Air conditioner control method, device, apparatus, and storage medium

Abstract

The application provides an air conditioner control method, device, equipment and storage medium. The air conditioner control method comprises the following steps: obtaining historical use data and current operation data corresponding to a target air conditioner; performing clustering processing according to the historical use data and target clustering parameters to obtain an air conditioner habit mode of the target air conditioner; determining a target habit mode in the air conditioner habit mode according to an associated dimension weight of the air conditioner habit mode and a habit mode strategy, the associated dimension weight being a weight parameter representing the quantitative quality of the air conditioner habit mode in a specified dimension; and performing air conditioner forgetting to turn off control according to the target habit mode and the current operation data to obtain an air conditioner control result. The application can accurately identify whether the user forgets to turn off the air conditioner without additional detection hardware during air conditioner operation, and performs corresponding air conditioner control processing when the user forgets to turn off the air conditioner, thereby reducing power consumption caused by forgetting to turn off the air conditioner, effectively reducing air conditioner detection costs and improving air conditioner energy-saving effect.

Description

Technical Field

[0001] This application relates to the field of air conditioning control technology, specifically to an air conditioning control method, device, equipment, and storage medium. Background Technology

[0002] Currently, with the rapid development of air conditioning technology, more and more users are using air conditioners for air conditioning. However, users commonly forget to turn off their air conditioners, leading to unnecessary energy waste and economic losses. Existing methods for detecting forgotten air conditioner shutdowns involve adding various sensors, significantly increasing hardware costs. Furthermore, the detection process is easily affected by environmental factors, resulting in low accuracy and a high risk of false positives and false negatives, thus impacting the user experience. Summary of the Invention

[0003] This application provides an air conditioning control method, apparatus, device, and storage medium, aiming to solve the technical problems of high cost and low accuracy in detecting air conditioners left on.

[0004] On one hand, embodiments of this application provide an air conditioning control method, which includes the following steps: Obtain historical usage data and current operating data for the target air conditioner; Clustering is performed based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The target habit pattern in the air conditioning habit pattern is determined based on the association dimension weights and habit pattern strategy of the air conditioning habit pattern. The association dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. Based on the target habit mode and the current operating data, the air conditioner is controlled to prevent it from turning off, and the air conditioner control result is obtained.

[0005] In one possible implementation of this application, determining the target habit pattern in the air conditioning habit pattern based on the association dimension weight and habit pattern strategy includes: Obtain the multimodal correlation parameters corresponding to the air conditioning habit mode; The association dimension weights of the air conditioning habit patterns are calculated based on the multimodal association parameters. The target habit pattern in the air conditioning habit pattern is selected based on the associated dimension weights and habit pattern strategy.

[0006] In one possible implementation of this application, the association dimension weights include any one or more of time dimension weights, quality dimension weights, frequency dimension weights, consistency dimension weights, and seasonal dimension weights; the step of calculating the association dimension weights of the air conditioning habit pattern based on the multimodal association parameters includes: Obtain the operating date difference corresponding to the air conditioner habit mode, and calculate the time dimension weight of the air conditioner habit mode based on the operating date difference, time decay factor and time weight function; And / or, obtain the clustering ratio and clustering data volume corresponding to the air conditioning habit pattern, and calculate the quality dimension weight of the air conditioning habit pattern based on the clustering ratio and the clustering data volume; And / or, calculate the frequency dimension weight of the air conditioning habit pattern based on the amount of clustered data corresponding to the air conditioning habit pattern and the amount of historical usage data; And / or, calculate the consistency dimension weight of the air conditioning habit pattern based on the consistency data corresponding to the air conditioning habit pattern; And / or, determine the seasonal dimension weight of the air conditioning habit mode based on the temperature identifier and month identifier corresponding to the air conditioning habit mode.

[0007] In one possible implementation of this application, selecting a target habit pattern from the air conditioning habit patterns based on the associated dimension weights and habit pattern strategy includes: If the habit pattern strategy is a comprehensive evaluation strategy, then the first target habit weight corresponding to the air conditioning habit pattern is obtained by weighting the weight of each associated dimension of the air conditioning habit pattern and the associated weight coefficient corresponding to the associated dimension weight and the normalization coefficient, and the air conditioning habit pattern with the highest first target habit weight is determined as the target habit pattern.

[0008] If the habit pattern strategy is a single evaluation strategy, then the weight of the associated dimension corresponding to the single evaluation strategy is determined as the second target habit weight in the air conditioning habit pattern, and the air conditioning habit pattern with the highest second target habit weight is determined as the target habit pattern.

[0009] In one possible implementation of this application, clustering is performed based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner, including: Obtain the neighborhood range parameter from the target clustering parameters and the target sampling quantity corresponding to the historical usage data; Feature extraction is performed on the historical usage data to obtain the historical usage features corresponding to the historical usage data; The historical usage features are clustered based on the neighborhood range parameter and the target sampling quantity to obtain historical data clusters. The air conditioning habit pattern of the target air conditioner is generated based on the historical data clusters and the cluster labels of the historical data clusters.

[0010] In one possible implementation of this application, obtaining the neighborhood range parameter in the target clustering parameters and the target sampling quantity corresponding to the historical usage data includes: If the number of historical data points in the historical usage data is greater than a preset threshold, a target nearest neighbor distance function corresponding to the historical usage data is generated. The neighborhood range parameter of the historical usage data is determined based on the inflection point of the function curve in the target nearest neighbor distance function. The target sampling quantity corresponding to the historical usage data is calculated based on the number of times the device was powered on and the preset frequency coefficient in the historical usage data.

[0011] In one possible implementation of this application, the air conditioner is left on for a while based on the target habit pattern and the current operating data to obtain the air conditioner control result, including: Obtain the predicted running data corresponding to the target habit pattern, and calculate the running deviation data between the predicted running data and the current running data; If the operating deviation data is greater than the preset operating deviation threshold, then the operating mode of the target air conditioner is determined to be the "forgot to turn off" mode. Based on the operating scenario type corresponding to the current operating data and the forgotten-to-turn-off mode, the air conditioner is controlled to achieve the air conditioner control result.

[0012] In one possible implementation of this application, the air conditioner is controlled to turn off based on the operating scenario type corresponding to the current operating data and the forgotten-to-turn-off mode, and the air conditioner control result is obtained, including: The running scenario type corresponding to the current running data is determined based on the boot-up and running time of the current running data. If the operating scenario is a reminder-to-operate scenario, then calculate the power consumption value of the target air conditioner in the forget-to-turn-off mode. The target air conditioner is switched to standby mode, and a reminder message for forgetting to turn off is generated based on the power consumption value for forgetting to turn off and the forgetting to turn off event corresponding to the forgetting to turn off mode, and the reminder message for forgetting to turn off is output.

[0013] On the other hand, this application provides an air conditioning control device, the air conditioning control device comprising: The data acquisition module is configured to acquire historical usage data and current operating data corresponding to the target air conditioner; The habit clustering module is configured to perform clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The multidimensional evaluation module is configured to determine the target habit pattern in the air conditioning habit pattern based on the associated dimension weights and habit pattern strategy of the air conditioning habit pattern, wherein the associated dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. The air conditioning control module is configured to control the air conditioning to turn off when not turned off based on the target habit mode and the current operating data, and obtain the air conditioning control result.

[0014] On the other hand, this application also provides an air conditioning control device, the air conditioning control device comprising: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the air conditioning control method.

[0015] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the steps in the air conditioning control method.

