A smart home-related integrated supervision system and method based on the Internet of Things

Abstract

The present invention discloses a smart home association integrated supervision system and method based on the Internet of Things, which relates to the technical field of Internet of Things device management, obtains the connection relationship and transmitted data information of Internet of Things devices, performs vector processing on the data information, classifies the data processing methods of Internet of Things devices according to the difference between the information vectors before and after the processing, obtains all the data information generated in the process of a certain task, calculates the first evaluation coefficient of the data information according to the data processing method of the Internet of Things devices and the distribution of the data processing results in the link of data information transmission, classifies the data information, calculates the second evaluation coefficient corresponding to each type of data information according to the influence range of each type of data information propagated in the network, obtains the occurrence frequency of each task, calculates the evaluation value of the data information according to the first evaluation coefficient and the second evaluation coefficient, and arranges the data information into a data information sequence.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things device management, and in particular to a smart home associated integrated supervision system and method based on the Internet of Things. Background Art

[0002] With the development of Internet of Things technology, smart home Internet of Things devices are used in more and more scenarios in people's daily lives. A large amount of data is acquired and transmitted in the home network environment. Home Internet of Things devices need to collect the life data of family members, so it is necessary to uniformly supervise the data transmitted in home Internet of Things devices, and it is necessary to distinguish between the public data in the home Internet of Things data and the data that only specific Internet of Things devices have the right to use.

[0003] Common methods for protecting data security include digital encryption and device whitelisting, but these two methods require manual setting of management rules for IoT devices. When new IoT devices are added, management rules need to be set for each newly added IoT device, which hinders the scalability of IoT devices and affects users' use of IoT devices. Summary of the invention

[0004] The purpose of the present invention is to provide a smart home associated integrated supervision system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solution: a smart home associated integrated supervision method based on the Internet of Things.

[0006] Methods include:

[0007] Step S100: in an IoT platform including several IoT devices, obtaining the connection relationship and transmitted data information of the IoT devices, wherein the IoT devices are smart home IoT devices, vectorizing the data information, and classifying the data processing methods of the IoT devices according to the differences between the information vectors before and after the processing;

[0008] Step S200: obtaining the operation log of the management system in the IoT platform, obtaining all data information generated by the IoT device in the process of executing the task assigned by the management system, and calculating the first evaluation coefficient of the data information according to the data processing mode of the IoT device and the distribution of the data processing result in the transmission link;

[0009] Step S300: classify the data information, calculate the proportion of each type of data information in all the data information, and calculate the second evaluation coefficient corresponding to each type of data information in combination with the influence range of each type of data information propagated in the network;

[0010] Step S400: acquiring the occurrence frequency of each task from the operation record of the network, collecting the first evaluation coefficient and the second evaluation coefficient of the data information, calculating the evaluation value of the data information, and arranging the data information into a data information sequence according to the evaluation value;

[0011] Step S500: extract the first several items of data information from the data information sequence, collect the data features contained in the data information, merge the data features into a data feature set, and feed back to the relevant administrator.

[0012] Furthermore, step S100 includes:

[0013] Step S101: obtaining data content contained in data information, and performing vector processing on the data information according to the data content to obtain a data vector corresponding to each piece of data information;

[0014] Step S102: For any IoT device, obtain a data vector a corresponding to a piece of data information input into any IoT device, obtain data information output after being processed by any IoT device, a data vector b corresponding to a piece of output data information, and calculate the difference γ between data vector a and data vector b ab ;

[0015] Step S103: Obtain a difference management threshold of any IoT device. When the difference between the data vector corresponding to the input data information and the data vector corresponding to the output data information is greater than the difference management threshold, the IoT device determines the processing method of the output data as the first type of processing method. When the difference between the data vector corresponding to the input data information and the data vector corresponding to the output data information is less than or equal to the difference management threshold, the IoT device determines the processing method of the output data as the first type of processing method or the second type of processing method.

