A data collection method and system based on industrial Internet

Abstract

The present invention discloses a data collection method and system based on the industrial Internet. A plurality of device data are obtained. A plurality of collected data are obtained. The collected data and the device data are established into a two-dimensional array and then split and merged into a one-dimensional array according to the vertical direction. The one-dimensional array is packaged and transmitted through the network. The data is unpacked and the one-dimensional data is reconstructed into a two-dimensional array to obtain a plurality of transmission collection data and a plurality of transmission device data. Based on the transmission device data and the transmission collection data, the operations that the data can be used for are obtained. According to the confidentiality of the operation, the transmission device data and the transmission collection data are stored in a database, and the data is accessed through a confidential data structure. The confidentiality of the operation is used to set the confidentiality of the data, and the confidentiality setting is aligned according to the actual situation. The operations that the data can perform are obtained more accurately. The confidentiality of the operation is used to prevent information islands, make the transmission process safer, and better protect the data.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data collection method and system based on the industrial Internet. Background Art

[0002] The Industrial Internet platform tightly connects equipment, production lines, factories, suppliers, products, and customers. Currently, the most typical Industrial Internet applications focus on remote O&M monitoring and predictive maintenance for high-value industrial equipment. Leveraging technologies such as the Internet of Things, industrial big data, and artificial intelligence, it manages the health of equipment such as construction vehicles, machine tools, fans, and compressors. This enables diagnosis, predictive alarms, and analysis of equipment failures, reducing maintenance costs and improving user experience. Due to the volume and complexity of industrial data, data classification is required during collection to automatically determine its type. Data security is also a key concern, and the problem of data silos must be addressed. Summary of the Invention

[0003] The purpose of the present invention is to provide a data collection method and system based on the industrial Internet to solve the above-mentioned problems existing in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a data collection method based on the Industrial Internet, comprising:

[0005] Obtaining multiple device data; the device data represents the data of the device collecting data at the time of collection, and the device data includes the type of collection data, device number and collection time;

[0006] Obtaining a plurality of collected data; the collected data is data collected by the collection device corresponding to the device number in the device data;

[0007] The collected data and the device data are established into a two-dimensional array, and then split and merged into a one-dimensional array according to the longitudinal direction, and the one-dimensional array is packaged and transmitted through the network;

[0008] Unpacking and reconstructing the one-dimensional data into a two-dimensional array to obtain multiple transmission collection data and multiple transmission device data;

[0009] Based on the transmission device data and the transmission collection data, obtaining an operation for which the data can be used;

[0010] According to the confidentiality of the operation, the transmission device data and the transmission collection data are stored in a database, and the data is accessed through a confidential data structure.

[0011] Optionally, obtaining the operation for which the data can be used based on the transmission device data and the transmission collection data includes:

[0012] Detecting the transmitted and collected data to determine whether it is erroneous data; the erroneous data indicates a device detection error;

[0013] If the collected data is not erroneous data, cluster analysis is performed on the transmitted collected data to determine whether there are abnormal points and obtain multiple cluster center points;

[0014] If there are abnormal points, delete the data at the abnormal points;

[0015] If no abnormal point exists, inputting the transmission device data into a first neural network for classification;

[0016] Based on the output of the first neural network and the plurality of cluster centers, operations that the data can be used for are obtained through the second neural network.

[0017] Optionally, the operation of obtaining data usable by a second neural network based on the output of the first neural network and the plurality of cluster centers includes:

[0018] Comparing the distance between the transmission and collection data and the cluster center point, the cluster where the cluster center with a distance smaller than other distances is located is regarded as the cluster of the transmission data to obtain the cluster category; the cluster category represents the degree of transmission and collection data;

[0019] Inputting the output and cluster categories of the first neural network into a second neural network for classification to obtain a second classification vector; the elements in the second classification vector represent the probability of the operation for which the transmission and collection data can be used;

[0020] The operation in which the elements in the second classification vector are greater than a threshold is used as the operation for transmitting the collected data.

