Electric appliance control system based on smart home

Abstract

The application discloses an electric appliance control system based on smart home, belongs to the technical field of smart home, and comprises a data correlation module, a control module and a server. The data correlation module is used for correlating smart electric appliances to obtain correlated smart devices. The control module is used for controlling smart home appliances. The specific method comprises the following steps: obtaining the correlated smart devices, setting characteristic factors of the correlated smart devices, setting a smart home appliance control scheme according to the characteristic factors and the corresponding correlated smart devices, forming a smart home appliance control scheme library, and establishing a matching vector space according to the smart home appliance control scheme library. The current time is obtained, the correlated smart devices are matched, corresponding characteristic factor data is collected, the obtained characteristic factor data is converted into characteristic vectors, the characteristic vectors are input into the matching vector space for matching, corresponding smart home appliance control scheme numbers are obtained, and corresponding smart home appliance control schemes are matched from the smart home appliance control scheme library according to the obtained smart home appliance control scheme numbers.

Description

Technical Field

[0001] This invention belongs to the field of smart home technology, specifically an appliance control system based on smart homes. Background Technology

[0002] With the development of science and technology and the improvement of people's living standards, computer, embedded systems, and network communication technologies are becoming increasingly integrated into people's lives, leading to a trend of intelligent development in people's homes and household appliances. Smart home products integrate automated control systems and computer network systems to achieve intelligent control. However, the interconnectivity of smart homes is not very good at present, and it is impossible to realize the personalized experience of users. Therefore, this invention provides an appliance control system based on smart homes, which is used to further improve the automation level of smart appliances in the home, realize interconnected control, and further improve the user's comfort experience. Summary of the Invention

[0003] To address the problems of the above solutions, this invention provides an appliance control system based on smart homes.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] An appliance control system based on smart home technology includes a data association module, a control module, and a server.

[0006] The data association module is used to associate smart appliances and obtain associated smart devices;

[0007] The control module is used for controlling smart home appliances, and the specific methods include:

[0008] Acquire associated smart devices, set feature factors for associated smart devices, set smart home appliance control schemes based on feature factors and corresponding associated smart devices, form a smart home appliance control scheme library, and establish a matching vector space based on the smart home appliance control scheme library;

[0009] The system obtains the current time, matches associated smart devices, collects corresponding feature factor data, converts the obtained feature factor data into feature vectors, inputs the feature vectors into the matching vector space for matching, obtains the corresponding smart home appliance control scheme number, matches the corresponding smart home appliance control scheme from the smart home appliance control scheme library based on the obtained smart home appliance control scheme number, and performs smart home appliance control based on the obtained smart home appliance control scheme.

[0010] Furthermore, the working method of the data association module includes:

[0011] Obtain the smart appliances in the user's home, mark them as target devices, obtain the historical usage data of the target devices, analyze the historical usage data, obtain the fixed association values between the target devices, set up a time correction coefficient table, mark two target devices as candidate associated devices, and mark them as i, where i = 1, 2,..., n, and n is a positive integer; match the fixed association values of the candidate associated devices, and mark them as GPi; obtain the current time, mark it as the matching time, input the matching time and the candidate associated devices into the time correction coefficient table for matching, obtain the corresponding time correction coefficient, and mark it as SXi; according to the initial association value formula Calculate the initial association value; where b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; set the smart appliance association threshold X1, and determine the corresponding associated smart devices according to the smart appliance association threshold X1 and the initial association value CGi.

[0012] Further, the method for analyzing the historical usage data includes:

[0013] Perform collaborative extraction of specified keywords for historical usage data to obtain single key data, perform transformation of the single key data to obtain key data coordinates, input the obtained key data coordinates into the coordinate space, perform clustering based on the K-means algorithm to obtain the corresponding clusters, integrate the single key data belonging to the same cluster into a key data set, and analyze the key data set to obtain the fixed association values between the corresponding target devices.

[0014] Further, the method for setting the characteristic factors of the associated smart devices includes:

[0015] Obtain the influencing factors that affect the activation of the associated smart devices, perform integration of the influencing factors, mark them as characteristic factors, and set the interval ranges of the corresponding characteristic factors.

[0016] Further, the method for establishing a matching vector space according to the smart home appliance control scheme library includes:

[0017] Identify the interval ranges of each characteristic factor corresponding to the smart home appliance control scheme, divide the vector regions corresponding to the smart home appliance control scheme in the vector space according to the identified interval ranges of the characteristic factors, set up an identification and matching unit, and the identification and matching unit is used to identify which vector region the input characteristic vector is located in, and match the corresponding smart home appliance control scheme number according to the identified vector region.

[0018] Further, it also includes a usage correction module, and the usage correction module is used to perform dynamic correction of the associated smart devices according to the user's usage data.