[0016] This application obtains historical usage data and current operating data of a target air conditioner; performs clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit patterns of the target air conditioner; determines the target habit pattern among the air conditioning habit patterns based on the association dimension weights and habit pattern strategies of the air conditioning habit patterns, where the association dimension weights are weight parameters characterizing the quantitative quality of the air conditioning habit patterns in a specified dimension; and performs air conditioning forget-to-turn-off control based on the target habit patterns and the current operating data to obtain the air conditioning control result. This achieves the following: during the operation of the target air conditioner, historical usage data and current operating data of the target air conditioner are obtained, and density-based clustering processing is performed on the historical usage data using target clustering parameters to obtain the air conditioning usage habits of multiple target air conditioners. The association dimension weights corresponding to the air conditioning habit patterns are calculated, and the target habit pattern among the air conditioning usage habits is selected based on the association dimension weights and habit pattern strategies for forget-to-turn-off control. This enables accurate identification of whether a user has forgotten to turn off the air conditioner during operation without additional detection hardware, and performs corresponding air conditioning control processing when the air conditioner is forgotten to turn off, reducing power consumption caused by forgetting to turn off the air conditioner, effectively reducing air conditioner detection costs, and improving air conditioner energy-saving performance. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of a scenario for the air conditioning control method according to an embodiment of this application; Figure 2 This is a flowchart illustrating one embodiment of the air conditioning control method in this application. Figure 3 A flowchart illustrating one embodiment of the air conditioning control method for determining a target habitual pattern provided in this application; Figure 4 A flowchart illustrating an embodiment of the air conditioning control method provided in this application for controlling an air conditioner that has not been turned off; Figure 5 A schematic diagram of the structure of one embodiment of the air conditioning control device provided in this application; Figure 6 This is a schematic diagram of one embodiment of the air conditioning control device provided in this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0022] Currently, with the rapid development of air conditioning technology, more and more users are using air conditioners for air conditioning. However, users commonly forget to turn off their air conditioners, leading to unnecessary energy waste and economic losses. Existing methods for detecting forgotten air conditioner shutdowns involve adding various sensors, significantly increasing hardware costs. Furthermore, the detection process is easily affected by environmental factors, resulting in low accuracy and a high risk of false positives and false negatives, thus impacting the user experience.

[0023] Based on this, this application proposes an air conditioning control method, apparatus, device, and computer-readable storage medium to solve the technical problems of high cost and low detection accuracy of air conditioning forgetting to be turned off in the prior art.

[0024] The air conditioning control method in this embodiment of the invention is applied to an air conditioning control device, which is set in an air conditioning control equipment. The air conditioning control equipment is provided with one or more processors, a memory, and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the air conditioning control method. The air conditioning control equipment can be any type of target air conditioner itself, or a smart terminal that communicates with the air conditioner, such as a mobile phone, tablet computer, smart home device, network device, and smart computer. Optionally, the air conditioning control equipment can also be a server or a service cluster composed of multiple servers.

[0025] like Figure 1 As shown, Figure 1 This is a schematic diagram of a scenario for an air conditioning control method according to an embodiment of the present application. In this embodiment of the present invention, the air conditioning control scenario includes an air conditioning control device 100 (the air conditioning control device 100 integrates an air conditioning control unit), and the air conditioning control device 100 is equipped with a computer-readable storage medium corresponding to the air conditioning control method to execute the steps of the air conditioning control method.

[0026] Understandable Figure 1 The air conditioning control device in the air conditioning control method scenario shown, or the device included in the air conditioning control device, does not constitute a limitation on the embodiments of the present invention. That is, the number or type of air conditioning control device included in the air conditioning control method scenario, or the number or type of device included in each device, does not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0027] In this embodiment of the invention, the air conditioning control device 100 is mainly used to: acquire historical usage data and current operating data corresponding to the target air conditioner; Clustering is performed based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The target habit pattern in the air conditioning habit pattern is determined based on the association dimension weights and habit pattern strategy of the air conditioning habit pattern. The association dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. Based on the target habit mode and the current operating data, the air conditioner is controlled to prevent it from turning off, and the air conditioner control result is obtained.

[0028] The air conditioning control device 100 in this embodiment of the invention can be any type of target air conditioner itself, or a smart terminal that communicates with the air conditioner, such as a mobile phone, tablet computer, smart forget-to-turn-off device, network device, and smart computer; optionally, the air conditioning control device can also be a server, or a service cluster composed of multiple servers.

[0029] This application provides an air conditioning control method, apparatus, device, and computer-readable storage medium, which will be described in detail below.

[0030] It will be understood by those skilled in the art that Figure 1 The application environment shown is only one application scenario related to the solution of this application and does not constitute a limitation on the application scenario of this application. Other application environments may include more than one application scenario. Figure 1 The number of more or fewer air conditioning control devices shown, or the air conditioning control network connections, for example Figure 1 Only one air conditioning control device is shown in the figure. It is understood that the scenario of the air conditioning control method may also include one or more air conditioning control devices, which are not limited here. The air conditioning control device 100 may also include a memory for storing historical usage data and other data.

[0031] It should be noted that, Figure 1The schematic diagram of the air conditioning control method shown is merely an example. The scenarios of the air conditioning control method described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention and do not constitute a limitation on the technical solutions provided in the embodiments of the present invention.

[0032] Based on the scenarios described above for air conditioning control methods, various embodiments of the air conditioning control method disclosed in this invention are proposed.

[0033] like Figure 2 As shown, Figure 2 This is a flowchart illustrating one embodiment of the air conditioning control method in this application. The air conditioning control method includes the following steps 201 to 204: 201. Obtain the historical usage data and current operating data corresponding to the target air conditioner; The air conditioning control method in this embodiment is applied to an air conditioning control device. The type and number of air conditioning control devices are not specifically limited. That is, the air conditioning control device can be one or more target air conditioners of any type, or a smart terminal that communicates with the air conditioner, such as a mobile phone, tablet computer, smart forget-to-turn-off device, network device, and smart computer.

[0034] Optionally, the target air conditioner can be any type of air conditioner that is currently in operation and is used to condition the air in the target operating area. For example, the target air conditioner can be any one or more of a wall-mounted air conditioner, floor-standing air conditioner, and distributed air conditioning system that is currently in operation.

[0035] Optionally, the historical usage data refers to the operating data of the target air conditioner during its past operation, used to record the on / off time data and related data information of the target air conditioner during its past operation. Optionally, in one specific embodiment, the historical usage data is a combination of the air conditioner's on-time and corresponding off-time recorded during its past operation. Optionally, in other embodiments, the historical usage data further includes related data information recording the air conditioner's on-time and off-time. Optionally, in one specific embodiment, the related data information includes any one or more of the following: ambient temperature identifier, operating date type, operating month information, and operating geographic information.

[0036] Optionally, the air conditioner start-up time refers to the start-up time of the target air conditioner during its past operation for air conditioning. The air conditioner shutdown time refers to the time data of when the target air conditioner shuts down after each operation.

[0037] Optionally, the ambient temperature identifier is a temperature classification identifier that characterizes the operating environment of the target air conditioner during operation. Optionally, in a specific embodiment, the ambient temperature identifier is a cooling period temperature identifier that characterizes an ambient temperature higher than a first temperature threshold (e.g., 30 degrees Celsius), a heating period temperature identifier that characterizes an ambient temperature lower than a second temperature threshold (e.g., 16 degrees Celsius or other temperature parameters), and a transition period temperature identifier that characterizes an ambient temperature higher than the second temperature threshold and lower than the first temperature threshold.

