Intelligent control method and device of Internet of Things system, equipment, storage medium and program product

Abstract

The invention discloses an intelligent control method and device of an Internet of Things system, equipment, a storage medium and a program product, and relates to the technical field of the Internet of Things, and the intelligent control method of the Internet of Things system comprises the steps: obtaining environment data of a monitoring environment based on a sensor module of an equipment layer; uploading the environment data to an application layer based on the distributed edge gateway; performing data dimension reduction processing on the environment data through an application service module of the application layer to obtain environment data features; performing feature completion based on the environmental data features to obtain complete data features; and performing data dimension raising processing on the complete data features to obtain complete data. Due to the edge gateway of the distributed framework, the stability and the safety of the Internet of Things system are improved; by supplementing the received data, the influence caused by data missing in the acquisition and transmission process is reduced.

Description

Technical Field

[0001] This application relates to the field of Internet of Things technology, and particularly to an intelligent control method, device, equipment, storage medium and program product for an Internet of Things system. Background Art

[0002] With the rapid development of technologies such as 5G, cloud computing, and artificial intelligence, the Internet of Things technology is also constantly innovating. For example, the applications of generative AI and edge intelligence in the Internet of Things are becoming more and more extensive, which not only improves efficiency, but also injects innovative vitality into traditional industries. In addition, innovative technologies such as passive Internet of Things and satellite Internet of Things are also constantly developing, which will contribute to a more diverse, full-scenario, and full-coverage mobile Internet of Things technology system.

[0003] Traditional Internet of Things systems adopt a centralized service architecture. When applied in scenarios such as smart factories and smart enterprises that require privacy and stability, problems such as data loss, data leakage, and data tampering may occur, making it difficult for the constructed Internet of Things system to meet user needs. Summary of the Invention

[0004] The main purpose of this application is to provide an intelligent control method, device, equipment, storage medium and program product for an Internet of Things system, aiming to solve the technical problem that traditional Internet of Things systems are prone to problems such as data loss, data leakage, and data tampering, making it difficult to meet user needs.

[0005] To achieve the above object, this application proposes an intelligent control method for an Internet of Things system, and the intelligent control method for the Internet of Things system includes:

[0006] Obtain environmental data of the monitored environment based on the sensor module at the device layer;

[0007] Upload the environmental data to the application layer based on a distributed edge gateway;

[0008] Perform data dimensionality reduction processing on the environmental data through the application service module at the application layer to obtain environmental data features;

[0009] Perform feature complementation based on the environmental data features to obtain complete data features;

[0010] Perform data dimensionality increase processing on the complete data features to obtain complete data.

[0011] In an embodiment, the step of uploading the environmental data to the application layer based on a distributed edge gateway includes:

[0012] Perform window detection on the environmental data based on a connection module to determine the proportion of abnormal data and the proportion of duplicate data in the environmental data;

[0013] When the proportion of the abnormal data and / or the proportion of the duplicate data exceeds a preset proportion threshold, obtain the intelligent behavior contract stored in the distributed blockchain node;

[0014] Determine a protection strategy adjustment parameter based on the intelligent behavior contract;

[0015] Determine the connection limit duration of the sensor module according to the protection strategy adjustment parameter; the connection limit duration is used to represent the interval time for receiving environmental data.

[0016] In one embodiment, after the step of determining the connection limit duration of the sensor module according to the protection strategy adjustment parameter, the method further includes:

[0017] If the connection limit duration exceeds a preset limit duration threshold, disconnect the distributed edge gateway from the sensor module and add the sensor module to the blacklist of the distributed edge gateway.

[0018] In one embodiment, the step of performing data dimensionality reduction processing on the environmental data through the application service module of the application layer to obtain environmental data features includes:

[0019] Perform standardization processing on the environmental data through the application service module of the application layer to obtain a standardized data matrix;

[0020] Construct a covariance matrix of the environmental data according to the standardized data matrix;

[0021] Perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors of the environmental data;

[0022] Project the environmental data onto the eigenvectors to obtain the dimensionality-reduced environmental data features.

[0023] In one embodiment, the step of performing feature completion on the environmental data features to obtain complete data features includes:

[0024] Identify the feature structure and potential variable relationship in the environmental data features;

[0025] Extract feature influence factors and feature common factors based on the feature structure and the potential variable relationship;

[0026] Create a missing imputation data set based on the feature influence factors and the feature common factors;

[0027] Perform feature imputation on the environmental data features based on the missing imputation data set to obtain complete data features.

