] The output value of the sound recognition model is the sound signal score at that moment, ranging from 0 to 1, indicating the degree of abnormality of the sound signal. For example, S = 0.1 indicates a normal bubbling sound, and S = 0.8 indicates a strong popping sound.

[0059] In this step, the risk assessment system converts the first top temperature, the first bottom temperature, the humidity inside the pot, and the sound signal into risk contribution terms for "boiling over / dry burning / anomaly", and then obtains a response strategy by comparing with a preset risk level.

[0060] Specifically, the risk assessment system is a linear weighted model.

[0061] Step S1302: Perform weighted summation on the top temperature factor, the bottom temperature factor, the humidity factor inside the pot, and the sound factor to obtain a risk score. Specifically, the risk score R satisfies the following formula: ; where the risk score output R ∈ [0.0, 1.0], and the weights w1, w2, w3, and w4 are the weights of the top temperature factor, the bottom temperature factor, the humidity factor inside the pot, and the sound factor respectively.

[0062] Step S1303: Compare the risk score with the preset risk level to obtain a response strategy.

[0063] In specific implementation, the correspondence between the risk score, the preset risk level, and the response strategy can be set as follows: When the risk score R < 0.3, it is determined as a low risk, and the response strategy is: maintain the first heating power; When the risk score 0.3 < R < 0.6, it is determined as a medium risk, and the response strategy is: reduce the first heating power to the second heating power; When the risk score R ≥ 0.6, it is determined as a high risk, and the risk of overflowing or burning of the pot is obvious, and the response strategy is: stop heating.

[0064] Step S140: Control the rice cooker to work according to the response strategy, and the response strategy includes: maintaining the first heating power, reducing the first heating power to the second heating power, and stopping heating.

[0065] In the above implementation process, by responding in a timely manner after scoring by the risk assessment system, risks such as "overheating", "boiling over", and "dry burning" in the boiling stage can be predicted and addressed in real time, avoiding bottom paste or water loss caused by overheating, thereby improving system safety and user satisfaction, and enhancing the intelligence and controllability of the rice cooker.

[0066] As another embodiment, the control method of the present invention further includes: Step S150: Set an initial first time threshold and a second time threshold according to the rice variety characteristics and user preference data, and automatically optimize the first time threshold and the second time threshold through a DQN model according to the initial first time threshold, the second time threshold, and the user feedback data.

[0067] In a specific implementation, when the top temperature is lower than the top reference temperature for a duration exceeding a first time threshold, the power is increased to promote stronger boiling. When the top temperature is higher than the reference temperature for a duration exceeding a second time threshold, the power is reduced to prevent overflow or burning of the pot.

[0068] By setting the first time threshold and the second time threshold, it is possible to avoid erroneous responses to short-term temperature disturbances, such as water vapor disturbances and misreadings. After setting the thresholds, a response will only be made if the temperature difference persists for a period of time, thereby promoting stronger boiling.

[0069] During the initial settings, different first time thresholds and second time thresholds can be set according to different rice types or different user taste preferences, so that the rice cooker can better adapt to the characteristics of different rice types and meet the taste requirements of different users.

[0070] For example, Thai fragrant rice is slightly harder and evaporates slowly, so the first time threshold can be set to 6 to 9 seconds, and the second time threshold can be set to 3 to 4 seconds. Brown rice gelatinizes slowly and requires a longer boiling time, so the first time threshold can be set to 10 to 12 seconds, and the second time threshold can be set to 4 to 5 seconds.

[0071] In this step, after the user uses the rice cooker multiple times, the first time threshold and the second time threshold can be automatically optimized by the DQN model based on the initial first time threshold and the second time threshold, as well as the user feedback data, so that the rice cooker "becomes smarter the more it cooks", which specifically includes the following: Step S1501: A DQN (enhanced Q network) model is established and trained. The DQN (enhanced Q network) model inputs a state vector and outputs a reward Q value corresponding to each possible action.

[0072] The state space S of the DQN (enhanced Q network) model is the temperature control characteristics such as temperature, humidity, heating time, rice type, water-rice ratio data collected by the current sensor, and the action space A is the combination of the first time threshold T1 and the second time threshold T2, such as the first time threshold , the second time threshold The reward function R is based on user ratings and safety feedback. For example, the higher the rice taste score, the higher the reward. If the rice overflows or burns dry, a large negative reward, such as -6 points, is given. For example, if the user scores 8 points and there is no overflow or dry burning, the reward is 10 points.