[0021] Optionally, according to the confidentiality of the operation, storing the transmission device data and the transmission collection data in a database and accessing the data through a confidential data structure includes:

[0022] Setting confidentiality for the transmission device data and the transmission collection data according to the confidentiality of the operation for which the transmission collection data can be used; the confidentiality includes full confidentiality, partial confidentiality and full non-confidentiality;

[0023] The fully confidential data and partially confidential data are stored in a data table of a confidentiality structure, and the data tables in the confidentiality structure are not connected;

[0024] All non-confidential data are stored in a data table with a non-confidential structure, and data is exchanged between two data tables in the non-confidential structure;

[0025] Access to transmission device data and transmission acquisition data in the database is performed through a confidential data structure.

[0026] Optionally, setting confidentiality for the transmitted collected data according to the confidentiality of an operation for which the transmitted collected data may be used includes:

[0027] If all operations that the transmission and collection data can be used for are confidential operations, set the confidentiality of the transmission device data and the transmission and collection data to be fully confidential;

[0028] If the operations that the transmission and collection data can be used for are all non-confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to all non-confidential

[0029] If the operations for which the transmission and collection data can be used are partially confidential operations and partially non-confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to partially confidential.

[0030] Optionally, accessing the transmission device data and the transmission collection data in the database through the confidential data structure includes:

[0031] The confidential data structure includes a non-confidential structure, a confidential structure and a partially confidential structure;

[0032] Circular connections are made between data tables in the non-confidential structure;

[0033] The data tables in the confidentiality structure are not connected and are distributed in a point-like manner;

[0034] The data tables in the confidential structure are connected to the partially confidential structure, and the data tables in the non-confidential structure are connected to the partially confidential structure; a data table in a confidential structure is connected to a partially confidential structure; a partially confidential structure is connected to multiple data tables in the non-confidential structure.

[0035] Optionally, the data table connection part in the confidentiality structure and the data table connection part in the non-confidentiality structure include:

[0036] Establishing a backup data table in a partially confidential structure; the data in the backup data table is data required for non-confidential operations;

[0037] Storing the label of the confidential data table and the label of the non-confidential data table corresponding to the non-confidential operation in the partial confidentiality structure;

[0038] Connecting the non-confidential data table corresponding to the label of the non-confidential data table to the interface of the partially confidential structure;

[0039] Accessing through non-confidential operations, finding a portion of the confidential structure that matches the label of the confidential data table and the label of the non-confidential data table corresponding to the non-confidential operation, and obtaining confidential data and non-confidential data;

[0040] When modifying non-confidential data in a partially confidential structure, the modified confidential data passed in after the modification must be manually confirmed before it can be modified.

[0041] Optionally, detecting the transmitted collected data and determining whether it is erroneous data includes:

[0042] Subtract the adjacent times of the same numbered equipment to obtain the time difference. The collected data whose time difference does not fall within the set range will be recorded as error data, stored in the error data database, and marked as an error in the detection equipment.

[0043] Compare the collected data type of the same labeled device with the marked data type. If they are different, record the collected data as error data, store it in the error data database, and mark the detection device as error.

[0044] If the collected data is not marked as erroneous data, the data situation is judged based on the transmission device data and the transmission collected data to obtain the data relationship.

[0045] Optionally, the step of creating a two-dimensional array from the data collected by the data collection device, splitting and merging the two-dimensional arrays vertically, packaging the one-dimensional arrays, and transmitting the data to a server via a network includes:

[0046] The collected data is constructed into a two-dimensional array with columns representing data content and rows representing data categories; the data categories include collected data, collected data type, device number and collection time; the data content represents the value corresponding to the data category;

[0047] Traverse the two-dimensional array from top to bottom and from left to right in columns, and input the values in the two-dimensional array into the one-dimensional array;

[0048] The one-dimensional data is packaged through the protocol and sent to the server.

