CN111207560A - Refrigerator behavior control method and device based on machine learning and refrigerator - Google Patents
Refrigerator behavior control method and device based on machine learning and refrigerator Download PDFInfo
- Publication number
- CN111207560A CN111207560A CN201911373659.0A CN201911373659A CN111207560A CN 111207560 A CN111207560 A CN 111207560A CN 201911373659 A CN201911373659 A CN 201911373659A CN 111207560 A CN111207560 A CN 111207560A
- Authority
- CN
- China
- Prior art keywords
- refrigerator
- behavior
- time
- machine learning
- predicted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000006399 behavior Effects 0.000 title claims abstract description 148
- 238000010801 machine learning Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 description 7
- 238000001816 cooling Methods 0.000 description 5
- 238000007710 freezing Methods 0.000 description 5
- 230000008014 freezing Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000000630 rising effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000009246 food effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/003—Arrangement or mounting of control or safety devices for movable devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2600/00—Control issues
- F25D2600/06—Controlling according to a predetermined profile
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Combustion & Propulsion (AREA)
- Devices That Are Associated With Refrigeration Equipment (AREA)
Abstract
The invention discloses a refrigerator behavior control method and device based on machine learning and a refrigerator, wherein the method comprises the following steps: acquiring the current time of the refrigerator; inputting the current time into a refrigerator behavior prediction model, and outputting identification information of a predicted behavior, wherein the refrigerator behavior prediction model is obtained by training based on a machine learning algorithm according to operation data of each historical time point of the refrigerator; and controlling the refrigerator to perform a behavior corresponding to the predicted behavior according to the identification information of the predicted behavior. Compared with the prior art, the refrigerator behavior control method based on machine learning establishes a refrigerator behavior prediction model based on machine learning according to statistics of operation data of the refrigerator at each historical time point, predicts the refrigerator behavior, and controls the refrigerator according to the predicted behavior, so that the refrigerator provides humanized service for users, and the refrigerator is more energy-saving and efficient to operate.
Description
Technical Field
The invention relates to the field of household appliance control, in particular to a refrigerator behavior control method and device based on machine learning and a refrigerator.
Background
At present, most of functions of traditional household appliances such as refrigerators need manual operation, such as switching to an intelligent mode or a holiday mode, adjusting the temperature of the refrigerators, connecting wifi and the like. With the development of the refrigerator, the functions of the refrigerator are more and more complex, which is not beneficial to the user experience.
Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning has been applied in a number of technical areas,
how to use machine learning on the refrigerator makes the refrigerator can provide more humanized service for the user, lets the user obtain better experience, and the refrigerator self can be more intelligent simultaneously, is the problem that we need solve at present stage.
Disclosure of Invention
The invention aims to provide a refrigerator behavior control method and device based on machine learning and a refrigerator.
In order to achieve one of the above objects, an embodiment of the present invention provides a refrigerator behavior control method based on machine learning, the method including:
acquiring the current time of the refrigerator;
inputting the current time into a refrigerator behavior prediction model, and outputting identification information of a predicted behavior, wherein the refrigerator behavior prediction model is obtained by training based on a machine learning algorithm according to operation data of each historical time point of the refrigerator;
and controlling the refrigerator to perform a behavior corresponding to the predicted behavior according to the identification information of the predicted behavior.
As a further improvement of an embodiment of the present invention, the method further includes establishing the refrigerator behavior prediction model, where the "establishing the refrigerator behavior prediction model" specifically includes:
acquiring running data of the refrigerator at each time point in a plurality of sampling periods according to the set sampling period to obtain a running parameter set;
preprocessing the operation parameter set to obtain a training sample set;
and establishing a refrigerator behavior prediction model according to the training sample set.
As a further improvement of an embodiment of the present invention, the "establishing the refrigerator behavior prediction model" specifically further includes:
and judging whether the refrigerator behavior prediction model needs to be corrected or not according to the difference between the predicted behavior of the refrigerator behavior prediction model and the actual behavior of the refrigerator, if so, adding the operation data of the actual behavior occurrence time point of the refrigerator into the operation parameter set according to the weight, preprocessing the operation parameter set again to obtain a new training sample set, and correcting the refrigerator behavior prediction model according to the new training sample set.