[0038] Optionally, the running date type is a classification identifier that characterizes the running dates of the target air conditioner during operation. Optionally, in a specific embodiment, the running date type includes weekday type, weekend type, and holiday type.

[0039] Optionally, the operating month information refers to the month information representing the target air conditioner during its operation. This operating month information can be any month in the Gregorian calendar (i.e., any month from January to December). The operating geographic information refers to the geographic location information representing the operating area corresponding to the target air conditioner. Optionally, in a specific embodiment, this operating geographic information can be the latitude and longitude information of the operating area corresponding to the target air conditioner, or other geographic location information capable of geographic positioning.

[0040] Optionally, the current operating data refers to the statistical operating time of the target air conditioner under the current time sequence. This current operating data includes the current start-up time and current running duration of the target air conditioner under the current time sequence.

[0041] Optionally, after obtaining the historical usage data and current operating data of the target air conditioner, the terminal may further cluster the historical usage data in subsequent steps to determine the user's air conditioner usage habits. Then, based on the air conditioner usage habits and current operating data, it may determine whether the user has forgotten to turn off the air conditioner, so as to control the air conditioner to be turned off when the user forgets to turn it off.

[0042] 202. Perform clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; Optionally, after obtaining the historical usage data of the target air conditioner, the terminal can also perform clustering processing based on the historical usage data and the target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner.

[0043] Optionally, the target clustering parameter is a clustering parameter used to cluster historical usage data to identify past usage patterns of air conditioners. Optionally, in a specific embodiment, the target clustering parameter includes a neighborhood range parameter and a target sampling number.

[0044] Optionally, the neighborhood range parameter is a parameter that defines the neighborhood range of data points during the clustering process, used to evaluate the distance threshold for whether any two data points are neighboring data points during the clustering process. Optionally, the target sampling number is the minimum number of neighbors required to characterize the core data point (i.e., the starting point of the cluster) corresponding to the air conditioning habit pattern cluster obtained during the clustering process.

[0045] Optionally, the air conditioner habit pattern is a classification of users' past usage habits of the target air conditioner, obtained by clustering historical usage data. Specifically, this air conditioner habit pattern records the habitual patterns of air conditioner start-up and shutdown times under different operating scenarios.

[0046] Optionally, after acquiring historical usage data, the air conditioning control device further acquires the target clustering parameters corresponding to the historical usage data, and extracts the neighborhood range parameter and the target sampling quantity corresponding to the historical usage data from the target clustering parameters.

[0047] Optionally, the air conditioning control device statistically analyzes the acquired historical usage data to obtain the number of historical data points corresponding to the historical usage data, and determines the neighborhood range parameter of the historical usage data by combining the number of historical data points with a preset quantity threshold. Optionally, in one specific embodiment, the preset quantity threshold is set to 10. Optionally, in other embodiments, the preset quantity threshold can be set to other quantity parameters according to the actual application scenario.

[0048] Optionally, if the number of historical data points is less than the preset number of data points, the air conditioning control device will determine the pre-stored default range parameter as the neighborhood range parameter corresponding to the historical usage data. Optionally, in a specific embodiment, the default range parameter is 120, that is, the range of the default range parameter is a 120-minute neighborhood range.

[0049] Optionally, if the number of historical data points in the historical usage data is greater than the preset number of data points, the air conditioning control device uses a target nearest neighbor distance function to calculate the neighborhood range parameter of the historical usage data. That is, the air conditioning control device calculates the target nearest neighbor distance between the target nearest neighbor points corresponding to each historical data point in the historical usage data, and fits the target nearest neighbor distance to obtain the target nearest neighbor distance function. Here, the target nearest neighbor distance is a quantitative parameter characterizing the distance between each historical data point and its corresponding target nearest neighbor point in the historical usage data. Optionally, the target nearest neighbor points are several nearest data points adjacent to the historical data points. Optionally, in a specific embodiment, the number of target nearest neighbor points is associated with a preset k value. In a specific embodiment, the k value is 4, that is, the air conditioning control device constructs a nearest neighbor graph with k=4 and generates the corresponding target nearest neighbor distance function. Optionally, in a specific embodiment, the target nearest neighbor distance function is a k-nearest neighbor graph function with k=4.

[0050] Optionally, after obtaining the target nearest neighbor distance function, the air conditioning control device also obtains the inflection point of the function curve in the target nearest neighbor function, and determines the inflection point of the function curve as the neighborhood range parameter of the historical usage data, thereby automatically determining the neighborhood range parameter of the historical usage data to balance the compactness and separation of clustering in subsequent steps.

[0051] Optionally, the air conditioning control device further calculates the target sampling quantity corresponding to the historical usage data based on the number of times the device has been turned on and a preset frequency coefficient. Specifically, the air conditioning control device calculates the product of the number of times the device has been turned on and the preset frequency coefficient to obtain the target number of times the device has been turned on, and determines the target sampling quantity of the historical usage data by using the target number of times the device has been turned on and a minimum limit quantity. The preset frequency coefficient is a pre-set coefficient parameter used to calculate the number of times the device has been turned on. Optionally, in one specific embodiment, the preset frequency coefficient is 1 / 5; the minimum limit quantity is the minimum sampling quantity required to ensure that the generated target sampling quantity meets the clustering statistical requirements. Optionally, in one specific embodiment, the minimum limit quantity is 5, and the formula for calculating the target sampling quantity is:

[0052] in, For the target number of samples, this The number of times the device is powered on is 1 / n, which is a preset number of times coefficient, and 5 is the minimum number of samples. Optionally, in other embodiments, the minimum number of samples can also be set to other values ​​greater than or equal to 4.

[0053] Optionally, after acquiring historical usage data of the target air conditioner, the air conditioning control device performs feature extraction on the historical usage data to obtain historical usage features corresponding to the historical usage data. Optionally, the historical usage features are feature representation information corresponding to the historical usage data. Optionally, in a specific embodiment, the historical usage features include any one or more of the historical time features, historical environmental features, historical statistical features, and historical power consumption features corresponding to the historical usage data. Among them, the historical time features include any one or more of the historical power-on time features, historical power-off time features, and historical operation duration features corresponding to the historical usage data. The historical environmental features include any one or more of the temperature identification features, date type features, and operating month features. The historical power consumption features are feature information characterizing the power consumption in the historical usage data. Optionally, in a specific embodiment, the historical power consumption features include any one or more of the unit power consumption features, cumulative power consumption features, and cumulative operating time features.

[0054] Optionally, after acquiring historical usage characteristics, the air conditioning control device performs clustering processing on the historical usage characteristics based on the neighborhood range parameter and the target sampling quantity to obtain historical data clusters. These historical data clusters are sets of historical usage characteristics belonging to the same usage habit category. Optionally, in a specific embodiment, the air conditioning control device uses DBSCAN clustering to perform clustering processing on the historical usage characteristics.

[0055] Optionally, after acquiring historical data clusters, the air conditioning control device also sets corresponding cluster labels for the usage habit categories corresponding to each historical data cluster, and generates the air conditioning habit pattern of the target air conditioner based on the historical data clusters and their cluster labels. That is, after generating the cluster labels, the air conditioning control device determines the usage habit pattern corresponding to the cluster labels as the air conditioning habit pattern of the target air conditioner. The cluster label records the label information corresponding to the air conditioning habit pattern, the air conditioner's start-up and shutdown times, and the associated data labels corresponding to the air conditioning habit pattern (such as ambient temperature identifier, operating date type, operating month information, and operating geographical information). Historical data points with the same cluster label belong to the same air conditioning habit pattern.