[0049] In a second aspect, an embodiment of the present invention provides a data acquisition system based on the Industrial Internet, including:

[0050] Acquisition module: Acquire multiple device data; the device data represents the data collected by the device collecting data at the time of collection, and the device data includes the type of collection data, device number and collection time; obtain multiple collection data; the collection data is the data collected by the collection device corresponding to the device number in the device data;

[0051] Transmission module: after creating a two-dimensional array of the collected data and the device data, split and merge them into a one-dimensional array according to the longitudinal direction, pack the one-dimensional array and transmit it through the network; unpack and reconstruct the one-dimensional data into a two-dimensional array to obtain multiple transmission collection data and multiple transmission device data;

[0052] Confidentiality module: based on the transmission device data and the transmission collection data, obtains the operation for which the data can be used; according to the confidentiality of the operation, stores the transmission device data and the transmission collection data in a database, and performs data access through a confidential data structure.

[0053] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0054] An embodiment of the present invention also provides a data collection method and system based on the industrial Internet, the method comprising: obtaining a plurality of device data. The device data represents the data collected by the device collecting the data at the time of collection, and the device data comprises the type of collection data, the device number and the collection time. Obtain a plurality of collection data. The collection data is the data collected by the collection device corresponding to the device number in the device data. The collection data and the device data are established into a two-dimensional array and then split and merged into a one-dimensional array according to the vertical direction, and the one-dimensional array is packaged and transmitted over the network. The data is unpacked and reconstructed into a two-dimensional array from the one-dimensional data to obtain a plurality of transmission collection data and a plurality of transmission device data. Based on the transmission device data and the transmission collection data, the operation for which the data can be used is obtained. According to the confidentiality of the operation, the transmission device data and the transmission collection data are stored in a database, and the data is accessed through a confidential data structure.

[0055] The first neural network classifies transmission device data, using clustering to extract hidden factors from the collected data. These factors are then fed into the second neural network to more accurately determine the operations that can be performed on the data. Operational confidentiality is used to set data confidentiality, tailored to specific circumstances. This allows for different data storage locations. Non-confidential data can be interconnected, allowing data exchange between non-confidential data to prevent information silos. Confidential data can be linked to non-confidential data through partially confidential structures to access backup confidential data. Access to the corresponding partially confidential structure is achieved through linking labels and non-confidential operations. If the label is incorrect, the confidential data cannot be used, enhancing confidential data security. Non-confidential data can be modified, while confidential data values can be modified from backup data, which is then replaced after manual confirmation. This not only enhances confidentiality but also facilitates data flow, preventing information silos and ensuring greater security during transmission, providing better data protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of a data collection method based on the Industrial Internet provided by an embodiment of the present invention.

[0057] Figure 2 This is a structural diagram of a confidential data structure in an industrial Internet-based data acquisition system provided by an embodiment of the present invention.

[0058] Figure 3 It is a block diagram of an electronic device provided by an embodiment of the present invention.

[0059] Labels in the figure: bus 500; receiver 501; processor 502; transmitter 503; memory 504; bus interface 505. DETAILED DESCRIPTION

[0060] The present invention will be described in detail below with reference to the accompanying drawings.

[0061] Example 1

[0062] like Figure 1 As shown, an embodiment of the present invention provides a data collection method based on the industrial Internet, the method comprising:

[0063] S101: Obtain multiple pieces of device data. The device data represents the data collected by the device at the time of collection, and the device data includes the type of collection data, device number, and collection time.

[0064] S102: Obtain multiple collected data. The collected data is data collected by the collection device corresponding to the device number in the device data.

[0065] S103: After the collected data and the device data are created into a two-dimensional array, they are split and merged into a one-dimensional array along the vertical direction, and the one-dimensional array is packaged and transmitted through the network.

