CN115628554A - Water heating method and device for water heater, electronic equipment and storage medium - Google Patents
Water heating method and device for water heater, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115628554A CN115628554A CN202211340061.3A CN202211340061A CN115628554A CN 115628554 A CN115628554 A CN 115628554A CN 202211340061 A CN202211340061 A CN 202211340061A CN 115628554 A CN115628554 A CN 115628554A
- Authority
- CN
- China
- Prior art keywords
- time
- hot water
- target object
- historical
- water heater
- 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.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/20—Control of fluid heaters characterised by control inputs
- F24H15/269—Time, e.g. hour or date
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/10—Control of fluid heaters characterised by the purpose of the control
- F24H15/172—Scheduling based on user demand, e.g. determining starting point of heating
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/40—Control of fluid heaters characterised by the type of controllers
- F24H15/486—Control of fluid heaters characterised by the type of controllers using timers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H9/00—Details
- F24H9/18—Arrangement or mounting of grates or heating means
- F24H9/1809—Arrangement or mounting of grates or heating means for water heaters
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H9/00—Details
- F24H9/20—Arrangement or mounting of control or safety devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Heat-Pump Type And Storage Water Heaters (AREA)
Abstract
The application relates to a water heating method and device for a water heater, electronic equipment and a storage medium. The method comprises the following steps: acquiring behavior sequence information obtained by detecting a target object; processing the behavior sequence information to obtain predicted hot water use time, wherein the predicted hot water use time is used for indicating the time of a target object for predicting hot water use; and determining the heating time of the water heater according to the predicted hot water use time, wherein the heating time of the water heater is the time for indicating the water heater to start to carry out hot water. By the method, the technical problem that the heating time of the water heater cannot be accurately predicted in the water heater in the related technology, and therefore hot water efficiency is low can be effectively solved.
Description
Technical Field
The application relates to the technical field of intelligent household equipment, in particular to a water heating method and device of a water heater, electronic equipment and a storage medium.
Background
At present, intelligent household equipment is more and more in the middle of entering into ordinary family, simultaneously, can effectively improve people's quality of life through intelligent household equipment.
In the aspect of household water heaters, at present, there is no substantial intelligent application function, and the existing technical scheme is to determine the water consumption time of a user only by modeling according to the parameters of the water heater, and the used data contains a small amount of information, so that the water consumption time of the user cannot be accurately predicted to determine the heating time of the water heater.
Aiming at the technical problem that the heating time of the water heater cannot be accurately predicted in the related art, an effective solution is not provided at present.
Disclosure of Invention
In order to solve the technical problem that the heating time of the water heater cannot be accurately predicted by the water heater, the application provides a water heating method and device of the water heater, electronic equipment and a storage medium.
In a first aspect, an embodiment of the present application provides a water heating method for a water heater, including:
acquiring behavior sequence information obtained by detecting a target object;
processing the behavior sequence information to obtain predicted hot water use time, wherein the predicted hot water use time is used for indicating the time of the target object for predicting hot water use;
and determining the heating time of the water heater according to the estimated hot water use time, wherein the heating time of the water heater is the time indicating the water heater to start to carry out hot water.
Optionally, as in the foregoing water heating method of a water heater, the obtaining of behavior sequence information obtained by detecting a target object includes
Detecting a target environment through a radar sensor to obtain a radar signal;
determining the target object in the target environment according to the radar signal;
and detecting the target object to obtain action sequence data and position sequence data of the target object, wherein the behavior sequence information comprises the action sequence data and the position sequence data, the action sequence data is used for indicating the sequence of different actions executed by the target object, and the position sequence data is used for indicating the sequence of stay of the target object between different positions.
Optionally, as in the foregoing water heater hot water method, the processing the behavior sequence information to obtain the predicted hot water usage time includes:
performing a first normalization operation on the position sequence data to obtain first normalization data; performing a second normalization operation on the action sequence data to obtain second normalization data;
and inputting the first normalization data and the second normalization data into a preset target network, and predicting to obtain the expected hot water use time.
Optionally, as in the foregoing water heater water heating method, the determining the target object located in the target environment according to the radar signal includes:
obtaining point cloud data of the target environment according to the radar signal;
determining a moving point of the movement in the point cloud data;
and clustering each motion point to obtain the target object.
Optionally, as in the foregoing water heater water heating method, the tracking the target object to obtain motion sequence data of the target object includes:
determining the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity corresponding to each position according to all the moving points corresponding to the target object in each position;
obtaining a characteristic sequence corresponding to each position based on the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity corresponding to each position;
and obtaining the action sequence data according to the characteristic sequence corresponding to each position and the sequence of the stay of the target object between different positions.