As a further improvement of an embodiment of the present invention, the operation data at each time point refers to a door opening time, a door opening duration, a WIFI opening time, an operation duration, a compartment temperature at each time point, and an ambient temperature of the refrigerator.
As a further improvement of an embodiment of the present invention, the "controlling the refrigerator to perform the behavior corresponding to the predicted behavior according to the identification information" specifically includes:
if the predicted behavior is that the refrigerator door is opened, the identification information comprises the time and duration for opening the refrigerator door;
and selecting a gear for pre-refrigerating the refrigerator and the pre-refrigerating time according to the time and duration for opening the refrigerator door, and controlling the refrigerator to pre-refrigerate when the pre-refrigerating time is reached.
As a further improvement of an embodiment of the present invention, the method further comprises:
and calculating the time difference between the opening time of the refrigerator door and the current time, and controlling the refrigerator to enter an energy-saving operation mode in the time difference if the time difference is greater than a first preset time length.
As a further improvement of an embodiment of the present invention, the "controlling the refrigerator to perform the behavior corresponding to the predicted behavior according to the identification information" specifically includes:
if the predicted behavior is to adjust the compartment temperature of the refrigerator, the identification information comprises adjusted time and temperature value, and the compartment temperature of the refrigerator is set to be the adjusted temperature value by controlling the adjusted time.
As a further improvement of an embodiment of the present invention, the method further comprises:
the identification information of the predicted behavior comprises the occurrence time of the predicted behavior, and the time difference between the occurrence time of the predicted behavior and the current time is calculated;
and if the time difference is greater than a second preset time length, controlling the WIFI function of the refrigerator to enter a sleep mode within the time difference.
In order to achieve one of the above objects, an embodiment of the present invention provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program operable on the processor, and the processor implements the steps of any one of the above refrigerator behavior control methods based on machine learning when executing the program.
In order to achieve one of the above objects, an embodiment of the present invention provides a refrigerator, which includes the electronic device.
Compared with the prior art, the refrigerator behavior control method based on machine learning establishes a refrigerator behavior prediction model based on machine learning according to statistics of operation data of the refrigerator at each historical time point, predicts the refrigerator behavior, and controls the refrigerator according to the predicted behavior, so that the refrigerator provides humanized service for users, and the refrigerator is more energy-saving and efficient to operate.
Drawings
Fig. 1 is a flow chart of the refrigerator behavior control method based on machine learning according to the present invention.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to these embodiments are included in the scope of the present invention.
After long-time research and big data analysis based on user operation data statistics, the operation of the user is found to have certain regularity in a certain period. For example, a user can open a refrigerator at 6 o' clock in the evening from Monday to Friday to store food materials, and then adjust the temperature of a freezing chamber to-16 ℃; or a user may use the functionality of WiFi or other intelligent modules during the day, but not at night; and so on.
Based on the cognition, the refrigerator behavior control method based on machine learning is provided, and the refrigerator behavior prediction method based on machine learning is established according to statistics of operation data of the refrigerator at each historical time point, predicts the refrigerator behavior, and controls the refrigerator according to the predicted behavior, so that the refrigerator provides humanized service for users, and meanwhile, the refrigerator is more energy-saving and efficient to operate. As shown in fig. 1, the method of the present invention comprises:
step S100: the current time of the refrigerator is acquired.
The current time of the refrigerator is used as an input of a refrigerator prediction model, and is preferably acquired when the refrigerator is in an idle state. The refrigerator is in an idle state, which means that the refrigerator has completed the operation corresponding to the last predicted action, but has not obtained the next predicted action.
Step S200: and inputting the current time into a refrigerator behavior prediction model, and outputting identification information of the predicted behavior, wherein the refrigerator behavior prediction model is obtained by training based on a machine learning algorithm according to the operation data of the refrigerator at each historical time point.
In this step, the next behavior of the refrigerator is predicted by inputting the current time to the refrigerator behavior prediction model, and the identification information includes information related to the next behavior, for example, what is the next behavior? The time of the next action, etc.
The refrigerator behavior prediction model can predict the next behavior of the refrigerator according to the current time of the refrigerator. The model is obtained by training based on a machine learning algorithm according to historical operating data of each time point of the refrigerator, and the specific establishing process comprises the following steps:
step S210: and acquiring the running data of the refrigerator at each time point in a plurality of sampling periods according to the set sampling period to obtain a running parameter set.