[0016] Generally speaking, there are two ways for IoT devices to process data information. One is to perform corresponding operations or feedback based on the data information, and the other is to forward the data information. For the first data processing method, which is also the first type of processing method in the solution, since the output result obtained by the IoT device after operation and data processing is significantly different from the input data, for the second type of processing method in the solution, the IoT device only forwards the input data information to the next IoT device, and performs relatively few operations on the input information, so the difference between the output data information and the input data information will be relatively small.

[0017] Further, step S200 includes:

[0018] Step S201: acquiring data information transmitted in the network from the occurrence of any task E to the end of any task E, and collecting data vectors corresponding to each piece of data information into a data vector set UE;

[0019] Step S202: Obtain i output links of a certain IoT device D in the network, obtain the data information corresponding to each output link, wherein each output link corresponds to a piece of data information, and collect the data vectors corresponding to each piece of data information into the output vector set OP D ;

[0020] Step S203: Obtain the data vector and set OP corresponding to the input data information of the input IoT device D D The difference of each data vector in is classified according to the first processing method and the second processing method of the IoT device D, where the number of data vectors obtained by the first processing method is i1, and the number of data vectors obtained by the second processing method is i2. The condition i1+i2=i is satisfied, and the first node coefficient α1 and the second node coefficient α2 of the IoT device D are calculated, where α1=i2 / i, α2=i1 / i;

[0021] Each IoT device is regarded as a node in the IoT network. The node coefficient is used to distinguish the working mode of the IoT device. When an IoT device mainly works in the second type of data processing mode, it means that the IoT device is more involved in forwarding and less involved in data processing. Therefore, the possibility of data passing through such an IoT device carrying user private data is low; when an IoT device mainly works in the first type of data processing mode, it means that the IoT device will participate in the actual processing of many data and produce specific data results. The difference between such specific data results and the input data information is greater, and the possibility of containing user feature information is greater;

[0022] The scheme needs to select data that is widely disseminated in the IoT device network. For the formula α1=i2 / i, when the proportion of the second type of processing method is larger, the value of the first node α1 will be larger, and it will be easier to be screened out in the subsequent sorting process;

[0023] Step S204: Sort the differences obtained in step S203 from high to low to obtain a difference sorting sequence, and calculate the ratio of the sequence number of each data vector in the difference sorting sequence to the total number of data vectors in the sorting sequence, where the ratio is the link weight corresponding to each data vector;

[0024] The output end of an IoT device may have more than one downstream device, or an IoT device may have more than one output end. After the data is processed, the results sent to different downstream devices may also be different. The data information output by the same IoT device is further screened to further screen out the information with relatively small differences from the input end, that is, the output data with relatively small operation of the IoT device is given a relatively high weight, which is easier to be screened out in the subsequent screening process;

[0025] Step S205: Obtain the processing method corresponding to the j-th data vector in the data vector set UE, and calculate the first evaluation coefficient k corresponding to the j-th data vector j 1, where k j 1=α×β j , α represents the node coefficient. When the jth data vector corresponds to the first type of processing method, α takes α1, and when the jth data vector corresponds to the second type of processing method, α takes α2. j represents the link weight corresponding to the jth data vector;

[0026] The first evaluation coefficient evaluates the working status of IoT devices from two dimensions. One is the working status of IoT devices themselves, and the other is the output result of Wuliangye devices.

[0027] Furthermore, step S300 includes:

[0028] Step S301: clustering the data vectors in the data vector set UE by using a clustering algorithm to obtain n categories of data vectors;

[0029] Step S302: obtaining a network topology of the IoT devices according to the connection relationship of the IoT devices, obtaining a total number num of device connection segments of the IoT devices in the network topology, wherein the device connection segment includes at least two IoT devices, and obtaining a data vector corresponding to data information existing in each device connection segment during the process from the start to the end of any task E;

[0030] The clustering algorithm is used to evaluate the distribution of data information vectors from the perspective of event results. Two points are considered. One is the proportion of the data category itself. When the number of data vectors in a data category is large, it means that the information contained in this type of data vector needs to flow into more IoT devices. On the other hand, considering the network link where the data information flows, some data may have a wide impact in a local network link, but rarely appear in the overall network link. There is still a high possibility that such data information contains user private information, so it is necessary to further screen the information data through the distribution of different categories of information in the network link;