[0056] Optionally, after acquiring the historical data clusters, the air conditioning control device further filters the target air conditioner's air conditioning usage patterns based on the sample size of each cluster. That is, the air conditioning control device sorts the historical data clusters in descending order of sample size, and identifies historical data clusters with a sorting number less than a preset threshold as air conditioning usage habits. In one specific embodiment, this preset threshold is 3. That is, the air conditioning control device identifies the top three historical data clusters with the largest sample sizes as air conditioning usage habits. Optionally, in other embodiments, this preset threshold can be set to a larger or smaller threshold value according to actual evaluation needs.

[0057] Optionally, in other embodiments, after acquiring the air conditioning habit pattern, the air conditioning control device also acquires the main cluster proportion and centroid distance of the historical data clusters corresponding to the air conditioning habit pattern, and evaluates the reliability of the air conditioning habit pattern through the main cluster proportion and centroid distance. The main cluster proportion represents the ratio between the number of cluster samples in each air conditioning habit pattern and the total number of valid samples. The centroid distance represents the distance from the historical data point in the historical data cluster corresponding to the air conditioning habit pattern to the average centroid of the cluster.

[0058] Optionally, if the main cluster proportion of the air conditioning habit mode is less than a preset proportion threshold or the centroid distance is greater than a preset distance threshold, then the reliability of the air conditioning habit mode is determined to be low. Optionally, in a specific embodiment, the preset proportion threshold is 0.2; the preset distance threshold is 100 (unit: minutes).

[0059] 203. Determine the target habit pattern in the air conditioning habit pattern based on the association dimension weights and habit pattern strategy of the air conditioning habit pattern; Optionally, after obtaining the various air conditioning habit modes of the target air conditioner, the air conditioning control device further filters the air conditioning habit modes according to the correlation dimension weight and habit mode strategy, so as to obtain the air conditioning operation mode that best matches the current operating conditions as the target habit mode.

[0060] Optionally, the association dimension weight is a weight parameter that characterizes the quantitative quality of air conditioning habit patterns in a specified dimension, and is used to evaluate the quality of user habit clustering of air conditioning habit patterns in the specified dimension. Optionally, the association dimension weight includes any one or more of the following: time dimension weight, quality dimension weight, frequency dimension weight, consistency dimension weight, and seasonal dimension weight.

[0061] Optionally, the time dimension weight is weight information for evaluating the effectiveness and importance of changes in air conditioning habit patterns over time.

[0062] Optionally, the quality dimension weights are weighted information used to evaluate the quality of air conditioning habit pattern clustering data. They are used to determine the clustering data quality of air conditioning habit patterns by considering the clustering ratio and data volume, thereby determining the stability of the air conditioning habit pattern. That is, the higher the quality dimension weight of an air conditioning habit pattern, the more stable the user habits corresponding to that pattern.

[0063] Optionally, the frequency dimension weight is the weight information for evaluating the usage frequency corresponding to the air conditioning habit mode, which is used to reflect the importance of the usage frequency.

[0064] Optionally, the consistency dimension weight is the weight information used to assess the stability of the air conditioner usage time corresponding to the air conditioner habit mode, that is, to assess whether the air conditioner start time and air conditioner turn-off time corresponding to the air conditioner habit mode are stable and consistent.

[0065] Optionally, the seasonal dimension weight is weight information that adjusts the weight of air conditioning habit patterns based on seasonal characteristics.

[0066] Optionally, the habit pattern strategy is a screening strategy used to filter air conditioning habit patterns based on the weights of related dimensions. This habit pattern strategy includes a comprehensive evaluation strategy and a single evaluation strategy. The comprehensive evaluation strategy uses a first target habit weight obtained by weighted summing of the weights of each related dimension and the related weight coefficients to screen air conditioning habit patterns. The single evaluation strategy uses a single related dimension weight to screen air conditioning habit patterns.

[0067] Optionally, after acquiring each air conditioning habit mode, the air conditioning control device also provides multimodal association parameters corresponding to the air conditioning habit mode. These multimodal association parameters are multi-dimensional parameters used to calculate the weighted data corresponding to different dimensions. Optionally, in a specific embodiment, these multimodal association parameters include multi-dimensional parameters such as the difference in operating dates, clustering ratio, cluster data volume, historical usage data volume, consistency data, temperature identifier, and month identifier.

[0068] Optionally, after obtaining the multimodal association parameters, the air conditioning control device also calculates the association dimension weight of the air conditioning habit mode based on the multimodal association parameters, and selects the target habit mode in the air conditioning habit mode based on the association dimension weight and the habit mode strategy.

[0069] Optionally, in one specific embodiment, the air conditioning control device obtains the operating date difference corresponding to the air conditioning habit mode, and calculates the time dimension weight of the air conditioning habit mode based on the operating date difference, the time decay factor, and the time weight function. That is, the air conditioning control device obtains the average operating date in each air conditioning habit mode, calculates the date difference between the average operating date and the current operating date corresponding to the current operating data, obtains the operating date difference, and calculates the time dimension weight of the air conditioning habit mode based on the operating date difference, the time decay factor, and the time weight function. The time decay factor is a calculation coefficient used to reduce the influence of historical data on the current prediction process. Optionally, in one specific embodiment, the time decay factor is set to 0.1. The expression of the time weight function is as follows:

[0070] in, Weights are based on the time dimension. The time decay factor, This is the difference between the running date and the date of execution.

[0071] Optionally, in another specific embodiment, the air conditioning control device further acquires the clustering ratio and clustering data volume corresponding to the air conditioning habit pattern, and calculates the quality dimension weight of the air conditioning habit pattern based on the clustering ratio and the clustering data volume. That is, the air conditioning control device acquires the clustering data volume and the total effective clustering data volume of the air conditioning habit pattern, calculates the ratio of the clustering data volume to the total effective clustering data volume to obtain the clustering ratio of the air conditioning habit pattern, and performs a logarithmic operation on the clustering data volume and the sample size of the largest cluster during the clustering process to obtain the clustering data volume weight.

[0072] Optionally, after obtaining the clustering ratio and cluster data volume weight, the air conditioning control device further uses the clustering ratio weight to weight the clustering ratio, and the data volume weight to weight the cluster data volume, and then performs a weighted sum to obtain the quality dimension weight. Optionally, in a specific embodiment, the calculation method of the quality dimension weight is as follows:

[0073] in, For the weight of the quality dimension, For clustering ratio, The clustering data volume weights are 0.6 and 0.4, respectively. Optionally, these clustering proportion weights and data volume weights can be adjusted according to actual needs.

[0074] Optionally, the air conditioning control device can also calculate the frequency dimension weight of the air conditioning habit pattern based on the amount of clustered data corresponding to the air conditioning habit pattern and the amount of historical usage data. That is, the air conditioning control device calculates the ratio of the amount of clustered data to the amount of historical usage data to obtain the frequency dimension weight of the air conditioning habit pattern, thereby determining the importance of the usage frequency of the air conditioning habit pattern.

