An air conditioner user identification method based on big data analysis

Abstract

The application is suitable for the technical field of air conditioner user identification, and provides an air conditioner user identification method and device based on big data analysis, which comprises the following steps: obtaining historical load data and historical environment data of a user; obtaining correlation data among time, load size and environment temperature based on the historical load data and the historical environment data of the user; determining daily maximum load and daily temperature index based on the correlation data; determining correlation indexes of multiple time periods based on the daily maximum load and the daily temperature index; and obtaining a determination result of whether the user is an air conditioner user based on the correlation indexes of the multiple time periods. The application can accurately identify air conditioner users, which is beneficial to efficiently carrying out air conditioner load management.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of air conditioner user identification, and particularly relates to an air conditioner user identification method and device based on big data analysis. BACKGROUND

[0002] Good air conditioner load management is an important measure to ensure stable operation of power supply, and in order to carry out air conditioner load management more accurately, air conditioner users must be identified. On the basis of identifying air conditioner users and their loads, air conditioner load optimization management can be well done.

[0003] At present, the method for obtaining whether a user uses an air conditioner and the specific situation of air conditioner load is to conduct household-by-household investigation and to install corresponding data collection or metering equipment on all air conditioner equipment of each household, and the like, that is, to collect data through user air conditioner side hardware installation, and then to upload the air conditioner load data collected or metered by the equipment. The household-by-household investigation method for investigating whether a user uses an air conditioner includes on-site investigation and online investigation, both of which consume a large amount of manpower and resources, and there are cases that users do not cooperate with the investigation and provide misleading information. The method of monitoring user air conditioner load through hardware needs to install hardware equipment at the user air conditioner, and to establish an uploading channel for the data collected by the hardware equipment. This method needs to invest a large amount of manpower and resources to install the related hardware equipment, and to install the hardware in each household, and in some cases, the air conditioner equipment needs to be modified, and a data collection and uploading channel needs to be established, and after the construction, the hardware needs to be maintained for a long time. For example, the patent document with the publication number CN117366783A needs to obtain the air conditioner power of the user when the air conditioner is normally running and abnormally running. For users who are unwilling to cooperate with the installation of hardware or the modification of the existing equipment environment, the hardware installation method is not feasible.

[0004] In such a case, air conditioner load management cannot be carried out accurately and efficiently. Therefore, there is an urgent need for a method for accurately identifying whether a user is an air conditioner user. SUMMARY

[0005] The embodiments of the application provide an air conditioner user identification method and device based on big data analysis, which can accurately identify air conditioner users and is beneficial to efficient air conditioner load management.

[0006] The application is implemented through the following technical solutions:

[0007] In a first aspect, the embodiments of the application provide an air conditioner user identification method based on big data analysis, which includes the following steps:

[0008] Obtaining historical load data and historical environment data of a user;

[0009] Based on the historical load data and the historical environment data of the user, obtaining correlation data among time, load size and environment temperature;

[0010] determine a daily maximum load and a daily temperature index based on the correlation data;

[0011] determine a correlation index of a plurality of time periods based on the daily maximum load and the daily temperature index;

[0012] obtain a determination result of whether the user is an air conditioner user based on the correlation index of the plurality of time periods.

[0013] In a possible implementation of the first aspect, the determining of the daily temperature index based on the correlation data comprises:

[0014] extracting a daily ambient temperature from the correlation data;

[0015] determining a daily minimum temperature and a daily maximum temperature based on the daily ambient temperature;

[0016] determining the daily temperature index based on the daily minimum temperature and the daily maximum temperature.

[0017] In a possible implementation of the first aspect, the determining of the daily temperature index based on the daily minimum temperature and the daily maximum temperature comprises:

[0018] if the daily minimum temperature is greater than a preset temperature, the daily temperature index = the daily maximum temperature - the preset temperature;

[0019] if the daily maximum temperature is less than the preset temperature, the daily temperature index = the preset temperature - the daily minimum temperature;

[0020] if the daily minimum temperature is less than or equal to the preset temperature, and the daily maximum temperature is greater than or equal to the preset temperature, the daily temperature index = max{ (the daily maximum temperature - the preset temperature), (the preset temperature - the daily minimum temperature)}.