[0031] Step S303: Obtain the device connection segments in which the data vector corresponding to the nrth category appears in all device connection segments during the process, and record the number of device connection segments as lin nr , calculate the link distribution coefficient L of the nrth category nr , L nr =lin nr / num;

[0032] Step S304: Obtain the number of data vectors h in the nrth category nr , the total number of data vectors in the data vector set UE H UE , calculate the data proportion coefficient B corresponding to the nrth category nr , B nr =h nr / H UE ;

[0033] Step S305: Calculate the second evaluation coefficient k corresponding to each data vector in the nrth category nr 2, k nr 2=L nr +B nr .

[0034] Furthermore, step S400 includes:

[0035] Step S401: Obtain the first evaluation coefficient k of the mth data vector in the data vector set UE m 1 and the second evaluation coefficient k m 2. Calculate the evaluation value μ of the mth data vector m , μ m =k m 1+k m 2;

[0036] After two rounds of screening, each data vector is assigned two values: one is the first evaluation coefficient corresponding to the process of IoT devices processing events, and the other is the second evaluation coefficient corresponding to the inventory of information distribution and information coverage after the network completes the event. The larger these two coefficients are, the more devices know the information contained in the data vector during the transmission process. From another perspective, in a certain IoT network, the information contained in the data vector is essential information for this network;

[0037] Step S402: obtaining evaluation values ​​corresponding to each data vector in the data vector set UE, arranging the evaluation values ​​from large to small, and aggregating the arranged evaluation values ​​to obtain a data information sequence.

[0038] Furthermore, step S500 includes:

[0039] Step S501: collect the first p data vectors in the data information sequence into a feature vector set V, and obtain the data content corresponding to each data vector in the feature vector set, where the set corresponding to the data content of the g-th data vector is sub g ;

[0040] Step S502: Calculate the content set U composed of the common parts of the data contents corresponding to all feature vectors in the feature vector set, U=sub1∪sub2∪sub3∪…∪sub p , where sub1, sub2, sub3, ... and sub p , respectively represent the first, second, third, ... and pth feature vector sets in the feature vector set V;

[0041] Step S503: Push the data content in U to the relevant administrator;

[0042] To filter out the widely disseminated data in IoT devices, one is to establish a database and push it to the newly added IoT devices so that the newly added IoT devices have a similar processing method as the original IoT devices, thereby enhancing the consistency of collaboration between IoT devices. On the other hand, non-privacy data can be separated from all data, so that the remaining privacy data can be better protected.

[0043] In order to better implement the above method, a smart home related integrated supervision system based on the Internet of Things is also proposed, the system includes:

[0044] A mode management module, a first evaluation coefficient calculation module, a second evaluation coefficient calculation module, an information sequence management module and a feature feedback module, wherein the mode management module is used to classify the data processing mode of the IoT device, the first evaluation coefficient calculation module is used to calculate the first evaluation coefficient, the second evaluation coefficient calculation module is used to calculate the second evaluation coefficient, the information sequence management module is used to arrange the data information into a data information sequence according to the evaluation value, and the feature feedback module is used to collect the features in the data information and feed them back to the relevant management personnel;

[0045] Furthermore, the mode management module includes: a vectorization unit, a difference calculation unit and a classification management unit, wherein the vectorization unit is used to vectorize the data transmitted in the Internet of Things network, the difference calculation unit is used to calculate the difference between the input data vector and the output data vector, and the classification management unit is used to classify different processing modes of the Internet of Things devices;

[0046] Further, the first evaluation coefficient calculation module includes: a difference management unit, a node coefficient calculation unit, a link weight calculation unit and a first evaluation coefficient calculation unit, wherein the difference management unit is used to collect the difference between the output data vector and the input data vector, the node coefficient calculation unit is used to calculate the node coefficient, the link weight calculation unit is used to calculate the link weight, and the first evaluation coefficient calculation unit is used to calculate the first evaluation coefficient;

