Air conditioner control method and device, storage medium and electronic equipment

Abstract

The application discloses an air conditioner control method and device, a storage medium and an electronic device, relates to the technical field of Internet of Things, and comprises the following steps: obtaining historical control data of an air conditioner to be controlled, wherein the historical control data comprises condition parameters of multiple conditions and corresponding state parameters; performing correlation calculation on each condition parameter and the state parameter respectively to obtain a correlation coefficient between each condition parameter and the state parameter; performing mutual information analysis on each target parameter and the state parameter to obtain a decision node corresponding to each target condition, wherein the target parameter is a condition parameter corresponding to a correlation coefficient exceeding a predetermined threshold, and the target condition is a condition corresponding to the target parameter; and constructing a decision tree according to the decision node corresponding to each condition, wherein the decision tree is used for predicting and controlling the air conditioner control operation. The application can effectively improve the control reliability of the air conditioner and improve the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things, and in particular to an air conditioner control method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the continuous development of air conditioner control technology, intelligent air conditioner control technology is more and more widely applied to various scenes, and the reliability of intelligent air conditioner control is very important for user experience.

[0003] At present, in the related technology of intelligent air conditioner control, there is a scheme of intelligently analyzing the control parameters (such as refrigeration temperature, humidification amount, etc.) of the air conditioner according to relevant information (such as weather and temperature, etc.), and intelligently controlling the air conditioner according to the control parameters. However, at present, the air conditioner control operation (such as voice wake-up or mode adjustment operation) of the user is often executed in response to the triggering of the air conditioner control operation or the change of the environment (such as the increase of indoor temperature, etc.). There is a lack of analysis or reliable analysis of the air conditioner control operation, which leads to problems such as errors in air conditioner control or failure to meet user needs.

[0004] Therefore, the current air conditioner control has the problem of poor control reliability, and it is necessary to improve the user experience. SUMMARY

[0005] The embodiments of the present application provide a scheme, which can effectively improve the control reliability of the air conditioner and improve the user experience.

[0006] The embodiments of the present application provide the following technical solutions:

[0007] According to an embodiment of the present application, an air conditioner control method comprises: obtaining historical operation data for a to-be-controlled air conditioner, the historical operation data including condition parameters of multiple conditions and corresponding state parameters, the state parameters corresponding to air conditioner control operations; performing correlation calculation on each of the condition parameters and the state parameters to obtain correlation coefficients between each of the condition parameters and the state parameters; performing mutual information analysis on each target parameter and the state parameters to obtain decision nodes corresponding to each target condition, the target parameter being a condition parameter corresponding to a correlation coefficient exceeding a predetermined threshold, and the target condition being a condition corresponding to the target parameter; and constructing a decision tree according to the decision nodes corresponding to each condition, the decision tree being used for predictive control of the air conditioner control operations.

[0008] In some embodiments of the present application, after the decision tree is constructed according to the decision nodes corresponding to the target conditions, the method further comprises: in response to detecting the air conditioner control operation for the to-be-controlled air conditioner, acquiring current condition parameters of the to-be-controlled air conditioner under multiple target conditions; using the decision tree to analyze the current condition parameters under the multiple conditions to obtain an operation state corresponding to the air conditioner control operation; and determining whether to execute the air conditioner control operation according to the operation state.

[0009] In some embodiments of the present application, the decision nodes corresponding to the target conditions are obtained by mutual information analysis of the target parameters and the state parameters, comprising: calculating information entropy and conditional entropy of each target condition relative to an execution state according to each target parameter and the corresponding state parameter, the execution state indicating that the air conditioner control operation is executed; calculating the difference between the information entropy and the conditional entropy of each target condition relative to the execution state respectively to obtain mutual information of each target condition and the execution state; determining a root condition as a root node and determining a sub-condition under the root condition as a leaf node corresponding to the root node, the root condition being the target condition corresponding to the highest mutual information, each leaf node corresponding to a branch; and determining a branch and a branch node corresponding to each other condition by calculating mutual information of a sub-condition parameter corresponding to each sub-condition under the root condition and a target parameter corresponding to the other condition, the other condition being a target condition other than the root condition in the multiple target conditions.

[0010] In some embodiments of the present application, the decision tree is constructed according to the decision nodes corresponding to the target conditions, comprising: connecting each branch node to a leaf node under the root node according to the corresponding branch to obtain the decision tree.

[0011] In some embodiments of the present application, before the decision nodes corresponding to the target conditions are obtained by mutual information analysis of the target parameters and the state parameters, the method further comprises: querying a scene threshold corresponding to a use scene of the to-be-controlled air conditioner according to the use scene to obtain the predetermined threshold; and acquiring condition parameters corresponding to a correlation coefficient exceeding the predetermined threshold from condition parameters of the multiple conditions to obtain multiple target parameters.