[0021] In a possible implementation of the first aspect, the determining of the correlation index of the plurality of time periods based on the daily maximum load and the daily temperature index comprises:

[0022] calculating a first correlation of the daily temperature index and the daily maximum load of a preset full-temperature time period based on the daily maximum load and the daily temperature index;

[0023] calculating a second correlation of the daily temperature index and the daily maximum load of a preset high-temperature time period based on the daily maximum load and the daily temperature index;

[0024] calculating a third correlation of the daily temperature index and the daily maximum load of a preset low-temperature time period based on the daily maximum load and the daily temperature index; the correlation index of the plurality of time periods comprises the first correlation, the second correlation, and the third correlation.

[0025] In a possible implementation of the first aspect, the determining whether the user is an air conditioner user based on the correlation indicators of the plurality of time periods comprises:

[0026] The determining whether the user is an air conditioner user based on the first correlation, the second correlation and the third correlation.

[0027] In a possible implementation of the first aspect, the determining whether the user is an air conditioner user based on the first correlation, the second correlation and the third correlation comprises:

[0028] If at least one of the following conditions is met, the user is an air conditioner user: the first correlation is greater than a first preset determination threshold, the second correlation is greater than a second preset determination threshold, and the third correlation is greater than a third preset determination threshold; otherwise, the user is a non-air conditioner user.

[0029] In a possible implementation of the first aspect, the obtaining of the correlation data among the time, the load size and the environment temperature based on the historical load data and the historical environment data of the user comprises:

[0030] The features of the load size and the first time stamp of the historical load data are extracted;

[0031] The features of the environment temperature and the second time stamp of the historical environment data are extracted;

[0032] The first time stamp corresponding to the feature of the load size and the second time stamp corresponding to the feature of the environment temperature are aligned to obtain the correlation data among the time, the load size and the environment temperature.

[0033] In a possible implementation of the first aspect, the determining of the daily maximum load based on the correlation data comprises:

[0034] The load size of each day is extracted from the correlation data;

[0035] The daily maximum load is determined based on the curve of the load size of each day.

[0036] In a possible implementation of the first aspect, the air conditioner user identification method based on big data analysis further comprises:

[0037] The determination result and the correlation indicators are saved to a big data platform;

[0038] The air conditioner load management system obtains the correlation indicators of the air conditioner user in the determination result from the big data platform;

[0039] The air conditioner load proportion of the user is determined based on the correlation indicators of the air conditioner user.

[0040] In a second aspect, the embodiments of the present application provide an air conditioner user identification device based on big data analysis, which executes the air conditioner user identification method based on big data analysis as in the first aspect, and comprises:

[0041] a data acquisition module configured to acquire historical load data and historical environment data of a user;

[0042] a data association module configured to obtain association data among time, load size and environment temperature based on the historical load data and the historical environment data of the user;

[0043] a data determination module configured to determine a daily maximum load and a daily temperature index based on the association data;

[0044] a correlation calculation module configured to determine a correlation index of a plurality of time periods based on the daily maximum load and the daily temperature index;

[0045] a result determination module configured to obtain a determination result of whether the user is an air conditioner user based on the correlation index of the plurality of time periods.

[0046] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0047] The air conditioner user identification method and device based on big data analysis provided by the embodiments of the present application can analyze the correlation between the load and the environment temperature without directly using the environment temperature, but first calculate a daily temperature index that can measure the comfort of the environment temperature. The greater the value of the daily temperature index, the less comfortable the environment temperature of the day. Then, the correlation between the daily temperature index and the load is analyzed, so that the correlation index can more significantly reflect the correlation between the environment temperature and the load, thereby accurately identifying the air conditioner user, which is conducive to efficiently carrying out air conditioner load management, optimizing power system scheduling, reducing system load peak, and improving power supply reliability and efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or related technical description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0049] Figure 1 is a flowchart of the air conditioner user identification method based on big data analysis provided by an embodiment of the present application;

[0050] Figure 2 is a structural schematic diagram of the air conditioner user identification device based on big data analysis provided by an embodiment of the present application. DETAILED DESCRIPTION

[0051] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0052] It is to be understood that the terminology "includes", "has", "holds", "contains" and / or "comprising", "including", "having" and their conjugates, as used herein, means "including but not limited to", and not to the exclusion of any other term or aspect.