[0047] Further, the second evaluation coefficient calculation module includes: a clustering calculation unit, a connection management unit, a link distribution coefficient calculation unit, a data proportion coefficient calculation unit and a second evaluation coefficient calculation unit, wherein the clustering calculation unit is used to cluster the data vectors in the data vector set UE, the connection management unit is used to obtain the number of device connection segments of the Internet of Things device in the network topology, the link distribution coefficient calculation unit is used to calculate the link distribution coefficient, the data proportion coefficient calculation unit is used to calculate the data proportion coefficient, and the second evaluation coefficient calculation unit is used to calculate the second evaluation coefficient;

[0048] Further, the information sequence management module includes: an evaluation value calculation unit and a data information sequence management unit, wherein the evaluation value calculation unit is used to calculate the evaluation value of each data vector, and the data information sequence management unit is used to collect the arranged evaluation values ​​to obtain a data information sequence;

[0049] Furthermore, the feature feedback module includes: a content analysis unit, a content collection management unit and an information push unit. The content analysis unit is used to obtain the data information sequence by collecting the arranged evaluation values. The content collection management unit is used to manage the content collection. The information push unit is used to push the relevant data content to the relevant administrator.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention analyzes the data information transmitted in the IoT device, obtains the difference in the data information before and after processing and the distribution pattern of similar information in the network, evaluates the scope of information dissemination, distinguishes widely disseminated information from information transmitted to specific devices, and uniformly supervises the information transmitted in the home IoT. By means of information feature aggregation, data information is managed and the scalability and usability of the home IoT are guaranteed, which also reduces the difficulty of realizing data management by configuring firewalls or encryption and decryption systems, and can also meet the usage habits of different home users for IoT devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 This is a schematic diagram of the structure of a smart home-related integrated supervision system based on the Internet of Things in the present invention;

[0053] Figure 2 It is a flow chart of a smart home-related integrated supervision method based on the Internet of Things in the patent of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 and Figure 2 , the present invention provides a technical solution:

[0056] Step S100: in an IoT platform including several IoT devices, obtaining the connection relationship and transmitted data information of the IoT devices, wherein the IoT devices are smart home IoT devices, vectorizing the data information, and classifying the data processing methods of the IoT devices according to the differences between the information vectors before and after processing;

[0057] Wherein, step S100 includes:

[0058] Step S101: obtaining data content contained in data information, and performing vector processing on the data information according to the data content to obtain a data vector corresponding to each piece of data information;

[0059] In an embodiment, a data vector corresponding to the data information is obtained by hot encoding the data content included in the data information or the instruction included in the data information, or the data information is vectorized according to semantics through a semantic instruction conversion model, such as a bag-of-words model;

[0060] Step S102: For any IoT device, obtain a data vector a corresponding to a piece of data information input into any IoT device, obtain data information output after being processed by any IoT device, a data vector b corresponding to a piece of output data information, and calculate the difference γ between data vector a and data vector b ab ;

[0061] During the implementation process, when a certain IoT device has more than one input information data, information aggregation is performed on the information data input simultaneously. The information aggregation method includes feature extraction of vector groups, vector addition, or definition of new vectors based on aggregated information.

[0062] Step S103: Obtain a difference management threshold of any IoT device. When the difference between the data vector corresponding to the input data information and the data vector corresponding to the output data information is greater than the difference management threshold, the IoT device's processing method for the output data is determined to be a first type of processing method. When the difference between the data vector corresponding to the input data information and the data vector corresponding to the output data information is less than or equal to the difference management threshold, the IoT device's processing method for the output data is determined to be either a first type of processing method or a second type of processing method.