[0028] In one embodiment, the step of creating a missing imputation data set based on the feature influence factor and the feature commonality factor includes:

[0029] Determining a target missing sample based on the feature influence factor and the feature commonality factor;

[0030] Analyzing the data estimation of the target missing sample based on Bayesian theory to obtain an imputation data model;

[0031] Sampling according to the imputation data model and using the model values obtained by sampling as the missing imputation data set.

[0032] In addition, to achieve the above object, the present application also proposes an intelligent control device for an Internet of Things system, and the intelligent control device for the Internet of Things system includes:

[0033] A data acquisition module, configured to acquire environmental data of a monitoring environment based on a sensor module at the device layer;

[0034] A distributed network module, configured to upload the environmental data to the application layer based on a distributed edge gateway;

[0035] A data dimensionality reduction module, configured to perform data dimensionality reduction processing on the environmental data through an application service module at the application layer to obtain environmental data features;

[0036] A data filling module, configured to perform feature filling based on the environmental data features to obtain complete data features;

[0037] A data dimensionality increase module, configured to perform data dimensionality increase processing on the complete data features to obtain complete data.

[0038] In addition, to achieve the above object, the present application also proposes an intelligent control device for an Internet of Things system, and the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the intelligent control method for the Internet of Things system as described above.

[0039] In addition, to achieve the above object, the present application also proposes a storage medium, and the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the intelligent control method for the Internet of Things system as described above are implemented.

[0040] In addition, to achieve the above object, the present application also provides a computer program product, and the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the intelligent control method for the Internet of Things system as described above are implemented.

[0041] One or more technical solutions proposed in this application have at least the following technical effects:

[0042] In this application, environmental data of the monitored environment is obtained through a sensor module at the device layer; the environmental data is uploaded to the application layer based on a distributed edge gateway; the application service module at the application layer performs data dimensionality reduction processing on the environmental data to obtain environmental data features; feature completion is performed based on the environmental data features to obtain complete data features; data dimensionality increase processing is performed on the complete data features to obtain complete data. Since a distributed architecture edge gateway is used, the stability and security of the IoT system are improved; by complementing the received data, the impact caused by data loss during the acquisition and transmission processes is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0044] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 It is a schematic flowchart provided for Embodiment 1 of the intelligent control method of the IoT system in this application;

[0046] Figure 2 It is a schematic flowchart provided for Embodiment 2 of the intelligent control method of the IoT system in this application;

[0047] Figure 3 It is a schematic flowchart provided for Embodiment 3 of the intelligent control method of the IoT system in this application;

[0048] Figure 4 It is a schematic module structure diagram of the intelligent control device of the IoT system in the embodiments of this application;

[0049] Figure 5 It is a schematic device structure diagram of the hardware operating environment involved in the intelligent control method of the IoT system in the embodiments of this application.

[0050] The implementation, functional features, and advantages of the objectives of this application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] It should be understood that the specific embodiments described here are only used to explain the technical solutions of this application and are not used to limit this application.

[0052] To better understand the technical solution of this application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0053] The main solution of the embodiment of this application is as follows: Obtain environmental data of the monitored environment based on the sensor module at the device layer; upload the environmental data to the application layer through the distributed edge gateway at the network layer; perform data dimensionality reduction processing on the environmental data through the application service module at the application layer to obtain environmental data features; perform feature completion based on the environmental data features to obtain complete data features; perform data dimensionality increase processing on the complete data features to obtain complete data.

[0054] This application provides a solution. Since an edge - type distributed gateway is used to aggregate and upload environmental data, the security and privacy protection during data are improved; by performing dimensionality reduction and completion on environmental data, the integrity and accuracy of system data are improved.

[0055] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a server, an Internet of Things system, etc., or an electronic device, a virtual device, etc. that can implement the above functions. Hereinafter, taking the Internet of Things system as an example, this embodiment and the following embodiments will be described.

[0056] Based on this, the embodiment of this application provides an intelligent control method for an Internet of Things system. Refer to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the intelligent control method for the Internet of Things system of this application.