[0019] Further, the working method of the usage correction module includes:

[0020] The system acquires user usage records of smart appliances within a specified time period, extracts and merges these records to obtain personalized data; it acquires associated smart devices, identifies the differences between personalized data and associated smart devices, identifies the time attributes of the differences, sets dynamic correction coefficients for the differences, supplements the dynamic correction coefficients based on the candidate associated devices, marks the dynamic correction coefficients as CYi, and calculates the dynamic association value according to the dynamic association value formula DTi=λ×CYi×CGi, where λ is the correction factor with a value range of 0<λ≤1; and dynamically adjusts the associated smart devices based on the calculated dynamic association value.

[0021] Furthermore, the dynamic correction coefficient CYi = 1 is applied to supplement the non-differentiated data.

[0022] Compared with the prior art, the beneficial effects of the present invention are: through the cooperation between the data association module and the control module, the smart home appliances in the house are intelligently associated, realizing the linkage control of the smart home appliances in the house, further improving the automation level of smart appliances in the house, and improving the user's comfort experience; by setting up a correction module, the user's personalized experience is improved, and dynamic adjustments are made according to the user's usage data, making the user's living environment more comfortable and considerate. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0025] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0026] like Figure 1 As shown, the smart home-based appliance control system includes a data association module, a usage correction module, a control module, and a server.

[0027] The data association module is used to associate smart appliances, and the specific methods include:

[0028] Obtain the smart appliances in the user's home, such as smart air conditioners, smart lights, etc.; mark them as target devices, obtain the historical usage data of the target devices, analyze the historical usage data, obtain the fixed correlation values between the target devices, set up a time correction coefficient table, mark two target devices as candidate associated devices, and mark them as i, where i = 1, 2, ……, n, and n is a positive integer; match the fixed correlation values of the candidate associated devices and mark them as GPi; obtain the current time and mark it as the matching time, input the matching time and the candidate associated devices into the time correction coefficient table for matching, obtain the corresponding time correction coefficient and mark it as SXi; according to the initial correlation value formula Calculate the initial correlation value; where b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; set the smart appliance association threshold X1, which is set through discussion by the expert group; determine the corresponding associated smart devices according to the smart appliance association threshold X1 and the initial correlation value CGi.

[0029] Determining the corresponding associated smart devices according to the smart appliance association threshold X1 and the initial correlation value CGi means identifying the association relationships of each associated device based on the determined associated devices, and integrating multiple associated devices, that is, including multiple associated smart appliances.

[0030] The historical usage data of the target devices refers to the past usage data of the same type of smart home appliances. For newly installed smart home appliances, the usage data of the same type of smart home appliances can be obtained from the Internet or other channels.

[0031] The methods for analyzing the historical usage data include:

[0032] Perform collaborative extraction of specified keywords for historical usage data to obtain single key data, perform transformation of single key data to obtain key data coordinates, input the obtained key data coordinates into the coordinate space, perform clustering based on the K-means algorithm to obtain the corresponding clusters, integrate the single key data belonging to the same cluster into a key data set, and analyze the key data set to obtain the fixed correlation values between the corresponding target devices.

[0033] Performing collaborative extraction of specified keywords for historical usage data is to set corresponding keywords according to each type of smart appliance, and then extract the corresponding data in the historical data according to the set keywords; for example, if a historical data includes data such as air conditioners and electric doors and windows, then performing collaborative extraction of specified keywords is to extract the usage association data between the air conditioner and the electric doors and windows, that is, the data on the state of the doors and windows when the air conditioner is running, which are mutually associated and influential data.

[0034] The methods for performing transformation of single key data include:

[0035] Identifying and assigning values ​​to single key data can be done by matching values ​​using an assignment table established by an expert group, or by intelligently assigning values ​​using a neural network model. The specific undisclosed parts are common knowledge in the field and will not be described in detail. After the assignment is completed, the data is integrated into key data coordinates. In this process, a corresponding coordinate template is set up, which means that the corresponding data is simply assigned and then filled into the corresponding position in the coordinate template.

[0036] Clustering is performed based on the K-means algorithm. The specific clustering process is common knowledge in this field. The value of K can be set according to the number of target devices.

[0037] Methods for analyzing key datasets include:

[0038] Obtain the distribution images of the corresponding clusters, integrate the key datasets and the corresponding cluster distribution images into analysis data, build an intelligent model based on the CNN network and the DNN network, build a training set based on the available analysis data, train the intelligent model, mark the successfully trained intelligent model as the analysis model, analyze the analysis data through the analysis model, and obtain the fixed correlation values ​​between the corresponding target devices.