[0063] Step S200: obtaining the operation log of the management system in the IoT platform, obtaining all data information generated by the IoT device in the process of executing the task assigned by the management system, and calculating the first evaluation coefficient of the data information according to the data processing mode of the IoT device and the distribution of the data processing result in the transmission link;

[0064] Wherein, step S200 includes:

[0065] Step S201: acquiring data information transmitted in the network from the occurrence of any task E to the end of any task E, and collecting data vectors corresponding to each piece of data information into a data vector set UE;

[0066] Step S202: Obtain i output links of a certain IoT device D in the network, obtain the data information corresponding to each output link, wherein each output link corresponds to a piece of data information, and collect the data vectors corresponding to each piece of data information into the output vector set OP D ;

[0067] Step S203: Obtain the data vector and set OP corresponding to the input data information of the input IoT device D D The difference of each data vector in is classified according to the first processing method and the second processing method of the IoT device D, where the number of data vectors obtained by the first processing method is i1, and the number of data vectors obtained by the second processing method is i2. The condition i1+i2=i is satisfied, and the first node coefficient α1 and the second node coefficient α2 of the IoT device D are calculated, where α1=i2 / i, α2=i1 / i;

[0068] Step S204: Sort the differences obtained in step S203 from high to low to obtain a difference sorting sequence, and calculate the ratio of the sequence number of each data vector in the difference sorting sequence to the total number of data vectors in the sorting sequence, where the ratio is the link weight corresponding to each data vector;

[0069] For example, IoT device D1 has three output terminals, with differences of 0.4, 0.5, and 0.6, and the difference management threshold is 0.55;

[0070] The first node coefficient of D1 is 2 / 3, and the second node coefficient of D1 is 1 / 3;

[0071] Step S205: Obtain the processing method corresponding to the j-th data vector in the data vector set UE, and calculate the first evaluation coefficient k corresponding to the j-th data vector j 1, where k j 1=α×β j , α represents the node coefficient. When the jth data vector corresponds to the first type of processing method, α takes α1, and when the jth data vector corresponds to the second type of processing method, α takes α2. j represents the link weight corresponding to the jth data vector;

[0072] In the above example, the first evaluation coefficient of the data vector corresponding to the second difference is k1=(2 / 3)×(2 / 3)=4 / 9.

[0073] Step S300: classify the data information, calculate the proportion of each type of data information in all the data information, and calculate the second evaluation coefficient corresponding to each type of data information in combination with the influence range of each type of data information propagated in the network;

[0074] Wherein, step S300 includes:

[0075] Step S301: clustering the data vectors in the data vector set UE by using a clustering algorithm to obtain n categories of data vectors;

[0076] Clustering methods include clustering vectors into high-dimensional lattice models, or clustering through vector clustering models;

[0077] Step S302: obtaining a network topology of the IoT devices according to the connection relationship of the IoT devices, obtaining a total number num of device connection segments of the IoT devices in the network topology, wherein the device connection segment includes at least two IoT devices, and obtaining a data vector corresponding to data information existing in each device connection segment during the process from the start to the end of any task E;

[0078] Step S303: Obtain the device connection segments in which the data vector corresponding to the nrth category appears in all device connection segments during the process, and record the number of device connection segments as lin nr , calculate the link distribution coefficient L of the nrth category nr , L nr =lin nr / num;

[0079] Step S304: Obtain the number of data vectors h in the nrth category nr, the total number of data vectors in the data vector set UE H UE , calculate the data proportion coefficient B corresponding to the nrth category nr , B nr =h nr / H UE ;

[0080] Step S305: Calculate the second evaluation coefficient k corresponding to each data vector in the nrth category nr 2, k nr 2=L nr +B nr ;

[0081] Step S400: acquiring the occurrence frequency of each task from the operation record of the network, collecting the first evaluation coefficient and the second evaluation coefficient of the data information, calculating the evaluation value of the data information, and arranging the data information into a data information sequence according to the evaluation value;

[0082] Wherein, step S400 includes:

[0083] Step S401: Obtain the first evaluation coefficient k of the mth data vector in the data vector set UE m 1 and the second evaluation coefficient k m 2. Calculate the evaluation value μ of the mth data vector m , μ m =k m 1+k m 2;

[0084] Step S402: obtaining evaluation values ​​corresponding to each data vector in the data vector set UE, arranging the evaluation values ​​from large to small, and aggregating the arranged evaluation values ​​to obtain a data information sequence.