[0012] In some embodiments of the present application, before the correlation of each condition parameter and the state parameter is calculated, the method further comprises: determining whether there is a missing value in the historical operation data; and if there is a missing value, performing interpolation processing on the historical operation data.

[0013] In some embodiments of this application, the step of interpolating the historical control data if missing values ​​exist includes: performing Lagrange interpolation on the historical control data if missing values ​​exist.

[0014] According to one embodiment of this application, an air conditioning control device includes: an acquisition module for acquiring historical operation data of an air conditioner to be controlled, the historical operation data including multiple condition parameters and corresponding state parameters, the state parameters corresponding to air conditioning control operations; a correlation calculation module for performing correlation calculations on each of the condition parameters and the state parameters to obtain correlation coefficients between each of the condition parameters and the state parameters; a node analysis module for performing mutual information analysis on each target parameter and the state parameters to obtain decision nodes corresponding to each target condition, the target parameter being a condition parameter corresponding to a correlation coefficient exceeding a predetermined threshold, and the target condition being a condition corresponding to the target parameter; and a construction module for constructing a decision tree based on the decision nodes corresponding to each target condition, the decision tree being used for predictive control of the air conditioning control operations.

[0015] In some embodiments of this application, after constructing a decision tree based on the decision nodes corresponding to each condition, the device further includes a control module, configured to: in response to detecting an air conditioning control operation for the air conditioner to be controlled, acquire the current condition parameters of the air conditioner to be controlled under multiple target conditions; analyze the current condition parameters under the multiple conditions using the decision tree to obtain the operation state corresponding to the air conditioning control operation; and confirm whether to execute the air conditioning control operation based on the operation state.

[0016] In some embodiments of this application, the node analysis module is configured to: calculate the information entropy and conditional entropy of each target condition relative to the execution state based on each target parameter and its corresponding state parameter, wherein the execution state refers to the air conditioning control operation being executed; calculate the difference between the information entropy and conditional entropy of each target condition relative to the execution state to obtain the mutual information between each target condition and the execution state; determine the root condition as the root node, and determine the sub-conditions under the root condition as the leaf nodes corresponding to the root node, wherein the root condition is the target condition corresponding to the highest mutual information, and each leaf node corresponds to a branch; determine the branches and branch nodes corresponding to each other condition by calculating the mutual information between the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions, wherein the other conditions are target conditions other than the root condition among multiple target conditions.

[0017] In some embodiments of this application, the construction module is used to: connect each of the branch nodes to the leaf nodes under the root node according to the corresponding branches, so as to obtain the decision tree.

[0018] In some embodiments of this application, before obtaining the decision node corresponding to each condition by performing mutual information analysis on each target parameter and the state parameter, the device further includes a threshold analysis module, used to: query the scene threshold corresponding to the usage scenario of the air conditioner to be controlled, and obtain the predetermined threshold; and obtain the condition parameter corresponding to the correlation coefficient exceeding the predetermined threshold from the condition parameters of the multiple conditions, and obtain the multiple target parameters.

[0019] In some embodiments of this application, before performing correlation calculations on each of the condition parameters and the state parameters, the device further includes an interpolation module for: determining whether there are missing values ​​in the historical control data; and if there are missing values, performing interpolation processing on the historical control data.

[0020] In some embodiments of this application, the interpolation module is used to: perform Lagrange interpolation on the historical manipulation data if there are missing values.

[0021] According to another embodiment of this application, a storage medium stores a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the methods described in the embodiments of this application.

[0022] According to another embodiment of this application, an electronic device may include: a memory storing a computer program; and a processor reading the computer program stored in the memory to execute the methods described in the embodiments of this application.

[0023] According to another embodiment of this application, a computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described in the embodiments of this application.

[0024] In this embodiment, historical operation data of the target user for the air conditioner to be controlled is obtained. The historical operation data includes condition parameters and corresponding state parameters for various conditions. The state parameters correspond to air conditioner control operations. Correlation calculations are performed on each condition parameter and each state parameter to obtain a correlation coefficient between each condition parameter and the state parameter. Mutual information analysis is performed on each target parameter and the state parameter to obtain a decision node corresponding to each target condition. The target parameter is the condition parameter corresponding to the correlation coefficient exceeding a predetermined threshold, and the target condition is the condition corresponding to the target parameter. A decision tree is constructed based on the decision nodes corresponding to each condition. The decision tree is used for predictive control of the air conditioner control operation.

[0025] In this way, the conditional parameters of the air conditioner to be controlled under various conditions and the corresponding state parameters of the air conditioner control operation are obtained. First, the conditional parameters corresponding to the correlation coefficients exceeding the predetermined threshold are screened out through correlation calculation. Then, the decision nodes corresponding to each condition are obtained by performing mutual information analysis on each target parameter and state parameter. The generated decision tree can reliably predict and analyze the user's air conditioner control operation, thereby reliably controlling the air conditioner, effectively improving the control reliability of the air conditioner, and enhancing the user experience. Attached Figure Description

[0026] 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart of an air conditioning control method according to an embodiment of this application is shown.

[0028] Figure 2 A block diagram of an air conditioning control device according to an embodiment of this application is shown.

[0029] Figure 3 A block diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0030] The present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the embodiments provided herein are merely illustrative of the present disclosure and are not intended to limit the present disclosure. Furthermore, the embodiments provided below are some embodiments for implementing the present disclosure, and not all embodiments for implementing the present disclosure. Unless otherwise specified, the technical solutions described in the embodiments of the present disclosure can be implemented in any combination.

[0031] It should be noted that, in the embodiments of this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a method or apparatus that includes a list of elements includes not only the elements expressly described, but also other elements not expressly listed, or elements inherent to implementing the method or apparatus. Without further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of other related elements (e.g., steps in the method or units in the apparatus, such as portions of circuitry, processors, programs, or software, etc.) in the method or apparatus that includes that element.

[0032] For example, the air conditioning control method provided in this embodiment includes a series of steps, but the air conditioning control method provided in this embodiment is not limited to the steps described. Similarly, the air conditioning control device provided in this embodiment includes a series of units, but the device provided in this embodiment is not limited to the units explicitly described, but may also include units that need to be set up for obtaining relevant information or processing based on information.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure.

[0034] It is understood that in the specific implementation of this application, data such as historical manipulation data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0035] Figure 1 A flowchart illustrating an embodiment of an air conditioning control method according to this application is shown. The device executing this air conditioning control method can be any device with processing capabilities, such as a computer, mobile phone, smartwatch, air conditioner, server, etc. In one embodiment of this application, the device serving as the executing device is specifically an air conditioner.

[0036] like Figure 1 As shown, the air conditioning control method may include steps S110 to S140.

[0037] Step S110: Obtain historical operation data for the air conditioner to be controlled. The historical operation data includes condition parameters and corresponding state parameters for various conditions. The state parameters correspond to air conditioner control operations. Step S120: Calculate the correlation between each condition parameter and the state parameter to obtain the correlation coefficient between each condition parameter and the state parameter. Step S130: Analyze the mutual information of each target parameter and the state parameter to obtain the decision node corresponding to each target condition. The target parameter is the condition parameter corresponding to the correlation coefficient exceeding a predetermined threshold, and the target condition is the condition corresponding to the target parameter. Step S140: Construct a decision tree based on the decision nodes corresponding to each condition. The decision tree is used for predictive control of the air conditioner control operation.

[0038] Historical control data can be pre-collected control data of the air conditioner to be controlled during a predetermined period. When performing the steps of the embodiments of this application, the historical control data corresponding to the air conditioner to be controlled can be obtained from a specified storage location. The historical control data can include condition parameters and corresponding status parameters of various conditions.

[0039] Conditions are the prerequisites that trigger the air conditioning control operation. These conditions can be varied, including ambient temperature, user mood, weather, and ambient humidity. Each condition corresponds to a condition parameter, and each condition parameter can include multiple sub-condition parameters. For example, if the condition is ambient temperature, the corresponding condition parameters include different temperature ranges, with each temperature range being a sub-condition parameter.

[0040] The status parameters correspond to the air conditioning control operations. For example, if the air conditioning control operation is voice wake-up, the corresponding status parameter could be the number of times the air conditioning is woken up by voice. Each condition's condition parameter can correspond to a status parameter, and the status parameter can include multiple sub-status parameters. Specifically, each sub-condition parameter can correspond to one sub-status parameter. For example, temperature range A (one sub-condition parameter) corresponds to 100 times of voice wake-up (one sub-status parameter), temperature range B (one sub-condition parameter) corresponds to 0 times of voice wake-up (one sub-status parameter), and so on.

[0041] Correlation calculations are performed on the conditional parameters and state parameters for each condition to obtain the correlation coefficient between each conditional parameter and the state parameter. For example, the correlation coefficient between the conditional parameter of ambient temperature and the corresponding state parameter is obtained. The correlation calculation method can be Pearson correlation coefficient, Kendall coefficient, or Spearman correlation coefficient, etc.

[0042] The correlation coefficient reflects the degree of correlation between a condition parameter and its corresponding state parameter. From a pool of condition parameters, the condition parameter with the correlation coefficient exceeding a predetermined threshold can be selected as the target parameter. The predetermined threshold can be set according to actual circumstances; in one embodiment of this application, the predetermined threshold is specifically 0.6.

[0043] By performing mutual information analysis on each target parameter and state parameter, the mutual information can reliably reflect the correlation between parameters, and the decision nodes corresponding to the target conditions for each target parameter can be reliably obtained through mutual information analysis. A decision tree is then constructed based on the decision nodes corresponding to each condition, and this decision tree can be used for reliable predictive control of the air conditioning control operation.

[0044] In this way, based on steps S110 to S140, the condition parameters of the air conditioner to be controlled under various conditions and the corresponding state parameters of the air conditioner control operation are obtained. First, the condition parameters corresponding to the correlation coefficients exceeding the predetermined threshold are screened out through correlation calculation. Then, the decision nodes corresponding to each condition are obtained by performing mutual information analysis on each target parameter and state parameter. The generated decision tree can reliably predict and analyze the user's air conditioner control operation, thereby reliably controlling the air conditioner, effectively improving the control reliability of the air conditioner, and enhancing the user experience.

[0045] The following description Figure 1 Further optional specific embodiments are provided for each step performed when controlling the air conditioner in the example implementation.

[0046] In one embodiment, after constructing a decision tree based on the decision nodes corresponding to each of the target conditions, the method further includes: in response to detecting an air conditioning control operation for the air conditioner to be controlled, obtaining current condition parameters of the air conditioner to be controlled under multiple target conditions, wherein the target conditions are the conditions corresponding to the target parameters; analyzing the current condition parameters under the multiple conditions using the decision tree to obtain the operation state corresponding to the air conditioning control operation; and confirming whether to execute the air conditioning control operation based on the operation state.

[0047] In this embodiment, when the user performs the air conditioning control operation on the air conditioner to be controlled, the current condition parameters of the air conditioner to be controlled under the target conditions corresponding to multiple target parameters are obtained. For example, the multiple target conditions include ambient temperature, user mood, weather and ambient humidity. The current condition parameters may include the temperature range corresponding to the current ambient temperature value, user mood information, weather information and humidity range corresponding to the ambient humidity value.

[0048] Decision trees can be used to perform decision analysis on the current condition parameters under various conditions to obtain the operation state corresponding to the air conditioning control operation. The operation state can include an execution state and a non-execution state. The execution state means that the operation can be executed, and the non-execution state means that the operation cannot be executed.

[0049] The system determines whether to execute an air conditioning control operation based on the operation status. For example, if the air conditioning control operation is to wake up the air conditioner by voice, and the operation status is "execution state," then the operation to wake up the air conditioner by voice can be executed directly. If the operation status is "non-execution state," then the system first asks the user whether to execute the operation to wake up the air conditioner by voice, thereby avoiding various misoperations or incorrect detection of voice wake-up that could lead to the air conditioner being woken up unintentionally.

[0050] In one embodiment, after constructing a decision tree based on the decision nodes corresponding to each of the target conditions, the method further includes: acquiring in real time the current condition parameters of the air conditioner to be controlled under multiple target conditions, wherein the target conditions are the conditions corresponding to the target parameters; analyzing the current condition parameters under the multiple conditions using the decision tree to obtain the operation state corresponding to the air conditioner control operation; and confirming whether to execute the air conditioner control operation based on the operation state.

[0051] In this embodiment, the current condition parameters of the air conditioner to be controlled are acquired in real time under various target conditions. The decision tree is used to perform decision analysis on the current condition parameters under various target conditions. Based on the operation status, it can be determined whether to execute the air conditioner control operation. For example, it can automatically determine whether to automatically switch the air conditioner mode when the relevant environment changes.

[0052] In one embodiment, the step of obtaining the decision node corresponding to each objective condition by performing mutual information analysis on each objective parameter and the state parameter includes:

[0053] Based on each target parameter and its corresponding state parameter, calculate the information entropy and condition entropy of each target condition relative to the execution state, where the execution state refers to the air conditioning control operation being executed;

[0054] The difference between the information entropy and condition entropy of each target condition relative to the execution state is calculated to obtain the mutual information between each target condition and the execution state;

[0055] The root condition is determined as the root node, and the sub-conditions under the root condition are determined as the leaf nodes corresponding to the root node. The root condition is the target condition corresponding to the highest mutual information, and each leaf node corresponds to a branch.

[0056] By calculating the mutual information between the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions, the branches and branch nodes corresponding to each of the other conditions are determined. The other conditions are target conditions other than the root condition among a variety of target conditions.

[0057] For example, the multiple target conditions specifically include four target conditions (ambient temperature, user mood, weather, and ambient humidity). Each target condition corresponds to a target parameter, and each target parameter corresponds to a state parameter, which is the number of times the air conditioner is activated via voice. The target parameters and state parameters corresponding to the four target conditions can be derived from several records. For example, a record may include four target parameters: a first ambient temperature range, a user's irritable mood, sunny weather, and dry ambient humidity, as well as whether the air conditioner was activated via voice under these four target parameters (if the air conditioner was activated via voice, it is in the executing state; if not, it is not in the non-executing state). Furthermore, from several records, the number of times the air conditioner was activated via voice under all first ambient temperature ranges (target parameters) can be determined (state parameters), and other target parameters and their corresponding state parameters can be obtained. Taking the ID3 algorithm for constructing a decision tree as an example, the decision nodes corresponding to each target condition can be obtained in the following way.

[0058] Based on each target parameter and its corresponding state parameter, the information entropy and condition entropy of the target condition relative to the execution state can be calculated. Specifically, the information entropy can be calculated using the following formula:

[0059]

[0060] Where E(S) is the information entropy. c is the number of operation states; for example, an operation state can include two states: an execution state and a non-execution state, i.e., c = 2. p i For each operation state, the probability is p. For example, if i = 1 represents the execution state, p i Let p be the probability of the executing state appearing in a number of records. If i = 2 represents the non-executing state, then p i This represents the probability of a non-executable state appearing in a number of records.

[0061] Specifically, the conditional entropy can be calculated based on the following formula:

[0062]

[0063] Where E(T, X) is the conditional entropy, P(c) is the joint probability of the execution state appearing simultaneously under different target conditions among the conditional parameters and state parameters corresponding to multiple target conditions, E(c) is the conditional probability of the execution state also appearing when different target conditions appear, and X is the total number of multiple target conditions (e.g., 4).

[0064] Furthermore, based on the formula: H = E(S) - E(T, X), the difference between the information entropy E(S) and the condition entropy E(T, X) of the target conditions corresponding to each target parameter relative to the execution state can be calculated to obtain the mutual information (also known as information gain) H between the target conditions and the execution state corresponding to each target parameter.

[0065] The target condition corresponding to the highest mutual information is taken as the root condition. For example, if the mutual information corresponding to the target condition of ambient temperature is the highest among the four target conditions, then the target condition of ambient temperature can be taken as the root condition, that is, ambient temperature will be the root node in the decision tree.

[0066] Each target condition can include multiple sub-conditions, and each sub-condition corresponds to a sub-condition parameter. For example, each sub-condition under ambient temperature can be a temperature range, and the sub-condition parameter is the specific temperature range value. Furthermore, the root condition serves as the root node, and the sub-conditions under the root condition can be determined as the leaf nodes corresponding to the root node. Each leaf node corresponds to a branch. The other conditions are the target conditions other than the root condition among the multiple target conditions.

[0067] Furthermore, based on the ID3 algorithm, the information entropy and conditional entropy of the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions can be calculated respectively, thereby obtaining the mutual information between each sub-condition under the root condition and other conditions. Based on the mutual information, the sub-conditions that are strongly related to each other condition (i.e. the sub-condition with the largest mutual information with other conditions) can be determined.

[0068] A branch formed by a strongly related sub-condition of a certain other condition, i.e., the branch corresponding to that other condition, becomes a branch node under that branch. The sub-conditions of that other condition then become leaf nodes at the next level below that branch node. This process continues, expanding the leaf nodes to determine all branches and branch nodes corresponding to other conditions.

[0069] Furthermore, constructing a decision tree based on the decision nodes corresponding to each of the target conditions may include: connecting each of the branch nodes to the leaf nodes under the root node according to the corresponding branches to obtain the decision tree.

[0070] In one embodiment, before obtaining the decision node corresponding to each objective condition by performing mutual information analysis on each objective parameter and the state parameter, the method further includes:

[0071] Based on the usage scenario of the air conditioner to be controlled, query the scenario threshold corresponding to the usage scenario to obtain the predetermined threshold; from the condition parameters of the multiple conditions, obtain the condition parameters corresponding to the correlation coefficients that exceed the predetermined threshold to obtain the multiple target parameters.

[0072] Usage scenarios include factories, homes, and offices. A preset scenario-to-threshold mapping table stores different usage scenarios and their corresponding thresholds. Based on the usage scenario of the air conditioner to be controlled, the corresponding scenario threshold can be retrieved from the scenario-to-threshold mapping table, and this retrieved threshold is used as the preset threshold. The usage scenario of the air conditioner to be controlled can be input by the user through voice or a user interface.

[0073] Furthermore, from the conditional parameters under various conditions, the conditional parameters corresponding to correlation coefficients exceeding a predetermined threshold related to the usage scenario are obtained, resulting in multiple target parameters. These multiple target parameters are related to the usage scenario, further improving the reliability of air conditioning control.

[0074] It is understood that in other embodiments, before obtaining the decision node corresponding to each target condition by performing mutual information analysis on each target parameter and the state parameter, the method further includes: obtaining a predetermined threshold that is uniformly set regardless of the usage scenario; obtaining the condition parameter corresponding to the correlation coefficient exceeding the predetermined threshold from the condition parameters of the multiple conditions, thereby obtaining multiple target parameters.

[0075] In one embodiment, before performing correlation calculations on each of the condition parameters and the state parameters, the method further includes: determining whether there are missing values ​​in the historical control data; if there are missing values, interpolating the historical control data.

[0076] In this embodiment, after obtaining historical control data, it is first determined whether there are missing values ​​in the historical control data; if there are missing values, the historical control data is interpolated. The missing values ​​in the historical control data can be supplemented through the difference processing, which further improves the decision tree construction effect and enhances the reliability of air conditioning control.

[0077] In one embodiment, the step of interpolating the historical control data if missing values ​​exist includes: performing Lagrange interpolation on the historical control data if missing values ​​exist.

[0078] In this embodiment, the historical control data is interpolated using Lagrange interpolation, which can effectively interpolate the historical control data of the air conditioner.

[0079] It is understood that in other embodiments, other existing interpolation algorithms can be used to interpolate historical manipulation data.

[0080] To facilitate better implementation of the air conditioning control method provided in this application, this application also provides an air conditioning control device based on the above-described air conditioning control method. The meanings of the terms used are the same as in the above-described air conditioning control method, and specific implementation details can be found in the descriptions within the method embodiments. Figure 2 A block diagram of an air conditioning control device according to an embodiment of this application is shown.

[0081] like Figure 2 As shown, the air conditioning control device 200 may include: an acquisition module 210 for acquiring historical operation data of the air conditioner to be controlled, the historical operation data including various condition parameters and corresponding state parameters, the state parameters corresponding to air conditioning control operations; a correlation calculation module 220 for performing correlation calculations on each of the condition parameters and the state parameters to obtain the correlation coefficient between each of the condition parameters and the state parameters; a node analysis module 230 for performing mutual information analysis on each target parameter and the state parameters to obtain decision nodes corresponding to each target condition, the target parameter being the condition parameter corresponding to a correlation coefficient exceeding a predetermined threshold, and the target condition being the condition corresponding to the target parameter; and a construction module 240 for constructing a decision tree based on the decision nodes corresponding to each condition, the decision tree being used for predictive control of the air conditioning control operations.

[0082] In some embodiments of this application, after constructing a decision tree based on the decision nodes corresponding to each condition, the device further includes a control module, configured to: in response to detecting an air conditioning control operation for the air conditioner to be controlled, acquire the current condition parameters of the air conditioner to be controlled under multiple target conditions; analyze the current condition parameters under the multiple conditions using the decision tree to obtain the operation state corresponding to the air conditioning control operation; and confirm whether to execute the air conditioning control operation based on the operation state.

[0083] In some embodiments of this application, the node analysis module is configured to: calculate the information entropy and conditional entropy of each target condition relative to the execution state based on each target parameter and its corresponding state parameter, wherein the execution state refers to the air conditioning control operation being executed; calculate the difference between the information entropy and conditional entropy of each target condition relative to the execution state to obtain the mutual information between each target condition and the execution state; determine the root condition as the root node, and determine the sub-conditions under the root condition as the leaf nodes corresponding to the root node, wherein the root condition is the target condition corresponding to the highest mutual information, and each leaf node corresponds to a branch; determine the branches and branch nodes corresponding to each other condition by calculating the mutual information between the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions, wherein the other conditions are target conditions other than the root condition among multiple target conditions.

[0084] In some embodiments of this application, the construction module is used to: connect each of the branch nodes to the leaf nodes under the root node according to the corresponding branches, so as to obtain the decision tree.

[0085] In some embodiments of this application, before obtaining the decision node corresponding to each condition by performing mutual information analysis on each target parameter and the state parameter, the device further includes a threshold analysis module, used to: query the scene threshold corresponding to the usage scenario of the air conditioner to be controlled, and obtain the predetermined threshold; and obtain the condition parameter corresponding to the correlation coefficient exceeding the predetermined threshold from the condition parameters of the multiple conditions, and obtain the multiple target parameters.

[0086] In some embodiments of this application, before performing correlation calculations on each of the condition parameters and the state parameters, the device further includes an interpolation module for: determining whether there are missing values ​​in the historical control data; and if there are missing values, performing interpolation processing on the historical control data.

[0087] In some embodiments of this application, the interpolation module is used to: perform Lagrange interpolation on the historical manipulation data if there are missing values.

[0088] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0089] Furthermore, embodiments of this application also provide an electronic device, such as... Figure 3 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically:

[0090] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0091] in:

[0092] The processor 301 is the control center of the electronic device. It connects to various parts of the computer device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 302, and by calling data stored in the memory 302, it performs various functions of the computer device and processes data, thereby providing overall monitoring of the electronic device. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user page, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 301.

[0093] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 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 according to the use of the computer device, etc. In addition, the memory 302 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 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0094] The electronic device also includes a power supply 303 that supplies power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 303 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.

[0095] The electronic device may also include an input unit 304, 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.

[0096] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device loads the executable files corresponding to the processes of one or more computer programs into the memory 302 according to the following instructions, and the processor 301 runs the computer programs stored in the memory 302, thereby realizing the various functions in the foregoing embodiments of this application. For example, the processor 301 can perform the following steps:

[0097] Historical operation data for the air conditioner to be controlled is acquired. This historical operation data includes conditional parameters and corresponding state parameters for various conditions, with the state parameters corresponding to air conditioner control operations. Correlation calculations are performed on each conditional parameter and each state parameter to obtain a correlation coefficient between them. Mutual information analysis is performed on each target parameter and the state parameter to obtain decision nodes corresponding to each target condition. The target parameter is the conditional parameter corresponding to a correlation coefficient exceeding a predetermined threshold, and the target condition is the condition corresponding to the target parameter. A decision tree is constructed based on the decision nodes corresponding to each condition, and this decision tree is used for predictive control of the air conditioner control operations.

[0098] In some embodiments of this application, after constructing a decision tree based on the decision nodes corresponding to each of the target conditions, the method may further include: in response to detecting the air conditioning control operation for the air conditioner to be controlled, obtaining the current condition parameters of the air conditioner to be controlled under multiple target conditions; using the decision tree to analyze the current condition parameters under the multiple conditions to obtain the operation state corresponding to the air conditioning control operation; and confirming whether to execute the air conditioning control operation based on the operation state.

[0099] In some embodiments of this application, the step of obtaining the decision node corresponding to each target condition by performing mutual information analysis on each target parameter and the state parameter includes: calculating the information entropy and condition entropy of each target condition relative to the execution state based on each target parameter and the corresponding state parameter, wherein the execution state refers to the air conditioning control operation being executed; calculating the difference between the information entropy and condition entropy of each target condition relative to the execution state to obtain the mutual information between each target condition and the execution state; determining the root condition as the root node, and determining the sub-conditions under the root condition as the leaf nodes corresponding to the root node, wherein the root condition is the target condition corresponding to the highest mutual information, and each leaf node corresponds to a branch; determining the branches and branch nodes corresponding to each other condition by calculating the mutual information between the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions, wherein the other conditions are target conditions other than the root condition among multiple target conditions.

[0100] In some embodiments of this application, constructing a decision tree based on the decision nodes corresponding to each of the target conditions includes: connecting each of the branch nodes to the leaf nodes under the root node according to the corresponding branches to obtain the decision tree.

[0101] In some embodiments of this application, before obtaining the decision node corresponding to each target condition by performing mutual information analysis on each target parameter and the state parameter, the method further includes: querying the scenario threshold corresponding to the usage scenario of the air conditioner to be controlled to obtain the predetermined threshold; and obtaining the condition parameter corresponding to the correlation coefficient exceeding the predetermined threshold from the condition parameters of the multiple conditions to obtain the multiple target parameters.

[0102] In some embodiments of this application, before performing correlation calculations on each of the condition parameters and the state parameters, the method further includes: determining whether there are missing values ​​in the historical control data; if there are missing values, interpolating the historical control data.

[0103] In some embodiments of this application, the step of interpolating the historical control data if missing values ​​exist includes: performing Lagrange interpolation on the historical control data if missing values ​​exist.

[0104] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by a computer program, or by a computer program controlling related hardware. The computer program can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0105] Therefore, embodiments of this application also provide a storage medium storing a computer program that can be loaded by a processor to execute the steps in any of the methods provided in embodiments of this application.

[0106] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0107] Since the computer program stored in the storage medium can execute the steps of any of the methods provided in the embodiments of this application, the beneficial effects that the methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0108] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0109] It should be understood that this application is not limited to the embodiments described above and shown in the accompanying drawings, but various modifications and changes can be made without departing from its scope.

Claims

1. An air conditioning control method, characterized in that, include: Acquire historical control data for the air conditioner to be controlled. The historical control data includes condition parameters and corresponding status parameters for various conditions. The status parameters correspond to the air conditioner control operation. Correlation calculations are performed on each of the condition parameters and the state parameters to obtain the correlation coefficient between each of the condition parameters and the state parameters. The correlation coefficient is used to reflect the degree of correlation between the condition parameters and the corresponding state parameters. By performing mutual information analysis on each target parameter and the state parameter, decision nodes corresponding to each target condition are obtained. The target parameter is the condition parameter corresponding to the correlation coefficient exceeding a predetermined threshold, the target condition is the condition corresponding to the target parameter, and the predetermined threshold is a pre-set threshold or a threshold determined according to the usage scenario of the air conditioner to be controlled. A decision tree is constructed based on the decision nodes corresponding to each of the target conditions, and the decision tree is used to perform predictive control on the air conditioning control operation. The step of obtaining decision nodes corresponding to each objective condition by performing mutual information analysis on each objective parameter and the state parameter includes: Based on each target parameter and its corresponding state parameter, calculate the information entropy and condition entropy of each target condition relative to the execution state, where the execution state refers to the air conditioning control operation being executed; The difference between the information entropy and condition entropy of each target condition relative to the execution state is calculated to obtain the mutual information between each target condition and the execution state; The root condition is determined as the root node, and the sub-conditions under the root condition are determined as the leaf nodes corresponding to the root node. The root condition is the target condition corresponding to the highest mutual information, and each leaf node corresponds to a branch. By calculating the mutual information between the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions, the branches and branch nodes corresponding to each of the other conditions are determined. The other conditions are target conditions other than the root condition among a variety of target conditions.

2. The method according to claim 1, characterized in that, After constructing a decision tree based on the decision nodes corresponding to each condition, the method further includes: In response to detecting the air conditioning control operation for the air conditioner to be controlled, the current condition parameters of the air conditioner to be controlled under multiple target conditions are obtained; The decision tree is used to analyze the current condition parameters under the various conditions to obtain the operation state corresponding to the air conditioning control operation; Determine whether to execute the air conditioning control operation based on the operating status.

3. The method according to claim 1, characterized in that, The step of constructing a decision tree based on the decision nodes corresponding to each of the target conditions includes: Each of the branch nodes is connected in series to the leaf node under the root node according to its corresponding branch, thus obtaining the decision tree.

4. The method according to claim 1, characterized in that, Before obtaining the decision node corresponding to each objective condition by performing mutual information analysis on each objective parameter and the state parameter, the method further includes: Based on the usage scenario of the air conditioner to be controlled, query the scenario threshold corresponding to the usage scenario to obtain the predetermined threshold; From the condition parameters of the various conditions, the condition parameters corresponding to the correlation coefficients that exceed the predetermined threshold are obtained, thus obtaining the various target parameters.

5. The method according to any one of claims 1 to 4, characterized in that, Before performing correlation calculations on each of the condition parameters and the state parameters, the method further includes: Determine whether the historical control data contains missing values; If missing values ​​exist, the historical manipulation data is interpolated.

6. The method according to claim 5, characterized in that, If missing values ​​exist, the historical manipulation data will be interpolated, including: If missing values ​​exist, the historical manipulation data is processed by Lagrange interpolation.

7. An air conditioning control device, characterized in that, include: The acquisition module is used to acquire historical operation data for the air conditioner to be controlled. The historical operation data includes various condition parameters and corresponding status parameters, and the status parameters correspond to the air conditioner control operation. The correlation calculation module is used to perform correlation calculations on each of the condition parameters and the state parameters respectively, and to obtain the correlation coefficient between each of the condition parameters and the state parameters. The correlation coefficient is used to reflect the degree of correlation between the condition parameters and the corresponding state parameters. The node analysis module is used to obtain the decision node corresponding to each target condition by performing mutual information analysis on each target parameter and the state parameter. The target parameter is the condition parameter corresponding to the correlation coefficient exceeding a predetermined threshold, the target condition is the condition corresponding to the target parameter, and the predetermined threshold is a pre-set threshold or a threshold determined according to the usage scenario of the air conditioner to be controlled. The step of obtaining decision nodes corresponding to each target condition by performing mutual information analysis on each target parameter and the state parameter includes: calculating the information entropy and conditional entropy of each target condition relative to the execution state based on each target parameter and the corresponding state parameter, wherein the execution state refers to the air conditioning control operation being executed; calculating the difference between the information entropy and conditional entropy of each target condition relative to the execution state to obtain the mutual information between each target condition and the execution state; determining the root condition as the root node, and determining the sub-conditions under the root condition as the leaf nodes corresponding to the root node, wherein the root condition is the target condition corresponding to the highest mutual information, and each leaf node corresponds to a branch; determining the branches and branch nodes corresponding to each other condition by calculating the mutual information between the sub-condition parameters corresponding to each sub-condition under the root condition and the target parameters corresponding to other conditions, wherein the other conditions are target conditions other than the root condition among multiple target conditions; A construction module is used to construct a decision tree based on the decision nodes corresponding to each of the target conditions, and the decision tree is used to perform predictive control on the air conditioning control operation.

8. A storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the method described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: Memory, which stores computer programs; A processor reads a computer program stored in memory to perform the method described in any one of claims 1 to 6.

Images