The sampling period can be day, week, month, season, year, etc., and preferably the sampling period is week. The operation data at each time point may include: the refrigerator control system comprises the refrigerator control system and the control method thereof, wherein the refrigerator control system comprises the refrigerator control system and the control method thereof, and the refrigerator control system comprises the door opening time, the door opening duration, the opening time of WIFI and other intelligent modules (such as a voice recognition function, an image recognition function, a menu recommendation function and the like), the running duration, the compartment temperature at each time point, the ambient temperature and the like.
It should be noted that the operation data at each time point obtained in the sampling period is the operation data at each time point of the nearest refrigerator, and may be, for example, historical basic operation data of the nearest week, the nearest month, the nearest three months, or the nearest half year, which is closer to the current operation time, so as to improve the prediction accuracy of the refrigerator behavior prediction model, and enable the refrigerator behavior prediction model to more accurately predict the next behavior of the refrigerator.
Step S220: and preprocessing the operation parameter set to obtain a training sample set.
The preprocessing refers to classifying and sorting the parameters in the operation parameter set, and preprocessing to obtain a training sample set.
The classification of the parameters is based on the refrigerator behavior and the time when the behavior occurs, and is a classification of the action and the time which need to be predicted. For example, for the time period of 7 am to 30 am to 8 am every monday, the refrigerator door is opened, the time for which the refrigerator door is opened in the time period can be classified into a category, and then the parameters of the category are preprocessed.
The preprocessing includes that the average value and the standard deviation sigma of each classified parameter, the deviation delta α between each parameter and the corresponding average value and the like are obtained, samples with the deviation exceeding the threshold value are removed according to the comparison of the deviation delta α and the deviation threshold value delta α max, the average value and the standard deviation are calculated again, whether the classification is reasonable or not is judged according to the standard deviation sigma, if the classification is not reasonable, the classification is carried out again, the preprocessing is carried out on the parameters of each class, and a training sample set is obtained.
Step S230: and establishing a refrigerator behavior prediction model according to the training sample set.
When the refrigerator behavior prediction model is generated based on machine learning algorithm training, generally, operation data of each time point of historical behaviors of a refrigerator is used as sample input data, identification information of predicted behaviors is used as sample output data, an initial machine learning model is trained until a model convergence condition is met, and then the refrigerator behavior prediction model is generated. In this embodiment, a CNN or RNN machine learning model may be employed for model training.
In a preferred embodiment, the refrigerator behavior prediction model is continuously modified by the latest training data to improve the prediction accuracy, so that the next behavior of the refrigerator and the time when the next behavior occurs can be predicted more accurately.
The correction method specifically comprises the following steps: and judging whether the refrigerator behavior prediction model needs to be corrected or not according to the difference between the predicted behavior of the refrigerator behavior prediction model and the actual behavior of the refrigerator, if so, adding the operation data of the actual behavior occurrence time point of the refrigerator into the operation parameter set according to the weight, preprocessing the operation parameter set again to obtain a new training sample set, and correcting the refrigerator behavior prediction model according to the new training sample set.
In a specific embodiment, first, according to the current behavior of the refrigerator, the current time is collected as the collected sample data, which category the currently collected sample belongs to is judged to belong to in the sample library, after the corresponding category is found, the time deviation of the sample from the predicted value (parameter corresponding to the predicted behavior of the refrigerator behavior prediction model) of the category is judged, if the time deviation is within the deviation threshold range, the sample is added into the category corresponding to the sample library in a coupling mode of a weighting coefficient β, at the moment, if the data volume of the sample library of the category exceeds the threshold, the sample with the largest deviation in the sample library is deleted, if the time deviation is greater than the deviation threshold, the currently collected sample is judged not to meet the precision requirement in the sample library, the sample is added into the category corresponding to the sample library in a coupling mode of a weighting coefficient gamma, at the moment, if the data volume of the sample library of the category exceeds the threshold, the sample with the largest deviation from the collected sample in the sample library is deleted, the weighting coefficient β and the weighting coefficient gamma can be adjusted according to the actual situation.
And if the currently collected sample does not belong to any one of the categories in the sample library, creating a new category, and adding the collected sample into the category.