[0085] Step S500: extracting the first several items of data information from the data information sequence, collecting the data features contained in the data information, integrating the data features into a data feature set, and feeding back to the relevant administrator;

[0086] Wherein, step S500 includes:

[0087] Step S501: collect the first p data vectors in the data information sequence into a feature vector set V, and obtain the data content corresponding to each data vector in the feature vector set, where the set corresponding to the data content of the g-th data vector is sub g ;

[0088] Step S502: Calculate the content set U composed of the common parts of the data contents corresponding to all feature vectors in the feature vector set, U=sub1∪sub2∪sub3∪…∪sub p, where sub1, sub2, sub3, ... and sub p , respectively represent the first, second, third, ... and pth feature vector sets in the feature vector set V;

[0089] Step S503: Push the data content in U to the relevant administrator;

[0090] In the actual real-time process, the administrator includes the actual data management personnel or the data management system with data management function.

[0091] The system includes:

[0092] A mode management module, a first evaluation coefficient calculation module, a second evaluation coefficient calculation module, an information sequence management module and a feature feedback module;

[0093] The mode management module is used to classify the data processing modes of the IoT devices, wherein the mode management module includes: a vectorization unit, a difference calculation unit and a classification management unit, wherein the vectorization unit is used to vectorize the data transmitted in the IoT network, the difference calculation unit is used to calculate the difference between the input data vector and the output data vector, and the classification management unit is used to classify different processing modes of the IoT devices;

[0094] The first evaluation coefficient calculation module is used to calculate the first evaluation coefficient, wherein the first evaluation coefficient calculation module includes: a difference management unit, a node coefficient calculation unit, a link weight calculation unit and a first evaluation coefficient calculation unit, wherein the difference management unit is used to collect the difference between the output data vector and the input data vector, the node coefficient calculation unit is used to calculate the node coefficient, the link weight calculation unit is used to calculate the link weight, and the first evaluation coefficient calculation unit is used to calculate the first evaluation coefficient;

[0095] The second evaluation coefficient calculation module is used to calculate the second evaluation coefficient, wherein the second evaluation coefficient calculation module includes: a clustering calculation unit, a connection management unit, a link distribution coefficient calculation unit, a data proportion coefficient calculation unit and a second evaluation coefficient calculation unit, wherein the clustering calculation unit is used to cluster the data vectors in the data vector set UE, the connection management unit is used to obtain the number of device connection segments of the Internet of Things device in the network topology, the link distribution coefficient calculation unit is used to calculate the link distribution coefficient, the data proportion coefficient calculation unit is used to calculate the data proportion coefficient, and the second evaluation coefficient calculation unit is used to calculate the second evaluation coefficient;

[0096] The information sequence management module is used to arrange the data information into a data information sequence according to the evaluation value, wherein the information sequence management module includes: an evaluation value calculation unit and a data information sequence management unit, wherein the evaluation value calculation unit is used to calculate the evaluation value of each data vector, and the data information sequence management unit is used to collect the arranged evaluation values ​​to obtain the data information sequence;

[0097] Among them, the feature feedback module is used to collect the features in the data information and feed them back to the relevant management personnel. Among them, the feature feedback module includes: a content analysis unit, a content collection management unit and an information push unit. The content analysis unit is used to obtain the data information sequence by collecting the arranged evaluation values, the content collection management unit is used to manage the content collection, and the information push unit is used to push the relevant data content to the relevant administrator.