[0057] In this embodiment, the intelligent control method for the Internet of Things system includes steps S10 to S40:

[0058] Step S10, obtain environmental data of the monitored environment based on the sensor module at the device layer;

[0059] It should be noted that the intelligent control method for the Internet of Things system in the embodiment of this application can be applied to the Internet of Things system, which may include a device layer, a network layer, and an application layer. Among them, the device layer includes the infrastructure required to build the Internet of Things system, and these infrastructures can be used to complete tasks such as environmental perception, data transmission, and data processing. The network layer is used to provide key services such as access control, protocol parsing, and transmission information processing for each basic device in the device layer. The application layer is responsible for environmental data processing and user management, and provides key services such as service interfaces and visualization interfaces.

[0060] It can be understood that the above monitoring environment is also the target monitoring environment of the Internet of Things system, such as the internal environment of a home monitored by a smart home system, the factory production line monitored by a smart industrial system, the internal environment of a hospital in a smart medical system, etc. A number of sensor modules can be set in the device layer. Through these sensor modules set in the monitoring environment, the Internet of Things system can obtain the environmental data of the monitoring environment by performing environmental perception.

[0061] Step S20: Upload the environmental data to the application layer based on the distributed edge gateway.

[0062] It can be understood that the edge gateway is also the gateway deployed on the edge side of the network in the Internet of Things system. In the embodiment of the present application, the edge gateway can be distributedly deployed on the edge side of the network, close to the data source or the user, so as to reduce the data transmission delay and improve the response speed. This distributed deployment method helps to reduce the burden on the data center in the application layer and reduces the problem that the centralized service architecture may have performance degradation or even system crash due to the large amount of data processed.

[0063] It should be noted that through the network layer of the present application, the connection between the device layer and the application layer can be realized, so as to realize data exchange. The application layer in the embodiment of the present application includes an application service module. By parsing the environmental data through this application service module, relevant application services can be provided for users.

[0064] It can be understood that in order to improve the security of the Internet of Things system, when uploading the environmental data to the application layer, operations such as verifying and encrypting the uploaded environmental data can be performed, so as to reduce risks such as data loss and data leakage during the data transmission process.

[0065] Step S30: Perform data dimensionality reduction processing on the environmental data through the application service module of the application layer to obtain environmental data features.

[0066] It can be understood that data dimensionality reduction processing is a processing method of reducing the feature dimension of environmental data from high-dimensional to low-dimensional. By performing data dimensionality reduction processing on the environmental data, representative features of the data can be extracted, and at the same time, irrelevant or redundant information can be removed, making the data more suitable for analysis, visualization, and the processing of machine learning models. By obtaining the environmental data features after dimensionality reduction, the operation load of the system can be reduced, and at the same time, it is convenient to provide data visualization services for users.

[0067] In some embodiments of the present application, the environmental data dimensionality reduction processing method of the embodiments of the present application may be a linear processing method, such as principal component analysis, linear discriminant analysis, stage singular value decomposition method, etc., or a non-linear processing method, such as autoencoder method, local linear embedding method, etc. The embodiments of the present application do not limit the environmental data dimensionality reduction processing method used, and can be selected according to the actual application situation.

[0068] Step S40: Based on the environmental data features, perform feature complementation to obtain complete data features;

[0069] Step S50: Perform data dimensionality increase processing on the complete data features to obtain complete data.

[0070] It can be understood that since different types of sensor modules, such as temperature sensing modules, humidity sensing modules, barometric pressure sensor modules, etc., can be set in the environment in practical applications, the environmental data collected usually includes data in multiple dimensions, such as temperature data, humidity data, barometric pressure data, etc. During the process of data collection and transmission, due to reasons such as equipment failures, unstable signals, and data transmission disconnections, the environmental data received by the application layer may be missing, resulting in a decrease in data quality and affecting the accuracy of applications such as data analysis and model prediction.

[0071] In some implementation manners of the embodiments of the present application, after receiving the environmental data and performing dimensionality reduction processing, the application service module can perform feature complementation on the environmental data features obtained by the dimensionality reduction processing, thereby improving the integrity of the data. Exemplarily, the feature complementation methods adopted in the embodiments of the present application may include interpolation method, model-based complementation method, proximity complementation, etc. The embodiments of the present application do not limit this.

[0072] It can be understood that the complete data features obtained after complementation can be used as features for applications such as data analysis and model prediction.

[0073] It should be understood that by performing dimensionality increase processing on the complete data features, complete data after dimensionality increase can be obtained. By storing and managing this complete data, applications such as data traceability and historical data analysis can be realized.

