Intelligent equipment control system and method based on cloud computing

Abstract

The invention discloses an intelligent equipment control system and method based on cloud computing, and relates to the technical field of equipment control. The system comprises a data acquisition and processing module, a user behavior analysis and preference modeling module, a standby energy consumption identification module and a real-time monitoring and adjusting module. The data acquisition and processing module collects historical power consumption data and external environment data of the smart home equipment, obtains a power consumption mode by analyzing the historical power consumption data, and performs historical energy efficiency evaluation in combination with the environment data to form an energy consumption portrait; the user behavior analysis and preference modeling module obtains user historical behavior data and constructs a user preference model; the standby energy consumption identification module identifies equipment with standby energy consumption and generates an energy-saving control scheme in combination with the use time period of the equipment; and the real-time monitoring and adjusting module implements the energy-saving control scheme, acquires the power consumption data and the environment data in real time, performs energy efficiency evaluation, and adjusts the energy-saving scheme according to the evaluation result.

Description

Technical Field

[0001] The present invention relates to the field of equipment control technology, and in particular to an intelligent equipment control system and method based on cloud computing. Background Art

[0002] With the rapid development of Internet of Things technology, smart home devices are gradually entering thousands of households. Smart home systems realize the automation and convenience of family life by integrating various devices, such as smart lighting, smart air conditioning, smart audio, security monitoring, etc. Users can remotely control these devices through smartphones, voice assistants, etc., which significantly improves the comfort and convenience of life.

[0003] However, although smart home devices have played an important role in improving living experience and quality of life, there are still obvious deficiencies in energy management and consumption. Many smart devices remain in standby mode even when not in use, resulting in the phenomenon of "standby energy consumption". This situation not only leads to unnecessary energy waste and increases household electricity expenditure, but also has an adverse impact on environmental protection. At present, the existing smart home control systems mainly focus on the convenient control of devices, and can usually achieve functions such as device switch control and timed tasks through smartphones, voice assistants, etc. However, the intelligent application of these control systems in energy management is still insufficient, and the existing systems usually lack accurate monitoring of device status, fail to accurately identify smart home devices with standby energy consumption, and cannot accurately determine when smart home devices with standby energy consumption are in a low power consumption state and when they are in a closed state, so that the potential of smart home control systems in energy saving and environmental protection cannot be fully utilized. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent equipment control system and method based on cloud computing to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A cloud computing-based intelligent device control method comprises the following steps:

[0007] Step S100. Use the cloud computing platform to collect historical power consumption data of smart home devices and corresponding external environment data, and obtain the power consumption mode of smart home devices by analyzing the historical power consumption data; perform historical energy efficiency evaluation on each smart home device in combination with the external environment data, so as to form an energy consumption profile of each smart home device;

[0008] Step S200. Obtain the user's historical behavior data, and identify the user's behavior pattern by combining the user's historical behavior data, the usage time of the smart home device, and the external environment data; and based on the user behavior pattern recognition results, build a user preference model for each smart home device;

[0009] Step S300. Identify smart home devices with standby energy consumption according to the corresponding energy consumption profile and user preference model; obtain the association relationship between smart home devices according to the identification result and the usage time period of each smart home device, so as to generate an energy-saving control solution for the smart home devices with standby energy consumption;

[0010] Step S400: Implement the energy-saving control scheme, obtain the real-time power consumption data of smart home devices with standby energy consumption and real-time external environment data, and perform real-time energy efficiency evaluation; according to the real-time energy efficiency evaluation results, adjust the energy-saving control scheme accordingly.

[0011] Furthermore, step S100 includes:

[0012] S101. Collect historical power consumption data of smart home devices and corresponding external environment data using a cloud computing platform. For each smart home device, record the historical power consumption data in different time periods as Pi(t), where i is the smart device number and t is a timestamp, such as divided by hours or minutes; the external environment data includes temperature, humidity and light intensity, which are recorded as Ek(t), where k represents the environmental parameter number; pre-process the historical power consumption data of smart home devices and the corresponding external environment data, and use smoothing technology to correct the data, so as to obtain standardized data of historical power consumption data and external environment data, which are expressed as Pa_i(t) and Ea_k(t), respectively;

[0013] S102. For each smart home device's historical power consumption data Pa_i(t), use the time series decomposition method to decompose the historical power consumption data in different time periods into the following parts: trend item Ti(t), seasonal item Si(t) and random item Ri(t); the trend item Ti(t) represents a long-term trend or baseline, such as the gradual aging of the device or the change in the frequency of use; the seasonal item Si(t) represents the repetitive changes of the device within a specific time period, such as daily or weekly fluctuations; the random item Ri(t) represents random fluctuations or abnormal fluctuations; and the decomposition formula is expressed as: Pa_i( t)=Ti(t)+Si(t)+Ri(t); According to the trend term Ti(t), seasonal term Si(t) and random term Ri(t) of each timestamp, a data unit Di_m(t) is formed, and Di_m(t)={Ti_m(t),Si_m(t),Ri_m(t)}, where m represents the data unit number; For each data unit Di_m(t), the distance metric d between Di_m(t) and all other data units is calculated, and the specific calculation formula is: d(Di_m(t),Di_n(t))={[Ti_m(t)-Ti_n(t)] 2 +[Si_m(t)-Si_n(t)] 2 +[Ri_m(t)-Ri_n(t)] 2}^(1 / 2), where Di_n(t) represents the nth data unit of the i-th smart home device, and Ti_n(t), Si_n(t) and Ri_n(t) represent the trend term, seasonal term and random term of the nth data unit of the i-th smart home device respectively; according to the distance metric d, the DBSCAN clustering algorithm is used to classify the data units, so as to obtain the power consumption mode M(t) of the corresponding smart home device, where the number of categories of the data unit is equal to the number of power consumption modes of the corresponding smart home device;

[0014] S103. For each data unit of each smart home device, the historical power consumption data Pa_i(t) corresponding to each data unit is combined with the external environment data Ea_k(t) corresponding to the same timestamp to calculate the corresponding historical energy efficiency index EEIi(t), and the specific calculation formula is:

[0015] EEIi(t)=[Pa_i(t)·Ai(t)] / {Ea_k(t)·J(t)·[1+ηi(t)]},

[0016] Among them, Ai(t) represents the environmental adaptability of smart home device i at timestamp t, and the specific calculation formula is:

[0017] Ai(t)=f1[Ea_1(t),Ea_2(t),...,Ea_k(t)],

[0018] Where Ea_1(t), Ea_2(t), ..., Ea_k(t) represent different environmental parameters in the external environmental data; f1 represents a mapping function that describes the relationship between environmental parameters and equipment energy efficiency. The specific function form can be linear regression, weighted sum, or a mapping obtained through a machine learning model (such as support vector machine, neural network, etc.); J(t) represents the seasonal adjustment factor, and the specific calculation formula is:

[0019] J(t)=1 / {1+α[sin(2πt) / T period ]},

[0020] Among them, α represents the amplitude of the adjustment factor, which reflects the impact of seasonality on energy efficiency; T period represents the length of the seasonal cycle; a sine function is used to simulate seasonal fluctuations. As time goes by, the seasonal factor J(t) will change periodically; ηi(t) represents the historical energy efficiency optimization index of smart furniture device i at timestamp t. The specific calculation formula is:

[0021] ηi(t)=Pmax_i / Pavg_i(t),

[0022] Among them, Pmax_i represents the maximum power consumption of smart furniture device i under optimal working conditions; Pavg_i(t) represents the average power consumption of smart furniture device i at timestamp t; ηi(t) is the optimization index of the device at a specific timestamp, reflecting the degree of energy efficiency optimization of the device in history; if the average power consumption of the device is close to the maximum power, the optimization index is low; if the device has been optimized in history, ηi(t) will be high. For each smart home device, the historical energy efficiency index EEIi(t) and the corresponding power consumption mode corresponding to each data unit are summarized to construct the corresponding energy consumption profile Ii, which is expressed as: Ii={[t1,EEIi(t1),M(t1)],[t2,EEIi(t2),M(t2)],...}, where [t1,EEIi(t1),M(t1)] and [t2,EEIi(t2),M(t2)] represent the historical energy efficiency index and power consumption mode corresponding to timestamps t1 and t2, respectively.

[0023] Furthermore, in S102, the data units are classified using the DBSCAN clustering algorithm according to the distance metric d, thereby obtaining the power consumption pattern of the corresponding smart home devices. The specific analysis process is as follows:

[0024] Set the neighborhood radius ε and the minimum number of neighborhood points Mp, where the neighborhood radius ε is defined as: the maximum distance around a data point. When the distance between two data units is less than or equal to this radius, they are considered to be adjacent; the minimum number of neighborhood points Mp is defined as: a data unit must contain at least Mp points (including itself) in its neighborhood to be marked as a core point. If this condition is not met in the neighborhood of a point, it is regarded as a boundary point or a noise point; for each data unit Di_m(t), obtain its distance metric d with all other data units. If a data unit Dm(t) has at least Mp data units in its neighborhood (including itself), it is regarded as a core point; that is, for a data unit Di_m(t), if the following condition is met: |{Di_n(t):d(Di_m(t),Di_n(t))≤ε}|≥Mp, then Di_m(t) is a core point, indicating that it can form a cluster; starting from the core point, traverse all data units whose distance to the core point is less than or equal to ε, and if these data units have not been classified, add them to the same cluster; this process is performed recursively until no more data units can be added to the cluster; all data units are divided into several clusters according to the data units in the core point and its neighborhood, where each cluster represents the power consumption pattern M(t) of a home appliance.

[0025] Further, step S200 includes:

[0026] S201. Collect historical behavior data of users from the cloud platform, wherein the historical behavior data includes daily behavior patterns of users, usage frequency and usage time of smart home devices, and association with external environment data; represent the historical behavior data as a time series set, i.e., Hu={hu(t1), hu(t2), ...}, wherein hu(t1) represents the characteristics of the historical behavior data of users at timestamp t1, such as the duration of a device being turned on, temperature adjustment preference, etc.; hu(t2) represents the characteristics of the historical behavior data of users at timestamp t2; cluster the characteristics of the historical behavior data of users, thereby dividing the historical behaviors of users into several categories, each category representing a user behavior pattern, represented as: {UP1, UP2, ...}; and annotate the background information of each behavior pattern in combination with the external environment data;

[0027] S202. For each smart home device, calculate the association strength Civ of the smart home device i in the corresponding user behavior pattern UPv, and the specific calculation formula is:

[0028] Civ=[Σt∈[1,T],Xiv(t)·Ui(t)] / [Σt∈[1,T],Ui(t)],

[0029] Wherein, Xiv(t) indicates whether the smart home device i is activated in the user behavior pattern UPv at timestamp t. If activated, Xiv(t) = 1, otherwise 0; T indicates the number of timestamps t; Ui(y) indicates the usage time of the smart home device i at timestamp t; the user preference value YPiv of the smart home device i under the corresponding user behavior pattern UPv is calculated, and the specific calculation formula is:

[0030] YPiv=[Σt∈[1,T],Civ·Ui(t)·ev(t)] / [Σt∈[1,T],Civ·Ui(t)], where ev(t) represents the external environment influencing factor of the user under the behavior pattern UPv; the user preference values ​​of smart home device i under all corresponding user behavior patterns are summarized to construct the corresponding user preference model, and the user preference model is expressed as.

[0031] YPi=Σv∈[1,K],bv·YPiv,

[0032] Where K represents the number of user behavior patterns corresponding to smart home device i; bv represents the weight factor of behavior pattern UPv.

[0033] Furthermore, step S300 includes:

[0034] S301. For each smart home device i, extract the historical energy efficiency index EEIi(t) and power consumption mode of each timestamp t according to the corresponding energy consumption portrait Ii, and extract the user preference value YPi of the smart home device i according to the user preference model; with a set period Ts, summarize the historical energy efficiency index EEIi(t) and power consumption mode of all timestamps t within the set period Ts in chronological order, and form a feature vector set Z, and Z = {z1, z2, ...}, where z1 and z2 represent the feature vectors of the first and second timestamps t respectively, and the number of feature vectors mz = Ts / t; and zmz = [EEIi(tmz), M(tmz)], where EEIi(tmz) and M(tmz) represent the historical energy efficiency index and power consumption mode of the mzth timestamp t respectively. Formula; for each element in the feature vector set Z, compare the historical energy efficiency indicators and power consumption patterns corresponding to the adjacent feature vectors. If there are r adjacent feature vectors in the feature vector set Z whose historical energy efficiency indicators and power consumption patterns are the same, and the user preference value YPi of the corresponding smart home device i is less than the threshold value YP, then the smart home device i has standby energy consumption, and the standby energy consumption time period is equal to the sum of the timestamps corresponding to the r adjacent feature vectors; and based on the standby energy consumption identification result, the smart home device in the standby energy consumption time period corresponding to the set period Ts is set to a shutdown or low power consumption state; wherein, the identification process of the smart home device with standby energy consumption is performed once every preset time period, so the smart home device with standby energy consumption is not fixed, but is updated with time.

[0035] S302. Obtain the usage time period UT of each smart home device in the set period Ts, and calculate the correlation degree GL between each standby energy consumption and other smart home devices based on the usage time period UT of the smart home device, and the corresponding calculation formula is:

[0036] GLij=|UTi∩UTj| / |UTi∪UTj|,

[0037] Among them, UTi represents the standby energy consumption time period of the smart home device i in the set period Ts, and UTj represents the usage time period of the smart home device j in the set period Ts; GLij is compared with the corresponding threshold GL, if GLi is greater than or equal to the threshold GL, the smart home device i is set to the shutdown state in the standby energy consumption time period; if GLi is less than the threshold GL, the smart home device i is set to the low power consumption state in the standby energy consumption time period.

