Terminal control method and device, air conditioning equipment and storage medium

Abstract

The invention relates to a terminal control method and device, air conditioning equipment and a storage medium. The method comprises the steps of obtaining user historical use data of a target terminal in a preset time period; a plurality of categories corresponding to the user classification model and condition data corresponding to each category are determined, different categories represent different energy-saving preference types, and for each category, the condition data represent conditions which need to be met by historical use data of users belonging to the category; the user classification model is a big data classification model obtained by pre-training according to terminal use historical data of a plurality of users; determining a user type of a target user corresponding to the target terminal according to the user historical use data, the plurality of categories and the condition data corresponding to each category; control parameters are determined according to the user types, the target terminal is controlled according to the control parameters, and different user types correspond to different control parameters.

Description

Technical Field

[0001] The present disclosure relates to the field of terminal control, and particularly to a terminal control method, device, air conditioning equipment and storage medium. Background Art

[0002] In recent years, energy conservation and emission reduction as well as comprehensive utilization of resources have been strongly supported. Future smart home appliances (such as air conditioners, refrigerators, etc.) will take technological innovation as the core to achieve energy conservation and comfort, and meet the energy conservation preference needs of different users.

[0003] Taking an air conditioner as an example, with the development of smart air conditioner technology, users' requirements for the comfort and energy saving of air conditioners are constantly increasing, and different users also have different preferences for energy saving of air conditioners. Making the air conditioner understand users, identify user needs, and formulate control methods suitable for different users has become a research hotspot in air conditioner development. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a terminal control method, device, air conditioning equipment and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a terminal control method is provided, including:

[0006] Obtaining historical user usage data of a target terminal within a preset time period;

[0007] Determining a plurality of categories corresponding to a user classification model and condition data respectively corresponding to each category, where different categories represent different energy conservation preference types, and for each category, the condition data represents the conditions that the historical usage data of users belonging to this category needs to meet. The user classification model is a big data classification model pre-trained according to the terminal usage historical data of multiple users;

[0008] Determining the user type of the target user corresponding to the target terminal according to the historical user usage data, the plurality of categories and the condition data respectively corresponding to each category, where the user type represents the energy conservation preference type of the target user using the target terminal;

[0009] Determining control parameters according to the user type, and controlling the target terminal according to the control parameters, where different user types correspond to different control parameters.

[0010] Optionally, the user classification model includes a fuzzy clustering algorithm model, and the determining a plurality of categories corresponding to the user classification model and condition data respectively corresponding to each category includes:

[0011] Obtaining a clustering result corresponding to the fuzzy clustering algorithm model, where the clustering result includes the plurality of categories and the clustering center data respectively corresponding to each category;

[0012] For each category, use the clustering center data corresponding to the category as the conditional data corresponding to the category.

[0013] Optionally, determining the user type of the target user corresponding to the target terminal according to the user historical usage data, the multiple categories, and the conditional data corresponding to each category respectively includes:

[0014] For each category, determine the data determination condition corresponding to the category according to the category and the conditional data corresponding to the category;

[0015] According to the user historical usage data and the data determination conditions corresponding to each category respectively, determine the target category corresponding to the user historical usage data from the multiple categories;

[0016] Use the energy-saving preference type corresponding to the target category as the user type.

[0017] Optionally, the fuzzy clustering algorithm model is pre-trained in the following manner:

[0018] Obtain the terminal usage historical data of multiple users within the preset time period;

[0019] Determine the number of clusters of the fuzzy clustering algorithm and the clustering center data of each category according to the terminal usage historical data of the multiple users;

[0020] Loop and execute the parameter update step until a preset stop condition is met;

[0021] Wherein, the parameter update step includes:

[0022] Determine the membership matrix according to the clustering center data and the terminal usage historical data of multiple users; for each user, the membership matrix represents the probability that the user belongs to each category respectively;

[0023] Update the clustering center data of each category according to the membership matrix;

[0024] The preset stop condition includes:

[0025] Reach the maximum number of iterations; or,

[0026] The clustering center data and / or the membership matrix meet the preset convergence accuracy.

[0027] Optionally, the terminal usage historical data includes multi-dimensional terminal usage historical data, and the method further includes:

[0028] Perform a correlation test on the multi-dimensional terminal usage historical data to obtain the correlation coefficients between the data of different dimensions;

[0029] After performing data screening on the multi-dimensional terminal usage historical data according to the correlation coefficients, target historical data is obtained. The dimension of the target historical data is less than or equal to the dimension of the terminal usage historical data, and the correlation coefficient between the data of different dimensions in the target historical data is less than or equal to a preset correlation coefficient threshold;

[0030] The determining the number of clusters of the fuzzy clustering algorithm and the cluster center data of each category according to the terminal usage historical data of the multiple users includes:

[0031] Determine the number of clusters of the fuzzy clustering algorithm and the cluster center data of each category according to the target historical data;

[0032] The determining the membership matrix according to the cluster center data and the terminal usage historical data of the multiple users includes:

[0033] Determine the membership matrix according to the cluster center data and the target historical data of the multiple users.

[0034] Optionally, the target terminal includes an air conditioner, and the user historical usage data includes at least one of the following data:

[0035] Cooling startup operation data, heating startup operation data, user cooling usage habits data, user heating usage habits data, air conditioner operation status data.

[0036] Optionally, the control parameters include at least one of the following parameters:

[0037] Set temperature correction value, open-loop stage frequency correction coefficient, electric auxiliary heating control start condition parameter, temperature-reached shutdown temperature correction value.

[0038] Optionally, the control parameters include the temperature-reached shutdown temperature correction value, and the determining the control parameters according to the user type includes:

[0039] In the case where the user type is the first user type, determine the temperature-reached shutdown temperature correction value as the first correction value; in the case where the user type is the second user type, determine the temperature-reached shutdown temperature correction value as the second correction value; wherein, the energy-saving requirement corresponding to the first user type is less than the energy-saving requirement corresponding to the second user type, and the first correction value is greater than the second correction value.