Optionally, as in the foregoing water heater hot water method, the determining the water heater heating time according to the predicted hot water usage time includes:
determining the heating time of the water heater as the current time under the condition that the time difference between the predicted hot water use time and the current time is less than or equal to the preset heating time;
and under the condition that the time difference between the estimated hot water use time and the current time is greater than a preset heating time, determining the heating time of the water heater to be the difference between the estimated hot water use time and the preset heating time.
Optionally, as in the foregoing water heater hot water method, before the processing the behavior sequence information to obtain the predicted hot water usage time, the method further includes:
acquiring, by a radar sensor, historical behavior sequence information generated by action of the target object in a target environment in each of a plurality of historical time periods, and historical hot water use time corresponding to each of the historical time periods, wherein each of the historical behavior sequence information includes historical position sequence data and historical action sequence data, and the historical position sequence data and the historical action sequence data corresponding to each of the historical time periods are used for indicating a sequence relation of stay of the target object between different positions in the historical time period, and the historical action sequence data is used for indicating a sequence relation of execution of different actions of the target object in the historical time period;
obtaining training data according to the historical position sequence data, the historical action sequence data and the historical hot water using time which correspond to the same historical time period;
training the network to be trained through a plurality of training data until the network to be trained meets the preset precision requirement, and obtaining the target network.
In a second aspect, an embodiment of the present application provides a water heating device for a water heater, including:
the acquisition module is used for acquiring behavior sequence information obtained by detecting a target object;
the processing module is used for processing the behavior sequence information to obtain expected hot water using time, wherein the expected hot water using time is used for indicating the expected hot water using time of the target object;
and the determining module is used for determining the heating time of the water heater according to the predicted hot water use time, wherein the heating time of the water heater is the time for indicating the water heater to start to carry out hot water.
In a third aspect, an embodiment of the present application provides an electronic device, including: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program, is configured to implement the method according to any of the preceding claims.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes a stored program, where the program is executed to perform the method according to any one of the preceding claims.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the method provided by the embodiment of the application, the behavior sequence information of the target object is determined, the predicted water consumption time of the target object is determined based on the behavior sequence information, and then the heating time of the water heater for heating water can be more accurately determined, so that the time for the water heater to start heating water can better meet the actual hot water use requirement of the target object, and meanwhile, the technical problem that the hot water efficiency is low due to the fact that the water heater cannot accurately predict the heating time of the water heater in the related technology can be effectively solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive labor.
FIG. 1 is a schematic flow chart illustrating a hot water heating method of a water heater according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating a hot water heating method of a water heater according to another embodiment of the present disclosure;
FIG. 3 is a schematic flow chart illustrating a hot water method for a water heater according to another embodiment of the present disclosure;
fig. 4 is a schematic layout diagram of a radar sensor according to an embodiment of the present disclosure;
FIG. 5 is a block diagram of a hot water device of a water heater according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
According to one aspect of an embodiment of the present application, a method for heating water in a water heater is provided. Alternatively, in the present embodiment, the water heater hot water method can be applied to a hardware environment formed by a terminal and a server. The server is connected with the terminal through a network, and can be used for providing services (such as data processing services and application services) for the terminal or a client installed on the terminal, and a database can be arranged on the server or independent of the server and used for providing data storage services for the server.
The network may include, but is not limited to, at least one of: wired networks, wireless networks. The wired network may include, but is not limited to, at least one of: wide area networks, metropolitan area networks, local area networks, which may include, but are not limited to, at least one of the following: WIFI (Wireless Fidelity), bluetooth. The terminal may not be limited to a PC, a mobile phone, a tablet computer, and the like.
The water heater hot water method of the embodiment of the application can be executed by the server, the terminal or both. The terminal executing the water heating method of the water heater of the embodiment of the application can also be executed by a client installed thereon.
Taking the example that the server executes the water heating method of the water heater in the embodiment as an example, fig. 1 is a water heating method of the water heater provided in the embodiment of the present application, and includes the following steps:
step S101, behavior sequence information obtained by detecting a target object is obtained;
the water heater hot water method in the embodiment can be applied to a scene in which the time for starting hot water of the water heater needs to be controlled.
To determine when the water heater is controlled to start heating water for a person, the position of the person may be detected to determine when the person needs to use the hot water.
The target object may be a person using the water heater.
Alternatively, the persons in the target environment (for example, a home environment, a work environment, and the like) may be detected by an image detection device or a radar sensor or the like, so as to obtain behavior sequence information corresponding to each person.
The behavior sequence information of the target object may be used to indicate the sequence of the target object executing each behavior. For example, the order of the target object's stay at various locations in the target environment, the order of the target object's execution of different actions, and so on.