[0075] Optionally, the air conditioning control device can also calculate the consistency dimension weight of the air conditioning habit mode based on the consistency data corresponding to the air conditioning habit mode. This consistency data represents the consistency of the air conditioning start-up standard deviation, air conditioning shutdown standard deviation, and proportional standard deviation corresponding to the air conditioning habit mode. The consistency data includes start-up standard deviation consistency data, shutdown standard deviation consistency data, and proportional standard deviation consistency data. Start-up standard deviation consistency data represents the degree of consistency of the start-up time standard deviation of each cluster of data in the air conditioning habit mode. Shutdown standard deviation consistency data represents the degree of consistency of the shutdown time standard deviation of each cluster of data in the air conditioning habit mode. Proportional standard deviation is data that assesses the degree of consistency of the proportion of usage time in the air conditioning habit mode. Optionally, after obtaining the start-up standard deviation consistency data, shutdown standard deviation consistency data, and proportional standard deviation consistency data, the air conditioning control device calculates the average value among these three data points to obtain the consistency dimension weight of the air conditioning habit mode.

[0076] Optionally, the air conditioning control device can also determine the seasonal dimension weight of the air conditioning habit mode based on the temperature and month identifiers corresponding to that habit mode. That is, the air conditioning control device obtains the geographic identifier information corresponding to the target air conditioner, and uses this geographic identifier information to obtain the temperature and month identifiers corresponding to the air conditioning habit mode. Then, it determines the target season identifier for the air conditioning habit mode based on these temperature and month identifiers, and obtains the pre-set seasonal dimension weights associated with this target season identifier. In other words, the air conditioning control device can set different seasonal dimension weights for different months based on the operating mode (e.g., cooling or heating) corresponding to the air conditioning habit mode. For example, when the air conditioning habit mode is cooling, the seasonal dimension weight is highest for summer; when the air conditioning habit mode is heating, the seasonal dimension weight is highest for winter.

[0077] Optionally, after determining the associated dimension weights corresponding to the air conditioning habit mode, the air conditioning control device further selects a target habit mode among the air conditioning habit modes based on the associated dimension weights and the corresponding habit mode strategy. That is, the air conditioning control device determines the target habit weights corresponding to the air conditioning habit modes based on the associated dimension weights and the habit mode strategy, and determines the air conditioning habit mode with the highest target habit weights as the target habit mode.

[0078] 204. Based on the target habit mode and the current operating data, perform air conditioner forget-to-turn-off control to obtain air conditioner control results.

[0079] Optionally, after acquiring the target habitual mode, the air conditioning control device also performs "forgot to turn off" control based on the target habitual mode and current operating data to obtain the air conditioning control result. That is, the air conditioning control device predicts whether the target air conditioner is in a "forgot to turn off" state based on the target habitual mode and current operating data, and performs "forgot to turn off" control on the target air conditioner when it is in a "forgot to turn off" state to obtain the air conditioning control result.

[0080] Optionally, after acquiring the target habit mode, the air conditioning control device acquires the predicted operating data corresponding to the target habit mode and calculates the operating deviation data between the predicted operating data and the current operating data. The predicted operating data is predicted time information obtained by predicting the operating data of the target air conditioner based on the target habit mode. Optionally, the predicted operating data includes predicted start-up time and predicted shutdown time. The predicted start-up time and predicted shutdown time are calculated as follows: Predicted boot time = Mean boot time ± Standard deviation of boot time Standard deviation multiple Predicted shutdown time = Mean shutdown time ± Standard deviation of shutdown time Standard deviation multiple The standard deviation multiplier is a factor that controls the width of the prediction time range.

[0081] Optionally, after acquiring the predicted operating data, the air conditioning control device also calculates the operating deviation data between the current operating data and the predicted operating data. This operating deviation data represents the difference between the current operating time in the current operating data and the predicted shutdown time in the predicted operating data. That is, if the target air conditioner continues to operate after the current operating time has exceeded the time interval corresponding to the predicted shutdown time, the air conditioning control device determines the operating time exceeding the preset shutdown time as the operating deviation data.

[0082] Optionally, if the air conditioning control device determines that the operating deviation data is greater than a preset operating deviation threshold, then the operating mode of the target air conditioner is determined to be the "forgot to turn off" mode. Here, the operating deviation threshold is a duration threshold used to assess whether the target air conditioner is in the "forgot to turn off" mode. Optionally, in a specific embodiment, the operating deviation threshold is 120 minutes. The "forgot to turn off" mode is an operating mode that represents an abnormal, continuous state in which the target air conditioner is in operation for an extended period while performing a normal shutdown procedure.

[0083] Optionally, after determining that the target air conditioner's operating mode is the "forgot to turn off" mode, the air conditioning control equipment performs air conditioner "forgot to turn off" control based on the operating scenario type corresponding to the current operating data and the "forgot to turn off" mode, and obtains the air conditioning control result. This enables the user to perform corresponding air conditioning control processing when forgetting to turn off the air conditioner, reducing power consumption caused by forgetting to turn off the air conditioner, effectively reducing air conditioner detection costs and improving air conditioner energy-saving effect.

[0084] In this embodiment, the air conditioning control device acquires historical usage data and current operating data corresponding to the target air conditioner; performs clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; determines the target habit pattern in the air conditioning habit pattern based on the association dimension weight and habit pattern strategy of the air conditioning habit pattern, wherein the association dimension weight is a weight parameter characterizing the quantitative quality of the air conditioning habit pattern in a specified dimension; and performs air conditioning forget-to-turn-off control based on the target habit pattern and the current operating data to obtain the air conditioning control result. This system acquires historical usage data and current operating data of a target air conditioner during its operation. It then performs density-based clustering on the historical data using target clustering parameters to obtain the air conditioner usage habits of multiple target air conditioners. The system calculates the association dimension weights corresponding to these habit patterns and uses a habit pattern strategy to select target habit patterns for forget-to-turn-off control. This allows for accurate identification of whether a user has forgotten to turn off the air conditioner without additional detection hardware, and enables corresponding air conditioner control when the user forgets to turn it off. This reduces power consumption caused by forgetting to turn off the air conditioner, effectively lowers air conditioner detection costs, and improves energy efficiency.

[0085] like Figure 3 As shown, Figure 3 This is a flowchart illustrating one embodiment of the air conditioning control method for determining a target habitual pattern provided in this application. Figure 3 In the illustrated embodiment, the air conditioning control method further includes steps 301 to 302: 301. If the habit pattern strategy is a comprehensive evaluation strategy, then the first target habit weight corresponding to the air conditioning habit pattern is obtained by weighting the weight of each associated dimension of the air conditioning habit pattern and the associated weight coefficient corresponding to the associated dimension weight and the normalization coefficient, and the air conditioning habit pattern with the highest first target habit weight is determined as the target habit pattern. 302. If the habit pattern strategy is a single evaluation strategy, then the weight of the associated dimension corresponding to the single evaluation strategy is determined as the second target habit weight in the air conditioning habit pattern, and the air conditioning habit pattern with the highest second target habit weight is determined as the target habit pattern.

[0086] Based on the above embodiments, in this embodiment, after determining the associated dimension weights corresponding to the air conditioning habit mode, the air conditioning control device further selects a target habit mode among the air conditioning habit modes according to the associated dimension weights and the corresponding habit mode strategy. That is, the air conditioning control device determines the target habit weight corresponding to the air conditioning habit mode according to the associated dimension weights and the habit mode strategy, and determines the air conditioning habit mode with the highest target habit weight as the target habit mode. The habit mode strategy includes a comprehensive evaluation strategy and a single evaluation strategy. The comprehensive evaluation strategy is a screening strategy that uses the weighted sum of each associated dimension weight and the associated weight coefficient to obtain the first target habit weight for screening air conditioning habit modes. The single evaluation strategy is a strategy that uses a single associated dimension weight to screen air conditioning habit modes.