[0038] Furthermore, step S400 includes:

[0039] Implement an energy-saving control scheme, obtain real-time power consumption data and real-time external environment data of smart home devices with standby energy consumption, and analyze the real-time power consumption data and real-time external environment data according to the analysis process of historical power consumption data and historical external environment data, so as to obtain a real-time energy consumption portrait I'i with standby energy consumption; compare the real-time energy consumption portrait I'i with standby energy consumption with the corresponding energy consumption portrait I, if in the selected period Ts, there are real-time energy efficiency indicators with Ns timestamps that are greater than the corresponding historical energy efficiency indicators, and save the corresponding energy-saving control scheme; if there are real-time energy efficiency indicators with Ns timestamps that are less than the corresponding historical energy efficiency indicators, and mark the corresponding energy-saving control scheme as an energy-saving control scheme to be optimized; manually adjust the energy-saving control scheme to be optimized until the real-time energy efficiency indicators with Ns timestamps are greater than the corresponding historical energy efficiency indicators, and save the adjusted energy-saving control scheme to be optimized; wherein Ns represents a preset quantity threshold.

[0040] An intelligent equipment control system based on cloud computing, the system includes: a data acquisition and processing module, a user behavior analysis and preference modeling module, a standby energy consumption identification module and a real-time monitoring and adjustment module;

[0041] The data collection and processing module uses the cloud computing platform to collect the historical power consumption data of smart home devices and the corresponding external environment data, and obtains the power consumption pattern of smart home devices by analyzing the historical power consumption data; it also conducts historical energy efficiency evaluation on each smart home device in combination with the external environment data, thereby forming an energy consumption profile of each smart home device;

[0042] The user behavior analysis and preference modeling module obtains the user's historical behavior data, combines the user's historical behavior data, the usage time of smart home devices and external environment data to identify the user's behavior pattern; and based on the user behavior pattern recognition results, builds a user preference model for each smart home device;

[0043] The standby energy consumption identification module identifies the smart home devices with standby energy consumption according to the corresponding energy consumption profile and user preference model; based on the identification results and the usage time period of each smart home device, the association relationship between the smart home devices is obtained, thereby generating an energy-saving control plan for the smart home devices with standby energy consumption;

[0044] The real-time monitoring and adjustment module implements the energy-saving control plan, obtains the real-time power consumption data of smart home devices with standby energy consumption and the real-time external environment data, and conducts real-time energy efficiency evaluation; according to the real-time energy efficiency evaluation results, the energy-saving control plan is adjusted accordingly.

[0045] Furthermore, the data acquisition and processing module includes a data preprocessing unit, a time series decomposition unit, and an energy consumption profile construction unit;

[0046] The data preprocessing unit collects historical power consumption data and external environment data of smart home devices from the cloud computing platform, and smoothes and standardizes the collected data; the time series decomposition unit decomposes the historical power consumption data into time series, extracts trend items, seasonal items and random items; the DBSCAN clustering algorithm is used to classify the power consumption data of smart home devices and identify different power consumption patterns; the energy consumption profile construction unit conducts historical energy efficiency evaluation on each smart home device in combination with external environment data, thereby forming an energy consumption profile of each smart home device.

[0047] Furthermore, the user behavior analysis and preference modeling module includes a historical behavior data collection unit, a behavior pattern recognition unit, and a preference model building unit;

[0048] The historical behavior data collection unit collects the user's historical behavior data; the behavior pattern recognition unit divides the user behavior data into different behavior patterns through a clustering algorithm, and annotates the background information of each behavior pattern in combination with the environmental data; the preference model construction unit constructs a user preference model for smart home devices based on the user behavior pattern and device usage data;

[0049] The standby energy consumption identification module includes a standby energy consumption identification unit and an energy-saving control scheme generation unit;

[0050] The standby energy consumption identification unit identifies smart home devices with standby energy consumption based on energy consumption profiles and user preference models; by comparing historical energy efficiency indicators, smart home device usage patterns and user preference values, it detects whether the smart home devices are in standby state and the time period of standby energy consumption; the energy-saving control scheme generation unit generates an energy-saving control scheme for the corresponding smart home devices based on the identified smart home devices with standby energy consumption and their usage time period.

[0051] Furthermore, the real-time monitoring and adjustment module includes a real-time monitoring and data acquisition unit, a real-time energy efficiency evaluation and comparison unit, and an energy-saving control scheme adjustment unit;

[0052] The real-time monitoring and data acquisition unit implements the energy-saving control plan and obtains the power consumption data and external environment data of the smart home devices in real time; the real-time energy efficiency evaluation and comparison unit compares the real-time collected power consumption data with the historical energy efficiency portrait to determine whether the real-time energy efficiency index is better than the corresponding historical energy efficiency index; the energy-saving control plan adjustment unit adjusts the corresponding energy-saving control plan according to the judgment result of the real-time energy efficiency evaluation and comparison unit.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention can accurately identify the standby energy consumption of the device through multi-dimensional analysis of historical power consumption data, external environment data and user behavior data, thereby effectively reducing unnecessary energy waste and reducing energy expenditure; the present invention uses a cloud computing platform for data processing and analysis, can obtain the power consumption data and external environment data of smart home devices in real time, and conduct continuous energy efficiency evaluation; by dynamically analyzing the energy efficiency status of the device, it can optimize the energy-saving control scheme in real time to ensure that the device is always in the optimal energy usage state. Compared with traditional fixed energy-saving schemes, the present invention can be flexibly adjusted according to real-time data, which is more intelligent and efficient. The existing technology usually lacks in-depth analysis of user behavior patterns, and the control system of smart home devices relies more on timed tasks and simple switch control. The present invention analyzes the user's historical behavior data and combines environmental data to accurately construct a user preference model, so that the control of smart home devices is more personalized and meets user needs. The identification of user behavior patterns not only improves the efficiency of device use, but also further improves the user experience. The present invention can more accurately predict the energy efficiency performance of the device under different environmental conditions and generate personalized energy-saving control schemes by constructing an energy efficiency portrait of each device and combining the historical energy efficiency indicators and power consumption patterns of the device; this precise energy efficiency management makes the energy consumption of the device more in line with the actual use requirements and avoids the device being in a high energy consumption state for a long time. Unlike the existing fixed energy-saving control strategy, the energy-saving control scheme of the present invention will be dynamically adjusted with the passage of time and changes in the use of the device; every preset time period, the system will re-evaluate the standby energy consumption of the device and optimize the control strategy; this dynamic optimization mechanism can continuously improve the efficiency of energy management and avoid the device from wasting a lot of energy in the standby state. In a smart home, multiple devices may be in standby or low-power consumption state in the same time period. The present invention realizes collaborative management between devices by analyzing the correlation between the use time periods between devices; when two or more devices have a high correlation in the standby period, the system can intelligently set these devices to the shutdown state to further reduce the overall energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 It is a schematic diagram of a module of an intelligent equipment control system based on cloud computing of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 , the present invention provides a technical solution:

[0059] An intelligent equipment control system based on cloud computing, the system includes: a data acquisition and processing module, a user behavior analysis and preference modeling module, a standby energy consumption identification module and a real-time monitoring and adjustment module;

[0060] The data collection and processing module uses the cloud computing platform to collect the historical power consumption data of smart home devices and the corresponding external environment data, and obtains the power consumption pattern of smart home devices by analyzing the historical power consumption data; it also conducts historical energy efficiency evaluation on each smart home device in combination with the external environment data, thereby forming an energy consumption profile of each smart home device;

[0061] The user behavior analysis and preference modeling module obtains the user's historical behavior data, combines the user's historical behavior data, the usage time of smart home devices and external environment data to identify the user's behavior pattern; and based on the user behavior pattern recognition results, builds a user preference model for each smart home device;

[0062] The standby energy consumption identification module identifies the smart home devices with standby energy consumption according to the corresponding energy consumption profile and user preference model; based on the identification results and the usage time period of each smart home device, the association relationship between the smart home devices is obtained, thereby generating an energy-saving control plan for the smart home devices with standby energy consumption;

[0063] The real-time monitoring and adjustment module implements the energy-saving control plan, obtains the real-time power consumption data of smart home devices with standby energy consumption and the real-time external environment data, and conducts real-time energy efficiency evaluation; according to the real-time energy efficiency evaluation results, the energy-saving control plan is adjusted accordingly.

[0064] The data acquisition and processing module includes a data preprocessing unit, a time series decomposition unit, and an energy consumption profile construction unit;

[0065] The data preprocessing unit collects historical power consumption data and external environment data of smart home devices from the cloud computing platform, and smoothes and standardizes the collected data; the time series decomposition unit decomposes the historical power consumption data into time series, extracts trend items, seasonal items and random items; the DBSCAN clustering algorithm is used to classify the power consumption data of smart home devices and identify different power consumption patterns; the energy consumption profile construction unit conducts historical energy efficiency evaluation on each smart home device in combination with external environment data, thereby forming an energy consumption profile of each smart home device.

[0066] The user behavior analysis and preference modeling module includes a historical behavior data collection unit, a behavior pattern recognition unit, and a preference model building unit;

[0067] The historical behavior data collection unit collects the user's historical behavior data; the behavior pattern recognition unit divides the user behavior data into different behavior patterns through a clustering algorithm, and annotates the background information of each behavior pattern in combination with the environmental data; the preference model construction unit constructs a user preference model for smart home devices based on the user behavior pattern and device usage data;

[0068] The standby energy consumption identification module includes a standby energy consumption identification unit and an energy-saving control scheme generation unit;

[0069] The standby energy consumption identification unit identifies smart home devices with standby energy consumption based on energy consumption profiles and user preference models; by comparing historical energy efficiency indicators, smart home device usage patterns and user preference values, it detects whether the smart home devices are in standby state and the time period of standby energy consumption; the energy-saving control scheme generation unit generates an energy-saving control scheme for the corresponding smart home devices based on the identified smart home devices with standby energy consumption and their usage time period.

[0070] The real-time monitoring and adjustment module includes a real-time monitoring and data acquisition unit, a real-time energy efficiency evaluation and comparison unit, and an energy-saving control scheme adjustment unit;

[0071] The real-time monitoring and data acquisition unit implements the energy-saving control plan and obtains the power consumption data and external environment data of the smart home devices in real time; the real-time energy efficiency evaluation and comparison unit compares the real-time collected power consumption data with the historical energy efficiency portrait to determine whether the real-time energy efficiency index is better than the corresponding historical energy efficiency index; the energy-saving control plan adjustment unit adjusts the corresponding energy-saving control plan according to the judgment result of the real-time energy efficiency evaluation and comparison unit.

[0072] A cloud computing-based intelligent device control method comprises the following steps:

[0073] Step S100. Use the cloud computing platform to collect historical power consumption data of smart home devices and corresponding external environment data, and obtain the power consumption mode of smart home devices by analyzing the historical power consumption data; perform historical energy efficiency evaluation on each smart home device in combination with the external environment data, so as to form an energy consumption profile of each smart home device;

[0074] Step S200. Obtain the user's historical behavior data, and identify the user's behavior pattern by combining the user's historical behavior data, the usage time of the smart home device, and the external environment data; and based on the user behavior pattern recognition results, build a user preference model for each smart home device;

[0075] Step S300. Identify smart home devices with standby energy consumption according to the corresponding energy consumption profile and user preference model; obtain the association relationship between smart home devices according to the identification result and the usage time period of each smart home device, so as to generate an energy-saving control solution for the smart home devices with standby energy consumption;

[0076] Step S400: Implement the energy-saving control scheme, obtain the real-time power consumption data of smart home devices with standby energy consumption and real-time external environment data, and perform real-time energy efficiency evaluation; according to the real-time energy efficiency evaluation results, adjust the energy-saving control scheme accordingly.

[0077] Step S100 includes:

[0078] S101. Collect historical power consumption data of smart home devices and corresponding external environment data using a cloud computing platform. For each smart home device, record the historical power consumption data in different time periods as Pi(t), where i is the smart device number and t is a timestamp, such as divided by hours or minutes; the external environment data includes temperature, humidity and light intensity, which are recorded as Ek(t), where k represents the environmental parameter number; pre-process the historical power consumption data of smart home devices and the corresponding external environment data, and use smoothing technology to correct the data, so as to obtain standardized data of historical power consumption data and external environment data, which are expressed as Pa_i(t) and Ea_k(t), respectively;

[0079] S102. For each smart home device's historical power consumption data Pa_i(t), use the time series decomposition method to decompose the historical power consumption data in different time periods into the following parts: trend item Ti(t), seasonal item Si(t) and random item Ri(t); the trend item Ti(t) represents a long-term trend or baseline, such as the gradual aging of the device or the change in the frequency of use; the seasonal item Si(t) represents the repetitive changes of the device within a specific time period, such as daily or weekly fluctuations; the random item Ri(t) represents random fluctuations or abnormal fluctuations; and the decomposition formula is expressed as: Pa_i( t)=Ti(t)+Si(t)+Ri(t); According to the trend term Ti(t), seasonal term Si(t) and random term Ri(t) of each timestamp, a data unit Di_m(t) is formed, and Di_m(t)={Ti_m(t),Si_m(t),Ri_m(t)}, where m represents the data unit number; For each data unit Di_m(t), the distance metric d between Di_m(t) and all other data units is calculated, and the specific calculation formula is: d(Di_m(t),Di_n(t))={[Ti_m(t)-Ti_n(t)] 2 +[Si_m(t)-Si_n(t)] 2 +[Ri_m(t)-Ri_n(t)] 2}^(1 / 2), where Di_n(t) represents the nth data unit of the i-th smart home device, and Ti_n(t), Si_n(t) and Ri_n(t) represent the trend term, seasonal term and random term of the nth data unit of the i-th smart home device respectively; according to the distance metric d, the DBSCAN clustering algorithm is used to classify the data units, so as to obtain the power consumption mode M(t) of the corresponding smart home device, where the number of categories of the data unit is equal to the number of power consumption modes of the corresponding smart home device;