[0039] Setting up a time correction factor table involves setting corresponding correction factors based on the time of two target devices, such as the specific time of the month or day. Since the correlation between different target devices varies in different seasons and times, the expert group can establish a time correction factor table based on the fixed correlation values ​​between each target device and match the corresponding time correction factors between target devices according to the type of target device.

[0040] Because different users may have different usage habits, and the settings of connected smart devices are not very personalized, it is necessary to make dynamic adjustments based on the user's usage data, so as to make the user's living environment more comfortable and considerate.

[0041] The usage correction module is used to dynamically correct associated smart devices based on user usage data, and the specific methods include:

[0042] The system retrieves user usage records of smart appliances within a specified time period (set by the system and adjustable by the user). These records are then extracted and merged to obtain personalized data. The system also retrieves associated smart devices, essentially adjusting the previously set associated devices based on the retrieved data. Differential data between the personalized data and associated smart devices is identified, along with the time attribute of the differential data (i.e., the corresponding time period). A dynamic correction coefficient is set for the differential data, supplemented with dynamic correction coefficients based on candidate associated devices, and denoted as CYi. For non-differentiated data, the dynamic correction coefficient CYi = 1 is added to the candidate associated devices. The dynamic association value is calculated using the formula DTi = λ × CYi × CGi, where λ is a correction factor with a range of 0 < λ ≤ 1. Finally, the associated smart devices are dynamically adjusted based on the calculated dynamic association value.

[0043] The method for extracting and merging records is the same as that in the data association module, and is equivalent to the key dataset.

[0044] Identifying the differences between personalized data and associated smart devices involves identifying the discrepancies between personalized data and associated smart devices. Specifically, it involves identifying whether a corresponding smart appliance is being used in conjunction with the associated smart device based on the personalized data. If no appliance is being used in conjunction or a new appliance is being used, the corresponding personalized data and the unassociated smart appliances are integrated into the differentiated data. This data is compared over a period of time and is not classified as differentiated data based on a single difference. There are corresponding thresholds, which are common knowledge in this field.

[0045] Methods for setting dynamic coefficient corrections include:

[0046] Identify the corresponding time attributes and abnormal appliances, which are those that have not been associated or have been newly associated; obtain the corresponding fixed association values, integrate the time attributes, abnormal appliances, and fixed association values ​​into dynamic data, perform dynamic data analysis, and obtain the corresponding dynamic correction coefficients; conduct intelligent analysis based on deep learning, the specific undisclosed aspects of which are common knowledge in this field.

[0047] The control module is used for controlling smart home appliances, and the specific methods include:

[0048] Acquire associated smart devices, set feature factors for associated smart devices, set smart home appliance control schemes based on feature factors and corresponding associated smart devices, form a smart home appliance control scheme library, and establish a matching vector space based on the smart home appliance control scheme library;

[0049] The system obtains the current time, matches associated smart devices, collects corresponding feature factor data, converts the obtained feature factor data into feature vectors, inputs the feature vectors into the matching vector space for matching, obtains the corresponding smart home appliance control scheme number, matches the corresponding smart home appliance control scheme from the smart home appliance control scheme library based on the obtained smart home appliance control scheme number, and performs smart home appliance control based on the obtained smart home appliance control scheme.

[0050] Methods for setting feature factors for associated smart devices include:

[0051] Obtain factors that influence the activation of associated smart devices, such as weather, temperature, air quality, and visibility. Integrate these factors, label them as feature factors, and set the corresponding range for each feature factor. This means that smart appliances will only be considered for activation if they are within the specified range. This can be set based on specific historical data.

[0052] Setting up a smart home appliance control scheme based on characteristic factors and corresponding associated smart devices involves setting up the operation scheme for the associated smart devices based on the corresponding characteristic factors and associated smart devices. Specifically, this is common knowledge in the field and can be set up manually.

[0053] Methods for establishing a matching vector space based on a smart home appliance control scheme library include:

[0054] Identify the range of each feature factor corresponding to the smart home appliance control scheme, divide the vector space into vector regions corresponding to the smart home appliance control scheme according to the identified feature factor range, set up an identification matching unit, the identification matching unit is used to identify which vector region the input feature vector is located in, and match the corresponding smart home appliance control scheme number according to the identified vector region.

[0055] Converting the acquired feature factor data into feature vectors involves converting the corresponding data into numerical values, and then integrating the numerical values ​​into feature vectors. During the conversion process, for the numerical data, a corresponding numerical matching table can be established, such as different values ​​corresponding to different weather conditions.