Since the daily work and rest of a person are generally regular, for example, after getting up, a person needs to wash his face and take a bath (i.e., hot water needs to be used), and after doing sports, a person needs to take a bath (i.e., hot water needs to be used). Therefore, the time for using hot water by the target object can be determined later based on the behavior sequence information of the target object.
And step S102, processing the behavior sequence information to obtain the expected hot water use time, wherein the expected hot water use time is used for indicating the time of the target object for expecting to use hot water.
After the behavior sequence information of the target object is acquired, the behavior sequence information may be processed through a preset target network.
The target network may be a model trained in advance to predict the expected hot water usage time, and the data input to the target network for prediction may be behavior sequence information or information obtained by preprocessing (e.g., normalizing) the behavior sequence information.
After the behavior sequence information is processed through a preset target network, the expected hot water use time can be obtained. The expected hot water use time can be predicted by the target network, and the target object uses the hot water.
And step S103, determining the heating time of the water heater according to the expected hot water use time, wherein the heating time of the water heater is the time for indicating the water heater to start to carry out hot water.
Since the hot water of the water heater requires a certain process, it is also necessary to determine the heating time of the water heater based on the expected hot water usage time after obtaining the expected hot water usage time.
Alternatively, the heating time of the water heater may be determined based on the hot water efficiency of the water heater, and generally, the higher the hot water efficiency is, the shorter the time interval between the heating time of the water heater and the expected hot water usage time is, the lower the hot water efficiency is, and the longer the time interval between the heating time of the water heater and the expected hot water usage time is.
After the heating time of the water heater is obtained, the water heater can be controlled to start to carry out hot water at the heating time of the water heater.
By the method in the embodiment, the behavior sequence information of the target object is determined, and the predicted water consumption time of the target object is determined based on the behavior sequence information, so that the heating time of the water heater for starting hot water can be more accurately determined, the time for starting hot water of the water heater can better meet the actual hot water use requirement of the target object, and meanwhile, the technical problem that the hot water efficiency is low due to the fact that the water heater cannot accurately predict the heating time of the water heater in the related technology can be effectively solved.
As an alternative embodiment, in the water heating method of the water heater, in the step S101, the obtaining behavior sequence information obtained by detecting the target object includes the following steps:
step S201, detecting a target environment through a radar sensor to obtain a radar signal.
That is, in this embodiment, the target environment is detected by the radar sensor to obtain the radar signal in the target environment.
The radar sensor can be arranged in one or more target environments, and can be selected according to the detection range of the radar sensor and the size of the target environment, so that the detection signals sent by the radar sensor or the radar sensors can cover the target environment.
For example, in a home environment as shown in FIG. 4, one radar sensor may be provided at each of the relatively independent areas (i.e., bedroom, bathroom, kitchen, and living room).
And S202, determining a target object in the target environment according to the radar signal.
After the radar signal is acquired, a target object located in the target environment may be determined based on the radar signal.
Optionally, an object moving in the monitored area may be obtained by the radar signal first, and the object is identified as a moving target; and at the same time, the number of the moving objects in the monitoring area can be 0, or one or more.
Because different general personnel still have certain difference in the aspect of habit of using hot water, in order to solve this problem, can carry out identification to the moving target according to radar signal, when the identity of moving target is the same with the identity of target object in the database, determine that the moving target in the target environment is the target object. Alternatively, identification may be achieved by adding an identification algorithm for distinguishing different persons, for example, by a camera-based human-type appearance recognition, or a gait recognition method using millimeter wave radar.
And, each different person can be trained a candidate network separately, so that each candidate network can be more accurately adapted to each person's habit of using hot water.
Step S203, detecting the target object to obtain action sequence data and position sequence data of the target object, wherein the behavior sequence information comprises the action sequence data and the position sequence data, the action sequence data is used for indicating the sequence of different actions executed by the target object, and the position sequence data is used for indicating the sequence of stay of the target object between different positions.
After the target object is determined, tracking detection can be performed on the target object to obtain motion sequence data and position sequence data of the target object.
Alternatively, the target environment may be divided into a plurality of different positions in advance according to the usage scenario, as shown in fig. 4, for example: windows, living rooms, sofas, tables, beds, desks, toilets, cooktops, etc., and moreover, for areas greater than a preset threshold, further divisions can be made, resulting in the positions shown in the figures: 3. 5, 6, 7, 14 so that the position sequence data can be determined more accurately.
Further, position sequence data indicating the sequence of the target object staying between different positions may be determined based on all the detected radar information. For example, get up (position 1) -go to toilet (position 2) -kitchen (position 3) -dining table (position 4) -go out (position 5), the start time (time-start), end time (time-end) and duration (time-duration) at each position are recorded. Then the sample sequence is: { { position 1, time-start 1, time-end 1, time-duration 1}, { position 2, time-start 2, time-end 2, time-duration 2}, { position 3, time-start 3, time-end 3, time-duration 3}, \ 8230; }.