[0080] S103. For each data unit of each smart home device, the historical power consumption data Pa_i(t) corresponding to each data unit is combined with the external environment data Ea_k(t) corresponding to the same timestamp to calculate the corresponding historical energy efficiency index EEIi(t), and the specific calculation formula is:

[0081] EEIi(t)=[Pa_i(t)·Ai(t)] / {Ea_k(t)·J(t)·[1+ηi(t)]},

[0082] Among them, Ai(t) represents the environmental adaptability of smart home device i at timestamp t, and the specific calculation formula is:

[0083] Ai(t)=f1[Ea_1(t),Ea_2(t),...,Ea_k(t)],

[0084] Where Ea_1(t), Ea_2(t), ..., Ea_k(t) represent different environmental parameters in the external environmental data; f1 represents a mapping function that describes the relationship between environmental parameters and equipment energy efficiency. The specific function form can be linear regression, weighted sum, or a mapping obtained through a machine learning model (such as support vector machine, neural network, etc.); J(t) represents the seasonal adjustment factor, and the specific calculation formula is:

[0085] J(t)=1 / {1+α[sin(2πt) / T period ]},

[0086] Among them, α represents the amplitude of the adjustment factor, which reflects the impact of seasonality on energy efficiency; T period represents the length of the seasonal cycle; a sine function is used to simulate seasonal fluctuations. As time goes by, the seasonal factor J(t) will change periodically; ηi(t) represents the historical energy efficiency optimization index of smart furniture device i at timestamp t. The specific calculation formula is:

[0087] ηi(t)=Pmax_i / Pavg_i(t),

[0088] Among them, Pmax_i represents the maximum power consumption of smart furniture device i under optimal working conditions; Pavg_i(t) represents the average power consumption of smart furniture device i at timestamp t; ηi(t) is the optimization index of the device at a specific timestamp, reflecting the degree of energy efficiency optimization of the device in history; if the average power consumption of the device is close to the maximum power, the optimization index is low; if the device has been optimized in history, ηi(t) will be high. For each smart home device, the historical energy efficiency index EEIi(t) and the corresponding power consumption mode corresponding to each data unit are summarized to construct the corresponding energy consumption profile Ii, which is expressed as: Ii={[t1,EEIi(t1),M(t1)],[t2,EEIi(t2),M(t2)],...}, where [t1,EEIi(t1),M(t1)] and [t2,EEIi(t2),M(t2)] represent the historical energy efficiency index and power consumption mode corresponding to timestamps t1 and t2, respectively.

[0089] In S102, the data units are classified using the DBSCAN clustering algorithm according to the distance metric d, thereby obtaining the power consumption pattern of the corresponding smart home devices. The specific analysis process is as follows:

[0090] Set the neighborhood radius ε and the minimum number of neighborhood points Mp, where the neighborhood radius ε is defined as: the maximum distance around a data point. When the distance between two data units is less than or equal to this radius, they are considered to be adjacent; the minimum number of neighborhood points Mp is defined as: a data unit must contain at least Mp points (including itself) in its neighborhood to be marked as a core point. If this condition is not met in the neighborhood of a point, it is regarded as a boundary point or a noise point; for each data unit Di_m(t), obtain its distance metric d with all other data units. If a data unit Dm(t) has at least Mp data units in its neighborhood (including itself), it is regarded as a core point; that is, for a data unit Di_m(t), if the following condition is met: |{Di_n(t):d(Di_m(t),Di_n(t))≤ε}|≥Mp, then Di_m(t) is a core point, indicating that it can form a cluster; starting from the core point, traverse all data units whose distance to the core point is less than or equal to ε, and if these data units have not been classified, add them to the same cluster; this process is performed recursively until no more data units can be added to the cluster; all data units are divided into several clusters according to the data units in the core point and its neighborhood, where each cluster represents the power consumption pattern M(t) of a home appliance.

[0091] Step S200 includes:

[0092] S201. Collect historical behavior data of users from the cloud platform, wherein the historical behavior data includes daily behavior patterns of users, usage frequency and usage time of smart home devices, and association with external environment data; represent the historical behavior data as a time series set, i.e., Hu={hu(t1), hu(t2), ...}, wherein hu(t1) represents the characteristics of the historical behavior data of users at timestamp t1, such as the duration of a device being turned on, temperature adjustment preference, etc.; hu(t2) represents the characteristics of the historical behavior data of users at timestamp t2; cluster the characteristics of the historical behavior data of users, thereby dividing the historical behaviors of users into several categories, each category representing a user behavior pattern, represented as: {UP1, UP2, ...}; and annotate the background information of each behavior pattern in combination with the external environment data;

[0093] S202. For each smart home device, calculate the association strength Civ of the smart home device i in the corresponding user behavior pattern UPv, and the specific calculation formula is:

[0094] Civ=[Σt∈[1,T],Xiv(t)·Ui(t)] / [Σt∈[1,T],Ui(t)],

[0095] Wherein, Xiv(t) indicates whether the smart home device i is activated in the user behavior pattern UPv at timestamp t. If activated, Xiv(t) = 1, otherwise 0; T indicates the number of timestamps t; Ui(y) indicates the usage time of the smart home device i at timestamp t; the user preference value YPiv of the smart home device i under the corresponding user behavior pattern UPv is calculated, and the specific calculation formula is:

[0096] YPiv=[Σt∈[1,T],Civ·Ui(t)·ev(t)] / [Σt∈[1,T],Civ·Ui(t)], where ev(t) represents the external environment influencing factor of the user under the behavior pattern UPv; the user preference values ​​of smart home device i under all corresponding user behavior patterns are summarized to construct the corresponding user preference model, and the user preference model is expressed as.

[0097] YPi=Σv∈[1,K],bv·YPiv,

[0098] Where K represents the number of user behavior patterns corresponding to smart home device i; bv represents the weight factor of behavior pattern UPv.