[0066] S104: Unpacking is performed and the one-dimensional data is reconstructed into a two-dimensional array to obtain a plurality of transmission collection data and a plurality of transmission device data.

[0067] The transmission device data is of fixed length, including zero padding when constructing a two-dimensional array. The transmission acquisition data is the original length after removing the zero padding of the two-dimensional array. The transmission acquisition data is normalized data.

[0068] S105: Based on the transmission device data and the transmission collection data, obtain an operation that the data can be used for.

[0069] S106: Based on the confidentiality of the operation, the transmission device data and the transmission collection data are stored in a database, and the data is accessed through a confidential data structure.

[0070] Optionally, obtaining the operation for which the data can be used based on the transmission device data and the transmission collection data includes:

[0071] Detecting the transmitted and collected data to determine whether it is erroneous data, wherein the erroneous data indicates a device detection error.

[0072] If the collected data is not erroneous data, cluster analysis is performed on the transmitted collected data to determine whether there are abnormal points, and a plurality of cluster center points are obtained.

[0073] The transmission and collection data are clustered using K-means. The cluster center represents the center point of the clusters that divide the data into different detection levels.

[0074] If there are outliers, delete the data at the outlier points.

[0075] If there is no abnormal point, the transmission equipment data is input into the first neural network for classification.

[0076] The data type, device number, and acquisition time of the transmission device data are input into a first neural network in a fixed input order, and the applicable operations are classified according to the transmission device data. The first neural network is a deep neural network (DNN).

[0077] Based on the output of the first neural network and the plurality of cluster centers, operations that the data can be used for are obtained through the second neural network.

[0078] Through the above method, anomalies may be errors in objects detected on the pipeline. Abnormal data can be removed to protect data accuracy. The transmission device data is partially classified according to the first neural network. The output of the first neural network and multiple cluster centers are combined to integrate more information and obtain the operations that the data can be used for.

[0079] Optionally, the operation of obtaining data usable by a second neural network based on the output of the first neural network and the plurality of cluster centers includes:

[0080] The distance between the transmission and collection data and the cluster center is compared, and the cluster with the cluster center whose distance is smaller than other distances is taken as the cluster of the transmission data to obtain the cluster category. The cluster category indicates the degree of transmission and collection data.

[0081] The Euclidean distance function is used to calculate the transmission and collection data and the cluster center point. For example, in this embodiment, the device can detect objects of three sizes and compare the width and height in the transmission and collection data with the cluster center point to obtain the cluster categories corresponding to the three sizes.

[0082] The output and cluster categories of the first neural network are input into a second neural network for classification to obtain a second classification vector; the elements in the second classification vector represent the probability of the operation that the transmission and collection data can be used for.

[0083] Among them, the first neural network is a deep neural network (Deep Neural Network, DNN).

[0084] The operation in which the elements in the second classification vector are greater than a threshold is used as the operation for transmitting the collected data.

[0085] In this embodiment, the threshold value is 0.95.

[0086] Through the above method, clustering is used to categorize transmission and collection data into different levels of accuracy. While conventionally using transmission device data as a classification factor, clustering is used to extract hidden factors from the transmission and collection data, which are then fed into a second neural network. Clustering controls the fusion of neural networks and combines feature points to classify the data, determining the operations that can be performed on the data. Different operations correspond to different confidentiality levels, resulting in different data storage methods.

[0087] Optionally, according to the confidentiality of the operation, storing the transmission device data and the transmission collection data in a database and accessing the data through a confidential data structure includes:

[0088] Setting confidentiality for the transmission device data and the transmission collection data according to the confidentiality of the operation for which the transmission collection data can be used; the confidentiality includes full confidentiality, partial confidentiality and full non-confidentiality;

[0089] The fully confidential data and partially confidential data are stored in a data table of a confidential structure, and the data tables in the confidential structure are not connected;

[0090] All non-confidential data are stored in a data table with a non-confidential structure, and data is exchanged between two data tables in the non-confidential structure;

[0091] Access to transmission device data and transmission acquisition data in the database is performed through a confidential data structure.