The action sequence data may be data for indicating the sequence of different actions performed by the target object, such as: getting up, going to a toilet, getting down from a kitchen, eating and going out; also, optionally, each location may have a corresponding action.
By the method in the embodiment, the action sequence data and the position sequence data of the target object are obtained by detecting the target object, so that the action sequence information of the target object can be determined through multiple dimensions, and the action of the target object can be determined more accurately.
As an alternative embodiment, in the water heating method of the water heater as described above, the step S102 processes the behavior sequence information to obtain the expected hot water usage time, and includes the following steps:
step S301, performing a first normalization operation on the position sequence data to obtain first normalization data; performing second normalization operation on the action sequence data to obtain second normalization data;
step S302, inputting the first normalization data and the second normalization data into a preset target network, and predicting to obtain the expected hot water use time.
That is, the data input to the target network is actually the first normalization operation performed on the position sequence data to obtain first normalization data; and performing second normalization operation on the action sequence data to obtain second normalization data.
Preferably, the first normalization operation and the second normalization operation are both normalization operations normalized to [0,1], and by normalization, the influence of the scalar size of the input data can be eliminated, and for any feature, the maximum value (max) and the minimum value (min) are set first, and if the current value is x, x = (x-min)/(max-min) is performed on x normalization.
After the first normalized data and the second normalized data are obtained, the first normalized data and the second normalized data can be input into a target network, and the predicted hot water use time can be obtained through prediction.
As an alternative embodiment, in the water heater water heating method, the step S202 of determining the target object located in the target environment according to the radar signal includes the following steps:
and S401, obtaining point cloud data of a target environment according to the radar signal.
Specifically, the radar signal is an echo signal of a radar, and scanning is performed in a monitored area according to a radar detection signal to obtain point cloud data with geometric position information; the point cloud is a massive point set of the surface characteristics of the point cloud and the target; each point in the point cloud data has a corresponding three-dimensional coordinate.
In step S402, in the point cloud data, a moving point of the movement is determined.
Because the radar detection device can obtain one frame of corresponding point cloud data every time the radar detection device emits a radar signal, static points and moving points (namely moving points) in the point cloud data can be obtained by comparing point cloud data of different frames.
And S403, clustering the motion points to obtain a target object.
Specifically, a radar of a moving object (e.g., a human) generally obtains a plurality of moving points to represent the moving object, and therefore, the moving points of the same moving object need to be clustered together through a clustering algorithm.
Optionally, the method for clustering point cloud data, based on the distance threshold and the point number threshold, includes the following steps:
1) Acquiring points which are not clustered currently, randomly selecting a point, taking the point as a central point, sequentially selecting a point from the rest points to calculate the distance between the two selected points, 2) if the distance is greater than a distance threshold, abandoning the point, and sequentially selecting the next point from the rest points to calculate the distance between the two selected points; if the distance is smaller than the distance threshold, saving the selected points, averaging the selected points with the previously saved points, then using the average value, sequentially selecting the next point from the remaining points to calculate the distance from the average value, and 3) repeating the process. Until the point cloud is traversed once. Each cluster is a new target.
After the moving target is obtained through clustering, the moving target can be identified, and when the identity of the moving target is the same as that of the target object, the target object is obtained through clustering.
The target object can be tracked by using an extended Kalman filter tracking algorithm, and the existing target at the previous moment can be tracked.
As shown in fig. 2, as an alternative embodiment, in the foregoing water heater water heating method, the step S203 of tracking the target object to obtain the motion sequence data of the target object includes the following steps:
step S501, determining a maximum doppler velocity, a minimum doppler velocity, and an average doppler velocity corresponding to each position according to all the moving points corresponding to the target object in each position.
In each position, the moving point corresponding to the target object is different, for example, in a kitchen, the target object may be mainly that the upper half of the body moves, so that the moving range of the moving point of the upper half of the body is larger than that of the moving point of the lower half of the body; when the sofa is used, all parts of the target object may move little or basically still, and the motion amplitude of each motion point is small.
After all the moving points corresponding to the target object in each position are obtained, because the point cloud data information includes the distance (r), the azimuth angle pitch angle (θ) and the doppler velocity, the maximum doppler velocity with the maximum doppler velocity and the minimum doppler velocity with the minimum doppler velocity can be calculated in all the moving points, and the average doppler velocity obtained by calculating the average value of the doppler velocities of all the moving points can be obtained.
Step S502, obtaining a characteristic sequence corresponding to each position based on the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity corresponding to each position;
and obtaining the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity corresponding to each position, namely using the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity as the characteristic sequence corresponding to each position.