[0099] Step S300 includes:

[0100] S301. For each smart home device i, extract the historical energy efficiency index EEIi(t) and power consumption mode of each timestamp t according to the corresponding energy consumption portrait Ii, and extract the user preference value YPi of the smart home device i according to the user preference model; with a set period Ts, summarize the historical energy efficiency index EEIi(t) and power consumption mode of all timestamps t within the set period Ts in chronological order, and form a feature vector set Z, and Z = {z1, z2, ...}, where z1 and z2 represent the feature vectors of the first and second timestamps t respectively, and the number of feature vectors mz = Ts / t; and zmz = [EEIi(tmz), M(tmz)], where EEIi(tmz) and M(tmz) represent the historical energy efficiency index and power consumption mode of the mzth timestamp t respectively. Formula; for each element in the feature vector set Z, compare the historical energy efficiency indicators and power consumption patterns corresponding to the adjacent feature vectors. If there are r adjacent feature vectors in the feature vector set Z whose historical energy efficiency indicators and power consumption patterns are the same, and the user preference value YPi of the corresponding smart home device i is less than the threshold value YP, then the smart home device i has standby energy consumption, and the standby energy consumption time period is equal to the sum of the timestamps corresponding to the r adjacent feature vectors; and based on the standby energy consumption identification result, the smart home device in the standby energy consumption time period corresponding to the set period Ts is set to a shutdown or low power consumption state; wherein, the identification process of the smart home device with standby energy consumption is performed once every preset time period, so the smart home device with standby energy consumption is not fixed, but is updated with time.

[0101] S302. Obtain the usage time period UT of each smart home device in the set period Ts, and calculate the correlation degree GL between each standby energy consumption and other smart home devices based on the usage time period UT of the smart home device, and the corresponding calculation formula is:

[0102] GLij=|UTi∩UTj| / |UTi∪UTj|,

[0103] Among them, UTi represents the standby energy consumption time period of the smart home device i in the set period Ts, and UTj represents the usage time period of the smart home device j in the set period Ts; GLij is compared with the corresponding threshold GL, if GLi is greater than or equal to the threshold GL, the smart home device i is set to the shutdown state in the standby energy consumption time period; if GLi is less than the threshold GL, the smart home device i is set to the low power consumption state in the standby energy consumption time period.

[0104] Step S400 includes:

[0105] Implement an energy-saving control scheme, obtain real-time power consumption data and real-time external environment data of smart home devices with standby energy consumption, and analyze the real-time power consumption data and real-time external environment data according to the analysis process of historical power consumption data and historical external environment data, so as to obtain a real-time energy consumption portrait I'i with standby energy consumption; compare the real-time energy consumption portrait I'i with standby energy consumption with the corresponding energy consumption portrait I, if in the selected period Ts, there are real-time energy efficiency indicators with Ns timestamps that are greater than the corresponding historical energy efficiency indicators, and save the corresponding energy-saving control scheme; if there are real-time energy efficiency indicators with Ns timestamps that are less than the corresponding historical energy efficiency indicators, and mark the corresponding energy-saving control scheme as an energy-saving control scheme to be optimized; manually adjust the energy-saving control scheme to be optimized until the real-time energy efficiency indicators with Ns timestamps are greater than the corresponding historical energy efficiency indicators, and save the adjusted energy-saving control scheme to be optimized; wherein Ns represents a preset quantity threshold.

[0106] In this embodiment, it is assumed that there is a smart home environment, taking the air conditioner (device 1) as an example; by monitoring the real-time power consumption data P(t) of the air conditioner and the real-time external environment data, such as temperature and humidity, its real-time energy efficiency index is calculated.

[0107] Assume that the historical data are:

[0108] Historical Energy Efficiency Index of Air Conditioners (EEI1(t)):

[0109] At 10:00:00 on December 1, 2023, EEI1(10:00)=0.75;.

[0110] 2023-12-1 11:00:00, EEI1(11:00)=0.78;

[0111] At 12:00:00 on December 1, 2023, EEI1(12:00)=0.80.

[0112] Assume that the real-time power consumption data P(t) and real-time external environment data Ea(t) are obtained from equipment and environmental sensors.

[0113] Assume that the real-time energy efficiency of device 1 (air conditioner) is as follows:

[0114] Air conditioning (device 1):

[0115] 2024-11-28 10:00:00, EEI1′(10:00)=0.80;

[0116] 2024-11-28 11:00:00, EEl1′(11:00)=0.75;

[0117] At 12:00:00 on November 28, 2024, EEl1′(12:00)=0.85;.

[0118] Comparison of air conditioners (equipment 1):

[0119] 2024-11-28 10:00:00: EEI1′(10:00)=0.80>EEI1(10:00)=0.75, so the condition is met (real time is greater than history);

[0120] 2024-11-28 11:00:00: EEl1′(11:00)=0.75<EEI1(11:00)=0.78, so the condition is not met (real time is less than history);

[0121] 2024-11-28 12:00:00: EEl1′(12:00)=0.85>EEI1(12:00)=0.80, so the condition is met (real time is greater than history);

[0122] Assume that the threshold value Ns=2 is set, that is, in the selected period Ts, and Ts=3 (hours), if there are 2 or more real-time energy efficiency indicators with timestamps greater than the corresponding historical energy efficiency indicators, the current energy-saving control plan can be saved, so the energy-saving control plan of the air conditioner is saved.

[0123] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0124] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cloud computing-based intelligent equipment control method, characterized in that: The method comprises the following steps: Step S100. Use the cloud computing platform to collect historical power consumption data of smart home devices and corresponding external environment data, and obtain the power consumption mode of smart home devices by analyzing the historical power consumption data; perform historical energy efficiency evaluation on each smart home device in combination with the external environment data, so as to form an energy consumption profile of each smart home device; Step S200. Obtain the user's historical behavior data, and identify the user's behavior pattern by combining the user's historical behavior data, the usage time of the smart home device, and the external environment data; and based on the user behavior pattern recognition results, build a user preference model for each smart home device; Step S300. Identify smart home devices with standby energy consumption according to the corresponding energy consumption profile and user preference model; obtain the association relationship between smart home devices according to the identification result and the usage time period of each smart home device, so as to generate an energy-saving control scheme for the smart home devices with standby energy consumption; Step S400: Implement the energy-saving control scheme, obtain the real-time power consumption data of smart home devices with standby energy consumption and real-time external environment data, and perform real-time energy efficiency evaluation; according to the real-time energy efficiency evaluation results, adjust the energy-saving control scheme accordingly.