[0098] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0099] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A smart home-related integrated supervision method based on the Internet of Things, characterized in that: The method comprises the following steps: Step S100: in an IoT platform including several IoT devices, obtaining the connection relationship and transmitted data information of the IoT devices, wherein the IoT devices are smart home IoT devices, vectorizing the data information, and classifying the data processing methods of the IoT devices according to the differences between the information vectors before and after processing; Step S100 includes: Step S101: obtaining data content contained in data information, and performing vector processing on the data information according to the data content to obtain a data vector corresponding to each piece of data information; Step S102: For any IoT device, obtain a data vector a corresponding to a piece of data information input to the IoT device, obtain data information output after being processed by the IoT device, a data vector b corresponding to a piece of output data information, and calculate the difference γ between the data vector a and the data vector b ab ; Step S103: Obtain a difference management threshold of any IoT device. When the difference between the data vector corresponding to the input data information and the data vector corresponding to the output data information is greater than the difference management threshold, the processing method of the IoT device for the output data is determined to be the first type of processing method. When the difference between the data vector corresponding to the input data information and the data vector corresponding to the output data information is less than or equal to the difference management threshold, the processing method of the IoT device for the output data is determined to be the first type of processing method or the second type of processing method. Step S200: obtaining the operation log of the management system in the IoT platform, obtaining all data information generated by the IoT device in the process of executing the task assigned by the management system, and calculating the first evaluation coefficient of the data information according to the data processing mode of the IoT device and the distribution of the data processing result in the transmission link; Step S200 includes: Step S201: acquiring data information transmitted in the network from the occurrence of any task E to the end of any task E, and collecting data vectors corresponding to each piece of data information into a data vector set UE; Step S202: Obtain i output links of a certain IoT device D in the network, obtain the data information corresponding to each output link, wherein each output link corresponds to a piece of data information, and collect the data vectors corresponding to each piece of data information into the output vector set OP D ; Step S203: Obtain a data vector set OP corresponding to the input data information of the input IoT device D D The difference of each data vector in is classified according to the first processing method and the second processing method of the IoT device D, where the number of data vectors obtained by the first processing method is i1, and the number of data vectors obtained by the second processing method is i2. The condition i1+i2=i is satisfied, and the first node coefficient α1 and the second node coefficient α2 of the IoT device D are calculated, where α1=i2 / i, α2=i1 / i; Step S204: Sort the differences obtained in step S203 from high to low to obtain a difference sorting sequence, and calculate the ratio of the sequence number of each data vector in the difference sorting sequence to the total number of data vectors in the sorting sequence, where the ratio is the link weight corresponding to each data vector; Step S205: Obtain the processing method corresponding to the j-th data vector in the data vector set UE, and calculate the first evaluation coefficient k corresponding to the j-th data vector j 1, where k j 1=α×β j , α represents the node coefficient. When the jth data vector corresponds to the first type of processing method, α takes α1, and when the jth data vector corresponds to the second type of processing method, α takes α2. j represents the link weight corresponding to the j-th data vector; Step S300: classify the data information, calculate the proportion of each type of data information in all the data information, and calculate the second evaluation coefficient corresponding to each type of data information in combination with the influence range of each type of data information propagated in the network; Step S300 includes: Step S301: clustering the data vectors in the data vector set UE by using a clustering algorithm to obtain n categories of data vectors; Step S302: obtaining a network topology of the IoT devices according to the connection relationship of the IoT devices, obtaining a total number num of device connection segments of the IoT devices in the network topology, wherein the device connection segment includes at least two IoT devices, and obtaining a data vector corresponding to data information existing in each device connection segment during the process from the start to the end of the arbitrary task E; Step S303: Obtain the device connection segments in which the data vector corresponding to the nrth category appears in all device connection segments in the process, and record the number of the device connection segments as lin nr , calculate the link distribution coefficient L of the nrth category nr , L nr =lin nr / num; Step S304: Obtain the number h of data vectors in the nrth category nr , the total number of data vectors in the data vector set UE H UE , calculate the data proportion coefficient B corresponding to the nrth category nr , B nr =h nr / H UE ; Step S305: Calculate the second evaluation coefficient k corresponding to each data vector in the nrth category nr 2, k nr 2=L nr +B nr ; Step S400: acquiring the occurrence frequency of each task from the operation record of the network, collecting the first evaluation coefficient and the second evaluation coefficient of the data information, calculating the evaluation value of the data information, and arranging the data information into a data information sequence according to the evaluation value; Step S500: extract the first several items of data information from the data information sequence, collect the data features contained in the data information, merge the data features into a data feature set, and feed back to the relevant administrator.