[0074] In the embodiment of the present application, environmental data of the monitored environment is acquired through a sensor module based on the device layer; the environmental data is uploaded to the application layer based on a distributed edge gateway; the environmental data is subjected to data dimensionality reduction processing through an application service module in the application layer to obtain environmental data features; feature completion is performed based on the environmental data features to obtain complete data features; and data dimensionality increase processing is performed on the complete data features to obtain complete data. Since a distributed architecture edge gateway is used, the stability and security of the Internet of Things system are improved; and by complementing the received data, the impact caused by data loss during the acquisition and transmission processes is reduced.

[0075] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as that in the above-mentioned first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2 , the step of uploading the environmental data to the application layer based on the distributed edge gateway includes:

[0076] Step S21, window detection is performed on the environmental data based on a connection module to determine the proportion of abnormal data and the proportion of duplicate data in the environmental data.

[0077] It should be noted that in the network layer of the embodiment of the present application, a connection module may be included. This connection module can connect two terminals (such as a collection module and an edge gateway, an edge gateway and a server, etc.) and detect the transmitted environmental data, so as to identify duplicate data and abnormal data therein, and then disconnect some irrelevant data and device terminals with problems. Specifically, the connection module of the embodiment of the present application can construct a number of consecutive detection windows based on the data transmission process of two connected terminals. This detection window can perform window detection on the environmental data received by the distributed edge gateway, thereby realizing the abnormal detection and statistics of the environmental data.

[0078] In some implementation manners of the embodiment of the present application, the detection time length of the detection window may be fixed, or may be set according to parameters such as the capacity and type of the acquired environmental data. The embodiment of the present application does not limit this. For each set detection window, the detected data can be recognized as environmental data.

[0079] It should be noted that by setting a detection window to detect a piece of environmental data, the proportion of abnormal data and the proportion of duplicate data in the environmental data can be determined. By comparing the proportion of abnormal data and the proportion of duplicate data with a preset proportion threshold, it can be determined whether the environmental data in this detection window is attack data. Specifically, step S22, when the proportion of abnormal data and / or the proportion of duplicate data exceeds the preset proportion threshold, obtain the intelligent behavior contract stored in the distributed blockchain.

[0080] It can be understood that the above preset ratio threshold is also the ratio threshold set in advance, and this ratio threshold may include the abnormal data ratio threshold, the duplicate data ratio threshold, and the data sum ratio threshold. When the ratio of abnormal data is greater than the abnormal data ratio threshold and / or the ratio of duplicate data is greater than the duplicate data ratio threshold and / or the sum of the ratio of abnormal data and the ratio of duplicate data is greater than the data sum ratio threshold, it can be considered that the received environmental data is attack data. At this time, the intelligent behavior contract stored in the distributed blockchain can be obtained.

[0081] It should be noted that in the embodiments of the present application, by combining blockchain technology and Internet of Things applications, the security of the Internet of Things system is improved. Specifically, in the embodiments of the present application, without relying on a traditional data center, devices that communicate with each other (such as distributed edge gateways, cloud servers in the application layer, device terminals in the device layer, etc.) can all be used as distributed blockchain nodes to construct a decentralized Internet of Things system.

[0082] It can be understood that the intelligent behavior contract, that is, the smart contract, is a computer program that can automatically execute relevant functions and business logics according to the contract content when triggered, and it has the characteristics of automatic execution and non-modifiability. The process of data processing can be predefined therein, so as to realize various services such as access control and traceability analysis.

[0083] It should be understood that each of the distributed blockchain nodes may include intelligent behavior contracts, and these intelligent behavior contracts may be the same or different, and the embodiments of the present application do not limit this. Through the obtained intelligent behavior contract, the protection strategy adjustment parameters can be determined. That is, step S23, determining the protection strategy adjustment parameters based on the intelligent behavior contract.

[0084] It should be noted that by executing the analysis process corresponding to the intelligent contract on the abnormal environmental data, the update of the protection adjustment parameters of the two connection terminals (the sending end and the receiving end) corresponding to the connection module (specifically, the protection adjustment parameters of the receiving end) can be performed, and then the connection limit duration of the two connection terminals (specifically, the connection limit duration of the receiving end) can be determined.

[0085] It should be noted that the above two connection terminals in the embodiments of the present application can be any two infrastructures in the Internet of Things system, such as a sensor module and a distributed edge gateway, a sensor module and a sensor module, a distributed edge gateway and a server, etc. The embodiments of the present application do not limit this. In the embodiments of the present application, the sensor module and the distributed edge gateway are taken as two connection terminals of the connection module as an example to describe the solution of the present application in detail. That is, in some embodiments of the present application, after step S23, the following steps are further included: step S24, determining the connection limit duration of the sensor module according to the protection policy adjustment parameter; the connection limit duration is used to represent the interval time for receiving environmental data.

