[0039] In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the specific embodiments of the present invention will be described below with reference to the drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings and obtained Other embodiments.
[0040] In order to make the drawings concise, the drawings only schematically show the parts related to the present invention, and they do not represent the actual structure of the product. In addition, in order to make the drawings concise and easy to understand, in some drawings, only one of the components with the same structure or function is schematically shown, or only one of them is marked. In this article, "a" not only means "only this one", but can also mean "more than one".
[0041] Such as figure 1 As shown, according to an embodiment of the present invention, a method for controlling an air purifier includes:
[0042] S1. Obtain multiple sets of working time period information of an air purifier;
[0043] S2. Run a cluster analysis algorithm on the multiple sets of working time period information to obtain the most frequently used working time period of the air purifier;
[0044] S3. Perform an automatic adjustment action on the on-off state of the air purifier according to the most frequently used working time period.
[0045] In a specific embodiment of the present invention, the method further includes: the cluster analysis algorithm is the K-MEANS algorithm. K-MEANS clustering analysis algorithm is an indirect clustering method based on the similarity measurement between samples, which is an unsupervised learning method. This algorithm uses k as a parameter to divide n objects into k clusters, so that the clusters have a higher degree of similarity, and the similarity between clusters is lower. The similarity is calculated based on the average value of the objects in a cluster (which is regarded as the center of gravity of the cluster). This algorithm first randomly selects k objects, and each object represents the centroid of a cluster. For each remaining object, according to the distance between the object and the centroid of each cluster, assign it to the most similar cluster. Then, calculate the new centroid of each cluster. Repeat the above process until the criterion function converges. The K-MEANS clustering analysis algorithm is a typical dynamic clustering algorithm with point-by-point modification and iteration. The main point is that the sum of squares of errors is the criterion function. The present invention uses the K-MEANS cluster analysis algorithm to obtain the historical working time period information of the air purifier, learns and analyzes the data information, and obtains the most frequently used working time period of the air purifier, and according to the most frequent The working time period and the current air quality information are combined to realize the control of the air purifier and make the use of the air purifier more user-friendly.
[0046] In a specific embodiment of the present invention, the method further includes: receiving monitoring information sent by an air purifier, where the monitoring information includes current air quality information; and intervening in the automation of step S3 according to the current air quality information Adjust behavior. The air purifier monitors the current air quality and sends the monitoring information to the cloud server. The monitoring information includes the current air quality information. The cloud server obtains the monitoring information, and intervenes in the automated adjustment behavior of step S3 according to the current air quality information.
[0047] In a specific embodiment of the present invention, the intervention in the automated adjustment behavior of step S3 includes: if the current time is in the most frequently used working period and the current air quality information is lower than a preset air quality threshold , Turn on the air purifier, for example, if the current time is in the most frequently used working time period and the current air quality information is poor, turn on the air purifier. If the current time is not in the most frequently used working time period and the current air quality information is lower than a preset air quality threshold, the user is reminded whether to turn on the air purifier, if the current time is not in the most frequently used When the working time period and the current air quality information is bad, the user is reminded whether to turn on the air purifier, so as to improve the current air quality. If the current time is in the most frequently used working period, and the current air quality information is higher than a preset air quality threshold, the air purifier is turned off, for example, if the current time is in the most frequently used working period When the time period and the current air quality information is good, the air purifier is turned off to save resources for the user. If the current time is not in the most frequently used working period, and the current air quality information is higher than a preset air quality threshold, turn off the air purifier, if the current time is not in the most frequently used working time When the current air quality information is good, turn off the air purifier.
[0048] Specifically, the step S1 further includes: obtaining wind speed data information corresponding to each group of working time period information of an air purifier. Record the working time period information of the air purifier and the corresponding wind speed data information. The working time period information includes the power-on time and the power-off time. When the air purifier is turned on and off, record the power on time and off time of the air purifier. And record the wind speed data information of the air purifier under the current working time. The air purifier sends the working time period information and wind speed data information to a cloud server. The cloud server saves the working time period information and wind speed data information. After a period of recording, the cloud server stores multiple groups of air purifier working time period information and wind speed data information. Provides analysis data objects for K-MEANS cluster analysis algorithm.
[0049] The cloud server obtains working time period information and wind speed data information of the air purifier. According to the K-MEANS clustering analysis algorithm, the working time period information and wind speed data information of n groups of air purifiers are taken as data objects, and k groups of data objects are arbitrarily selected from the n groups of data objects as initial clustering centers. Obtain the average value of each group of data objects, that is, obtain the center value of the cluster objects, calculate the distance between each group of data objects and these center values, and re-divide the corresponding data objects according to the minimum distance, that is, in the k In the group of data objects, the difference between each group of data objects and the central value is calculated, and the corresponding data objects are re-divided according to the minimum difference, and the initial clustering result is formed, completing an iteration. After the re-divided data object, if the central value changes, the average value of the data object with the changed central value is recalculated. Repeat the iterative process and change the center value until the calculated new center value is equal to the original center value or less than the specified threshold, which means that the function has converged and the algorithm is completed. The new center value is the most frequently used air purifier The working time period and the corresponding wind speed parameters.