[0053] It is to be understood that the terminology "and / or", as used herein, refers to any combination of one or more of the associated listed items, and all possible combinations, and includes these combinations.

[0054] In addition, in the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0055] In the present application, the reference "an embodiment", "one embodiment" or "some embodiments" means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in further some embodiments" and the like appearing in the present specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "including but not limited to", unless otherwise specifically emphasized.

[0056] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0057] Figure 1 is a flowchart of the air conditioner user identification method based on big data analysis provided by an embodiment of the present application, with reference to Figure 1The air conditioner user identification method based on big data analysis comprises the following steps:

[0058] In step 101, historical load data and historical environment data of a user are acquired.

[0059] For example, the historical load data and the historical environment data of the user can be acquired from a user power information collection system or a power load management system and a weather data system. The historical load data is a total load curve of the user in the past more than one year, and the collection frequency is once every 15 minutes. The historical environment data can be meteorological data including temperature.

[0060] The profile data of the user can also be acquired. The profile data of the user can include the geographical position of the user or a relevant code for identifying the geographical position of the user, and the historical environment data is historical meteorological data corresponding to the geographical position or the relevant address code of the user.

[0061] The load data collection system stores historical load data in a period of time to ensure the running speed and timely update of the system. The historical load data in a long period of time and the weather data acquired from the weather data system are sequentially stored in a profile database to ensure the order and safety of the data.

[0062] In step 102, the correlation data among time, load size and environment temperature is obtained based on the historical load data and the historical environment data of the user.

[0063] For example, the historical load data and the historical meteorological data of the user are correlated to generate data with the content of

time, load size, environment temperature

[0064] Step 102 comprises the following steps:

[0065] The feature of the load size and the first time stamp of the historical load data are extracted, the feature of the environment temperature and the second time stamp of the historical environment data are extracted, the first time stamp corresponding to the feature of the load size is aligned with the second time stamp corresponding to the feature of the environment temperature, and the correlation data among time, load size and environment temperature is obtained.

[0066] In step 103, the daily maximum load and the daily temperature index are determined based on the correlation data.

[0067] For example, the daily maximum load is determined based on the correlation data, which comprises the following steps: the load size of each day is extracted from the correlation data; and the daily maximum load is determined based on the curve of the load size of each day.

[0068] Exemplarily, determining the daily temperature index based on the correlation data comprises: extracting the daily ambient temperature from the correlation data; determining the daily minimum temperature and the daily maximum temperature based on the daily ambient temperature; determining the daily temperature index based on the daily minimum temperature and the daily maximum temperature.

[0069] Exemplarily, determining the daily temperature index based on the daily minimum temperature and the daily maximum temperature comprises:

[0070] If the daily minimum temperature is greater than the preset temperature, the daily temperature index Tc = the daily maximum temperature - the preset temperature.

[0071] If the daily maximum temperature is less than the preset temperature, the daily temperature index Tc = the preset temperature - the daily minimum temperature.

[0072] If the daily minimum temperature is less than or equal to the preset temperature and the daily maximum temperature is greater than or equal to the preset temperature, the daily temperature index Tc = max {(the daily maximum temperature - the preset temperature), (the preset temperature - the daily minimum temperature)}.

[0073] Wherein, in order to make the temperature index more regionally relevant, the preset temperature can be set to 20℃, which can be the average temperature of a certain region. Then the temperature index when the daily minimum temperature is greater than 20℃ is different from that when the daily maximum temperature is lower than 20℃, that is, the temperature index when the temperature is higher is different from that when the temperature is lower.

[0074] The embodiment does not directly use the ambient temperature to analyze the correlation with the load, but first calculates the temperature index Tc that can measure the comfort of the ambient temperature. The greater Tc is, the more uncomfortable the daily ambient temperature is. Then analyzing the correlation between Tc and the load can make the correlation index more significantly reflect the correlation between the ambient temperature and the load.

[0075] Step 104, determining the correlation index of a plurality of time periods based on the daily maximum load and the daily temperature index.