[0087] Optionally, if the air conditioning control device determines that the habitual pattern strategy is a comprehensive evaluation strategy, it calculates the weighted sum of the weight of each associated dimension of the air conditioning habitual pattern and the associated weight coefficient corresponding to that associated dimension weight to obtain the first target habitual weight corresponding to the air conditioning habitual pattern. Here, the associated weight coefficient is the weight coefficient corresponding to each associated dimension weight predicted by the air conditioning control device through machine learning. Optionally, in a specific embodiment, the associated weight coefficient includes a time weight coefficient, a quality weight coefficient, a frequency weight coefficient, a consistency weight coefficient, and a seasonal weight coefficient. The associated weight coefficient can be set to a larger or smaller value according to the actual scenario requirements. For example, in a specific embodiment, the time weight coefficient is 0.25, the quality weight coefficient is 0.3, the frequency weight coefficient is 0.4, the consistency weight coefficient is 0.3, and the seasonal weight coefficient is 0.15 in the associated weight coefficients corresponding to the comprehensive evaluation strategy.

[0088] Optionally, after obtaining the associated dimension weights and their corresponding associated weight coefficients, the air conditioning control device uses the associated weight coefficients to perform a weighted summation of the associated dimension weights to obtain a weighted total associated weight. It then calculates the ratio of this weighted total associated weight to a normalized coefficient to obtain the first target habitual weight. The normalized coefficient is the sum of all associated weight coefficients.

[0089] Optionally, after calculating the first target habit weight corresponding to each air conditioning habit mode, the air conditioning control device determines the air conditioning habit mode with the highest first target habit weight as the target habit mode. Here, the first target habit weight is weight data used for comprehensive evaluation of air conditioning habit modes.

[0090] Optionally, if the air conditioning control device determines that the habit pattern strategy is a single evaluation strategy, then the weight of the associated dimension corresponding to the single evaluation strategy is determined as the second target habit weight in the air conditioning habit pattern, and the air conditioning habit pattern with the highest second target habit weight is determined as the target habit pattern. That is, the air conditioning control device reads the priority evaluation dimension (e.g., seasonal dimension priority, quality dimension priority, frequency priority, etc.) corresponding to the single evaluation strategy, determines the weight of the associated dimension corresponding to the priority evaluation dimension as the second target habit weight in the air conditioning habit pattern, and determines the air conditioning habit pattern with the highest second target habit weight as the target habit pattern.

[0091] In this embodiment, the air conditioning control device obtains a habit pattern strategy. If the habit pattern strategy is a comprehensive evaluation strategy, then the first target habit weight corresponding to the air conditioning habit pattern is obtained based on the weighted sum and normalization coefficient of the weight of each associated dimension of the air conditioning habit pattern and the associated weight coefficient corresponding to the associated dimension weight. The air conditioning habit pattern with the highest first target habit weight is determined as the target habit pattern. If the habit pattern strategy is a single evaluation strategy, then the associated dimension weight corresponding to the single evaluation strategy is determined as the second target habit weight in the air conditioning habit pattern, and the air conditioning habit pattern with the highest second target habit weight is determined as the target habit pattern. This achieves multi-dimensional filtering of the target habit pattern in the air conditioning habit pattern, improves the accuracy of target habit pattern filtering, and thus improves the subsequent forget-to-turn-off control.

[0092] like Figure 4 As shown, Figure 4 A flowchart illustrating an embodiment of the air conditioning control method provided in this application for controlling an air conditioner that has not been turned off is shown below. Figure 4 In the illustrated embodiment, the air conditioning control method includes steps 401 to 403: 401. Determine the running scenario type corresponding to the current running data based on the boot-up running time of the current running data; 402. If the operating scenario is a reminder-to-operate scenario, then calculate the power consumption value of the target air conditioner in the forget-to-turn-off mode. 403. Switch the target air conditioner to standby mode, and generate a forget-to-turn-off reminder message based on the power consumption value of forgetting to turn off and the forget-to-turn-off event corresponding to the forget-to-turn-off mode, and output the forget-to-turn-off reminder message.

[0093] Based on the above embodiments, in this embodiment, after determining that the target air conditioner's operating mode is the "forgot to turn off" mode, the air conditioning control device performs air conditioner "forgot to turn off" control according to the operating scenario type corresponding to the current operating data and the "forgot to turn off" mode, and obtains the air conditioning control result. This enables the user to perform corresponding air conditioning control processing when forgetting to turn off the air conditioner, reduces the power consumption caused by forgetting to turn off the air conditioner, effectively reduces air conditioning detection costs, and improves the energy-saving effect of the air conditioner.

[0094] Optionally, the air conditioning control device determines the operating scenario type corresponding to the current operating data based on the start-up time of the current operating data. That is, after determining that the target air conditioner's operating mode is "forget to turn off," the air conditioning control device obtains the start-up time from the current operating data and determines the operating scenario type corresponding to the current operating data based on the start-up time and current time information. Here, the start-up time represents the start-up time information of the target air conditioner during this operation. The current time information represents the local time information of the target air conditioner during its current operation.

[0095] Optionally, the air conditioning control equipment pre-sets different operating scenario types for assessing whether to issue a "forgot to turn off" reminder for different operating time nodes corresponding to the start-up and turn-off times. These operating scenario types include a "to be reminded" operating scenario and a "no reminder" operating scenario. The "to be reminded" operating scenario represents the scenario where an air conditioner "forgot to turn off" reminder is to be output. The "no reminder" operating scenario represents the scenario where no air conditioner "forgot to turn off" reminder is issued. The "to be reminded" operating scenario is correspondingly set with a reminder start-up interval and a reminder turn-off interval. That is, if the target air conditioner's start-up time falls within the reminder start-up interval and the current operating time falls within the reminder turn-off interval, then the target air conditioner's operating scenario is determined to be a "to be reminded" operating scenario. Optionally, in a specific embodiment, the reminder start-up interval is 18:00-24:00, and the reminder turn-off interval is 6:00-18:00 the next day.

[0096] Optionally, if the air conditioning control device determines that the target air conditioner's operating scenario is a reminder-required operating scenario, then it calculates the power consumption value of the target air conditioner in the "forgot to turn off" mode. Optionally, in a specific embodiment, the calculation method for the power consumption value is as follows:

[0097] Where E represents the power consumption value when the device is left on, Q represents the historical cumulative power consumption value for the target statistical period (e.g., 3 months) in the historical usage data, and H represents the cumulative operating hours for the target statistical period in the historical usage data. This is the actual shutdown time. To predict shutdown time.

[0098] Optionally, after determining that the operating scenario is a scenario to be reminded, the air conditioning control device switches the target air conditioner to standby mode (i.e., turns off the target air conditioner and records the actual shutdown time), and generates a reminder message for forgetting to turn off based on the power consumption value of forgetting to turn off and the forgetting to turn off event corresponding to the forgetting to turn off mode, and outputs the reminder message for forgetting to turn off.

[0099] In this embodiment, the air conditioning control device determines the operating scenario type corresponding to the current operating data based on the start-up time of the current operating data. If the operating scenario is a reminder-only operating scenario, the device calculates the power consumption value of the target air conditioner in the "forgot to turn off" mode. The target air conditioner is then switched to standby mode, and a reminder message is generated based on the power consumption value and the "forgot to turn off" event corresponding to the "forgot to turn off" mode. This reminder message is then output. This method enables the air conditioner to be turned off when it is forgotten and the operating scenario is a reminder-only operating scenario, and quantifies the power consumption to remind the user, thereby reducing the probability of subsequent "forgot to turn off" events and improving the energy-saving effect of the target air conditioner.