[0092] Through the above method, confidentiality of operations is used to set data confidentiality, and confidentiality settings are aligned according to actual conditions. Non-confidential data is interconnected, and data exchange between non-confidential data prevents information silos. Confidential data, on the other hand, must be accessed through a confidential data structure, thus preventing information silos.

[0093] Optionally, setting confidentiality for the transmitted collected data according to the confidentiality of an operation for which the transmitted collected data may be used includes:

[0094] If all operations for which the transmission and collection data can be used are confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to be fully confidential.

[0095] If all operations for which the transmission and collection data can be used are non-confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to all be non-confidential.

[0096] If the operations for which the transmission and collection data can be used are partially confidential operations and partially non-confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to partially confidential.

[0097] Through the above method, data confidentiality is set based on the confidentiality of the operation. This prevents data that is subject to confidentiality operations from communicating with each other, thus maintaining data confidentiality. However, data that is not subject to confidentiality operations can interact with each other, while data that is partially confidential and partially non-confidential can be set to confidentiality but can still be accessed through the confidential data structure. This can greatly enhance data security.

[0098] Optionally, access to the transmission device data and transmission acquisition data in the database through a confidential data structure, including:

[0099] The confidential data structure includes a non-confidential structure, a confidential structure and a partially confidential structure.

[0100] Wherein, the confidential data structure is as follows: Figure 2 shown.

[0101] Circular connections are made between data tables in the non-confidential structure.

[0102] The data tables in the confidentiality structure are not connected and are distributed in a point-like manner.

[0103] Data tables in a confidential structure are connected to partially confidential structures, and data tables in a non-confidential structure are connected to partially confidential structures. A data table in a confidential structure is connected to a partially confidential structure. A partially confidential structure is connected to multiple data tables in a non-confidential structure.

[0104] Through the above method, the data tables in the confidential structure do not communicate data, while the non-confidential structure can communicate data with each other through closed connections one by one. Then, when a non-confidential operation needs to use confidential data, it is necessary to use part of the confidential structure to make an indirect structure to protect the confidential data.

[0105] Optionally, the data table connection part in the confidentiality structure and the data table connection part in the non-confidentiality structure include:

[0106] Establishing a backup data table in a partially confidential structure; the data in the backup data table is data required for non-confidential operations;

[0107] Storing the label of the confidential data table and the label of the non-confidential data table corresponding to the non-confidential operation in the partial confidentiality structure;

[0108] Connecting the non-confidential data table corresponding to the label of the non-confidential data table to the interface of the partially confidential structure;

[0109] Accessing through non-confidential operations, finding a portion of the confidential structure that matches the label of the confidential data table and the label of the non-confidential data table corresponding to the non-confidential operation, and obtaining confidential data and non-confidential data;

[0110] When modifying non-confidential data in a partially confidential structure, the modified confidential data passed in after the modification must be manually confirmed before it can be modified.

[0111] Through this method, some confidential structures can connect non-confidential data that can be used for non-confidential purposes. Confidential data can be retrieved without being directly modified after backing it up. By combining the non-confidential operation with the confidential data table number corresponding to the non-confidential operation, the data can be retrieved through a combination of these two methods. After use, non-confidential data can be modified directly, while confidential data values can be modified by modifying the backup data and then replacing the original data after manual confirmation. This not only increases confidentiality security, but also facilitates data circulation and prevents information silos.

[0112] Optionally, detecting the transmitted collected data and determining whether it is erroneous data includes:

[0113] Subtract the adjacent times of the same numbered equipment to obtain the time difference. The collected data whose time difference does not fall within the set range will be recorded as error data, stored in the error data database, and marked as an error in the detection equipment.