2. According to claim 1, a smart home-related integrated supervision method based on the Internet of Things is characterized by: Step S400 includes: Step S401: Obtain the first evaluation coefficient k of the mth data vector in the data vector set UE m 1 and the second evaluation coefficient k m 2. Calculate the evaluation value μ of the mth data vector m , μ m =k m 1+k m 2; Step S402: obtaining evaluation values ​​corresponding to each data vector in the data vector set UE, arranging the evaluation values ​​from large to small, and aggregating the arranged evaluation values ​​to obtain a data information sequence.

3. According to claim 2, a smart home-related integrated supervision method based on the Internet of Things is characterized by: Step S500 includes: Step S501: collect the first p data vectors in the data information sequence into a feature vector set V, and obtain the data content corresponding to each data vector in the feature vector set, where the set corresponding to the data content of the g-th data vector is sub g ; Step S502: Calculate the content set U composed of the common parts of the data contents corresponding to all feature vectors in the feature vector set, U=sub1∪sub2∪sub3∪…∪sub p , where sub1, sub2, sub3, ... and sub p , respectively represent the first, second, third, ... and pth feature vector sets in the feature vector set V; Step S503: Push the data content in U to relevant administrators.

4. A smart home associated integrated supervision system applied to a smart home associated integrated supervision method based on the Internet of Things as described in any one of claims 1 to 3, characterized in that: The system includes the following modules: a mode management module, a first evaluation coefficient calculation module, a second evaluation coefficient calculation module, an information sequence management module and a feature feedback module, wherein the mode management module is used to classify the data processing mode of the Internet of Things device, the first evaluation coefficient calculation module is used to calculate the first evaluation coefficient, the second evaluation coefficient calculation module is used to calculate the second evaluation coefficient, the information sequence management module is used to arrange the data information into a data information sequence according to the evaluation value, and the feature feedback module is used to collect the features in the data information and feed them back to the relevant management personnel.

5. The smart home associated integrated monitoring system according to claim 4 is characterized in that: The mode management module includes: a vectorization unit, a difference calculation unit and a classification management unit, wherein the vectorization unit is used to vectorize the data transmitted in the Internet of Things network, the difference calculation unit is used to calculate the difference between the input data vector and the output data vector, and the classification management unit is used to classify the different processing modes of the Internet of Things devices.

6. The smart home-related integrated monitoring system according to claim 4 is characterized in that: The first evaluation coefficient calculation module includes: a difference management unit, a node coefficient calculation unit, a link weight calculation unit and a first evaluation coefficient calculation unit, wherein the difference management unit is used to collect the difference between the output data vector and the input data vector, the node coefficient calculation unit is used to calculate the node coefficient, the link weight calculation unit is used to calculate the link weight, and the first evaluation coefficient calculation unit is used to calculate the first evaluation coefficient; The second evaluation coefficient calculation module includes: a clustering calculation unit, a connection management unit, a link distribution coefficient calculation unit, a data proportion coefficient calculation unit and a second evaluation coefficient calculation unit, wherein the clustering calculation unit is used to cluster the data vectors in the data vector set UE, the connection management unit is used to obtain the number of device connection segments of the Internet of Things devices in the network topology, the link distribution coefficient calculation unit is used to calculate the link distribution coefficient, the data proportion coefficient calculation unit is used to calculate the data proportion coefficient, and the second evaluation coefficient calculation unit is used to calculate the second evaluation coefficient.

7. The smart home associated integrated monitoring system according to claim 4 is characterized in that: The information sequence management module includes: an evaluation value calculation unit and a data information sequence management unit, wherein the evaluation value calculation unit is used to calculate the evaluation value of each data vector, and the data information sequence management unit is used to collect the arranged evaluation values ​​to obtain a data information sequence; The feature feedback module includes: a content analysis unit, a content collection management unit and an information push unit. The content analysis unit is used to obtain the data information sequence by collecting the arranged evaluation values. The content collection management unit is used to manage the content collection. The information push unit is used to push the relevant data content to the relevant administrator.

Images