[0100] To better implement the air conditioning control method in the embodiments of this application, an air conditioning control device is also provided in the embodiments of this application, such as... Figure 5 As shown, Figure 5 This is a schematic diagram of one embodiment of the air conditioning control device provided in this application. Specifically, the air conditioning control device 500 includes: Data acquisition module 501 is configured to acquire historical usage data and current operating data corresponding to the target air conditioner; The habit clustering module 502 is configured to perform clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The multidimensional evaluation module 503 is configured to determine the target habit pattern in the air conditioning habit pattern based on the associated dimension weights and habit pattern strategy of the air conditioning habit pattern, wherein the associated dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. The air conditioning control module 504 is configured to control the air conditioning to turn off when it is not turned off, based on the target habit mode and the current operating data, and obtain the air conditioning control result.

[0101] In one possible implementation of this embodiment, the air conditioning control device determines the target habit pattern in the air conditioning habit pattern based on the associated dimension weights and habit pattern strategy, including: Obtain the multimodal correlation parameters corresponding to the air conditioning habit mode; The association dimension weights of the air conditioning habit patterns are calculated based on the multimodal association parameters. The target habit pattern in the air conditioning habit pattern is selected based on the associated dimension weights and habit pattern strategy.

[0102] In one possible implementation of this embodiment, the associated dimension weights in the air conditioning control device include any one or more of the following: time dimension weights, quality dimension weights, frequency dimension weights, consistency dimension weights, and seasonal dimension weights. The air conditioning control device calculates the association dimension weights of the air conditioning habit mode based on the multimodal association parameters, including: Obtain the operating date difference corresponding to the air conditioner habit mode, and calculate the time dimension weight of the air conditioner habit mode based on the operating date difference, time decay factor and time weight function; And / or, obtain the clustering ratio and clustering data volume corresponding to the air conditioning habit pattern, and calculate the quality dimension weight of the air conditioning habit pattern based on the clustering ratio and the clustering data volume; And / or, calculate the frequency dimension weight of the air conditioning habit pattern based on the amount of clustered data corresponding to the air conditioning habit pattern and the amount of historical usage data; And / or, calculate the consistency dimension weight of the air conditioning habit pattern based on the consistency data corresponding to the air conditioning habit pattern; And / or, determine the seasonal dimension weight of the air conditioning habit mode based on the temperature identifier and month identifier corresponding to the air conditioning habit mode.

[0103] In one possible implementation of this embodiment, the air conditioning control device's selection of the target habit pattern from the air conditioning habit patterns based on the associated dimension weights and habit pattern strategy includes: If the habit pattern strategy is a comprehensive evaluation strategy, then the first target habit weight corresponding to the air conditioning habit pattern is obtained by weighting the weight of each associated dimension of the air conditioning habit pattern and the associated weight coefficient corresponding to the associated dimension weight and the normalization coefficient, and the air conditioning habit pattern with the highest first target habit weight is determined as the target habit pattern.

[0104] If the habit pattern strategy is a single evaluation strategy, then the weight of the associated dimension corresponding to the single evaluation strategy is determined as the second target habit weight in the air conditioning habit pattern, and the air conditioning habit pattern with the highest second target habit weight is determined as the target habit pattern.

[0105] In one possible implementation of this embodiment, the air conditioning control device performs clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner, including: Obtain the neighborhood range parameter from the target clustering parameters and the target sampling quantity corresponding to the historical usage data; Feature extraction is performed on the historical usage data to obtain the historical usage features corresponding to the historical usage data; The historical usage features are clustered based on the neighborhood range parameter and the target sampling quantity to obtain historical data clusters. The air conditioning habit pattern of the target air conditioner is generated based on the historical data clusters and the cluster labels of the historical data clusters.

[0106] In one possible implementation of this embodiment, the air conditioning control device obtains the neighborhood range parameter in the target clustering parameters and the target sampling quantity corresponding to the historical usage data, including: If the number of historical data points in the historical usage data is greater than a preset threshold, a target nearest neighbor distance function corresponding to the historical usage data is generated. The neighborhood range parameter of the historical usage data is determined based on the inflection point of the function curve in the target nearest neighbor distance function. The target sampling quantity corresponding to the historical usage data is calculated based on the number of times the device was powered on and the preset frequency coefficient in the historical usage data.

[0107] In one possible implementation of this embodiment, the air conditioning control device performs air conditioning left-on control based on the target habit mode and the current operating data, and obtains the air conditioning control result, including: Obtain the predicted running data corresponding to the target habit pattern, and calculate the running deviation data between the predicted running data and the current running data; If the operating deviation data is greater than the preset operating deviation threshold, then the operating mode of the target air conditioner is determined to be the "forgot to turn off" mode. Based on the operating scenario type corresponding to the current operating data and the forgotten-to-turn-off mode, the air conditioner is controlled to achieve the air conditioner control result.

[0108] In one possible implementation of this embodiment, the air conditioning control device performs air conditioning shutdown control based on the operating scenario type corresponding to the current operating data and the forgotten shutdown mode, and obtains the air conditioning control result, including: The running scenario type corresponding to the current running data is determined based on the boot-up and running time of the current running data. If the operating scenario is a reminder-to-operate scenario, then calculate the power consumption value of the target air conditioner in the forget-to-turn-off mode. The target air conditioner is switched to standby mode, and a reminder message for forgetting to turn off is generated based on the power consumption value for forgetting to turn off and the forgetting to turn off event corresponding to the forgetting to turn off mode, and the reminder message for forgetting to turn off is output.

[0109] In this embodiment, the air conditioning control device acquires historical usage data and current operating data corresponding to the target air conditioner; performs clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; determines the target habit pattern in the air conditioning habit pattern based on the association dimension weight and habit pattern strategy of the air conditioning habit pattern, wherein the association dimension weight is a weight parameter characterizing the quantitative quality of the air conditioning habit pattern in a specified dimension; and performs air conditioning forget-to-turn-off control based on the target habit pattern and the current operating data to obtain the air conditioning control result. This system acquires historical usage data and current operating data of a target air conditioner during its operation. It then performs density-based clustering on the historical data using target clustering parameters to obtain the air conditioner usage habits of multiple target air conditioners. The system calculates the association dimension weights corresponding to these habit patterns and uses a habit pattern strategy to select target habit patterns for forget-to-turn-off control. This allows for accurate identification of whether a user has forgotten to turn off the air conditioner without additional detection hardware, and enables corresponding air conditioner control when the air conditioner is forgotten. This reduces power consumption caused by forgetting to turn off the air conditioner, effectively lowers air conditioner detection costs, and improves energy efficiency.

[0110] This invention also provides an air conditioning control device, such as... Figure 6 As shown, Figure 6 This is a schematic diagram of one embodiment of the air conditioning control device provided in this application.

[0111] The air conditioning control device integrates any one of the air conditioning control devices provided in the embodiments of the present invention, and the air conditioning control device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to execute the steps of the air conditioning control method in any of the embodiments described above.

[0112] Specifically, the air conditioning control device may include components such as a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will understand that... Figure 6 The air conditioning control device structure shown does not constitute a limitation on the air conditioning control device. It may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 601 is the control center of the air conditioning control device. It connects various parts of the air conditioning control device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, it performs various functions and processes data of the air conditioning control device, thereby providing overall monitoring of the air conditioning control device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601.