[0086] It should be noted that the above protection policy adjustment parameter is also the parameter used to adjust the protection policy in the connection terminal. Specifically, the protection policy of the embodiments of the present application can be expressed by the following formula:

[0087] S = {N, M, d, p, t};

[0088] Wherein, S is used to represent the protection policy, N is used to represent the timestamp when the last attack data appears, M is used to represent the timestamp when the current attack data appears, p is used to represent the protection policy adjustment parameter, d is used to represent the connection limit duration, and t is used to represent the disconnection time.

[0089] It should be noted that by monitoring the timestamps of the attack data in the environmental data, the attack data occurrence frequency of the sensor module that sends the environmental data can be determined. Based on this attack data occurrence frequency, a new protection policy adjustment parameter can be generated, and then the connection limit duration can be adjusted based on the new protection policy adjustment parameter. For the determination method of the protection policy adjustment parameter, it can be generated based on a machine learning model or obtained based on other methods. The embodiments of the present application do not limit this.

[0090] In some embodiments of the present application, the method for obtaining the protection policy adjustment parameter can be as follows:

[0091]

[0092] Wherein, represents the protection policy adjustment parameter before adjustment, p is used to represent the protection policy adjustment parameter after adjustment, and α is used to represent the adjustment weight coefficient, and this adjustment weight coefficient can be set according to requirements.

[0093] It can be understood that the growth rate of the protection policy adjustment parameter is related to the time interval since the last appearance of the attack data, that is, the more frequently the attack data appears, the faster the protection policy adjustment parameter grows.

[0094] It should be noted that in the embodiments of the present application, the larger the protection policy adjustment parameter is, the longer the connection limit duration is. In some embodiments of the present application, the relationship between the protection policy adjustment parameter and the connection limit duration can be referred to the following formula:

[0095]

[0096] Wherein, d is used to represent the adjusted connection limit duration, is used to represent the connection limit duration before adjustment, and β is used to represent the adjustment weight coefficient of the connection limit duration. The adjustment weight coefficient is a positive number and its value can be set according to actual applications.

[0097] It can be understood that as the number of occurrences of the attack data detected by the sensor module increases, the limit duration will gradually increase. In some embodiments of the present application, after the step of determining the connection limit duration of the sensor module according to the protection policy adjustment parameter, the following steps are further included:

[0098] If the connection limit duration exceeds the preset limit duration threshold, disconnect the connection between the distributed edge gateway and the sensor module and add the sensor module to the blacklist of the distributed edge gateway.

[0099] It can be understood that when the connection limit duration exceeds the preset limit duration threshold, it can indicate that the frequency of the attack data appearance is too high or the number of occurrences of the attack data is too large. At this time, it can be considered that the sensor module may have a device failure or be a false malicious terminal. Therefore, it can be added to the blacklist accordingly. For the terminals in the blacklist, their access can be prohibited, thereby improving the security of the system.

[0100] In the embodiments of the present application, by performing window detection on the environmental data based on the connection module, the proportion of abnormal data and the proportion of duplicate data in the environmental data are determined; when the proportion of abnormal data and / or the proportion of duplicate data exceed the preset proportion threshold, the intelligent behavior contract stored in the distributed blockchain node is obtained; the protection policy adjustment parameter is determined based on the intelligent behavior contract; the connection limit duration of the sensor module is determined according to the protection policy adjustment parameter; the connection limit duration is used to represent the interval time for receiving environmental data. Since the environmental data is identified and detected, when the proportion of abnormal data and / or the proportion of duplicate data exceed the preset proportion threshold, the protection policy is adjusted through the intelligent contract, the new protection policy adjustment parameter is determined, and then the connection limit duration is modified, thereby improving the data security of the Internet of Things system.

[0101] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the content that is the same as or similar to the above-mentioned embodiment 1 and / or embodiment 2 can be referred to the above introduction and will not be described in detail hereinafter. On this basis, please refer to Figure 3 The step of performing dimensionality reduction processing on the environmental data through the application service module of the application layer to obtain environmental data features includes:

[0102] Step S31, performing standardization processing on the environmental data through the application service module of the application layer to obtain a standardized data matrix.

[0103] Step S32, constructing a covariance matrix of the environmental data according to the standardized data matrix.