[0056] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0057] The working principle of this invention is as follows: Smart appliances are associated through a data association module to obtain associated smart devices; associated smart devices are acquired, feature factors of the associated smart devices are set, and smart appliance control schemes are set according to the feature factors and corresponding associated smart devices to form a smart appliance control scheme library; a matching vector space is established based on the smart appliance control scheme library; the current time is acquired, associated smart devices are matched, corresponding feature factor data is collected, the acquired feature factor data is converted into characteristic vectors, the characteristic vectors are input into the matching vector space for matching to obtain the corresponding smart appliance control scheme number; the corresponding smart appliance control scheme is matched from the smart appliance control scheme library based on the obtained smart appliance control scheme number; and smart appliances are controlled according to the obtained smart appliance control scheme.

[0058] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A smart home based electrical appliance control system characterized in that, The system comprises a data association module, a control module and a server. The data association module is used for intelligent appliance association to obtain associated intelligent devices. The smart electrical appliances in the user's home are acquired, marked as target devices, the historical use data of the target devices is acquired, the historical use data is analyzed, the fixed correlation values between the target devices are obtained, a time correction coefficient table is set, each two target devices are marked as a candidate correlation device, and are marked as i, wherein i=1, 2, …, n, n is a positive integer; the fixed correlation values of the candidate correlation devices are matched, and are marked as GPi; the current time is acquired, marked as a matching time, the matching time and the candidate correlation devices are input into the time correction coefficient table for matching, the corresponding time correction coefficients are obtained, and are marked as SXi; the initial correlation value formula The initial correlation value is calculated; wherein b1 and b2 are both proportional coefficients, and the value range is 0 The smart electrical appliance correlation threshold X1 is set, and the corresponding correlation smart device is determined according to the smart electrical appliance correlation threshold X1 and the initial correlation value CGi; The control module is used for intelligent appliance control, and the specific method comprises the following steps: obtaining the associated intelligent devices, setting characteristic factors of the associated intelligent devices, setting an intelligent appliance control scheme according to the characteristic factors and the corresponding associated intelligent devices, forming an intelligent appliance control scheme library, and establishing a matching vector space according to the intelligent appliance control scheme library. The method for setting the characteristic factors of the associated intelligent devices comprises the following steps: obtaining influence factors affecting the start of the associated intelligent devices, the influence factors comprising weather, temperature, air quality and visibility; integrating the influence factors, marking them as characteristic factors, and setting interval ranges of the corresponding characteristic factors. The current time is obtained, the associated intelligent devices are matched, the corresponding characteristic factor data are collected, the obtained characteristic factor data are converted into characteristic vectors, the characteristic vectors are input into the matching vector space for matching, the corresponding intelligent appliance control scheme number is obtained, the corresponding intelligent appliance control scheme is matched from the intelligent appliance control scheme library according to the obtained intelligent appliance control scheme number, and the intelligent appliance control is performed according to the obtained intelligent appliance control scheme. 2.The smart home based appliance control system according to claim 1, wherein, The method for analyzing the historical use data comprises the following steps: The historical use data are specified, keywords are extracted, single key data are obtained, the single key data are converted, key data coordinates are obtained, the obtained key data coordinates are input into a coordinate space, clustering is performed based on a K-means algorithm, corresponding clusters are obtained, single key data belonging to the same cluster are integrated into a key data set, the key data set is analyzed, and fixed association values between corresponding target devices are obtained. 3.The smart home based appliance control system according to claim 1, wherein, The method for establishing the matching vector space according to the intelligent appliance control scheme library comprises the following steps: Each characteristic factor interval range corresponding to the intelligent appliance control scheme is identified, the vector region corresponding to the intelligent appliance control scheme is divided in the vector space according to the identified characteristic factor interval range, an identification matching unit is set, the identification matching unit is used for identifying in which vector region the input characteristic vector is located, and the corresponding intelligent appliance control scheme number is matched according to the identified vector region. 4.The smart home based appliance control system of claim 1, wherein, The system further comprises a use correction module, which is used for dynamic correction of the associated intelligent devices according to the use data of the user. 5.The smart home based appliance control system of claim 4, wherein, The working method of the use correction module comprises the following steps: Obtaining the use record of the user to the intelligent electric appliance within a specified time, extracting and merging the use record to obtain personalized data; obtaining the associated smart device, identifying the differentiated data between the personalized data and the associated smart device, identifying the time attribute of the differentiated data, setting the dynamic correction coefficient of the differentiated data, supplementing the dynamic correction coefficient according to the to-be-selected associated device, marking the dynamic correction coefficient as CYi, and calculating the dynamic correlation value according to the dynamic correlation value formula The dynamic correlation value is calculated, wherein λ is a correction factor, and the value range is 0<λ≤1; and the dynamic adjustment of the associated smart device is performed according to the calculated dynamic correlation value. 6.The smart home based appliance control system of claim 5, wherein, For non-differentiated data supplement, the dynamic correction coefficient CYi is 1.

Images