For example, in the kitchen, the maximum Doppler velocity is D max Minimum Doppler velocity D min Average Doppler velocity D aver Then the sequence of features in the kitchen is [ D ] max ，D min ，D aver ]。
Step S503, obtaining action sequence data according to the characteristic sequence corresponding to each position and the sequence of the stay of the target object between different positions.
After the feature sequences corresponding to each position are determined, all the feature sequences can be connected based on the sequence of the target object staying between different positions, and then the action sequence data can be obtained.
For example, different locations have different sequences of motion characteristics: [ [ maximum doppler velocity 1, minimum doppler velocity 1, average doppler velocity 1], [ maximum doppler velocity 2, minimum doppler velocity 2, average doppler velocity 2], [ maximum doppler velocity 3, minimum doppler velocity 3, average doppler velocity 3], \ 8230 ].
As an alternative embodiment, in the method for heating water by a water heater as described above, the step S103 of determining the heating time of the water heater according to the expected hot water usage time includes the following steps:
step S601, determining the heating time of the water heater as the current time under the condition that the time difference between the predicted hot water use time and the current time is less than or equal to the preset heating time;
step S602, determining the heating time of the water heater as the difference between the predicted hot water usage time and the preset heating time period when the time difference between the predicted hot water usage time and the current time is greater than the preset heating time period.
After the expected hot water usage time is obtained, that is, the time when the target object is expected to need hot water usage is estimated, the hot water is not heated all the time for energy saving, so that the time when the water heater starts to heat water needs to be determined.
The preset heating time length can be predetermined, the preset heating time length can be the time length required by the water heater to heat water in the water heater, and further, the heating time of the water heater is determined to be the current time when the time difference between the expected hot water use time and the current time is less than or equal to the preset heating time length, namely, the water heater is heated immediately; and under the condition that the time difference between the predicted hot water use time and the current time is greater than the preset heating time, determining the heating time of the water heater to be the difference between the predicted hot water use time and the preset heating time, namely heating when the predicted hot water use time is advanced by the preset heating time.
For example, when the preset heating time period is 1 hour:
1) Estimated hot water usage time-current time < =1 hour;
for example, if the predicted expected hot water usage time is about to be used within 1 hour, the water heater hot water mode is immediately turned on:
2) Predicted hot water usage time-current time >1 hour;
and (3) predicting the hot water using time, wherein the hot water using time is used after 1 hour, and the heating time of the water heater is predicted:
water heater heating time = expected hot water usage time-1 hour.
As shown in fig. 3, as an alternative embodiment, in the water heating method for a water heater, before the step S102 processes the behavior sequence information to obtain the expected hot water usage time, the method further includes the following steps:
step S701, acquiring, by a radar sensor, historical behavior sequence information generated by action of a target object in a target environment in each of a plurality of historical time periods, and historical hot water use time corresponding to each historical time period, wherein each historical behavior sequence information comprises historical position sequence data and historical action sequence data, and the historical position sequence data and the historical action sequence data correspond to each historical time period, the historical position sequence data is used for indicating a sequence relation of stay of the target object in different positions in the historical time period, and the historical action sequence data is used for indicating a sequence relation of execution of different actions of the target object in the historical time period.
In order to train to obtain a target network meeting the preset precision requirement, multiple sets of historical data of a target object need to be collected in advance to train the network to be trained.
Alternatively, the historical behavior sequence information generated by the action of the target object within the target environment in each of the plurality of historical time periods may be acquired by radar.
Similarly, the historical behavior sequence information may include: historical position sequence data used for indicating the sequence relation of the stops of the target object among different positions in the historical time period; and historical position sequence data used for indicating the sequence relation of the stops of the target object between different positions in the historical time period.
The time length of each of the historical time periods may be a preset time length, for example, half an hour, and further, the historical behavior sequence information of each of the historical time periods and the historical hot water usage time corresponding to each of the historical time periods may be acquired. In general, the duration of acquiring the behavior sequence information is the same as the duration of each historical time period.
For example, the target object may be continuously tracked and detected by the radar sensor to obtain total historical behavior sequence information in the total historical time period, then the total historical time period is divided according to a preset time length of each historical time period to obtain a plurality of historical time periods, and the historical behavior sequence information corresponding to each historical time period is obtained according to a time corresponding to each historical behavior (i.e., a historical position and a historical action) in the total historical behavior sequence information. And the historical hot water usage time corresponding to the historical total time period may be taken as the historical hot water usage time corresponding to each of the historical total time periods.
Step S702, a piece of training data is obtained according to the historical position sequence data, the historical action sequence data and the historical hot water using time which correspond to the same historical time period.