[0050] Through this technical solution, the historical data information of the smart air purifier is studied and analyzed, and the user's habitual behavior of using the smart air purifier is analyzed, so as to turn on and off the air purification for the user according to the user's habitual behavior and current air quality information The air purifier and adjusting the wind speed of the air purifier make the use of the air purifier more intelligent and user-friendly, and it also reduces the user's frequent manual operation of the smart air purifier, bringing a good experience to the user.
[0051] Such as figure 2 As shown, an embodiment of the present invention, a cloud server, includes:
[0052] The obtaining module 20 obtains multiple sets of working time period information of an air purifier;
[0053] The analysis module 21 runs a cluster analysis algorithm on the multiple sets of working time period information to obtain the most frequently used working time period of the air purifier;
[0054] The control module 22 performs an automatic adjustment action on the on-off state of the air purifier according to the most frequently used working time period.
[0055] In the acquisition module, the wind speed data information corresponding to each group of working time period information of an air purifier is also acquired. The acquiring module acquires working time period information of the air purifier and corresponding wind speed data information, and the working time period information includes power-on time and power-off time. After a period of recording, multiple groups of air purifier working time information and wind speed data information are stored. Provides analysis data objects for K-MEANS cluster analysis algorithm.
[0056] In the analysis module, the cluster analysis algorithm includes the K-MEANS algorithm. According to the K-MEANS clustering analysis algorithm, the working time period information and wind speed data information of n groups of air purifiers are taken as data objects, and k groups of data objects are arbitrarily selected from the n groups of data objects as initial clustering centers. Obtain the central value of each group of data objects, among the k groups of data objects, calculate the difference between each group of data objects and the central value, and re-divide the corresponding data objects according to the minimum difference, and form an initial cluster As a result, one iteration is completed. After the re-divided data object, if the central value changes, the average value of the data object with the changed central value is recalculated. Repeat the iterative process and change the center value until the calculated new center value is equal to the original center value or less than the specified threshold, which means that the function has converged and the algorithm is completed. The new center value is the most frequently used air purifier The working time period and the corresponding wind speed parameters.
[0057] In a specific embodiment of the present invention, the cloud server further includes an air monitoring module for receiving monitoring information sent by an air purifier, the monitoring information including current air quality information, and intervening according to the current air quality information The automatic adjustment behavior of the control module.
[0058] The control module performs an automatic adjustment action on the on-off state of the air purifier according to the most frequently used working time period. In a specific embodiment of the present invention, the control module includes a first execution unit, a second execution unit, a third execution unit, and a fourth execution unit. In the first execution unit, if the current time is in the most frequently used working time period and the current air quality information is lower than a preset air quality threshold, the air purifier is turned on. In the second execution unit, if the current time is not in the most frequently used working time period and the current air quality information is lower than a preset air quality threshold, the user is reminded whether to turn on the air purifier. In the third execution unit, if the current time is in the most frequently used working time period and the current air quality information is higher than a preset air quality threshold, the air purifier is turned off. In the fourth execution unit, if the current time is not in the most frequently used working time period, and the current air quality information is higher than a preset air quality threshold, the air purifier is turned off.
[0059] Through this technical solution, the use of the smart air purifier is more intelligent and humanized, and the user's frequent manual operation of the smart air purifier is also reduced, which brings a better experience to the user.
[0060] Such as image 3 As shown, an embodiment of the present invention is an air purifier control system. The system includes at least one air purifier 30 and the cloud server 31 described above. Specifically, the air purifier records working time period information and wind speed data information corresponding to each group of working time period information. The working time period information includes power-on time and power-off time. The air purifier sends working time period information and wind speed data information to the cloud server. The cloud server stores working time period information and wind speed data information. After multiple data records, the cloud server obtains multiple sets of working time period information of the air purifier, and wind speed data information corresponding to each set of working time period information. The cloud server runs the K-MEANS clustering analysis algorithm on the multiple sets of working time period information to obtain the most frequently used working time period of the air purifier, and according to the most frequently used working time period, The on-off state of the air purifier performs an automatic adjustment action.
[0061] In summary, through the technical solution of the present invention, the use of the smart air purifier is more intelligent and humanized, and the user has a better experience.
[0062] It should be noted that the above embodiments can be freely combined as required. The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications are also It should be regarded as the protection scope of the present invention.