[0073] Step S1502: Each time the user turns on the machine to cook, the state S is obtained and the optimal action a is selected: that is, the recommended combination of the first time threshold T1 and the second time threshold T2. After the cooking is completed, the user feedback data is obtained and stored. The DQN model is continuously trained and updated, and the strategy is updated after each cooking.

[0074] Example 2

[0075] The embodiment of the present invention discloses an intelligent rice cooker boiling control system based on multi-sensor fusion, such as Figure 2 As shown, Figure 2 It is an intelligent rice cooker boiling control system based on multi-sensor fusion, including: A second aspect of an embodiment of the present invention discloses an intelligent rice cooker boiling control system based on multi-sensor fusion, which includes: The initial unit 210 is used to control the heating of the rice cooker by a preset initial heating power when the rice cooker switches from the heating stage to the boiling stage, and obtain a first top temperature, a first bottom temperature, and a heating time of the rice cooker in real time; an adjusting unit 220, configured to adjust an initial heating power according to the first top temperature, the first bottom temperature, and the first heating duration, and control heating of the rice cooker according to the adjusted first heating power; An evaluation unit 230 is configured to establish a risk assessment system, input the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score into the risk assessment system, obtain a risk score output by the risk assessment system, compare the risk score with a preset risk level, and obtain a response strategy; The response unit 240 is used to control the operation of the rice cooker according to the response strategy, and the response strategy includes: maintaining the first heating power, reducing the first heating power to the second heating power, and stopping heating.

[0076] Furthermore, the evaluation unit 230 includes: A factor unit is used to establish a risk assessment system, wherein the risk assessment system converts the current top temperature, bottom temperature, pot humidity and pot sound signal scores into a top temperature factor, a bottom temperature factor, a pot humidity factor and a sound factor respectively; A calculation unit, used to perform weighted summation of the top temperature factor, the bottom temperature factor, the pot humidity factor, and the sound factor to obtain a risk score; The strategy unit is used to compare the risk score with the preset risk level and obtain a response strategy.

[0077] Example 3

[0078] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Figure 3 As shown, the electronic device may include: A memory 310 storing executable program code; a processor 320 coupled to the memory 310; The processor 320 calls the executable program code stored in the memory 310 to execute part or all of the steps in the boiling control method of an intelligent rice cooker based on multi-sensor fusion in Example 1.

[0079] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute some or all of the steps in a method for controlling boiling of an intelligent rice cooker based on multi-sensor fusion in embodiment 1.

[0080] An embodiment of the present invention further discloses a computer program product, wherein when the computer program product is run on a computer, the computer is caused to execute some or all of the steps in the intelligent rice cooker boiling control method based on multi-sensor fusion in embodiment one.

[0081] An embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product. When the computer program product is run on a computer, the computer executes some or all of the steps in the intelligent rice cooker boiling control method based on multi-sensor fusion in Example 1.

[0082] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the processes does not necessarily mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0083] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the objectives of this embodiment as needed.

[0084] In addition, the functional units in the embodiments of the present invention may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The integrated unit may be implemented in the form of hardware or software functional units.

[0085] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several requests for causing a computer device (which can be a personal computer, server, or network device, specifically a processor in the computer device) to execute some or all of the steps of the method described in various embodiments of the present invention.

[0086] In the embodiments provided herein, it should be understood that "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information.

[0087] Those skilled in the art will appreciate that some or all of the steps in the various methods of the embodiments may be performed by instructing related hardware through a program. The program may be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0088] The above is a detailed introduction to the control method, device, electronic device and storage medium of an intelligent rice cooker boiling control system based on multi-sensor fusion disclosed in an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for controlling boiling of an intelligent rice cooker based on multi-sensor fusion, characterized in that: It includes the following: When the rice cooker switches from the heating stage to the boiling stage, the rice cooker is heated by a preset initial heating power control, and the first top temperature, the first bottom temperature, the humidity in the pot, the heating time and the sound signal score of the rice cooker are obtained in real time; Adjusting the initial heating power according to the first top temperature, the first bottom temperature, and the first heating time, and controlling the electric rice cooker to heat according to the adjusted first heating power; Establishing a risk assessment system, inputting the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score into the risk assessment system, obtaining a risk score output by the risk assessment system, comparing the risk score with a preset risk level, and obtaining a response strategy; According to the response strategy, the operation of the rice cooker is controlled, and the response strategy includes: maintaining the first heating power, reducing the first heating power to the second heating power, and stopping heating.