[0104] It should be noted that data standardization processing is a common data preprocessing method. By converting the original environmental data into new data with specific attributes, the differences between the environmental data collected by different sensor modules in the same dimension can be eliminated. Further, a covariance matrix is constructed based on the standardized data matrix, so that the environmental data has better mathematical properties, facilitating subsequent data analysis and feature extraction steps.

[0105] Step S33, performing eigenvalue decomposition on the covariance matrix to obtain the eigenvectors of the environmental data.

[0106] Step S34, projecting the environmental data onto the eigenvectors to obtain the dimensionality-reduced environmental data features.

[0107] It should be noted that by performing eigenvalue decomposition on the covariance matrix, the eigenvalues in each feature direction of the environmental data and the eigenvectors corresponding to the eigenvalues can be obtained. It can be understood that the eigenvalues can represent the variances in each feature direction, and the eigenvectors represent the weights in the corresponding feature directions. By projecting the original environmental data onto each feature direction, the dimensionality-reduced environmental data features can be obtained.

[0108] In some implementation manners of the embodiments of the present application, by sorting the eigenvalues in descending order, and a preset number of eigenvalues can be selected from the sorted eigenvalues as the principal components of the environmental data. By projecting the original environmental data onto the selected feature directions, the dimensionality-reduced environmental data features can be obtained. By analyzing the dimensionality-reduced data, the structure and features of the data can be analyzed more intuitively.

[0109] In some implementation manners of the embodiments of the present application, in order to complement the environmental data features, the step of performing feature complementation based on the environmental data features to obtain complete data features includes:

[0110] Identify the feature structure and potential variable relationships in the environmental data features;

[0111] Extract feature impact factors and feature commonality factors based on the feature structure and the potential variable relationships;

[0112] Create a missing imputation data set based on the feature impact factors and the feature commonality factors;

[0113] Perform feature imputation on the environmental data features based on the missing imputation data set to obtain complete data features.

[0114] It should be noted that factor analysis can be performed on the dimensionality-reduced environmental data features to identify the structures and potential variable relationships existing in the data. Potential factors of the environmental data features are extracted through factor analysis methods such as principal component analysis or maximum likelihood estimation, and then the feature structure and potential variable relationships in the environmental data features are determined.

[0115] It can be understood that the above feature structure can be used to represent attributes such as the eigenvalue changes of each feature of the environmental data. The above potential variable relationships are used to represent the hidden attributes or hidden relationships between each feature of the environmental data (such as light and temperature, humidity and temperature, etc.). Through the feature structure and potential variable relationships, the connections between the data can be better understood, so as to better model the data generation process.

[0116] It should be noted that the above feature impact factors are also the potential variable relationships that have an important impact on the feature structure, and the above feature commonality factors are also the potential variable relationships between the environmental data features that may be related. The feature impact factors and feature commonality factors can be extracted by using a neural network model or other methods, and the embodiments of the present application do not limit this.

[0117] Further, the step of creating a missing imputation data set based on the feature impact factors and the feature commonality factors includes:

[0118] Determine the target missing samples based on the feature impact factors and the feature commonality factors;

[0119] Analyze the data estimation of the target missing samples based on Bayesian theory to obtain an imputation data model;

[0120] Sample according to the imputation data model and use the model values obtained by sampling as the missing imputation data set.

[0121] It should be noted that for environmental data features with internal connections, their change features often have correlations. Based on the feature influence factors and feature common factors between these environmental data features, it is possible to determine whether there are missing data. If so, it is possible to determine which environmental data features are missing, which parts of the environmental data features are missing, and the corresponding probabilities, that is, to determine the target missing samples.

[0122] It should be explained that a prior distribution can be set for the target missing samples when determining them, and this prior distribution can be set according to the historically collected environmental data. Further, a likelihood function of the target missing samples can be constructed based on the feature common factors between the associated features to describe the relationship between the known data and the missing data. Based on the prior distribution and the likelihood function, the posterior distribution of the target missing data can be calculated, and this posterior distribution can be used as the obtained imputation data model. By sampling the values in the imputation data model, model values can be obtained, and the obtained model values can be used as missing values to impute the target missing samples, that is, the model values obtained by sampling can be used as the missing imputation data set.