After the historical position sequence data, the historical action sequence data and the historical hot water using time corresponding to each historical time period are obtained, a piece of training data can be obtained according to the historical position sequence data, the historical action sequence data and the historical hot water using time corresponding to the same historical time period.
Optionally, when the normalization data corresponding to the position sequence data and the normalization data corresponding to the motion sequence data are used as input data during prediction, a first historical normalization data may be obtained based on the historical position sequence data, a second historical normalization data may be obtained based on the historical motion sequence data, and training data composed of the first historical normalization data, the second historical normalization data, and the historical hot water usage time may be obtained. Wherein the historical hot water usage time is label data.
Step S703, training the network to be trained through the plurality of training data until the network to be trained meets the preset accuracy requirement, and obtaining a target network.
After the training data is obtained, the network to be trained can be trained through a plurality of training data in all the training data until the network to be trained meets the preset precision requirement, and a target network is obtained.
Further, the network to be trained may be a long-term memory network (LSTM).
By the method in the embodiment, the target network corresponding to the target object can be obtained through training, so that the target network can be more accurately suitable for the target object to predict the heating time of the water heater, and the user experience can be effectively improved.
An application example to which any of the foregoing embodiments is applied is provided as follows:
p11, setting of sensor equipment;
1. the radar sensors are distributed and arranged:
a plurality of radar sensors are distributed as shown in fig. 4.
2. Water sensor for water heater
When a user uses hot water of the water heater, the water consumption behavior of the user can be detected, and the water consumption time is recorded for the subsequent training of the lstm model to be trained.
P12: data acquired by radar sensor
The radar can finally extract point cloud data, namely data corresponding to a target object after signal processing, wherein information contained in each point comprises distance, azimuth angle, elevation angle, doppler velocity, signal-to-noise ratio and the like.
P13: radar-based target clustering tracking
After signal processing, the information of the moving points can be obtained, and the specific position of each moving point in the space coordinate system can be calculated according to the information of the moving points. A radar of a moving object (such as a human) can obtain a plurality of moving points to represent the moving object, so that the moving points of the same moving object need to be clustered together through a clustering algorithm. The invention provides a clustering method for processing point cloud data, which is based on a distance threshold and a point threshold and comprises the following steps:
1) Acquiring points which are not clustered currently, randomly selecting a point, taking the point as a central point, sequentially selecting a point from the rest points to calculate the distance between the two selected points, 2) if the distance is greater than a distance threshold, abandoning the point, and sequentially selecting the next point from the rest points to calculate the distance between the two selected points; if the distance is less than the distance threshold, saving the selected points, averaging the points with the previously saved points, then using the average value, sequentially selecting the next point from the remaining points to calculate the distance from the average value, and 3) repeating the above process. Until the point cloud is traversed once. Each cluster is a new target.
The target object can be tracked by using an extended Kalman filter tracking algorithm.
P14: location sequence data
First, a scene area in the radar detection area is established, as shown in fig. 4. The required devices may include: distributed radar, network equipment, a database and an information processing system. Different scenes correspond to different behaviors, for example, people eat food beside a dining table. Different areas of the home are divided into different states, with the numbers in fig. 4 representing different areas in the home (i.e., the target environment). The corresponding start and end times and durations of the target object under different regions may be collected using the table shown below.
| Location area | Starting time | End time | Duration of |
| 1 | |||
| 2 | |||
| 3 | |||
| …… |
And collecting the duration of different areas in a period of time, and using the collected position sequence data as a training sample.
A sequence of positions is as follows: getting up (position 1) -going to the toilet (position 2) -kitchen (position 3) -dining table (position 4) -going out (position 5), recording the start time (time-start), end time (time-end) and duration (time-duration) at each position. Then the sample sequence is:
{ { position 1, time-start, time-end, time-duration }, { position 2, time-start, time-end, time-duration }, { position 3, time-start, time-end, time-duration }, \8230 }
P15: extraction of action sequence data
And (3) feature extraction, namely calculating continuous action features in the same position in S14 according to point cloud data of each target, and extracting the micro Doppler features: maximum doppler velocity, minimum doppler velocity, average doppler velocity. The three characteristics are calculated by using Doppler velocity in information contained in the point cloud of the target; since each target person has more than one point cloud data, the maximum doppler velocity, the minimum doppler velocity and the average doppler velocity can be obtained by calculating the maximum, minimum and average values.
The same position finally obtains a characteristic sequence: [ maximum Doppler velocity, minimum Doppler velocity, average Doppler velocity ].
And forming an action characteristic sequence corresponding to the position sequence data by the characteristic sequence corresponding to each position in the position sequence data: [ [ maximum doppler velocity 1, minimum doppler velocity 1, average doppler velocity 1], [ maximum doppler velocity 2, minimum doppler velocity 2, average doppler velocity 2], \\ 8230 ], ].