[0076] Exemplarily, the air conditioner users in the electricity users are divided into two types, one of which is to use the air conditioner only when the winter and summer temperature is not suitable, such as ordinary residents, etc., and the other of which is to use the air conditioner in spring and autumn seasons, etc., such as users who build computer rooms, and the heat dissipation air conditioner of the computer room is always on. Since the cooling and heating efficiency of the air conditioner is related to the indoor and outdoor temperature difference, and other conditions such as indoor temperature setting are unchanged, the greater the indoor and outdoor temperature difference, the lower the cooling efficiency of the air conditioner, and the greater the power of the air conditioner to achieve the same cooling effect. Therefore, the air conditioner load shows the correlation with the temperature. When cooling, the more the outdoor temperature is higher than the indoor temperature, the greater the power of the air conditioner; when heating, the more the outdoor temperature is lower than the indoor temperature, the greater the power of the air conditioner. Based on the above analysis, for the users whose non-air conditioner load remains stable, the total load shows the correlation with the ambient temperature, and then the correlation between the load and the temperature index is determined.

[0077] In determining the correlation between the load performance and the temperature index, it is considered that some users turn on the air conditioner in winter and summer, which shows that the annual load and temperature index correlation is high. Some users only turn on the air conditioner in summer, which shows that the summer correlation is high and the winter correlation is low, and if the overall correlation is directly calculated, the correlation is low. Some users have low air conditioner usage in summer, but use air conditioners for heating in winter, such as electric heating users, which shows that the winter correlation is high, but the overall correlation is low. Therefore, the present embodiment adopts the above combination logic, and the overall correlation reaches a certain threshold, or the summer and winter correlations reach a certain threshold, which can determine that the user has obvious air conditioner load.

[0078] Therefore, step 104 comprises:

[0079] Based on the daily maximum load and the daily temperature index, a first correlation between the daily temperature index and the daily maximum load in a preset full-temperature period is calculated. The preset full-temperature period can be the whole year.

[0080] Exemplarily, the correlation indicators of the above-mentioned multiple time periods can be represented by Pearson correlation coefficients. The Pearson correlation coefficient of the sample can be obtained by estimating the covariance and standard deviation of the sample. The expression of the first correlation r1 is as follows:

[0081]

[0082] Wherein, indicates the mean of the sample of the daily temperature index in the preset full-temperature period; indicates the mean of the sample of the daily maximum load in the preset full-temperature period; n indicates the number of samples of the daily temperature index and the daily maximum load in the preset full-temperature period; x i indicates the i-th sample of the daily temperature index in the preset full-temperature period; y i indicates the i-th sample of the daily maximum load in the preset full-temperature period.

[0083] Based on the daily maximum load and the daily temperature index, a second correlation between the daily temperature index and the daily maximum load in a preset high-temperature period is calculated. The preset high-temperature period can be April-September.

[0084] The expression of the second correlation r2 is as follows:

[0085]

[0086] Wherein, indicates the mean of the sample of the daily temperature index in the preset high-temperature period; indicates the mean of the sample of the daily maximum load in the preset high-temperature period; m indicates the number of samples of the daily temperature index and the daily maximum load in the preset high-temperature period; x jthe jth sample of the daily temperature index of the preset high-temperature time period; y j the jth sample of the daily maximum load of the preset high-temperature time period.

[0087] Based on the daily maximum load and the daily temperature index, a third correlation of the daily temperature index and the daily maximum load of a preset low-temperature time period is calculated; wherein the preset low-temperature time period can be October-December and January-March. The correlation indicators of multiple time periods include the first correlation, the second correlation and the third correlation.

[0088] The expression of the third correlation r3 is as follows:

[0089]

[0090] wherein, the mean of the samples of the daily temperature index of the preset low-temperature time period; the mean of the samples of the daily maximum load of the preset low-temperature time period; p represents the number of the samples of the daily temperature index and the samples of the daily maximum load of the preset low-temperature time period; x k the kth sample of the daily temperature index of the preset low-temperature time period; y k the kth sample of the daily maximum load of the preset low-temperature time period.

[0091] In this embodiment, the Pearson correlation coefficient is used to calculate the correlation indicators of multiple time periods, which can measure the linear relationship strength and direction between the daily maximum load and the daily temperature index of different time periods, and is fast and easy to calculate.

[0092] In step 105, based on the correlation indicators of multiple time periods, a determination result of whether the user is an air conditioner user is obtained.