[0114] Compare the collected data type of the same labeled device with the marked data type. If they are different, record the collected data as error data, store it in the error data database, and mark the detection device as error.

[0115] If the collected data is not marked as erroneous data, the data situation is judged based on the transmission device data and the transmission collected data to obtain the data relationship.

[0116] Optionally, the step of creating a two-dimensional array from the data collected by the data collection device, splitting and merging the two-dimensional arrays vertically, packaging the one-dimensional arrays, and transmitting the data to a server via a network includes:

[0117] The collected data is constructed into a two-dimensional array with columns representing data content and rows representing data categories; the data categories include collected data, collected data type, device number and collection time; the data content represents the value corresponding to the data category;

[0118] Traverse the two-dimensional array from top to bottom and from left to right in columns, input the values in the two-dimensional array into a one-dimensional array; package the one-dimensional data through the protocol and send it to the server.

[0119] Using the above method, transmission device data is classified using a first neural network. The output of the first neural network and multiple cluster centers are combined to integrate more information and determine the operations that the data can be used for. While conventional transmission device data is used as a classification factor, in situations where transmission data can only be used later and cannot participate in data analysis, clustering is used to extract hidden factors from the transmission data and input them into a second neural network. Clustering controls the fusion of the neural network and combines feature points to classify the data, more accurately determining the operations that the data can perform. Different operations correspond to different confidentiality levels, resulting in different data storage methods. The confidentiality of the data is set based on the confidentiality of the operation, and the confidentiality settings are adjusted based on the actual situation. Non-confidential data is interconnected, allowing data exchange between non-confidential data to prevent information silos. Partially confidential structures connect non-confidential data that can be used for non-confidential purposes, preventing direct modification of confidential data after backing up. To retrieve data, the non-confidential operation is combined with the confidentiality table number corresponding to the non-confidential operation to find the label of the confidential data table and the label of the non-confidential data table. This combination allows for retrieval. After use, non-confidential data can be modified immediately, while confidential data values can be modified using backup data, which can then be replaced after manual confirmation. This not only enhances confidentiality security but also facilitates data flow, preventing information silos. Confidential data must be accessed through a confidential data structure, thus preventing information silos. This prevents data silos and enhances data security during transmission, providing better data protection. The goal is to prioritize which data can be used directly and shared, while which remains confidential, thus preventing the formation of information silos.

[0120] Example 2

[0121] Based on the above-mentioned data acquisition method based on the industrial Internet, an embodiment of the present invention also provides a data acquisition system based on the industrial Internet, which includes an acquisition module, a transmission module and a confidentiality module.

[0122] The acquisition module is used to obtain multiple pieces of device data; the device data represents the data collected by the device collecting the data at the time of collection, and the device data includes the type of collection data, the device number, and the collection time. Multiple pieces of collected data are obtained; the collected data is the data collected by the collection device corresponding to the device number in the device data.

[0123] The transmission module is used to create a two-dimensional array of the collected data and the device data, split and merge them vertically into a one-dimensional array, package the one-dimensional array, and transmit it over the network. The module is used to unpack and reconstruct the one-dimensional data into a two-dimensional array to obtain multiple transmission collection data and multiple transmission device data.

[0124] The confidentiality module is used to obtain the operation that the data can be used for based on the transmission device data and the transmission collection data. According to the confidentiality of the operation, the transmission device data and the transmission collection data are stored in a database and the data is accessed through a confidential data structure.

[0125] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0126] The embodiment of the present invention further provides an electronic device, such as Figure 3 As shown, it includes a memory 504, a processor 502, and a computer program stored in the memory 504 and executable on the processor 502. When the processor 502 executes the program, it implements the steps of any one of the aforementioned methods for data collection based on the industrial Internet.