[0113] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and air conditioning control by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the air conditioning control equipment, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0114] The air conditioning control equipment also includes a power supply 603 that supplies power to various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0115] The air conditioning control device may also include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0116] Although not shown, the air conditioning control device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 601 in the air conditioning control device loads the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 runs the application programs stored in the memory 602 to realize various functions, as follows: Obtain historical usage data and current operating data for the target air conditioner; Clustering is performed based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The target habit pattern in the air conditioning habit pattern is determined based on the association dimension weights and habit pattern strategy of the air conditioning habit pattern. The association dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. Based on the target habit mode and the current operating data, the air conditioner is controlled to prevent it from turning off, and the air conditioner control result is obtained.

[0117] Therefore, embodiments of the present invention provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, which is loaded by a processor to execute the steps in any of the air conditioning control methods provided in the embodiments of the present invention. For example, the computer program loaded by the processor can execute the following steps: Obtain historical usage data and current operating data for the target air conditioner; Clustering is performed based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The target habit pattern in the air conditioning habit pattern is determined based on the association dimension weights and habit pattern strategy of the air conditioning habit pattern. The association dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. Based on the target habit mode and the current operating data, the air conditioner is controlled to prevent it from turning off, and the air conditioner control result is obtained.

[0118] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0119] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0120] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0121] The above provides a detailed description of an air conditioning control method provided by the embodiments of this application. Specific embodiments have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An air conditioning control method, characterized in that, The air conditioning control method includes: Obtain historical usage data and current operating data for the target air conditioner; Clustering is performed based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The target habit pattern in the air conditioning habit pattern is determined based on the association dimension weights and habit pattern strategy of the air conditioning habit pattern. The association dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. Based on the target habit mode and the current operating data, the air conditioner is controlled to prevent it from turning off, and the air conditioner control result is obtained.

2. The air conditioning control method according to claim 1, characterized in that, The step of determining the target habit pattern in the air conditioning habit pattern based on the association dimension weights and habit pattern strategy includes: Obtain the multimodal correlation parameters corresponding to the air conditioning habit mode; The association dimension weights of the air conditioning habit patterns are calculated based on the multimodal association parameters. The target habit pattern in the air conditioning habit pattern is selected based on the associated dimension weights and habit pattern strategy.

3. The air conditioning control method according to claim 2, characterized in that, The associated dimension weights include any one or more of the following: time dimension weights, quality dimension weights, frequency dimension weights, consistency dimension weights, and seasonal dimension weights. The step of calculating the association dimension weights of the air conditioning habit pattern based on the multimodal association parameters includes: Obtain the operating date difference corresponding to the air conditioner habit mode, and calculate the time dimension weight of the air conditioner habit mode based on the operating date difference, time decay factor and time weight function; And / or, obtain the clustering ratio and clustering data volume corresponding to the air conditioning habit pattern, and calculate the quality dimension weight of the air conditioning habit pattern based on the clustering ratio and the clustering data volume; And / or, calculate the frequency dimension weight of the air conditioning habit pattern based on the amount of clustered data corresponding to the air conditioning habit pattern and the amount of historical usage data; And / or, calculate the consistency dimension weight of the air conditioning habit pattern based on the consistency data corresponding to the air conditioning habit pattern; And / or, determine the seasonal dimension weight of the air conditioning habit mode based on the temperature identifier and month identifier corresponding to the air conditioning habit mode.

4. The air conditioning control method according to claim 2, characterized in that, The step of selecting the target habit pattern from the air conditioning habit patterns based on the associated dimension weights and habit pattern strategy includes: If the habit pattern strategy is a comprehensive evaluation strategy, then the first target habit weight corresponding to the air conditioning habit pattern is obtained by weighting the weight of each associated dimension of the air conditioning habit pattern and the associated weight coefficient corresponding to the associated dimension weight and the normalization coefficient, and the air conditioning habit pattern with the highest first target habit weight is determined as the target habit pattern. If the habit pattern strategy is a single evaluation strategy, then the weight of the associated dimension corresponding to the single evaluation strategy is determined as the second target habit weight in the air conditioning habit pattern, and the air conditioning habit pattern with the highest second target habit weight is determined as the target habit pattern.

5. The air conditioning control method according to claim 1, characterized in that, The step of performing clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner includes: Obtain the neighborhood range parameter from the target clustering parameters and the target sampling quantity corresponding to the historical usage data; Feature extraction is performed on the historical usage data to obtain the historical usage features corresponding to the historical usage data; The historical usage features are clustered based on the neighborhood range parameter and the target sampling quantity to obtain historical data clusters. The air conditioning habit pattern of the target air conditioner is generated based on the historical data clusters and the cluster labels of the historical data clusters.

6. The air conditioning control method according to claim 5, characterized in that, The step of obtaining the neighborhood range parameter in the target clustering parameters and the target sampling quantity corresponding to the historical usage data includes: If the number of historical data points in the historical usage data is greater than a preset threshold, a target nearest neighbor distance function corresponding to the historical usage data is generated. The neighborhood range parameter of the historical usage data is determined based on the inflection point of the function curve in the target nearest neighbor distance function. The target sampling quantity corresponding to the historical usage data is calculated based on the number of times the device was powered on and the preset frequency coefficient in the historical usage data.

7. The air conditioning control method according to claim 1, characterized in that, The step of controlling the air conditioner to turn off based on the target habit pattern and the current operating data, and obtaining the air conditioner control result, includes: Obtain the predicted running data corresponding to the target habit pattern, and calculate the running deviation data between the predicted running data and the current running data; If the operating deviation data is greater than the preset operating deviation threshold, then the operating mode of the target air conditioner is determined to be the "forgot to turn off" mode. Based on the operating scenario type corresponding to the current operating data and the forgotten-to-turn-off mode, the air conditioner is controlled to achieve the air conditioner control result.

8. The air conditioning control method according to claim 7, characterized in that, The step of controlling the air conditioner to turn off based on the operating scenario type corresponding to the current operating data and the forgotten-to-turn-off mode, and obtaining the air conditioner control result, includes: The running scenario type corresponding to the current running data is determined based on the boot-up and running time of the current running data. If the operating scenario is a reminder-to-operate scenario, then calculate the power consumption value of the target air conditioner in the forget-to-turn-off mode. The target air conditioner is switched to standby mode, and a reminder message for forgetting to turn off is generated based on the power consumption value for forgetting to turn off and the forgetting to turn off event corresponding to the forgetting to turn off mode, and the reminder message for forgetting to turn off is output.

9. An air conditioning control device, characterized in that, The air conditioning control device includes: The data acquisition module is configured to acquire historical usage data and current operating data corresponding to the target air conditioner; The habit clustering module is configured to perform clustering processing based on the historical usage data and target clustering parameters to obtain the air conditioning habit pattern of the target air conditioner; The multidimensional evaluation module is configured to determine the target habit pattern in the air conditioning habit pattern based on the associated dimension weights and habit pattern strategy of the air conditioning habit pattern, wherein the associated dimension weights are weight parameters that characterize the quantitative quality of the air conditioning habit pattern in a specified dimension. The air conditioning control module is configured to control the air conditioning to turn off when not turned off based on the target habit mode and the current operating data, and obtain the air conditioning control result.

10. An air conditioning control device, characterized in that, The air conditioning control equipment includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the air conditioning control method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the steps of the air conditioning control method according to any one of claims 1 to 8.

Images