2. The intelligent rice cooker boiling control method based on multi-sensor fusion according to claim 1, characterized in that: The method comprises: adjusting the initial heating power according to the first top temperature, the first bottom temperature, and the first heating time, and controlling the heating of the rice cooker according to the adjusted first heating power; comprising: Calculate in real time the difference between the top temperature of the rice cooker and the top reference temperature, and the duration of the difference, based on the first top temperature, the first bottom temperature, and the first heating duration; the top reference temperature is the highest value of the top temperature detected in real time during the heating stage of the rice cooker, and the bottom reference temperature is the bottom temperature of the rice cooker at the end of the heating stage; According to the difference between the top temperature and the top reference temperature, the bottom reference temperature is dynamically adjusted, and the difference between the adjusted bottom reference temperature and the current bottom temperature is used as the input of a PID closed-loop controller. The PID closed-loop controller outputs a first heating power, and the rice cooker is controlled to heat according to the first heating power.

3. The intelligent rice cooker boiling control method based on multi-sensor fusion according to claim 2, characterized in that: Also includes: When the electric rice cooker is heated according to the first heating power control, if it is detected that the real-time top temperature is lower than the top reference temperature, and the first duration for which the top temperature is lower than the top reference temperature reaches a first time threshold, an operation of increasing the current heating power is triggered; If it is detected that the top temperature is higher than the top reference temperature, and a second duration of the top temperature being higher than the top reference temperature reaches a second time threshold, an operation of reducing the current heating power is triggered.

4. The intelligent rice cooker boiling control method based on multi-sensor fusion according to claim 3, characterized in that: The triggering operation of increasing the current heating power or triggering the reduction of the current heating power includes: processing the first heating power through the EMA algorithm to obtain a third heating power, triggering an increase in the third heating power or triggering a reduction in the third heating power, and making the difference between the third heating power after the triggering change and the first heating power within a preset limit.

5. The intelligent rice cooker boiling control method based on multi-sensor fusion according to claim 3 is characterized in that: Also includes: According to the characteristics of the rice and user preference data, an initial first time threshold and a second time threshold are set, and according to the initial first time threshold and the second time threshold, and the user feedback data, the first time threshold and the second time threshold are automatically optimized through the DQN model.

6. The intelligent rice cooker boiling control method based on multi-sensor fusion according to claim 1, characterized in that: The risk assessment system is established, and the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score are input into the risk assessment system to obtain a risk score output by the risk assessment system, including: A risk assessment system is established, which converts the current top temperature, bottom temperature, humidity in the pot and sound signal scores in the pot into risk contribution items for assessing the risk of the rice cooker boiling over, drying out or being abnormal. The risk contribution items include the top temperature factor, the bottom temperature factor, the humidity in the pot factor and the sound factor; the top temperature factor, the bottom temperature factor, the humidity in the pot factor and the sound factor are weighted and summed to obtain a risk score.

7. The intelligent rice cooker boiling control method based on multi-sensor fusion according to claim 1, characterized in that: The sound signal score is obtained by the following steps: The internal sound signals of the rice cooker during the boiling stage are collected in real time, the collected sound signals are framed and windowed, and MFCC feature data is extracted. The MFCC feature data is input into a pre-trained sound recognition model using a convolutional neural network to obtain a sound signal score. The sound signal score is a numerical value between 0 and 1.

8. An intelligent rice cooker boiling control system based on multi-sensor fusion, characterized in that: It includes: an initial unit, configured to control the heating of the rice cooker by using a preset initial heating power when the rice cooker switches from a heating stage to a boiling stage, and to obtain in real time a first top temperature, a first bottom temperature, and a heating time of the rice cooker; an adjusting unit, configured to adjust an initial heating power according to the first top temperature, the first bottom temperature, and the first heating duration, and control heating of the rice cooker according to the adjusted first heating power; an evaluation unit, configured to establish a risk evaluation system, input the first top temperature, the first bottom temperature, the humidity in the pot, and the sound signal score into the risk evaluation system, obtain a risk score output by the risk evaluation system, compare the risk score with a preset risk level, and obtain a response strategy; The response unit is used to control the operation of the rice cooker according to the response strategy, wherein the response strategy includes: maintaining the first heating power, reducing the first heating power to the second heating power, and stopping heating.

9. An electronic device, characterized in that: It includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the intelligent rice cooker boiling control method based on multi-sensor fusion according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that It stores a computer program, wherein the computer program enables a computer to execute the intelligent rice cooker boiling control method based on multi-sensor fusion according to any one of claims 1 to 7.

Images