It should be noted that if no predicted refrigerator behavior occurs, one sample in the category corresponding to this behavior and time (the sample may be a sample with the maximum deviation) is deleted.
It should be noted that when the sample size of a certain category does not meet the minimum requirement, the behavior of the category is not predicted.
Step S300: and controlling the refrigerator to perform a behavior corresponding to the predicted behavior according to the identification information of the predicted behavior.
The identification information of the predicted behavior is used for identifying the impending behavior of the refrigerator and predicting the time of the occurrence of the behavior. And controlling the refrigerator to perform a behavior corresponding to the predicted behavior according to the identification information of the predicted behavior, namely controlling the refrigerator to be matched with the behavior to be generated when a certain behavior of the refrigerator is predicted to be generated, so that the refrigerator can be more energy-saving and efficient, or more humanized service can be provided for a user, or better experience is brought to the user, and the like.
In a specific embodiment, the "controlling the refrigerator to perform the behavior corresponding to the predicted behavior according to the identification information" specifically includes:
if the predicted behavior is that the refrigerator door is opened, the identification information comprises the time and duration for opening the refrigerator door;
and selecting a gear for pre-refrigerating the refrigerator and the pre-refrigerating time according to the time and duration for opening the refrigerator door, and controlling the refrigerator to pre-refrigerate when the pre-refrigerating time is reached.
Under normal conditions, after the refrigerator door is opened, the temperature of the compartment rapidly rises, the temperature fluctuation of the compartment is large, the fresh-keeping effect of food materials stored in the compartment is influenced, particularly the food materials sensitive to the temperature are high, the temperature rise in the compartment is high, and the food materials are easy to rot and deteriorate. When the refrigerator is pre-cooled before the refrigerator door is opened, the temperature of the compartment can rise slowly, the temperature fluctuation of the compartment is small, and the influence on the fresh-keeping effect of food materials stored in the compartment is small. In addition, the opening duration of the refrigerator door is in direct proportion to the room temperature rising degree, namely the longer the opening duration is, the more the room temperature rising degree is, and the room temperature rising degree is equal to the ambient temperature, so that the corresponding prefabricated cold gear can be selected according to the predicted duration for opening the refrigerator door, the longer the duration is, the higher the prefabricated cold gear is, and the more the refrigerating capacity is. The pre-cooling time precedes the predicted time of the predicted behavior, and may be, for example, 10 minutes, 15 minutes, etc. in advance. Therefore, for different opening time lengths of the refrigerator door, the same pre-cooling gear can be selected to start pre-cooling at different pre-cooling starting times, for example, when the refrigerator door is predicted to be opened for a longer time, the pre-cooling is selected to be performed relatively earlier.
In addition, when the refrigerator is precooled, the rotating speed of the compressor of the refrigerator is slowly increased, and compared with the condition that the rotating speed of the compressor of the refrigerator is suddenly increased when the refrigerator is not precooled, the slowly increased rotating speed can prolong the service life of the compressor.
It should be noted that the time difference between the starting time and the current time can be calculated by acquiring the next starting time of the refrigerator door, and if the time difference is greater than a first preset time, the refrigerator is controlled to enter an energy-saving operation mode within the time difference. For example, the current time is 10 o 'clock at night, the next time the door of the refrigerator is opened is predicted to be 8 o' clock in the next morning, and the refrigerator can be controlled to be in an energy-saving operation mode in the middle, so that the mode can provide enough fresh keeping for food and saves electricity at most.
In another specific embodiment, the "controlling the refrigerator to perform the behavior corresponding to the predicted behavior according to the identification information" specifically includes:
if the predicted behavior is to adjust the compartment temperature of the refrigerator, the identification information comprises adjusted time and temperature value, and the compartment temperature of the refrigerator is set to be the adjusted temperature value by controlling the adjusted time. For example, through a refrigerator behavior prediction model, the temperature of the freezing chamber of the refrigerator is predicted to be adjusted to-16 degrees at 7 pm on friday nights (generally, a user purchases more food materials in the period, and the temperature of the freezing chamber of the refrigerator is adjusted to be low for quick freezing), the refrigerator is controlled to adjust the freezing chamber to-16 degrees at the time, the workload of the user can be saved, and more humanized services and better experience can be provided for the user.