[0093] For example, step 105 includes determining whether the user is an air conditioner user based on the first correlation, the second correlation and the third correlation.

[0094] Determining whether the user is an air conditioner user based on the first correlation, the second correlation and the third correlation includes:

[0095] If at least one of the following conditions is met, the user is an air conditioner user: the first correlation is greater than a first preset determination threshold, the second correlation is greater than a second preset determination threshold, and the third correlation is greater than a third preset determination threshold; otherwise, the user is a non-air conditioner user, i.e., the first correlation, the second correlation and the third correlation do not exceed the corresponding thresholds.

[0096] Wherein, the first preset determination threshold, the second preset determination threshold and the third preset determination threshold are configurable parameters, and the default values can be set to 0.2.

[0097] It should be noted that in some special areas, the selection of multiple time periods can be adjusted, or the corresponding preset determination threshold can be adjusted.

[0098] No matter whether the user turns on the air conditioner in summer, winter or all year round, as long as the correlation exceeds the threshold, it means that the user uses the air conditioner in winter and summer or only in summer or only in winter. Therefore, non-air conditioner users and air conditioner users can be accurately screened out.

[0099] In addition, different types of correlation indicators can be used to mark summer air conditioner users, winter air conditioner users and all-year air conditioner users, so as to accurately distinguish various types of air conditioner users and improve analysis efficiency.

[0100] For example, the air conditioner user identification method based on big data analysis further comprises: saving the determination result and the correlation indicator to the big data platform; obtaining the correlation indicator of the air conditioner user in the determination result from the big data platform by using the air conditioner load management system; and determining the air conditioner load proportion of the user based on the correlation indicator of the air conditioner user.

[0101] To sum up, the air conditioner user identification method based on big data analysis provided by the embodiment of the application can analyze the correlation between the load and the environment temperature without directly using the environment temperature, but first calculates the daily temperature index that can measure the comfort of the environment temperature. The greater the value of the daily temperature index, the less comfortable the environment temperature is on the day. By analyzing the correlation between the daily temperature index and the load, the correlation indicator can more significantly reflect the correlation between the environment temperature and the load, so as to accurately identify the air conditioner user, which is beneficial to efficiently carry out air conditioner load management, optimize power system scheduling, reduce system load peak, and improve power supply reliability and efficiency.

[0102] For energy management, the method can realize fine energy monitoring and management. By accurately identifying the air conditioner user, the load demand can be better monitored and predicted, so as to optimize the power system scheduling, reduce the system load peak, and improve the power supply reliability and efficiency.

[0103] The method is helpful for promoting the construction of smart grid. Through air conditioner user identification, more comprehensive user behavior data support can be provided for smart grid, dynamic load management, intelligent power market transaction and other functions can be realized, and the safe and stable operation and intelligent development of power grid can be promoted.

[0104] The method can assist in analyzing user electricity consumption behavior. Combined with other user data analysis, the user's electricity consumption behavior mode can be deeply studied, and personalized energy service and customized solution can be supported.

[0105] The air conditioner user identification method also has a positive impact on marketing and service improvement. Based on user behavior analysis, enterprises can develop targeted marketing strategies, provide customized products and services, enhance customer satisfaction, and promote market competitiveness and brand influence.

[0106] Referring to Figure 2 The embodiment of the present application provides an air conditioner user identification device based on big data analysis, which executes the air conditioner user identification method based on big data analysis as described above. The device comprises a data acquisition module 201, a data association module 202, a data determination module 203, a correlation calculation module 204 and a result determination module 205.

[0107] The data acquisition module 201 is used to acquire the historical load data and historical environment data of the user.

[0108] The data association module 202 is used to obtain the association data between time, load size and environment temperature based on the historical load data and historical environment data of the user.

[0109] The data determination module 203 is used to determine the daily maximum load and daily temperature index based on the association data.

[0110] The correlation calculation module 204 is used to determine the correlation index of multiple time periods based on the daily maximum load and the daily temperature index.

[0111] The result determination module 205 is used to obtain the determination result of whether the user is an air conditioner user based on the correlation index of multiple time periods.

[0112] Illustratively, the data determination module 203 is specifically used to determine the daily temperature index based on the association data.