[0123] In the embodiment of the present application, the application service module of the application layer performs standardization processing on the environmental data to obtain a standardized data matrix; constructs a covariance matrix of the environmental data according to the standardized data matrix; performs eigenvalue decomposition on the covariance matrix to obtain the eigenvectors of the environmental data; projects the environmental data onto the eigenvectors to obtain the environmental data features after dimensionality reduction. Since the collected environmental data is processed to facilitate data completion, problems such as low data value and abnormal data analysis results caused by data missing are reduced.

[0124] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the intelligent control method of the Internet of Things system of the present application. Based on this technical concept, more forms of simple transformations are within the protection scope of the present application.

[0125] The present application also provides an intelligent control device for an Internet of Things system. Please refer to Figure 4 The intelligent control device of the Internet of Things system includes:

[0126] A data acquisition module 10, configured to acquire environmental data of a monitored environment based on a sensor module of a device layer;

[0127] A distributed network module 20, configured to upload the environmental data to an application layer based on a distributed edge gateway;

[0128] A data dimensionality reduction module 30, configured to perform data dimensionality reduction processing on the environmental data through an application service module of the application layer to obtain environmental data features;

[0129] The data completion module 40 is configured to perform feature completion based on the environmental data features to obtain complete data features;

[0130] The data dimension elevation module 50 is configured to perform data dimension elevation processing on the complete data features to obtain complete data. The intelligent control device of the Internet of Things system provided by this application adopts the intelligent control method of the Internet of Things system in the above embodiment, and can solve the technical problem that the traditional Internet of Things system is prone to problems such as data loss, data leakage, and data tampering, making it difficult to meet user requirements. Compared with the prior art, the beneficial effects of the intelligent control device of the Internet of Things system provided by this application are the same as those of the intelligent control method of the Internet of Things system provided by the above embodiment, and other technical features in the intelligent control device of the Internet of Things system are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0131] This application provides an intelligent control device for an Internet of Things system. The intelligent control device for the Internet of Things system includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the intelligent control method of the Internet of Things system in Embodiment 1 above.

[0132] Next, refer to Figure 5 , which shows a schematic structural diagram of an intelligent control device for an Internet of Things system suitable for implementing the embodiments of this application. The intelligent control device for the Internet of Things system in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The intelligent control device for the Internet of Things system shown is only an example, and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0133] As Figure 5As shown in the figure, the intelligent control device of the Internet of Things system may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the intelligent control device of the Internet of Things system are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the intelligent control device of the Internet of Things system to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows the intelligent control device of the Internet of Things system with various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems can be alternatively implemented or had.

[0134] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0135] The intelligent control device of the Internet of Things system provided by the present application adopts the intelligent control method of the Internet of Things system in the above embodiments, and can solve the technical problem that the traditional Internet of Things system is prone to problems such as data loss, data leakage, and data tampering, making it difficult to meet the user's needs. Compared with the prior art, the beneficial effects of the intelligent control device of the Internet of Things system provided by the present application are the same as those of the intelligent control method of the Internet of Things system provided by the above embodiments, and the other technical features in the intelligent control device of the Internet of Things system are the same as those disclosed in the method of the previous embodiment, and will not be elaborated here.

[0136] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0137] As described above, the above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0138] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the intelligent control method of the Internet of Things system in the above embodiments.

[0139] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, system or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0140] The above computer-readable storage medium can be included in the intelligent control device of the Internet of Things system; it can also exist separately without being assembled into the intelligent control device of the Internet of Things system.

[0141] The above computer-readable storage medium carries one or more programs, which, when executed by the intelligent control device of the Internet of Things system, cause the intelligent control device of the Internet of Things system to:

[0142] Obtain environmental data of the monitored environment based on the sensor module at the device layer;

[0143] Upload the environmental data to the application layer based on the distributed edge gateway;

[0144] Perform data dimensionality reduction processing on the environmental data through the application service module at the application layer to obtain environmental data features;

[0145] Perform feature completion based on the environmental data features to obtain complete data features;

[0146] Perform data dimensionality increase processing on the complete data features to obtain complete data.

[0147] Computer program code for performing the operations of the present application can be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++, and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN: Local Area Network) or a wide area network (WAN: Wide Area Network) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0148] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0149] The modules described in the embodiments of the present application can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0150] The readable storage medium provided by the present application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the intelligent control method of the above-mentioned Internet of Things system, which can solve the technical problems that traditional Internet of Things systems are prone to data loss, data leakage, data tampering, etc., resulting in difficulty in meeting user requirements. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the intelligent control method of the Internet of Things system provided by the above embodiments, and will not be elaborated here.