2. The intelligent device control method based on cloud computing according to claim 1, characterized in that: The step S100 includes: S101. Collect historical power consumption data of smart home devices and corresponding external environment data using a cloud computing platform. For each smart home device, record the historical power consumption data in different time periods as Pi(t), where i is the smart device number and t is a timestamp; the external environment data includes temperature, humidity and light intensity, which are recorded as Ek(t), where k represents the environmental parameter number; preprocess the historical power consumption data of smart home devices and the corresponding external environment data, and use smoothing technology to correct the data, so as to obtain standardized data of historical power consumption data and external environment data, which are expressed as Pa_i(t) and Ea_k(t), respectively; S102. For the historical power consumption data Pa_i(t) of each smart home device, use the time series decomposition method to decompose the historical power consumption data in different time periods into the following parts: trend item Ti(t), seasonal item Si(t) and random item Ri(t); the trend item Ti(t) represents a long-term trend or baseline; the seasonal item Si(t) represents the repetitive change of the device within a specific time period; the random item Ri(t) represents random fluctuation or abnormal fluctuation; and the decomposition formula is expressed as: Pa_i(t) = Ti(t) + Si(t) + Ri(t); according to the trend item Ti(t), seasonal item Si(t) and random item Ri(t) of each timestamp, a data unit Di_m(t) is formed, and Di_m(t) = {Ti_m(t), Si_m(t), Ri_m(t)}, where m represents the data unit number; for each data unit Di_m(t), calculate the distance metric d between Di_m(t) and all other data units, and the specific calculation formula is: d(Of_m(t),Of_n(t))={[You_m(t)-You_n(t)] 2 +[Si_m(t)-Si_n(t)] 2 +[In_m(t)-In_n(t)] 2 }^(1 / 2), Where Di_n(t) represents the nth data unit of the i-th smart home device, and Ti_n(t), Si_n(t) and Ri_n(t) represent the trend item, seasonal item and random item of the nth data unit of the i-th smart home device respectively; according to the distance metric d, the DBSCAN clustering algorithm is used to classify the data units, so as to obtain the power consumption pattern M(t) of the corresponding smart home device, where the number of categories of the data unit is equal to the number of power consumption patterns of the corresponding smart home devices; S103. For each data unit of each smart home device, the historical power consumption data Pa_i(t) corresponding to each data unit is combined with the external environment data Ea_k(t) corresponding to the same timestamp to calculate the corresponding historical energy efficiency index EEIi(t), and the specific calculation formula is: EEIi(t)=[Pa_i(t)·Ai(t)] / {Ea_k(t)·J(t)·[1+ηi(t)]}, Among them, Ai(t) represents the environmental adaptability of smart home device i at timestamp t, and the specific calculation formula is: Ai(t)=f1[Ea_1(t),Ea_2(t),...,Ea_k(t)], Where Ea_1(t), Ea_2(t), ..., Ea_k(t) represent different environmental parameters in the external environmental data; f1 represents the mapping function, which describes the relationship between environmental parameters and equipment energy efficiency; J(t) represents the seasonal adjustment factor, and the specific calculation formula is: J(t)=1 / {1+α[sin(2πt) / T period ]}, Among them, α represents the amplitude of the adjustment factor; T period represents the length of the seasonal cycle; ηi(t) represents the historical energy efficiency optimization index of smart furniture device i at timestamp t. The specific calculation formula is: ηi(t)=Pmax_i / Pavg_i(t), Among them, Pmax_i represents the maximum power consumption of smart furniture device i under optimal working conditions; Pavg_i(t) represents the average power consumption of smart furniture device i at timestamp t; for each smart home device, the historical energy efficiency index EEIi(t) and the corresponding power consumption mode corresponding to each data unit are summarized to construct the corresponding energy consumption profile Ii, which is expressed as: Ii={[t1,EEIi(t1),M(t1)],[t2,EEIi(t2),M(t2)],...}, where [t1,EEIi(t1),M(t1)] and [t2,EEIi(t2),M(t2)] represent the historical energy efficiency indicators and power consumption modes corresponding to timestamps t1 and t2, respectively.

3. The intelligent device control method based on cloud computing according to claim 2 is characterized in that: In S102, the data units are classified using the DBSCAN clustering algorithm according to the distance metric d, so as to obtain the power consumption pattern of the corresponding smart home device. The specific analysis process is as follows: Set the neighborhood radius ε and the minimum number of neighborhood points Mp. For each data unit Di_m(t), calculate the distance d between it and all other data units. If a data unit Dm(t) has at least Mp data units in its neighborhood (including itself), it is considered a core point. That is, for a data unit Di_m(t), if the following conditions are met: |{Di_n(t):d(Di_m(t),Di_n(t))≤ε}|≥Mp, then Di_m(t) is a core point, indicating that it can form a cluster. Starting from the core point, traverse all data units whose distance to the core point is less than or equal to ε. If these data units have not been classified, add them to the same cluster. This process is performed recursively until no more data units can be added to the cluster; all data units are divided into several clusters according to the data units in the core point and its neighborhood, where each cluster represents the power consumption pattern M(t) of a home appliance.

4. The intelligent device control method based on cloud computing according to claim 2 is characterized in that: The step S200 includes: S201. Collect historical behavior data of users from the cloud platform, wherein the historical behavior data includes daily behavior patterns of users, usage frequency and usage time of smart home devices, and association with external environment data; represent the historical behavior data as a time series set, i.e., Hu={hu(t1), hu(t2), ...}, wherein hu(t1) represents the characteristics of the historical behavior data of users at timestamp t1; hu(t2) represents the characteristics of the historical behavior data of users at timestamp t2; cluster the characteristics of the historical behavior data of users, thereby dividing the historical behaviors of users into several categories, each category representing a user behavior pattern, represented as: {UP1, UP2, ...}; and annotate the background information of each behavior pattern in combination with the external environment data; S202. For each smart home device, calculate the association strength Civ of the smart home device i in the corresponding user behavior pattern UPv, and the specific calculation formula is: Civ=[Σt∈[1,T],Xiv(t)·Ui(t)] / [Σt∈[1,T],Ui(t)], Wherein, Xiv(t) indicates whether the smart home device i is activated in the user behavior pattern UPv at timestamp t. If activated, Xiv(t) = 1, otherwise 0; T indicates the number of timestamps t; Ui(y) indicates the usage time of the smart home device i at timestamp t; the user preference value YPiv of the smart home device i under the corresponding user behavior pattern UPv is calculated, and the specific calculation formula is: YPiv=[Σt∈[1,T],Civ·Ui(t)·ev(t)] / [Σt∈[1,T],Civ·Ui(t)], where ev(t) represents the external environment influencing factor of the user under the behavior pattern UPv; the user preference values ​​of smart home device i under all corresponding user behavior patterns are summarized to construct the corresponding user preference model, and the user preference model is expressed as. YPi=Σv∈[1,K],bv·YPiv, Where K represents the number of user behavior patterns corresponding to smart home device i; bv represents the weight factor of behavior pattern UPv.