In a preferred embodiment, the method further comprises: the identification information of the predicted behavior comprises the occurrence time of the predicted behavior, and the time difference between the occurrence time of the predicted behavior and the current time is calculated;
and if the time difference is greater than a second preset time length, controlling the WIFI function of the refrigerator to enter a sleep mode within the time difference.
The second preset duration can be several hours, so that the WIFI can enter a sleep mode after the user has a rest at night or when the user is out of work at daytime, or the WIFI can be turned off. It should be noted that, besides controlling the refrigerator WIFI to be turned on and enter the sleep mode, the refrigerator WIFI may also be controlled to be turned on, turned off or enter the sleep mode according to the user habit, so as to save the workload of the user, save the electric energy of the refrigerator, and provide more humanized service and better experience for the user.
According to the refrigerator behavior control method based on machine learning, the refrigerator behavior prediction model based on machine learning is established according to statistics of operation data of the refrigerator at each historical time point, the refrigerator behavior is predicted, and the refrigerator is controlled according to the predicted behavior, so that the refrigerator provides humanized service for users, and meanwhile, the refrigerator is more energy-saving and efficient to operate. After the refrigerator is learned for a period of time, self-adaptation to the surrounding environment and manual operation can be achieved.
The invention further provides an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor executes the program to realize any one of the steps of the refrigerator behavior control method based on the machine learning, namely, the steps of any one of the technical schemes of the refrigerator behavior control method based on the machine learning.
The invention further provides a refrigerator which comprises the electronic device.
It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A refrigerator behavior control method based on machine learning, the method comprising:
acquiring the current time of the refrigerator;
inputting the current time into a refrigerator behavior prediction model, and outputting identification information of a predicted behavior, wherein the refrigerator behavior prediction model is obtained by training based on a machine learning algorithm according to operation data of each historical time point of the refrigerator;
and controlling the refrigerator to perform a behavior corresponding to the predicted behavior according to the identification information of the predicted behavior.
2. The refrigerator behavior control method based on machine learning of claim 1, further comprising building the refrigerator behavior prediction model, wherein building the refrigerator behavior prediction model specifically comprises:
acquiring running data of the refrigerator at each time point in a plurality of sampling periods according to the set sampling period to obtain a running parameter set;
preprocessing the operation parameter set to obtain a training sample set;
and establishing a refrigerator behavior prediction model according to the training sample set.
3. The refrigerator behavior control method based on machine learning according to claim 2, wherein the "establishing the refrigerator behavior prediction model" further comprises:
and judging whether the refrigerator behavior prediction model needs to be corrected or not according to the difference between the predicted behavior of the refrigerator behavior prediction model and the actual behavior of the refrigerator, if so, adding the operation data of the actual behavior occurrence time point of the refrigerator into the operation parameter set according to the weight, preprocessing the operation parameter set again to obtain a new training sample set, and correcting the refrigerator behavior prediction model according to the new training sample set.
4. The machine learning-based refrigerator behavior control method according to claim 2, wherein:
the operation data of each time point refers to the door opening time and the door opening time of the refrigerator, the opening time and the operation time of the WIFI, and the room temperature and the environment temperature of each time point.
5. The refrigerator behavior control method based on machine learning according to claim 1, wherein the "controlling the refrigerator to perform the behavior corresponding to the predicted behavior according to the identification information" specifically includes:
if the predicted behavior is that the refrigerator door is opened, the identification information comprises the time and duration for opening the refrigerator door;
and selecting a gear for pre-refrigerating the refrigerator and the pre-refrigerating time according to the time and duration for opening the refrigerator door, and controlling the refrigerator to pre-refrigerate when the pre-refrigerating time is reached.
6. The machine learning based refrigerator behavior control method of claim 5, further comprising:
and calculating the time difference between the opening time of the refrigerator door and the current time, and controlling the refrigerator to enter an energy-saving operation mode in the time difference if the time difference is greater than a first preset time length.
7. The refrigerator behavior control method based on machine learning according to claim 1, wherein the "controlling the refrigerator to perform the behavior corresponding to the predicted behavior according to the identification information" specifically includes:
if the predicted behavior is to adjust the compartment temperature of the refrigerator, the identification information comprises adjusted time and temperature value, and the compartment temperature of the refrigerator is set to be the adjusted temperature value by controlling the adjusted time.