[0127] Among them, Figure 3 In the embodiment of the present invention, a bus architecture (represented by bus 500) is shown. Bus 500 may include any number of interconnected buses and bridges, and bus 500 links various circuits including one or more processors represented by processor 502 and memory represented by memory 504. Bus 500 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 505 provides an interface between bus 500 and receiver 501 and transmitter 503. Receiver 501 and transmitter 503 may be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 502 is responsible for managing bus 500 and general processing, while memory 504 may be used to store data used by processor 502 when performing operations.

[0128] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the steps of any method of the industrial Internet-based data collection method described above and the data involved above.

[0129] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general-purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages can be utilized to realize the content of the present invention described herein, and the above description of specific languages is for the purpose of disclosing the best mode of the present invention.

[0130] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0131] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the invention.

[0132] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0133] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination.

[0134] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the apparatus according to an embodiment of the present invention. The present invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0135] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A data collection method based on the industrial Internet, characterized in that: include: Obtaining multiple device data; the device data represents the data of the device collecting data at the time of collection, and the device data includes the type of collection data, device number and collection time; Obtain multiple acquisition data; The collected data is data collected by the collection device corresponding to the device number in the device data; The collected data and the device data are established into a two-dimensional array, and then split and merged into a one-dimensional array according to the longitudinal direction, and the one-dimensional array is packaged and transmitted through the network; Unpacking and reconstructing the one-dimensional data into a two-dimensional array to obtain multiple transmission collection data and multiple transmission device data; Based on the transmission device data and the transmission collection data, obtaining an operation for which the data can be used; Setting confidentiality for the transmission device data and the transmission collection data according to the confidentiality of the operation for which the transmission collection data can be used; the confidentiality includes full confidentiality, partial confidentiality and full non-confidentiality; The fully confidential data and partially confidential data are stored in a data table of a confidentiality structure, and the data tables in the confidentiality structure are not connected; All non-confidential data are stored in a data table with a non-confidential structure, and data is exchanged between two data tables in the non-confidential structure; Access to transmission device data and transmission acquisition data in the database is performed through a confidential data structure.

2. The data collection method based on the industrial Internet according to claim 1 is characterized in that: The operation of obtaining data that can be used based on the transmission device data and the transmission collection data includes: Detecting the transmitted and collected data to determine whether it is erroneous data; the erroneous data indicates a device detection error; If the collected data is not erroneous data, cluster analysis is performed on the transmitted collected data to determine whether there are abnormal points and obtain multiple cluster center points; If there are abnormal points, delete the data at the abnormal points; If no abnormal point exists, inputting the transmission device data into a first neural network for classification; Based on the output of the first neural network and the plurality of cluster centers, operations that the data can be used for are obtained through the second neural network.

3. The data collection method based on the industrial Internet according to claim 2 is characterized in that: The operations for obtaining data usable by the second neural network based on the output of the first neural network and the plurality of cluster centers include: Comparing the distance between the transmission and collection data and the cluster center point, the cluster where the cluster center with a distance smaller than other distances is located is regarded as the cluster of the transmission data to obtain the cluster category; the cluster category represents the degree of transmission and collection data; Inputting the output and cluster categories of the first neural network into a second neural network for classification to obtain a second classification vector; the elements in the second classification vector represent the probability of the operation for which the transmission and collection data can be used; The operation in which the elements in the second classification vector are greater than a threshold is used as the operation for transmitting the collected data.

4. The data collection method based on the industrial Internet according to claim 1 is characterized in that: Setting confidentiality for the transmitted collected data according to the confidentiality of the operation for which the transmitted collected data may be used comprises: If all operations that the transmission and collection data can be used for are confidential operations, set the confidentiality of the transmission device data and the transmission and collection data to be fully confidential; If the operations that the transmission and collection data can be used for are all non-confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to all non-confidential If the operations for which the transmission and collection data can be used are partially confidential operations and partially non-confidential operations, the confidentiality of the transmission device data and the transmission and collection data is set to partially confidential.

5. The data collection method based on the industrial Internet according to claim 1 is characterized in that: The access to the transmission device data and the transmission collection data in the database through the confidential data structure includes: The confidential data structure includes a non-confidential structure, a confidential structure and a partially confidential structure; Circular connections are made between data tables in the non-confidential structure; The data tables in the confidentiality structure are not connected and are distributed in a point-like manner; The data tables in the confidential structure are connected to the partially confidential structure, and the data tables in the non-confidential structure are connected to the partially confidential structure; a data table in a confidential structure is connected to a partially confidential structure; a partially confidential structure is connected to multiple data tables in the non-confidential structure.

6. The data collection method based on the industrial Internet according to claim 5 is characterized in that: The data table connection part confidentiality structure in the confidentiality structure and the data table connection part confidentiality structure in the non-confidentiality structure include: Establishing a backup data table in a partially confidential structure; the data in the backup data table is data required for non-confidential operations; Storing the label of the confidential data table and the label of the non-confidential data table corresponding to the non-confidential operation in the partial confidentiality structure; Connecting the non-confidential data table corresponding to the label of the non-confidential data table to the interface of the partially confidential structure; Accessing through non-confidential operations, finding a portion of the confidential structure that matches the label of the confidential data table and the label of the non-confidential data table corresponding to the non-confidential operation, and obtaining confidential data and non-confidential data; When modifying non-confidential data in a partially confidential structure, the modified confidential data passed in after the modification must be manually confirmed before it can be modified.

7. The data collection method based on the industrial Internet according to claim 2 is characterized in that: The detecting, transmitting and collecting data and determining whether the data is erroneous data includes: Subtract the adjacent times of the same numbered equipment to obtain the time difference. The collected data whose time difference does not fall within the set range will be recorded as error data, stored in the error data database, and marked as an error in the detection equipment. Compare the collected data type of the same labeled device with the marked data type. If they are different, record the collected data as error data, store it in the error data database, and mark the detection device as error. If the collected data is not marked as erroneous data, the data situation is judged based on the transmission device data and the transmission collected data to obtain the data relationship.

8. The data collection method based on the industrial Internet according to claim 1 is characterized in that: The method of creating a two-dimensional array of the data collected by the data collection device and then splitting and merging the two-dimensional arrays vertically into one-dimensional arrays, packaging the one-dimensional arrays, and transmitting the data to the server via the network includes: The collected data is constructed into a two-dimensional array with columns representing data content and rows representing data categories; the data categories include collected data, collected data type, device number and collection time; the data content represents the value corresponding to the data category; Traverse the two-dimensional array from top to bottom and from left to right in columns, and input the values in the two-dimensional array into the one-dimensional array; The one-dimensional data is packaged through the protocol and sent to the server.

9. A data acquisition system based on the industrial Internet, characterized in that: include: Acquisition module: obtains multiple device data; the device data represents the data of the device collecting data at the time of collection, and the device data includes the type of collection data, device number and collection time; Obtaining a plurality of collected data; the collected data is data collected by the collection device corresponding to the device number in the device data; Transmission module: after creating a two-dimensional array of the collected data and the device data, splitting and merging the two-dimensional arrays vertically, packaging the one-dimensional arrays and transmitting them through the network; Unpacking and reconstructing the one-dimensional data into a two-dimensional array to obtain multiple transmission collection data and multiple transmission device data; Confidentiality module: based on the transmission device data and the transmission collection data, obtains the operations that the data can be used for; The confidentiality of the transmission device data and the transmission collection data is set according to the confidentiality of the operations for which the transmission collection data can be used; the confidentiality includes full confidentiality, partial confidentiality and full non-confidentiality; the full confidential data and the partial confidential data are stored in a data table of a confidential structure, and the data tables in the confidential structure are not connected; the full non-confidential data is stored in a data table of a non-confidential structure, and the data tables in the non-confidential structure interact with each other; the transmission device data and the transmission collection data in the database are accessed through the confidential data structure.

Images