[0151] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the intelligent control method of the Internet of Things system as described above.

[0152] The computer program product provided by the present application can solve the technical problems that traditional Internet of Things systems are prone to data loss, data leakage, data tampering, etc., resulting in difficulty in meeting user requirements. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the intelligent control method of the Internet of Things system provided by the above embodiments, and will not be elaborated here.

[0153] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. An intelligent control method for an Internet of Things system, characterized in that, The method includes: Obtaining environmental data of the monitored environment based on the sensor module at the device layer; Uploading the environmental data to the application layer based on the distributed edge gateway; Performing data dimensionality reduction processing on the environmental data through the application service module at the application layer to obtain environmental data features; Performing feature completion based on the environmental data features to obtain complete data features; Performing data dimensionality increase processing on the complete data features to obtain complete data.

2. The intelligent control method of the Internet of Things system according to claim 1, characterized in that, The step of uploading the environmental data to the application layer based on the distributed edge gateway includes: Performing window detection on the environmental data based on the connection module to determine the proportion of abnormal data and the proportion of duplicate data in the environmental data; When the proportion of abnormal data and / or the proportion of duplicate data exceeds a preset proportion threshold, obtaining the intelligent behavior contract stored in the distributed blockchain node; Determining the protection policy adjustment parameter based on the intelligent behavior contract; Determining the connection limit duration of the sensor module according to the protection policy adjustment parameter; the connection limit duration is used to represent the interval time for receiving environmental data.

3. The intelligent control method of the Internet of Things system according to claim 2, characterized in that, After the step of determining the connection limit duration of the sensor module according to the protection policy adjustment parameter, it further includes: If the connection limit duration exceeds the preset limit duration threshold, disconnecting the connection between the distributed edge gateway and the sensor module and adding the sensor module to the blacklist of the distributed edge gateway.

4. The intelligent control method of the Internet of Things system according to claim 1, characterized in that, The step of performing data dimensionality reduction processing on the environmental data through the application service module at the application layer to obtain environmental data features includes: Performing standardization processing on the environmental data through the application service module at the application layer to obtain a standardized data matrix; Constructing the covariance matrix of the environmental data according to the standardized data matrix; Performing eigenvalue decomposition on the covariance matrix to obtain the eigenvectors of the environmental data; Projecting the environmental data onto the eigenvectors to obtain the dimensionality-reduced environmental data features.

5. The intelligent control method of the Internet of Things system according to claim 4, characterized in that, The step of performing feature completion based on the environmental data features to obtain complete data features includes: Identifying the feature structure and potential variable relationship in the environmental data features; Extracting feature influence factors and feature common factors based on the feature structure and the potential variable relationship; Creating a missing imputation data set based on the feature influence factors and the feature common factors; Performing feature imputation on the environmental data features based on the missing imputation data set to obtain complete data features.

6. The intelligent control method of the Internet of Things system according to claim 5, characterized in that, The step of creating a missing imputation data set based on the feature influence factors and the feature common factors includes: Determining the target missing samples based on the feature influence factors and the feature common factors; Analyzing the data estimation of the target missing samples based on the Bayesian theory to obtain an imputation data model; Sampling according to the imputation data model and using the sampled model values as the missing imputation data set.

7. An intelligent control device for an Internet of Things system, characterized in that, The intelligent control device of the Internet of Things system includes: A data acquisition module for obtaining environmental data of the monitored environment based on the sensor module at the device layer; A distributed network module for uploading the environmental data to the application layer based on the distributed edge gateway; A data dimensionality reduction module, configured to perform data dimensionality reduction processing on the environmental data through the application service module of the application layer to obtain environmental data features; A data completion module, configured to perform feature completion based on the environmental data features to obtain complete data features; A data dimensionality increase module, configured to perform data dimensionality increase processing on the complete data features to obtain complete data.

8. An intelligent control device for an Internet of Things system, characterized in that, The device includes: a memory, a processor, and an intelligent control program of the Internet of Things system stored on the memory and executable on the processor, and the intelligent control program of the Internet of Things system is configured to implement the steps of the intelligent control method of the Internet of Things system according to any one of claims 1 to 6.

9. A storage medium, characterized in that, An intelligent control program of the Internet of Things system is stored on the storage medium, and when the intelligent control program of the Internet of Things system is executed by a processor, the steps of the intelligent control method of the Internet of Things system according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the intelligent control method of the Internet of Things system according to any one of claims 1 to 6 are implemented.

Images