P16: predicting the predicted hot water use time by a long-time and short-time memory network (LSTM);
the predictive model uses a long-short term memory network (LSTM) to train and predict two types of time series data (i.e., motion series data and location series data) collected.
1. Data preparation and preprocessing:
two types of data: position sequence data and action sequence data;
data volume: extracting the action sequence every half hour;
normalization: the position sequence data and the action sequence data are normalized to be between [0,1 ].
2. Training of the LSTM model to be trained (i.e., the network to be trained):
training data: position sequence data and action sequence data (namely historical behavior sequence information) in the half hour period;
labeling: the user heating time (i.e., the historical hot water usage time) detected by the water heater water sensor.
And training the LSTM model to be trained through the data to obtain the trained LSTM model (namely, a target network).
Therefore, the self-training learning in the user home can be realized, and the self-training learning method has better adaptability.
3. Predicted by the trained LSTM model:
position sequence data and motion sequence data within the current half hour are extracted and input into an LSTM model to acquire predicted expected hot water use time.
P17: predicting the heating time of the water heater:
1) Predicted hot water usage time-current time < =1 hour;
for example, a predicted expected hot water usage time, which is just about to be used within 1 hour, will immediately turn on the water heater hot water mode:
2) Predicted hot water usage time-current time >1 hour;
and predicting the hot water using time, wherein the hot water is used after 1 hour, and then predicting the heating time of the water heater:
water heater heating time = expected hot water usage time-1 hour.
As shown in fig. 5, according to an embodiment of another aspect of the present application, the present application further provides a hot water device of a water heater, comprising:
the acquisition module 1 is used for acquiring behavior sequence information obtained by detecting a target object;
the processing module 2 is used for processing the behavior sequence information to obtain predicted hot water use time, wherein the predicted hot water use time is used for indicating the time of a target object for predicting hot water use;
and the determining module 3 is used for determining the heating time of the water heater according to the predicted hot water use time, wherein the heating time of the water heater is the time for indicating the water heater to start to carry out hot water.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
According to another embodiment of the present application, there is also provided an electronic apparatus including: as shown in fig. 6, the electronic device may include: the system comprises a processor 1501, a communication interface 1502, a memory 1503 and a communication bus 1504, wherein the processor 1501, the communication interface 1502 and the memory 1503 complete communication with each other through the communication bus 1504.
A memory 1503 for storing a computer program;
the processor 1501 is configured to implement the steps of the above-described method embodiments when executing the program stored in the memory 1503.
The bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this is not intended to represent only one bus or type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
The embodiment of the present application further provides a computer-readable storage medium, where the storage medium includes a stored program, and when the program runs, the method steps of the above method embodiment are executed.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above description is merely illustrative of particular embodiments of the invention that enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of heating water in a water heater, comprising:
acquiring behavior sequence information obtained by detecting a target object;
processing the behavior sequence information to obtain predicted hot water use time, wherein the predicted hot water use time is used for indicating the time of the target object for predicting hot water use;
and determining the heating time of the water heater according to the predicted hot water use time, wherein the heating time of the water heater is the time for indicating the water heater to start to carry out hot water.
2. The water heating method for the water heater according to claim 1, wherein the step of obtaining the behavior sequence information obtained by detecting the target object comprises
Detecting a target environment through a radar sensor to obtain a radar signal;
determining the target object in the target environment according to the radar signal;
and detecting the target object to obtain action sequence data and position sequence data of the target object, wherein the behavior sequence information comprises the action sequence data and the position sequence data, the action sequence data is used for indicating the sequence of different actions executed by the target object, and the position sequence data is used for indicating the sequence of the stay of the target object between different positions.
3. The water heating method of the water heater according to claim 2, wherein the step of processing the behavior sequence information to obtain the predicted hot water use time comprises the following steps:
performing a first normalization operation on the position sequence data to obtain first normalization data; performing a second normalization operation on the action sequence data to obtain second normalization data;
and inputting the first normalized data and the second normalized data into a preset target network, and predicting to obtain the expected hot water use time.
4. The method for heating water in a water heater according to claim 2, wherein the step of determining the target object in the target environment according to the radar signal comprises:
obtaining point cloud data of the target environment according to the radar signal;
determining moving points of movement in the point cloud data;
and clustering each motion point to obtain the target object.
5. The water heating method for the water heater according to claim 4, wherein the tracking the target object to obtain the action sequence data of the target object comprises:
determining the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity corresponding to each position according to all the moving points corresponding to the target object in each position;
obtaining a characteristic sequence corresponding to each position based on the maximum Doppler velocity, the minimum Doppler velocity and the average Doppler velocity corresponding to each position;
and obtaining the action sequence data according to the characteristic sequence corresponding to each position and the sequence of the stay of the target object between different positions.