[0113] Based on the association data, the daily temperature index is determined, comprising:

[0114] Extracting the daily environment temperature from the association data;

[0115] Determining the daily minimum temperature and the daily maximum temperature based on the daily environment temperature;

[0116] Determining the daily temperature index based on the daily minimum temperature and the daily maximum temperature.

[0117] Illustratively, the daily temperature index is determined based on the daily minimum temperature and the daily maximum temperature, comprising:

[0118] If the daily minimum temperature is greater than the preset temperature, the daily temperature index = daily maximum temperature - preset temperature;

[0119] If the daily maximum temperature is less than the preset temperature, the daily temperature index = preset temperature - daily minimum temperature;

[0120] If the daily minimum temperature is less than or equal to the preset temperature, and the daily maximum temperature is greater than or equal to the preset temperature, then the daily temperature index = max {(daily maximum temperature - preset temperature), (preset temperature - daily minimum temperature)}.

[0121] For example, the correlation calculation module 204 is specifically configured to:

[0122] Based on the daily maximum load and the daily temperature index, a first correlation between the daily temperature index and the daily maximum load in a preset full-temperature period is calculated.

[0123] Based on the daily maximum load and the daily temperature index, a second correlation between the daily temperature index and the daily maximum load in a preset high-temperature period is calculated.

[0124] Based on the daily maximum load and the daily temperature index, a third correlation between the daily temperature index and the daily maximum load in a preset low-temperature period is calculated. The correlation indicators of the plurality of time periods include the first correlation, the second correlation, and the third correlation.

[0125] For example, the result determination module 205 is specifically configured to:

[0126] Based on the first correlation, the second correlation, and the third correlation, it is determined whether the user is an air conditioner user.

[0127] For example, based on the first correlation, the second correlation, and the third correlation, it is determined whether the user is an air conditioner user, including:

[0128] If at least one of the following conditions is met: the first correlation is greater than a first preset determination threshold, the second correlation is greater than a second preset determination threshold, and the third correlation is greater than a third preset determination threshold, then the user is an air conditioner user; otherwise, the user is a non-air conditioner user.

[0129] For example, the data correlation module 202 is specifically configured to:

[0130] The features of the load size and the first time stamp of the historical load data are extracted;

[0131] The features of the environmental temperature and the second time stamp of the historical environmental data are extracted;

[0132] The first time stamp corresponding to the feature of the load size and the second time stamp corresponding to the feature of the environmental temperature are aligned to obtain correlation data between time, load size, and environmental temperature.

[0133] For example, the data determination module 203 is specifically configured to further determine the daily maximum load based on the correlation data. Based on the correlation data, the daily maximum load is determined, including:

[0134] The load size of each day is extracted from the correlation data;

[0135] determining the daily maximum load based on the curve of the daily load size.

[0136] The air conditioner user identification device based on big data analysis also includes an air conditioner load proportion determination module.

[0137] The air conditioner load proportion determination module is specifically configured to:

[0138] save the determination result and the correlation index to the big data platform;

[0139] acquire the correlation index of the air conditioner user in the determination result from the big data platform by using the air conditioner load management system;

[0140] determine the air conditioner load proportion of the user based on the correlation index of the air conditioner user.

[0141] It should be noted that, although several units / modules or sub-units / modules of the air conditioner user identification device based on big data analysis are mentioned in the foregoing detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into several units / modules for embodiment.

[0142] In addition, although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, certain steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps.

[0143] The present application also provides a computer readable storage medium, which stores computer execution instructions, when the processor executes the computer execution instructions, the method for identifying air conditioner users based on big data analysis provided by the above-mentioned embodiments of the present application is realized.

[0144] In the above-mentioned embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0145] The above examples are only used to illustrate the technical solutions of the present application, but not limit the same; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for identifying an air conditioner user based on big data analysis, the method comprising: The method comprises the following steps: obtaining historical load data and historical environment data of a user; based on the historical load data and historical environment data of the user, obtaining correlation data between time, load size and environment temperature; based on the correlation data, determining the daily maximum load and the daily temperature index; based on the daily maximum load and the daily temperature index, determining the correlation index of multiple time periods; based on the correlation index of multiple time periods, obtaining the determination result of whether the user is an air conditioner user; based on the correlation data, determining the daily temperature index, comprising: extracting the daily environment temperature from the correlation data; based on the daily environment temperature, determining the daily minimum temperature and the daily maximum temperature; based on the daily minimum temperature and the daily maximum temperature, determining the daily temperature index; based on the daily minimum temperature and the daily maximum temperature, determining the daily temperature index, comprising: if the daily minimum temperature is greater than the preset temperature, then the daily temperature index = daily maximum temperature - preset temperature; if the daily maximum temperature is less than the preset temperature, then the daily temperature index = preset temperature - daily minimum temperature; if the daily minimum temperature is less than or equal to the preset temperature, and the daily maximum temperature is greater than or equal to the preset temperature, then the daily temperature index = max{ (daily maximum temperature - preset temperature), (preset temperature - daily minimum temperature)}.