5. The intelligent device control method based on cloud computing according to claim 4 is characterized in that: The step S300 includes: S301. For each smart home device i, extract the historical energy efficiency index EEIi(t) and power consumption mode of each timestamp t according to the corresponding energy consumption portrait Ii, and extract the user preference value YPi of the smart home device i according to the user preference model; with a set period Ts, summarize the historical energy efficiency index EEIi(t) and power consumption mode of all timestamps t within the set period Ts in chronological order, and form a feature vector set Z, and Z = {z1, z2, ...}, where z1 and z2 represent the feature vectors of the first and second timestamps t respectively, and the number of feature vectors mz = Ts / t; and zmz = [EEIi(tmz), M(tmz)], where EEIi(tmz) and M(tmz) respectively represent the historical energy efficiency index and power consumption mode of the mzth timestamp t; for each element in the feature vector set Z, compare the historical energy efficiency index and power consumption mode corresponding to the adjacent feature vectors; if there are r adjacent feature vectors in the feature vector set Z whose historical energy efficiency index and power consumption mode are the same, and the user preference value YPi of the corresponding smart home device i is less than the threshold value YP, then the smart home device i has standby energy consumption, and the standby energy consumption time period is equal to the sum of the timestamps corresponding to the r adjacent feature vectors; and based on the standby energy consumption identification result, the smart home device in the standby energy consumption time period corresponding to the set period Ts is set to a shutdown or low power consumption state; S302. Obtain the usage time period UT of each smart home device in the set period Ts, and calculate the correlation degree GL between each standby energy consumption and other smart home devices based on the usage time period UT of the smart home device, and the corresponding calculation formula is: GLij=|UTi∩UTj| / |UTi∪UTj|, Among them, UTi represents the standby energy consumption time period of the smart home device i in the set period Ts, and UTj represents the usage time period of the smart home device j in the set period Ts; GLij is compared with the corresponding threshold GL, if GLi is greater than or equal to the threshold GL, the smart home device i is set to the shutdown state in the standby energy consumption time period; if GLi is less than the threshold GL, the smart home device i is set to the low power consumption state in the standby energy consumption time period.

6. The intelligent device control method based on cloud computing according to claim 5 is characterized in that: The step S400 includes: Implement an energy-saving control scheme, obtain real-time power consumption data and real-time external environment data of smart home devices with standby energy consumption, and analyze the real-time power consumption data and real-time external environment data according to the analysis process of historical power consumption data and historical external environment data, so as to obtain a real-time energy consumption portrait I'i with standby energy consumption; compare the real-time energy consumption portrait I'i with standby energy consumption with the corresponding energy consumption portrait I, if in the selected period Ts, there are real-time energy efficiency indicators with Ns timestamps that are greater than the corresponding historical energy efficiency indicators, and save the corresponding energy-saving control scheme; if there are real-time energy efficiency indicators with Ns timestamps that are less than the corresponding historical energy efficiency indicators, and mark the corresponding energy-saving control scheme as an energy-saving control scheme to be optimized; manually adjust the energy-saving control scheme to be optimized until the real-time energy efficiency indicators with Ns timestamps are greater than the corresponding historical energy efficiency indicators, and save the adjusted energy-saving control scheme to be optimized; wherein Ns represents a preset quantity threshold.

7. A cloud computing-based intelligent device control system, applied to a cloud computing-based intelligent device control method according to any one of claims 1 to 6, characterized in that: The system includes: a data acquisition and processing module, a user behavior analysis and preference modeling module, a standby energy consumption identification module, and a real-time monitoring and adjustment module; The data collection and processing module uses the cloud computing platform to collect the historical power consumption data of smart home devices and the corresponding external environment data, and obtains the power consumption mode of smart home devices by analyzing the historical power consumption data; and performs a historical energy efficiency evaluation on each smart home device in combination with the external environment data, thereby forming an energy consumption profile of each smart home device; The user behavior analysis and preference modeling module obtains the user's historical behavior data, combines the user's historical behavior data, the usage time of the smart home device and the external environment data to perform user behavior pattern recognition; and builds a user preference model for each smart home device based on the user behavior pattern recognition result; The standby energy consumption identification module identifies the smart home devices with standby energy consumption according to the corresponding energy consumption profile and the user preference model; obtains the association relationship between the smart home devices according to the identification result and the usage time period of each smart home device, thereby generating an energy-saving control solution for the smart home devices with standby energy consumption; The real-time monitoring and adjustment module implements an energy-saving control scheme, obtains real-time power consumption data of smart home devices with standby energy consumption and real-time external environment data, and performs real-time energy efficiency evaluation; according to the real-time energy efficiency evaluation results, the energy-saving control scheme is adjusted accordingly.

8. The intelligent equipment control system based on cloud computing according to claim 7 is characterized in that: The data acquisition and processing module includes a data preprocessing unit, a time series decomposition unit and an energy consumption profile construction unit; The data preprocessing unit collects historical power consumption data and external environment data of smart home devices from the cloud computing platform, and performs smoothing and standardization processing on the collected data; The time series decomposition unit performs time series decomposition on historical electricity consumption data to extract trend items, seasonal items and random items; uses the DBSCAN clustering algorithm to classify the electricity consumption data of smart home devices and identify different electricity consumption patterns; the energy consumption portrait construction unit performs historical energy efficiency evaluation on each smart home device in combination with external environment data, thereby forming an energy consumption portrait of each smart home device.

9. The intelligent equipment control system based on cloud computing according to claim 7, characterized in that: The user behavior analysis and preference modeling module includes a historical behavior data collection unit, a behavior pattern recognition unit, and a preference model building unit; The historical behavior data collection unit collects the historical behavior data of the user; the behavior pattern recognition unit divides the user behavior data into different behavior patterns through a clustering algorithm, and marks the background information of each behavior pattern in combination with the environmental data; The preference model building unit builds a user preference model for smart home devices based on user behavior patterns and device usage data; The standby energy consumption identification module includes a standby energy consumption identification unit and an energy-saving control scheme generation unit; The standby energy consumption identification unit identifies smart home devices with standby energy consumption based on the energy consumption profile and the user preference model; By comparing historical energy efficiency indicators, smart home device usage patterns and user preference values, it is detected whether the smart home device is in standby state and the time period of standby energy consumption; the energy-saving control scheme generation unit generates an energy-saving control scheme for the corresponding smart home device based on the identified smart home devices with standby energy consumption and their usage time period.

10. The intelligent equipment control system based on cloud computing according to claim 7, characterized in that: The real-time monitoring and adjustment module includes a real-time monitoring and data acquisition unit, a real-time energy efficiency evaluation and comparison unit, and an energy-saving control scheme adjustment unit; The real-time monitoring and data acquisition unit implements the energy-saving control plan and acquires the power consumption data and external environment data of the smart home devices in real time; the real-time energy efficiency evaluation and comparison unit compares the real-time collected power consumption data with the historical energy efficiency portrait to determine whether the real-time energy efficiency index is better than the corresponding historical energy efficiency index; the energy-saving control plan adjustment unit adjusts the corresponding energy-saving control plan according to the judgment result of the real-time energy efficiency evaluation and comparison unit.

Images