6. The method of claim 1, wherein determining a heater heating time based on the predicted hot water usage time comprises:
determining the heating time of the water heater as the current time under the condition that the time difference between the predicted hot water use time and the current time is less than or equal to the preset heating time;
and under the condition that the time difference between the estimated hot water use time and the current time is greater than a preset heating time, determining the heating time of the water heater to be the difference between the estimated hot water use time and the preset heating time.
7. The water heating method of claim 3, wherein before the step of processing the behavior sequence information to obtain the predicted hot water usage time, the method further comprises:
acquiring, by a radar sensor, historical behavior sequence information generated by the action of the target object in a target environment in each of a plurality of historical time periods, and historical hot water use time corresponding to each of the historical time periods, wherein each of the historical behavior sequence information includes historical position sequence data and historical action sequence data, and the historical position sequence data and the historical action sequence data corresponding to each of the historical time periods are used for indicating a sequence relation of stay of the target object between different positions in the historical time period, and the historical action sequence data is used for indicating a sequence relation of execution of different actions of the target object in the historical time period;
obtaining training data according to the historical position sequence data, the historical action sequence data and the historical hot water using time which correspond to the same historical time period;
training the network to be trained through a plurality of training data until the network to be trained meets the preset precision requirement, and obtaining the target network.
8. A water heater hot water device, comprising:
the acquisition module is used for acquiring behavior sequence information obtained by detecting a target object;
the processing module is used for processing the behavior sequence information to obtain predicted hot water use time, wherein the predicted hot water use time is used for indicating the time of the target object for predicting the use of hot water;
and the determining module is used for determining the heating time of the water heater according to the expected hot water use time, wherein the heating time of the water heater is the time for indicating the water heater to start to carry out hot water.
9. An electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program, implementing the method of any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the storage medium comprises a stored program, wherein the program when executed performs the method of any of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211340061.3A CN115628554A (en) | 2022-10-27 | 2022-10-27 | Water heating method and device for water heater, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211340061.3A CN115628554A (en) | 2022-10-27 | 2022-10-27 | Water heating method and device for water heater, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115628554A true CN115628554A (en) | 2023-01-20 |
Family
ID=84908932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211340061.3A Pending CN115628554A (en) | 2022-10-27 | 2022-10-27 | Water heating method and device for water heater, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115628554A (en) |
-
2022
- 2022-10-27 CN CN202211340061.3A patent/CN115628554A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110925969B (en) | Air conditioner control method and device, electronic equipment and storage medium | |
| Ngamakeur et al. | A survey on device-free indoor localization and tracking in the multi-resident environment | |
| WO2020103409A1 (en) | Detection method, detection apparatus, terminal and detection system | |
| WO2017216511A1 (en) | Estimating a number of occupants in a region | |
| CN111033445B (en) | System and method for gesture recognition | |
| Ueda et al. | A method for recognizing living activities in homes using positioning sensor and power meters | |
| US11516625B2 (en) | Systems and methods for mapping a given environment | |
| KR20200084380A (en) | Smart Home Airconditioner Automatic control system based on Artificial Intelligence | |
| CN112097374A (en) | Device control method, device and computer readable medium | |
| Komai et al. | Elderly person monitoring in day care center using Bluetooth Low Energy | |
| Clement et al. | Detecting activities of daily living with smart meters | |
| Basu et al. | Tracking motion and proxemics using thermal-sensor array | |
| CN111489019B (en) | Sleep quality prediction method and device | |
| CN112690761A (en) | Sleep state detection method, device, equipment and computer readable medium | |
| Hillyard et al. | Never use labels: Signal strength-based Bayesian device-free localization in changing environments | |
| US7302369B2 (en) | Traffic and geometry modeling with sensor networks | |
| US20190004550A1 (en) | Control of a heating/cooling system | |
| Bhattacharya et al. | Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation | |
| Dissanayake et al. | Indolabel: Predicting indoor location class by discovering location-specific sensor data motifs | |
| KR102371180B1 (en) | Smart Home Airconditioner Automatic control system based on Artificial Intelligence | |
| CN115628554A (en) | Water heating method and device for water heater, electronic equipment and storage medium | |
| CN113421179A (en) | Home-based old-age care environment improvement based on historical multidimensional data stream and active feedback | |
| CN115176722A (en) | Bathing early warning method and device, storage medium and equipment | |
| CN113313165B (en) | People counting method, device, equipment and storage medium based on radar | |
| JP5450703B2 (en) | Method and apparatus for determining a spatial area in which a target is located |
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 |