8. The machine learning-based refrigerator behavior control method of claim 1, further comprising:
the identification information of the predicted behavior comprises the occurrence time of the predicted behavior, and the time difference between the occurrence time of the predicted behavior and the current time is calculated;
and if the time difference is greater than a second preset time length, controlling the WIFI function of the refrigerator to enter a sleep mode within the time difference.
9. An electronic device comprising a memory and a processor, the memory storing a computer program operable on the processor, wherein the processor implements the steps in the machine learning-based refrigerator behavior control method of any one of claims 1-8 when executing the program.
10. A refrigerator characterized in that it comprises an electronic device according to claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911373659.0A CN111207560B (en) | 2019-12-27 | 2019-12-27 | Refrigerator behavior control method and device based on machine learning and refrigerator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911373659.0A CN111207560B (en) | 2019-12-27 | 2019-12-27 | Refrigerator behavior control method and device based on machine learning and refrigerator |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111207560A true CN111207560A (en) | 2020-05-29 |
CN111207560B CN111207560B (en) | 2022-06-24 |
Family
ID=70784077
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911373659.0A Active CN111207560B (en) | 2019-12-27 | 2019-12-27 | Refrigerator behavior control method and device based on machine learning and refrigerator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111207560B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111550961A (en) * | 2020-04-26 | 2020-08-18 | 青岛海尔电冰箱有限公司 | Method for predicting temperature of refrigerator compartment and intelligent refrigerator |
CN111664490A (en) * | 2020-06-28 | 2020-09-15 | 海尔优家智能科技(北京)有限公司 | Control method and device of cigarette machine and storage medium |
CN112503818A (en) * | 2020-11-18 | 2021-03-16 | 深圳Tcl新技术有限公司 | Refrigerator and door opening method thereof, and computer storage medium |
CN112728841A (en) * | 2020-12-29 | 2021-04-30 | Tcl家用电器(合肥)有限公司 | Intelligent control method and device for lamp decoration, refrigerator and storage medium |
CN114413563A (en) * | 2022-01-17 | 2022-04-29 | 广东哈士奇制冷科技股份有限公司 | Refrigeration equipment control method and system, electronic equipment and readable storage medium |
WO2022166687A1 (en) * | 2021-02-08 | 2022-08-11 | 广州富港万嘉智能科技有限公司 | Control method and apparatus of intelligent refrigerator and intelligent refrigerator |
US11483174B1 (en) * | 2021-06-30 | 2022-10-25 | Amazon Technologies, Inc. | Device functionality control utilizing activity prediction |
CN116717938A (en) * | 2023-08-09 | 2023-09-08 | 江苏星星冷链科技有限公司 | Method and system for detecting and controlling internal environment of refrigerator |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100705767B1 (en) * | 2005-12-20 | 2007-04-09 | 주식회사 대우일렉트로닉스 | Method for controlling refrigeration of kimchi refrigerator |
KR20120039881A (en) * | 2010-10-18 | 2012-04-26 | 주식회사 대우일렉트로닉스 | Refrigerator and operation method thereof |
CN106549833A (en) * | 2015-09-21 | 2017-03-29 | 阿里巴巴集团控股有限公司 | A kind of control method and device of intelligent home device |
CN109960296A (en) * | 2019-04-02 | 2019-07-02 | 广州市雪涛制冷设备有限公司 | A method of it is predicted for adaptive environment transformation temperature |
-
2019
- 2019-12-27 CN CN201911373659.0A patent/CN111207560B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100705767B1 (en) * | 2005-12-20 | 2007-04-09 | 주식회사 대우일렉트로닉스 | Method for controlling refrigeration of kimchi refrigerator |
KR20120039881A (en) * | 2010-10-18 | 2012-04-26 | 주식회사 대우일렉트로닉스 | Refrigerator and operation method thereof |
CN106549833A (en) * | 2015-09-21 | 2017-03-29 | 阿里巴巴集团控股有限公司 | A kind of control method and device of intelligent home device |
CN109960296A (en) * | 2019-04-02 | 2019-07-02 | 广州市雪涛制冷设备有限公司 | A method of it is predicted for adaptive environment transformation temperature |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111550961A (en) * | 2020-04-26 | 2020-08-18 | 青岛海尔电冰箱有限公司 | Method for predicting temperature of refrigerator compartment and intelligent refrigerator |