2. The air conditioner user recognition method based on big data analysis according to claim 1, wherein, based on the daily maximum load and the daily temperature index, calculating the first correlation of the daily temperature index and the daily maximum load in the preset full-temperature time period; based on the daily maximum load and the daily temperature index, calculating the second correlation of the daily temperature index and the daily maximum load in the preset high-temperature time period; based on the daily maximum load and the daily temperature index, calculating the third correlation of the daily temperature index and the daily maximum load in the preset low-temperature time period; the correlation index of multiple time periods includes the first correlation, the second correlation and the third correlation. based on the first correlation, the second correlation and the third correlation, determining whether the user is an air conditioner user. 3.The air conditioner user recognition method based on big data analysis of claim 2, wherein, 4. The air conditioner user identification method based on big data analysis according to claim 3, wherein: based on the first correlation, the second correlation and the third correlation, determining whether the user is an air conditioner user, comprising: if at least one of the first correlation is greater than the first preset determination threshold, the second correlation is greater than the second preset determination threshold, and the third correlation is greater than the third preset determination threshold, then the user is an air conditioner user; otherwise, the user is a non-air conditioner user. based on the historical load data and historical environment data of the user, obtaining correlation data between time, load size and environment temperature, comprising: extracting the load size feature and the first timestamp of the historical load data; 5.The air conditioner user recognition method based on big data analysis of claim 1, wherein, extracting the environment temperature feature and the second timestamp of the historical environment data; ​ ​ Align the first timestamp corresponding to the feature of the load size and the second timestamp corresponding to the feature of the ambient temperature, to obtain the correlation data among time, load size and ambient temperature. 6.The air conditioner user recognition method based on big data analysis of claim 1, wherein, The method further comprises: Extracting daily load size from the correlation data; Determining the daily maximum load based on the curve of the daily load size. 7.The air conditioner user recognition method based on big data analysis of claim 1, wherein, The method further comprises: Saving the determination result and the correlation index to a big data platform; Obtaining the correlation index of the air conditioner user in the determination result from the big data platform by using an air conditioner load management system; Determining the air conditioner load proportion of the user based on the correlation index of the air conditioner user. 8.An air conditioner user recognition apparatus based on big data analysis, which performs the air conditioner user recognition method based on big data analysis according to any one of claims 1 to 7, characterized by, The method comprises: A data acquisition module configured to acquire historical load data and historical environment data of a user; A data correlation module configured to obtain correlation data among time, load size and ambient temperature based on the historical load data and the historical environment data of the user; A data determination module configured to determine a daily maximum load and a daily temperature index based on the correlation data; A correlation calculation module configured to determine correlation indexes of multiple time periods based on the daily maximum load and the daily temperature index; A result determination module configured to obtain a determination result of whether the user is an air conditioner user based on the correlation indexes of the multiple time periods. The data determination module is specifically configured to: Extract daily ambient temperature from the correlation data; Determine a daily minimum temperature and a daily maximum temperature based on the daily ambient temperature; Determine the daily temperature index based on the daily minimum temperature and the daily maximum temperature. The data determination module is further specifically configured to: If the daily minimum temperature is greater than a preset temperature, then the daily temperature index = daily maximum temperature - preset temperature; If the daily maximum temperature is less than the preset temperature, then the daily temperature index = preset temperature - daily minimum temperature; If the daily minimum temperature is less than or equal to the preset temperature and the daily maximum temperature is greater than or equal to the preset temperature, then the daily temperature index = max{(daily maximum temperature - preset temperature), (preset temperature - daily minimum temperature)}.

Images