[0040] Optionally, the control parameter further includes the electric auxiliary heating control start condition parameter, and the electric auxiliary heating control start condition parameter includes at least one of the electric auxiliary heating switch judgment temperature difference and the ambient temperature comfort zone temperature range boundary value;

[0041] The determining the control parameter according to the user type includes:

[0042] When the user type is the first user type, determining that the electric auxiliary heating switch judgment temperature difference is the first temperature difference, and the ambient temperature comfort zone temperature range boundary value is the third temperature;

[0043] When the user type is the second user type, determining that the electric auxiliary heating switch judgment temperature difference is the second temperature difference, and the ambient temperature comfort zone temperature range boundary value is the fourth temperature;

[0044] Wherein, the first temperature difference is less than the second temperature difference, and the third temperature is greater than the fourth temperature.

[0045] Optionally, the control parameter further includes the open-loop stage frequency correction coefficient, and the determining the control parameter according to the user type includes:

[0046] When the user type is the first user type, determining that the open-loop stage frequency correction coefficient is the first correction coefficient; when the user type is the second user type, determining that the open-loop stage frequency correction coefficient is the second correction coefficient; wherein, the first correction coefficient is greater than the second correction coefficient.

[0047] Optionally, the control parameter further includes a set temperature correction value, and the determining the control parameter according to the user type includes:

[0048] When the user type is the first user type, determining that the set temperature correction value is the third correction value; when the user type is the second user type, determining that the set temperature correction value is the fourth correction value; wherein, the third correction value is less than the fourth correction value.

[0049] According to a second aspect of the embodiments of the present disclosure, there is provided a terminal control device, including:

[0050] An acquisition module, configured to acquire the user historical usage data of the target terminal within a preset time period;

[0051] A first determination module, configured to determine a plurality of categories corresponding to a user classification model and conditional data respectively corresponding to each category, where different categories represent different energy-saving preference types, and for each category, the conditional data represents the conditions that the historical usage data of users belonging to this category needs to meet, and the user classification model is a big data classification model pre-trained according to the terminal usage historical data of multiple users;

[0052] A second determination module, configured to determine the user type of the target user corresponding to the target terminal according to the user historical usage data, the plurality of categories, and the conditional data respectively corresponding to each category, where the user type represents the energy-saving preference type of the target user using the target terminal;

[0053] A control module, configured to determine a control parameter according to the user type and control the target terminal according to the control parameter, where different user types correspond to different control parameters.

[0054] According to a third aspect of the embodiments of the present disclosure, there is provided an air conditioning device, including:

[0055] A processor;

[0056] A memory for storing processor-executable instructions;

[0057] Wherein, the processor is configured to: execute the steps of the method described in the first aspect of the present disclosure.

[0058] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the terminal control method provided in the first aspect of the present disclosure are implemented.

[0059] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: It is possible to classify the energy-saving preference types corresponding to different terminal users based on a user classification model determined by big data analysis of the terminal usage historical data of multiple users, so as to fully exploit the value of terminal usage big data, identify the energy-saving preference needs of users when using the terminal from the perspective of big data, and have better universality. Further, through this user classification model, the energy-saving preference types corresponding to different terminal users are classified, so that the control parameters matching the energy-saving preference type of the user can be determined based on the classification result, which can meet the energy-saving preference needs of different users and improve user satisfaction and energy-saving comfort.

[0060] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0061] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0062] Figure 1 It is a flowchart of a terminal control method shown according to an exemplary embodiment.

[0063] Figure 2 is according to Figure 1 It is a flowchart of a terminal control method shown according to the illustrated embodiment.

[0064] Figure 3 is according to Figure 1 It is a flowchart of a terminal control method shown according to the illustrated embodiment.

[0065] Figure 4 It is a flowchart of a training method for a fuzzy clustering algorithm model shown according to an exemplary embodiment.

[0066] Figure 5 It is a block diagram of a terminal control device shown according to an exemplary embodiment.

[0067] Figure 6 is according to Figure 5 It is a block diagram of a terminal control device shown according to the illustrated embodiment.

[0068] Figure 7 It is a block diagram of a device 700 for terminal control shown according to an exemplary embodiment. Detailed implementation manners

[0069] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0070] It should be noted that all actions of obtaining signals, information, or data in the present disclosure are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where it is located and obtaining the authorization given by the owner of the corresponding device.

[0071] The present disclosure is mainly applied to the scenario of intelligent control of terminals. The terminal may include intelligent household appliances (such as air conditioners, refrigerators, etc.), or may also include vehicles.

[0072] Taking an air conditioner as an example, different users have different preferences for power saving of the air conditioner, and it is difficult for a fixed control strategy to meet the power saving preference requirements of different users. In the related art, it is possible to collect the user air conditioner usage behavior data and environmental parameters corresponding to the air conditioner to be controlled currently, so as to extract the behavior characteristics of the user using the air conditioner. Then, an expert experience model is used to cluster the cold and heat preferences of the user. However, the expert experience model focuses on the rationality of the preset clustering logic and does not fully explore the value of the big data of the user using the air conditioner, and its universality and real-time performance need to be improved.

[0073] To solve the above existing problems, the present disclosure provides a terminal control method, device, air conditioning equipment and storage medium. The following will describe the specific embodiments of the present disclosure in detail with reference to the accompanying drawings.

[0074] Figure 1 is a flowchart of a terminal control method shown according to an exemplary embodiment. This method can be applied to a server (or referred to as "the cloud"). As Figure 1 shown, the method includes the following steps.

[0075] In step S11, obtain the user historical usage data of the target terminal within a preset time period.

[0076] Among them, the preset time period may include a preset historical time period with the current moment as the end moment (such as the user historical usage data generated when the user uses the target terminal in the past 7 days).

[0077] In addition, the user historical usage data may include multi-dimensional user usage data. For example, taking the target terminal as an air conditioner, the user historical usage data may include one or more of refrigeration start-up operation data, heating start-up operation data, user refrigeration usage habits data, user heating usage habits data, and air conditioner operation status data.

[0078] Among them, the refrigeration start-up operation data may include, for example, the number of refrigeration days in the past 7 days, the number of refrigeration hours in the past 7 days, and the average daily refrigeration hours, etc. The heating start-up operation data may include, for example, the number of heating days in the past 7 days, the number of heating hours in the past 7 days, and the average daily heating hours, etc. The user refrigeration usage habits data may include the refrigeration start-up frequency of the air conditioner, the average value of the set refrigeration temperature, the maximum value of the refrigeration set temperature, and the minimum value of the refrigeration set temperature, etc. The user heating usage habits data may include the heating start-up frequency of the air conditioner, the average value of the set heating temperature, the maximum value of the heating set temperature, and the minimum value of the heating set temperature, etc. The air conditioner operation status data may include the average operation frequency of the refrigeration compressor in the past seven days and the average operation frequency of the heating compressor in the past seven days, etc.

[0079] In one implementation, a target terminal (such as an air conditioner) can collect the historical usage data of the users of the target terminal within a preset time period, and then upload it to the cloud. In this way, the cloud can obtain the historical usage data of the users. After that, the cloud can classify the users of the target terminal according to the user classification model obtained by big data analysis based on the historical usage data of the users, and obtain the user types of the users of the target terminal.

[0080] In step S12, multiple categories corresponding to the user classification model and the conditional data corresponding to each category are determined. Different categories represent different energy-saving preference types. For each category, the conditional data represents the conditions that the historical usage data of the users belonging to this category needs to meet. The user classification model is a big data classification model pre-trained according to the terminal usage historical data of multiple users.

[0081] Among them, the user classification model can include a pre-trained fuzzy clustering algorithm model. In a possible implementation, the cloud can receive the terminal usage historical data of multiple users uploaded by multiple terminals. In this way, the terminals can obtain the big data of terminal usage. After that, based on big data analysis, the pre-set big data classification model (such as a fuzzy clustering algorithm model) can be trained to obtain the user classification model. Among them, the terminal usage historical data of the multiple users for model training can also include the terminal usage data obtained by different terminals within the preset time period. The energy-saving preference types can include, for example, strong energy-saving type, general power-saving type, and comfortable operation type.

[0082] Taking the user classification model as the fuzzy clustering algorithm model as an example, for the fuzzy clustering algorithm, after the corresponding model is trained, a clustering result can be obtained. The clustering result can include multiple categories and the clustering center data corresponding to each category. In the present disclosure, the number of these categories represents the number of user types (or "energy-saving preference types"), and different categories represent different user energy-saving preference types. The clustering center data corresponding to each category is the conditional data corresponding to this category, and usually represents the mean value of the terminal usage historical data of the users belonging to the user type corresponding to this category.

[0083] In step S13, according to the historical usage data of the users, the multiple categories, and the conditional data corresponding to each category, the user type of the target user corresponding to the target terminal is determined. The user type represents the energy-saving preference type of the target user using the target terminal.

[0084] Exemplarily, for the use of an air conditioner, if it is determined based on the user's historical usage data of the air conditioner in the past 7 days that the user has used the air conditioner for a relatively large number of cooling days (e.g., ≥ 5 days) and the set cooling temperature is relatively low (e.g., < 24°C), it can be determined that the user type of this user is the comfortable operation type; if it is determined based on the user's historical usage data of the air conditioner in the past 7 days that the user has used the air conditioner for a relatively small number of cooling days (e.g., < 3 days) and the set cooling temperature is relatively high (e.g., > 27°C), it can be determined that the user type of this user is the strong energy-saving type; if it is determined based on the user's historical usage data of the air conditioner in the past 7 days that the user has used the air conditioner for a medium number of cooling days (e.g., 3 days ≤ cooling days < 5 days) and the set cooling temperature is medium (e.g., 24°C ≤ set cooling temperature < 27°C), it can be determined that the user type of this user is the general power-saving type. The above examples are only for illustration, and the present disclosure does not limit this.

[0085] After the cloud determines the user type of the user of the target terminal, it can obtain the control parameters corresponding to the user type of the target terminal based on the corresponding relationship between the preset user type and the control parameters.

[0086] In step S14, control parameters are determined according to the user type, and the target terminal is controlled according to the control parameters. Different user types correspond to different control parameters.

[0087] Taking the terminal to be controlled as an air conditioner as an example, the control parameters may include at least one of the following parameters: set temperature correction value, open-loop stage frequency correction coefficient, electric auxiliary heat control start condition parameter, temperature reach stop temperature correction value.

[0088] Different users have different energy-saving preference requirements for the terminal. If a fixed control strategy is used to control the operation of the terminal, it is bound to be difficult to meet the power-saving preference requirements of different users. Therefore, the present disclosure starts from the actual needs of users through big data algorithms, identifies the user types corresponding to different users, and determines the corresponding control parameters based on different user types to control the terminal, so as to provide customized services for users, improve the user experience, and save energy consumption at the same time.

[0089] In one implementation manner of this step, after the cloud determines the control parameters corresponding to the user type, it can send the control parameters to the target terminal so that the target terminal controls the terminal based on the control parameters.

[0090] In another implementation manner, it can also be determined by the target terminal itself based on the user classification model, and after determining the control parameters corresponding to the user type, the terminal is controlled.

[0091] By using the above method, it is possible to classify the energy-saving preference types corresponding to different terminal users based on the user classification model determined by big data analysis of the terminal usage historical data of multiple users, so as to fully exploit the value of terminal usage big data, identify the energy-saving preference requirements of users when using terminals from the perspective of big data, and have better universality. Further, through this user classification model, the energy-saving preference types corresponding to different terminal users can be classified, and thus the control parameters matching the energy-saving preference types of the users can be determined based on the classification results, which can meet the energy-saving preference requirements of different users and improve user satisfaction and energy-saving comfort.

[0092] In one implementation, the user classification model may include a fuzzy clustering algorithm model.

[0093] Figure 2 is based on Figure 1 The flowchart of a terminal control method shown in the illustrated embodiment is as follows Figure 2 As shown, step S12 includes the following sub-steps:

[0094] In step S121, obtain the clustering result corresponding to the fuzzy clustering algorithm model, where the clustering result includes multiple categories and the clustering center data corresponding to each category respectively.

[0095] Among them, the fuzzy clustering algorithm model is usually a big data classification model pre-trained by the cloud based on the terminal usage historical data of multiple users uploaded by each terminal. For the fuzzy clustering algorithm, after the corresponding model is trained, a clustering result can be obtained, and the clustering result can include multiple categories and the clustering center data corresponding to each category respectively. In the present disclosure, the number of these categories represents the number of user types (or "energy-saving preference types"), and different categories represent different user energy-saving preference types. The clustering center data corresponding to each category represents the mean value of the terminal usage historical data of the users belonging to the user type corresponding to this category.

[0096] In step S122, for each category, use the clustering center data corresponding to this category as the conditional data corresponding to this category.

[0097] Figure 3 is based on Figure 1 The flowchart of a terminal control method shown in the illustrated embodiment is as follows Figure 3 As shown, step S13 includes the following sub-steps:

[0098] In step S131, for each category, determine the data determination condition corresponding to this category according to this category and the conditional data corresponding to this category.

[0099] Among them, the conditional data corresponding to the category may include the clustering center data corresponding to the category.

[0100] In one implementation manner, the data determination condition corresponding to the category may be determined based on the clustering center data corresponding to the category and a preset data change amount. For example, based on the clustering center data, the data obtained by adding and / or subtracting the preset data change amount may be used as the data determination condition corresponding to the category.

[0101] Exemplarily, taking the terminal as an air conditioner as an example, assume that the clustering result determined by the fuzzy clustering algorithm model according to the terminal usage historical data of multiple users includes three categories. Among them, the clustering center data corresponding to Category 1 is: the number of cooling days in the past 7 days is 6 days, and the set cooling temperature in the past 7 days is 23 degrees; the clustering center data corresponding to Category 2 is: the number of cooling days in the past 7 days is 4 days, and the set cooling temperature in the past 7 days is 25 degrees; the clustering center data corresponding to Category 3 is: the number of cooling days in the past 7 days is 2 days, and the set cooling temperature in the past 7 days is 28 degrees. Assume that the preset data change amount corresponding to the number of cooling days is 1 day, and the preset data change amount corresponding to the set cooling temperature is 1 degree. Then, the data determination condition corresponding to Category 1 can be determined as the number of cooling days in the past 7 days ≥ 5 days, and the set cooling temperature in the past 7 days ≤ 24 degrees; the data determination condition corresponding to Category 2 can be determined as 3 days ≤ the number of cooling days in the past 7 days < 5 days, and 24 degrees < the set cooling temperature in the past 7 days ≤ 26 degrees; the data determination condition corresponding to Category 3 can be determined as the number of cooling days in the past 7 days < 3 days, and the set cooling temperature in the past 7 days > 26 degrees. The above examples are only for illustration, and the present disclosure does not limit this.

[0102] It should be noted that based on the clustering center data corresponding to each category, the user energy-saving preference type corresponding to the category can also be determined. Continuing with the above example, the clustering center data corresponding to Category 1 is: the number of cooling days in the past 7 days is 6 days, and the set cooling temperature in the past 7 days is 23 degrees; the clustering center data corresponding to Category 2 is: the number of cooling days in the past 7 days is 4 days, and the set cooling temperature in the past 7 days is 25 degrees; the clustering center data corresponding to Category 3 is: the number of cooling days in the past 7 days is 2 days, and the set cooling temperature in the past 7 days is 28 degrees. Accordingly, it can be determined that the energy-saving preference type corresponding to Category 1 is the comfortable operation type, the energy-saving preference type corresponding to Category 2 is the general power-saving type, and the energy-saving preference type corresponding to Category 3 is the strong energy-saving type. This is only for illustration here, and the present disclosure does not limit this.

[0103] In step S132, according to the user historical usage data and the data determination conditions respectively corresponding to each category, the target category corresponding to the user historical usage data is determined from the multiple categories.

[0104] In this step, for each category, when it is determined that the user's historical usage data meets the data determination conditions corresponding to the category, it is determined that this category is the target category corresponding to the user's historical usage data.

[0105] In step S133, the energy-saving preference type corresponding to the target category is used as the user type.

[0106] Exemplarily, assume that the target terminal is an air conditioner, and the user's historical usage data for the past 7 days obtained for the air conditioner user shows that the number of cooling days in the past 7 days is 4 days, and the set cooling temperature in the past 7 days is 25 degrees. Continuing with the above example, it can be determined that the target category corresponding to this air conditioner user is Category Two, and the energy-saving preference type corresponding to Category Two is the general power-saving type. Therefore, the user type corresponding to this air conditioner user is the general power-saving type. This is only an example for illustration, and the present disclosure is not limited thereto.

[0107] Figure 4 is a flowchart of a training method for a fuzzy clustering algorithm model shown according to an exemplary embodiment. As Figure 4 shown, the method includes the following steps:

[0108] In step S401, obtain the terminal usage historical data of multiple users within the preset time period.

[0109] Same as the user's historical usage data within the preset time period, the terminal usage historical data within the preset time period also includes multi-dimensional data. For example, taking an air conditioner as an example, the terminal usage historical data may include one or more of cooling startup operation data, heating startup operation data, user cooling usage habits data, user heating usage habits data, and air conditioner operation status data.

[0110] In one implementation, each terminal can upload the terminal usage historical data of the user collected within the preset time period to the cloud. In this way, the cloud can obtain the terminal usage historical data of multiple users uploaded by multiple terminals. After that, the cloud can perform big data statistics and train the fuzzy clustering algorithm model based on the terminal usage historical data of multiple users.

[0111] In step S402, determine the clustering number of the fuzzy clustering algorithm and the clustering center data of each category according to the terminal usage historical data of the multiple users.

[0112] In one implementation, the elbow method can be used to determine the number of clusters based on the terminal usage historical data of multiple users. After initializing the cluster center data corresponding to each cluster (i.e., each category) based on the terminal usage historical data of multiple users, the cluster center data of each category is obtained. The specific implementation of the elbow method and the initialization to obtain the cluster center data of each category can refer to the descriptions in relevant literature and will not be specifically limited herein.

[0113] In step S403, the parameter update step is executed in a loop until a preset stop condition is met.

[0114] In the present disclosure, the parameter update step includes: determining a membership matrix according to the cluster center data and the terminal usage historical data of multiple users; for each user, the membership matrix represents the probabilities that the user belongs to each category respectively; and updating the cluster center data of each category according to the membership matrix.

[0115] The preset stop condition includes: reaching the maximum number of iterations; or, the cluster center data and / or the membership matrix meet a preset convergence accuracy. This preset convergence accuracy can be an empirical value.

[0116] Among them, the membership matrix can be an m*n matrix, where m represents the number of users corresponding to the terminal usage historical data, and n represents the number of clusters. For each user, the membership matrix can represent the probabilities that the user belongs to each category. By way of example, assuming m = 2 (for example, including two users, user A and user B), and n = 3 (i.e., 3 categories, category one, category two, and category three), the membership matrix can be expressed as Among them, a1, a2, and a3 represent the probabilities that user A belongs to category one, category two, and category three respectively, and b1, b2, and b3 represent the probabilities that user B belongs to category one, category two, and category three respectively.

[0117] In this way, when it is determined that the preset stop condition is met, it is determined that the algorithm converges, and the clustering result when the algorithm converges can be obtained, so as to identify the user types of different users based on this clustering result.

[0118] In one implementation, during the process of pre-training a user classification model based on the terminal usage historical data of multiple users, the input data can be converted into a matrix. Since the terminal usage historical data usually includes multi-dimensional terminal usage historical data and the dimensions of different data have different units, in the present disclosure, the terminal usage historical data of multiple input users can be subjected to data standardization processing to eliminate the influence of data with different units on model training.

[0119] It should also be noted that, in order to further improve the accuracy of the user classification model, before model training, a correlation test can be performed on the multi-dimensional historical data of terminal usage to screen out the data for clustering analysis.

[0120] In one implementation, a correlation test can be performed on the multi-dimensional historical data of terminal usage to obtain the correlation coefficients between the data of different dimensions; after screening the multi-dimensional historical data of terminal usage according to the correlation coefficients, target historical data is obtained. The dimension of the target historical data is less than or equal to the dimension of the historical data of terminal usage, and the correlation coefficient between the data of different dimensions in the target historical data is less than or equal to a preset correlation coefficient threshold.

[0121] Among them, in the process of screening the multi-dimensional historical data of terminal usage according to the correlation coefficients to obtain the target historical data, based on the correlation coefficients, for the data of two or more dimensions with a strong correlation relationship, only one dimension of the data can be retained as the target historical data. For example, the data of two dimensions with a correlation coefficient greater than the preset correlation coefficient threshold can be regarded as the data with a strong correlation relationship.

[0122] It should be noted that considering that the usage frequency of the cooling mode of the air conditioner is higher than that of the heating mode, therefore, if the multi-dimensional historical data of terminal usage is the usage data of the air conditioner, in the process of performing a correlation test to obtain the target historical data, the usage data of users with the cooling function of the air conditioner can be retained as much as possible.

[0123] In this way, the clustering number of the fuzzy clustering algorithm and the clustering center data of each category can be determined according to the target historical data; the membership matrix described above can be determined according to the clustering center data and the target historical data of multiple users.

[0124] So far, the cloud can train a user classification model based on the big data analysis of the historical data of terminal usage of multiple users.

[0125] Taking the target terminal as an air conditioner as an example, the control parameter can include at least one of the following parameters: set temperature correction value, open-loop stage frequency correction coefficient, electric auxiliary heating control start condition parameter, temperature-reached shutdown temperature correction value.

[0126] Next, taking the air conditioner as an example, the specific implementation method for determining the control parameter based on different user types will be described.

[0127] In one implementation, the control parameter includes a temperature correction value for reaching the set temperature and stopping operation. The temperature for reaching the set temperature and stopping operation of an air conditioner generally refers to the temperature threshold at which the air conditioning system stops cooling or heating operations when the indoor temperature reaches a certain level. This temperature threshold can be set according to different air conditioning devices and user requirements.

[0128] In the present disclosure, when the user type is the first user type, the temperature correction value for reaching the set temperature and stopping operation is determined as the first correction value; when the user type is the second user type, the temperature correction value for reaching the set temperature and stopping operation is determined as the second correction value.

[0129] Among them, the energy-saving requirement corresponding to the first user type is less than the energy-saving requirement corresponding to the second user type. For example, if the first user type is a comfort operation type, the second user type can be a strong energy-saving type or a general power-saving type; if the first user type is a general power-saving type, the second user type can be a strong energy-saving type. Additionally, the first correction value is greater than the second correction value.

[0130] Taking the first user type as the comfort operation type and the second user type as the strong energy-saving type as an example, the temperature correction value for reaching the set temperature and stopping operation corresponding to users of the comfort operation type can be 1°C, and the temperature correction value for reaching the set temperature and stopping operation corresponding to users of the strong energy-saving type can be 0°C. In this way, for users of the comfort operation type, on the basis of the original temperature difference parameter for reaching the set temperature and stopping operation, it can be reduced by 1°C; for users of the strong energy-saving type, the original temperature difference parameter for reaching the set temperature and stopping operation can be maintained unchanged.

[0131] In the present disclosure, the temperature difference parameter for reaching the set temperature and stopping operation to be adjusted can have multiple levels, and the judgment temperature differences for reaching the set temperature and stopping operation corresponding to different levels are different. The cloud can determine different temperature correction values for reaching the set temperature and stopping operation based on the temperature difference parameters for reaching the set temperature and stopping operation at different levels.

[0132] Exemplarily, the air conditioner to be controlled includes three levels: the cooling temperature difference for reaching the set temperature and stopping operation 1, the cooling temperature difference for reaching the set temperature and stopping operation 2, and the cooling temperature difference for reaching the set temperature and stopping operation 3. The different temperature correction values for reaching the set temperature and stopping operation corresponding to different user types determined by the cloud can be the following situations:

[0133] Correction of the cooling temperature difference for reaching the set temperature and stopping operation 3: For users of the comfort operation type, for the cooling temperature difference for reaching the set temperature and stopping operation 3, on the basis of the original temperature difference 3 parameter, it is reduced by 1°C; for users of the general power-saving type, on the basis of the original temperature difference 3 parameter, it is reduced by 0.5°C; for users of the strong energy-saving type, the original temperature difference 3 parameter is maintained unchanged.

[0134] Correction of the cooling temperature difference for reaching the set temperature and stopping operation 2: For users of the comfort operation type, for the cooling temperature difference for reaching the set temperature and stopping operation 2, on the basis of the original temperature difference 2 parameter, it is reduced by 0.5°C; for users of the general power-saving type and the strong energy-saving type, the original temperature difference 2 parameter is maintained unchanged.

[0135] Correction of the temperature difference 1 for refrigeration reaching the set temperature and stopping: For users of the comfortable operation type, general power-saving type, and strong energy-saving type, the original temperature difference 1 parameter remains unchanged.

[0136] In this way, different temperature correction values for reaching the set temperature and stopping can be determined for different user types, so as to control the temperature for reaching the set temperature and stopping of the air conditioner based on the temperature correction value for reaching the set temperature and stopping that matches the user type, thereby meeting the energy-saving requirements of different users.

[0137] In one implementation, the control parameter may further include an electric auxiliary heating control start condition parameter, and the electric auxiliary heating control start condition parameter may include at least one of an electric auxiliary heating switch judgment temperature difference and a boundary value of the ambient temperature comfortable zone temperature range.

[0138] Among them, the electric auxiliary heating switch judgment temperature difference may further include an electric auxiliary heating on judgment temperature difference and an electric auxiliary heating off judgment temperature difference. The boundary value of the ambient temperature comfortable zone temperature range may include a lower limit of the indoor ambient temperature comfortable zone for a wall-mounted unit and an upper limit of the indoor ambient temperature comfortable zone for a wall-mounted unit.

[0139] In this way, in the process of determining the control parameter according to the user type in step S14, when the user type is the first user type, the electric auxiliary heating switch judgment temperature difference may be determined as the first temperature difference, and the boundary value of the ambient temperature comfortable zone temperature range may be determined as the third temperature; when the user type is the second user type, the electric auxiliary heating switch judgment temperature difference may be determined as the second temperature difference, and the boundary value of the ambient temperature comfortable zone temperature range may be determined as the fourth temperature; where the first temperature difference is less than the second temperature difference, and the third temperature is greater than the fourth temperature.

[0140] Exemplarily, continuing to take the first user type as the comfortable operation type and the second user type as the strong energy-saving type as an example, the cloud can determine that the electric auxiliary heating on judgment temperature difference corresponding to users of the comfortable operation type is 3°C; the electric auxiliary heating on judgment temperature difference corresponding to users of the strong energy-saving type is 5°C. The cloud determines that the electric auxiliary heating off judgment temperature difference corresponding to users of the comfortable operation type is 1°C; the electric auxiliary heating off judgment temperature difference corresponding to users of the strong energy-saving type is 2.5°C. The cloud determines that the lower limit of the indoor ambient temperature comfortable zone corresponding to users of the comfortable operation type is 25°C; the lower limit of the indoor ambient temperature comfortable zone corresponding to users of the strong energy-saving type is 23°C. The cloud determines that the upper limit of the indoor ambient temperature comfortable zone corresponding to users of the comfortable operation type is 29°C; the upper limit of the indoor ambient temperature comfortable zone corresponding to users of the strong energy-saving type is 27°C. The above examples are only for illustration, and the present disclosure is not limited thereto.

[0141] In one implementation, the control parameter may further include the open-loop stage frequency correction coefficient. In this way, in the process of determining the control parameter according to the user type in step S14, when the user type is the first user type, the open-loop stage frequency correction coefficient may be determined as the first correction coefficient; when the user type is the second user type, the open-loop stage frequency correction coefficient may be determined as the second correction coefficient; wherein, the first correction coefficient is greater than the second correction coefficient.

[0142] Exemplarily, continuing with the example where the first user type is the comfort operation type and the second user type is the strong energy-saving type, the cloud determines that the open-loop stage frequency correction coefficient corresponding to the comfort operation type user is 1, and the open-loop stage frequency correction coefficient corresponding to the strong energy-saving type user is 0.8. In this way, the air conditioner may not correct the open-loop stage frequency based on the comfort operation type user, and the open-loop stage frequency based on the strong energy-saving type user may be multiplied by 0.8 on the basis of the original frequency to meet the energy-saving requirements of the strong energy-saving type user. The above example is only for illustration, and the present disclosure is not limited thereto.

[0143] In one implementation, the control parameter further includes a set temperature correction value. In this way, in the process of determining the control parameter according to the user type in step S14, when the user type is the first user type, the set temperature correction value may be determined as the third correction value; when the user type is the second user type, the set temperature correction value may be determined as the fourth correction value; wherein, the third correction value is less than the fourth correction value.

[0144] Exemplarily, in the cooling mode, the lower the temperature, the more power-consuming. Therefore, in the cooling mode, when the user sets the temperature ≥ 27°C, the actual set temperatures of the strong energy-saving type, general power-saving type, and comfort operation type users may not be corrected. When the user sets the temperature ≥ 24°C and the set temperature is less than 27°C, the actual set temperature of the strong energy-saving type user is corrected upward by 1.5°C according to the set temperature and does not exceed 27°C; the actual set temperature of the general power-saving type user is corrected upward by 1°C according to the set temperature and does not exceed 27°C; the actual set temperature of the comfort operation type user is not corrected. When the user sets the temperature less than 24°C, the actual set temperature of the strong energy-saving type user is corrected upward by 2°C according to the set temperature and does not exceed 24°C; the actual set temperature of the general power-saving type user is corrected upward by 1.5°C according to the set temperature and does not exceed 24°C; the actual set temperature of the comfort operation type user is not corrected.

[0145] In the heating mode, the higher the temperature, the more power-consuming it is. When the user sets the temperature ≥ 25°C, for users of the strong energy-saving type, the actual set temperature is corrected downward by 2°C from the set temperature and is not lower than 25°C; for users of the general power-saving type, the actual set temperature is corrected downward by 1.5°C from the set temperature and is not lower than 25°C; for users of the comfortable operation type, the actual set temperature is not corrected. When the user sets the temperature > 20°C and the set temperature ≤ 25°C, for users of the strong energy-saving type, the actual set temperature is corrected downward by 1.5°C from the set temperature and is not lower than 20°C; for users of the general power-saving type, the actual set temperature is corrected downward by 1°C from the set temperature and is not lower than 20°C; for users of the comfortable operation type, the actual set temperature is not corrected. When the user sets the temperature < 20°C, for users of the strong energy-saving type, the general power-saving type, and the comfortable operation type, the actual set temperature is not corrected.

[0146] Figure 5 It is a block diagram of a terminal control device shown according to an exemplary embodiment, as Figure 5 shown, the device includes:

[0147] An acquisition module 501, configured to acquire historical user usage data of a target terminal within a preset time period;

[0148] A first determination module 502, configured to determine a plurality of categories corresponding to a user classification model and condition data respectively corresponding to each category. Different categories represent different energy-saving preference types. For each category, the condition data represents the conditions that the historical usage data of users belonging to this category needs to meet. The user classification model is a big data classification model pre-trained according to the terminal usage historical data of multiple users;

[0149] A second determination module 503, configured to determine the user type of the target user corresponding to the target terminal according to the historical user usage data, the plurality of categories, and the condition data respectively corresponding to each category. The user type represents the energy-saving preference type of the target user using the target terminal;

[0150] A control module 504, configured to determine control parameters according to the user type and control the target terminal according to the control parameters. Different user types correspond to different control parameters.

[0151] Optionally, the user classification model includes a fuzzy clustering algorithm model. The first determination module 502 is configured to acquire the clustering result corresponding to the fuzzy clustering algorithm model. The clustering result includes the plurality of categories and the clustering center data respectively corresponding to each category. For each category, the clustering center data corresponding to this category is used as the condition data corresponding to this category.

[0152] Optionally, the second determination module 503 is configured to, for each category, determine the data determination condition corresponding to the category according to the category and the condition data corresponding to the category; determine the target category corresponding to the user historical usage data from the multiple categories according to the user historical usage data and the data determination conditions respectively corresponding to each category; and use the energy-saving preference type corresponding to the target category as the user type.

[0153] Optionally, Figure 6 is based on Figure 5 The block diagram of a terminal control device shown in the illustrated embodiment is as Figure 6 shown, and the device further includes:

[0154] The model training module 505 is configured to pre-train the fuzzy clustering algorithm model in the following manner:

[0155] Obtain the terminal usage historical data of multiple users within the preset time period;

[0156] Determine the clustering number of the fuzzy clustering algorithm and the clustering center data of each category according to the terminal usage historical data of the multiple users;

[0157] Loop to execute the parameter update step until a preset stop condition is met;

[0158] Wherein, the parameter update step includes:

[0159] Determine the membership matrix according to the clustering center data and the terminal usage historical data of multiple users; for each user, the membership matrix represents the probability that the user belongs to each category respectively;

[0160] Update the clustering center data of each category according to the membership matrix;

[0161] The preset stop condition includes:

[0162] Reaching the maximum number of iterations; or,

[0163] The clustering center data and / or the membership matrix meet the preset convergence accuracy.

[0164] Optionally, the terminal usage history data includes multi-dimensional terminal usage history data. The model training module 505 is configured to perform a correlation test on the multi-dimensional terminal usage history data to obtain the correlation coefficients between the data of different dimensions; after performing data screening on the multi-dimensional terminal usage history data according to the correlation coefficients, target historical data is obtained. The dimension of the target historical data is less than or equal to the dimension of the terminal usage history data, and the correlation coefficient between the data of different dimensions in the target historical data is less than or equal to a preset correlation coefficient threshold; determine the clustering number of the fuzzy clustering algorithm and the clustering center data of each category according to the target historical data; determine the membership matrix according to the clustering center data and the target historical data of multiple users.

[0165] Optionally, the target terminal includes an air conditioner, and the user historical usage data includes at least one of the following data:

[0166] Cooling start-up operation data, heating start-up operation data, user cooling usage habits data, user heating usage habits data, air conditioner operation status data.

[0167] Optionally, the control parameters include at least one of the following parameters:

[0168] Set temperature correction value, open-loop stage frequency correction coefficient, electric auxiliary heating control start condition parameter, temperature correction value for reaching temperature and stopping operation.

[0169] Optionally, the control parameters include the temperature correction value for reaching temperature and stopping operation. The control module 504 is configured to determine that the temperature correction value for reaching temperature and stopping operation is a first correction value when the user type is the first user type; determine that the temperature correction value for reaching temperature and stopping operation is a second correction value when the user type is the second user type; wherein, the energy-saving requirement corresponding to the first user type is less than the energy-saving requirement corresponding to the second user type, and the first correction value is greater than the second correction value.

[0170] Optionally, the control parameters further include the electric auxiliary heating control start condition parameter, and the electric auxiliary heating control start condition parameter includes at least one of the electric auxiliary heating switch judgment temperature difference and the boundary value of the environmental temperature comfort zone temperature range;

[0171] The control module 504 is configured to determine that the electric auxiliary heating switch judgment temperature difference is a first temperature difference and the boundary value of the environmental temperature comfort zone temperature range is a third temperature when the user type is the first user type;

[0172] When the user type is the second user type, determine that the temperature difference for judging the electric auxiliary heating switch is the second temperature difference, and the boundary value of the temperature range of the ambient temperature comfort zone is the fourth temperature;

[0173] Wherein, the first temperature difference is less than the second temperature difference, and the third temperature is greater than the fourth temperature.

[0174] Optionally, the control parameter further includes the open-loop stage frequency correction coefficient. The control module 504 is configured to determine that the open-loop stage frequency correction coefficient is the first correction coefficient when the user type is the first user type; and determine that the open-loop stage frequency correction coefficient is the second correction coefficient when the user type is the second user type; wherein, the first correction coefficient is greater than the second correction coefficient.

[0175] Optionally, the control parameter further includes a set temperature correction value. The control module 504 is configured to determine that the set temperature correction value is the third correction value when the user type is the first user type; and determine that the set temperature correction value is the fourth correction value when the user type is the second user type; wherein, the third correction value is less than the fourth correction value.

[0176] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0177] The present disclosure also provides an air conditioning device (such as an air conditioner), which may include a processor; a memory for storing processor-executable instructions; wherein, the processor is configured to: execute the above terminal control method.

[0178] The present disclosure also provides a computer-readable storage medium, on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the terminal control method provided by the present disclosure are implemented.

[0179] In another exemplary embodiment, a computer program product is also provided, which includes a computer program capable of being executed by a programmable device, and the computer program has a code portion for executing the above terminal control method when executed by the programmable device.

[0180] Figure 7 It is a block diagram of a device 700 for terminal control shown according to an exemplary embodiment. For example, the device 700 may be provided as a server. Refer to Figure 7, Device 700 includes a processing component 722, which further includes one or more processors, and memory resources represented by a memory 732 for storing instructions executable by the processing component 722, such as application programs. The application programs stored in the memory 732 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 722 is configured to execute instructions to perform the above terminal control method.

[0181] Device 700 may also include a power component 726 configured to perform power management of the device 700, a wired or wireless network interface 750 configured to connect the device 700 to a network, and an input / output interface 758. Device 700 may operate based on an operating system stored in the memory 732, such as Windows Server TM , Mac OS X TM , Unix TM , Linux TM , FreeBSD TM or the like.

[0182] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and examples are only illustrative, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0183] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A terminal control method, characterized in that, The method includes: Obtaining the user's historical usage data of the target terminal within a preset time period; Determining a plurality of categories corresponding to the user classification model and the conditional data corresponding to each category. Different categories represent different energy-saving preference types. For each category, the conditional data represents the conditions that the historical usage data of users belonging to this category needs to meet. The user classification model is a big data classification model pre-trained according to the terminal usage historical data of multiple users; According to the user's historical usage data, the plurality of categories, and the conditional data corresponding to each category, determining the user type of the target user corresponding to the target terminal. The user type represents the energy-saving preference type of the target user when using the target terminal; Determining control parameters according to the user type, and controlling the target terminal according to the control parameters. Different user types correspond to different control parameters.

2. The method according to claim 1, characterized in that, The user classification model includes a fuzzy clustering algorithm model. The determining of the plurality of categories corresponding to the user classification model and the conditional data corresponding to each category includes: Obtaining the clustering result corresponding to the fuzzy clustering algorithm model. The clustering result includes the plurality of categories and the clustering center data corresponding to each category; For each category, taking the clustering center data corresponding to this category as the conditional data corresponding to this category.

3. The method according to claim 1, characterized in that, The determining of the user type of the target user corresponding to the target terminal according to the user's historical usage data, the plurality of categories, and the conditional data corresponding to each category includes: For each category, determining the data determination condition corresponding to this category according to this category and the conditional data corresponding to this category; According to the user's historical usage data and the data determination conditions corresponding to each category, determining the target category corresponding to the user's historical usage data from the plurality of categories; Taking the energy-saving preference type corresponding to the target category as the user type.

4. The method according to claim 2, characterized in that, The fuzzy clustering algorithm model is pre-trained in the following manner: Obtaining the terminal usage historical data of multiple users within the preset time period; Determining the clustering number of the fuzzy clustering algorithm and the clustering center data of each category according to the terminal usage historical data of the multiple users; Repeatedly executing the parameter update step until a preset stop condition is met; Wherein, the parameter update step includes: Determining the membership matrix according to the clustering center data and the terminal usage historical data of multiple users. For each user, the membership matrix represents the probability that the user belongs to each category respectively; Updating the clustering center data of each category according to the membership matrix; The preset stop condition includes: Reaching the maximum number of iterations; or, The clustering center data and / or the membership matrix meet the preset convergence accuracy.

5. The method according to claim 4, characterized in that, The terminal usage historical data includes multi-dimensional terminal usage historical data. The method further includes: Performing a correlation test on the multi-dimensional terminal usage historical data to obtain the correlation coefficients between data of different dimensions; After screening the multi-dimensional terminal usage historical data according to the correlation coefficient, target historical data is obtained. The dimension of the target historical data is less than or equal to the dimension of the terminal usage historical data, and the correlation coefficient between the data of different dimensions in the target historical data is less than or equal to a preset correlation coefficient threshold; The determining the number of clusters of the fuzzy clustering algorithm and the cluster center data of each category according to the terminal usage historical data of the multiple users includes: Determining the number of clusters of the fuzzy clustering algorithm and the cluster center data of each category according to the target historical data; The determining the membership matrix according to the cluster center data and the terminal usage historical data of the multiple users includes: Determining the membership matrix according to the cluster center data and the target historical data of the multiple users.

6. The method according to any one of claims 1-5, characterized in that, The target terminal includes an air conditioner, and the user historical usage data includes at least one of the following data: Cooling start-up operation data, heating start-up operation data, user cooling usage habit data, user heating usage habit data, air conditioner operation status data.

7. The method according to claim 6, characterized in that, The control parameters include at least one of the following parameters: Set temperature correction value, open-loop stage frequency correction coefficient, electric auxiliary heating control start condition parameter, temperature correction value for reaching temperature and stopping operation.

8. The method according to claim 7, wherein The control parameters include the temperature correction value for reaching temperature and stopping operation, and the determining the control parameters according to the user type includes: In the case where the user type is the first user type, determining the temperature correction value for reaching temperature and stopping operation as the first correction value; in the case where the user type is the second user type, determining the temperature correction value for reaching temperature and stopping operation as the second correction value; wherein, the energy-saving requirement corresponding to the first user type is less than the energy-saving requirement corresponding to the second user type, and the first correction value is greater than the second correction value.

9. The method according to claim 8, wherein The control parameters further include the electric auxiliary heating control start condition parameter, and the electric auxiliary heating control start condition parameter includes at least one of the temperature difference for judging the electric auxiliary heating switch and the boundary values of the environmental temperature comfort zone temperature range; The determining the control parameters according to the user type includes: In the case where the user type is the first user type, determining the temperature difference for judging the electric auxiliary heating switch as the first temperature difference, and the boundary value of the environmental temperature comfort zone temperature range as the third temperature; In the case where the user type is the second user type, determining the temperature difference for judging the electric auxiliary heating switch as the second temperature difference, and the boundary value of the environmental temperature comfort zone temperature range as the fourth temperature; Wherein, the first temperature difference is less than the second temperature difference, and the third temperature is greater than the fourth temperature.

10. The method according to claim 8, wherein The control parameters further include the open-loop stage frequency correction coefficient, and the determining the control parameters according to the user type includes: In the case where the user type is the first user type, determining the open-loop stage frequency correction coefficient as the first correction coefficient; in the case where the user type is the second user type, determining the open-loop stage frequency correction coefficient as the second correction coefficient; wherein, the first correction coefficient is greater than the second correction coefficient.

11. The method according to claim 8, wherein The control parameter further includes a set temperature correction value, and determining the control parameter according to the user type includes: When the user type is the first user type, determining the set temperature correction value as a third correction value; when the user type is the second user type, determining the set temperature correction value as a fourth correction value; wherein, the third correction value is less than the fourth correction value.

12. A terminal control device, wherein including: An acquisition module, configured to acquire historical user usage data of a target terminal within a preset time period; A first determination module, configured to determine multiple categories corresponding to a user classification model and condition data respectively corresponding to each category, different categories represent different energy-saving preference types, and for each category, the condition data represents the conditions that the historical usage data of users belonging to this category needs to meet, and the user classification model is a big data classification model pre-trained according to the terminal usage historical data of multiple users; A second determination module, configured to determine the user type of the target user corresponding to the target terminal according to the user historical usage data, the multiple categories, and the condition data respectively corresponding to each category, and the user type represents the energy-saving preference type of the target user using the target terminal; A control module, configured to determine a control parameter according to the user type, and control the target terminal according to the control parameter, and different user types correspond to different control parameters.

13. An air conditioning device, wherein including: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to: execute the terminal control method according to any one of claims 1-11.

14. A computer-readable storage medium having computer program instructions stored thereon, wherein When the program instruction is executed by the processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images