CN111664490A (en) * | 2020-06-28 | 2020-09-15 | 海尔优家智能科技(北京)有限公司 | Control method and device of cigarette machine and storage medium |
CN112503818A (en) * | 2020-11-18 | 2021-03-16 | 深圳Tcl新技术有限公司 | Refrigerator and door opening method thereof, and computer storage medium |
CN112503818B (en) * | 2020-11-18 | 2023-10-13 | 深圳Tcl新技术有限公司 | Refrigerator, door opening method thereof and computer storage medium |
CN112728841A (en) * | 2020-12-29 | 2021-04-30 | Tcl家用电器(合肥)有限公司 | Intelligent control method and device for lamp decoration, refrigerator and storage medium |
WO2022166687A1 (en) * | 2021-02-08 | 2022-08-11 | 广州富港万嘉智能科技有限公司 | Control method and apparatus of intelligent refrigerator and intelligent refrigerator |
US11483174B1 (en) * | 2021-06-30 | 2022-10-25 | Amazon Technologies, Inc. | Device functionality control utilizing activity prediction |
CN114413563A (en) * | 2022-01-17 | 2022-04-29 | 广东哈士奇制冷科技股份有限公司 | Refrigeration equipment control method and system, electronic equipment and readable storage medium |
CN114413563B (en) * | 2022-01-17 | 2023-10-31 | 广东哈士奇制冷科技股份有限公司 | Refrigeration equipment control method, refrigeration equipment control system, electronic equipment and readable storage medium |
CN116717938A (en) * | 2023-08-09 | 2023-09-08 | 江苏星星冷链科技有限公司 | Method and system for detecting and controlling internal environment of refrigerator |
CN116717938B (en) * | 2023-08-09 | 2023-09-29 | 江苏星星冷链科技有限公司 | Method and system for detecting and controlling internal environment of refrigerator |
Also Published As
Publication number | Publication date |
---|---|
CN111207560B (en) | 2022-06-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111207560B (en) | Refrigerator behavior control method and device based on machine learning and refrigerator | |
EP3411634B1 (en) | Data learning server and method for generating and using learning model thereof | |
CN111795484B (en) | Intelligent air conditioner control method and system | |
CN108302719B (en) | Control method, device and system of multi-split air conditioning system and storage medium | |
CN105318499A (en) | User behavior self-learning air conditioning system and control method thereof | |
EP3989594A1 (en) | Information processing method, information processing device, and program | |
US8078318B2 (en) | Appliance control apparatus and method | |
WO2022166687A1 (en) | Control method and apparatus of intelligent refrigerator and intelligent refrigerator | |
CN105318483A (en) | Air-conditioner sleep mode control method and air-conditioner sleep mode control device | |
US20200379417A1 (en) | Techniques for using machine learning for control and predictive maintenance of buildings | |
CN112527037B (en) | Greenhouse environment regulation and control method and system with environment factor prediction function | |
CN108052010A (en) | Intelligent electric appliance method for self regulating, device, computer equipment and storage medium | |
CN112308209A (en) | Personalized air conditioner intelligent learning method based on deep learning | |
CN101995823B (en) | Energy-saving control method based on statistical forecasting technology | |
CN110836525A (en) | Self-adaptive adjusting method and device for air conditioner running state | |
Shresthamali et al. | Power management of wireless sensor nodes with coordinated distributed reinforcement learning | |
CN110044073B (en) | Control method and system of water heater | |
WO2021042368A1 (en) | Power consumption control and scheme generation method, device, system, and storage medium | |
CN116792882A (en) | Remote intelligent control management system for air conditioner | |
CN114187685B (en) | Method, system, equipment and medium for optimizing power consumption of intelligent lock | |
CN110925944A (en) | Control method and control device of air conditioning system and air conditioning system | |
CN112486683B (en) | Processor control method, control apparatus, and computer-readable storage medium | |
CN111076491B (en) | Refrigerator and control method thereof | |
CN113757920A (en) | Defrosting control method and device, computer equipment and storage medium | |
CN114234370B (en) | Multi-split air conditioner control method and device and multi-split air conditioner |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |