A method and system for secure transmission between water affairs Internet of Things equipment and platform

Abstract

The present invention belongs to the field of information security technology, and provides a method and system for secure transmission between water conservancy Internet of Things devices and platforms. The method includes: using an encryption chip to encrypt data to be transmitted; calling a data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted, and obtaining a corresponding sensitivity value; determining a target communication method according to the sensitivity value, and transmitting the encrypted data to be transmitted to the water conservancy Internet of Things platform based on the target communication method; wherein the target communication method is the operator's APN private network or the Internet. The present invention uses a data sensitivity analysis model to analyze the sensitivity value of the data to be transmitted, and then selects a suitable target communication method based on this, and uses an encryption chip to encrypt and transmit the data to be transmitted, thereby achieving the purpose of ensuring the security and transmission rate of data transmission at the same time.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a method and system for secure transmission of water Internet of Things equipment and platforms. Background Art

[0002] At present, most water IoT sensing devices use wireless transmission mode, where data is transmitted to the operator's base station and then transmitted to the corresponding IoT data receiving platform via the Internet. This mode has the following main disadvantages: 1) Figure 1 As shown in Figure 2, the IoT platform is exposed to the Internet and is easily sniffed and targeted by attacks. Figure 2 As shown in Figure 3, the operator network base station can be forged, resulting in data being unable to be reported, operation instructions being unable to be interfaced, and even fake base stations forging data or operation instructions. 3) Reference Figure 3 As shown, a backdoor is left in the terminal device when it leaves the factory, and the device can interact with multiple addresses for data.

[0003] The above shortcomings lead to problems such as data leakage and data hostage-taking when data is transmitted between the water affairs IoT sensing device and the IoT data receiving platform. The present invention aims to solve this technical problem. Summary of the invention

[0004] In order to solve at least one of the above technical problems, the present invention specifically provides a method, system, electronic device, computer storage medium and computer program product for secure transmission between water Internet of Things devices and platforms.

[0005] The present invention provides a method for secure transmission between a water conservancy Internet of Things device and a platform, which is applied to a water conservancy Internet of Things device and includes the following steps: using an encryption chip to encrypt data to be transmitted; calling a data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted to obtain a corresponding sensitivity value; determining a target communication mode according to the sensitivity value, and transmitting the encrypted data to be transmitted to a water conservancy Internet of Things platform based on the target communication mode; wherein the target communication mode is an operator APN private network or the Internet.

[0006] Furthermore, the use of an encryption chip to encrypt the data to be transmitted includes: the encryption chip uses an asymmetric encryption algorithm to encrypt the data to be transmitted, wherein the key in the encryption chip is generated by the water conservancy Internet of Things platform and written into the encryption chip.

[0007] Furthermore, the calling of the data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted to obtain corresponding sensitivity values ​​includes: performing feature analysis on the data to be transmitted to obtain key features, wherein the key features include data type, data accuracy, data timeliness, data integrity, data source, and data purpose; calling the data sensitivity analysis model to perform in-depth analysis and processing on the key features to obtain the corresponding sensitivity values.

[0008] Furthermore, the data sensitivity analysis model is constructed based on a convolutional network, and the data sensitivity analysis model includes an input layer, a convolutional feature layer, an activation function, a pooling layer, a normalization layer, a fully connected layer, and an output layer; wherein the activation function adopts the ReLU function, and the normalization layer adopts batch normalization.

[0009] Furthermore, the data sensitivity analysis model is trained in the following manner: collecting several groups of first data corresponding to data type, data accuracy, data timeliness, data integrity, data source, and data usage purpose, each group of first data contains a corresponding first sensitivity label; combining the above several groups of data in pairs or more to obtain several groups of second data, each group of second data contains a corresponding second sensitivity label, and the second sensitivity label is obtained by semantically analyzing all the first sensitivity labels contained in each group of second data by a general large model; using the second data to train the data sensitivity analysis model until the training termination condition is met, and the training termination condition is constructed with a minimum loss function; the calculation formula of the loss function is as follows: ; In the above formula, is the loss function, is the number of training data from the second data that have been put into training, is the second sensitivity label of the i-th training data put into training, The predicted sensitivity label of the i-th training data output by the data sensitivity analysis model; is a drop coefficient, which decreases as the amount of training data from the second data that has been put into training increases, is the weight coefficient matrix of the i-th training data.

[0010] Further, determining the target communication mode according to the sensitivity value includes: when the sensitivity value is higher than a sensitivity threshold, setting the target communication mode to the operator APN private network; when the sensitivity value is not higher than the sensitivity threshold, setting the target communication mode to the Internet.

[0011] The present invention also provides a method for secure transmission between a water conservancy Internet of Things device and a platform, which is applied to the water conservancy Internet of Things device and includes an encryption module, a sensitivity analysis module, and a communication transmission module; the encryption module is used to encrypt the data to be transmitted using an encryption chip; the sensitivity analysis module is used to call a data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted and obtain a corresponding sensitivity value; the communication transmission module is used to determine a target communication mode according to the sensitivity value, and transmit the encrypted data to be transmitted to the water conservancy Internet of Things platform based on the target communication mode; wherein the target communication mode is the operator's APN private network or the Internet.

[0012] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method as described in any of the preceding items.

[0013] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0014] The present invention also provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor of an electronic device, any of the methods described above is implemented.

[0015] The beneficial effect of the present invention is that the present invention constructs a data sensitivity analysis model, uses the model to first perform sensitivity analysis on the data to be transmitted, obtains the corresponding sensitivity value, and then selects the appropriate target communication method according to the sensitivity value, thereby achieving the purpose of ensuring the security and transmission rate of data transmission at the same time. In addition, the present invention also sets an encryption chip in the water conservancy Internet of Things device, uses the encryption chip to encrypt the data to be transmitted before transmitting it, and even through the Internet communication method with lower security, the security of data transmission can be ensured to a high degree. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of illegal data attacks directly attacking the IoT platform on the Internet.

[0018] Figure 2This is a schematic diagram of fake base station data hijacking.

[0019] Figure 3 This is a schematic diagram of sending data to the manufacturer through the backdoor of the device.

[0020] Figure 4 It is a flow chart of a method for secure transmission between a water Internet of Things device and a platform provided in an embodiment of the present invention.

[0021] Figure 5 It is a schematic diagram of a water Internet of Things device provided by an embodiment of the present invention transmitting data to be transmitted through an operator's private network APN.

[0022] Figure 6 It is a schematic diagram of encrypting data to be transmitted by a water conservancy Internet of Things device provided in an embodiment of the present invention.

[0023] Figure 7 It is a structural diagram of a data sensitivity analysis model provided by an embodiment of the present invention.

[0024] Figure 8 It is a structural diagram of a system for secure transmission between a water Internet of Things device and a platform provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0026] See also Figure 4 As shown, an embodiment of the present invention provides a method for secure transmission between a water conservancy Internet of Things device and a platform, which is applied to a water conservancy Internet of Things device, and includes the following steps: using an encryption chip to encrypt data to be transmitted; calling a data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted, and obtaining a corresponding sensitivity value; determining a target communication mode according to the sensitivity value, and transmitting the encrypted data to be transmitted to a water conservancy Internet of Things platform based on the target communication mode; wherein the target communication mode is an operator APN private network or the Internet.

[0027] The present invention sets two communication modes for data transmission between water IoT devices and water IoT platforms, namely, the operator APN private network and the Internet. The Internet communication mode refers to the data transmission between water IoT devices and water IoT platforms through various heterogeneous networks such as wired networks, 3G, 4G, LTE, etc., but its network environment is complex and easily attacked by algorithm cracking and protocol cracking; refer to Figure 5 As shown in the figure, in the operator APN private network communication mode, after the water IoT device is connected to the wireless base station, it sends data to the water IoT platform through the operator's private network. Because the data transmission is no longer through the Internet, but the operator's private network, it can effectively prevent the water IoT device from sending data to the manufacturer's platform. At the same time, the water IoT platform, the recipient of the data, will not be attacked by the Internet network. Although the operator APN private network communication mode is more secure, compared with the public Internet, the dedicated APN usually has a fixed bandwidth limit, which may affect the data transmission between the water IoT device and the water IoT platform when there is high traffic demand.

[0028] In view of the above technical problems, the present invention constructs a data sensitivity analysis model, which is used to perform sensitivity analysis on the data to be transmitted, obtain the corresponding sensitivity value, and then select the appropriate target communication mode according to the sensitivity value, thereby achieving the purpose of ensuring the security and transmission rate of data transmission at the same time. Figure 6 As shown, the present invention also sets an encryption chip in the water Internet of Things device, and uses the encryption chip to encrypt the data to be transmitted before transmitting it. Even through the less secure Internet communication method, the security of data transmission can be ensured to a high degree.

[0029] Furthermore, the use of an encryption chip to encrypt the data to be transmitted includes: the encryption chip uses an asymmetric encryption algorithm to encrypt the data to be transmitted, wherein the key in the encryption chip is generated by the water conservancy Internet of Things platform and written into the encryption chip.

[0030] In this embodiment, the present invention adopts terminal protection based on encryption chip, specifically, by adding a dedicated encryption chip to the water IoT device to achieve secure data transmission. The encryption chip algorithm adopts an asymmetric encryption algorithm, and its key is generated by the IoT platform and written into the encryption chip. During the data transmission interaction process, encryption and decryption are performed to effectively avoid man-in-the-middle attacks caused by fake base stations.

[0031] Furthermore, the calling of the data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted to obtain corresponding sensitivity values ​​includes: performing feature analysis on the data to be transmitted to obtain key features, wherein the key features include data type, data accuracy, data timeliness, data integrity, data source, and data purpose; calling the data sensitivity analysis model to perform in-depth analysis and processing on the key features to obtain the corresponding sensitivity values.

[0032] In this embodiment, before determining the sensitivity value of the data to be transmitted, it is necessary to first determine which features of the data to be transmitted are related to its sensitivity. In fact, multiple data features such as data type, data accuracy, data timeliness, data integrity, data source, and data usage purpose can characterize the sensitivity of the data to be transmitted, so it is difficult to determine the sensitivity value of the data to be transmitted through a single functional relationship or comparison table. In this regard, the present invention sets up the above-mentioned data sensitivity analysis model, which performs in-depth analysis and processing on the above-mentioned multiple key features, and evaluates and obtains the sensitivity value corresponding to the data to be transmitted.

[0033] Among them, data types include personal user data, such as user name, address, billing information, etc., as well as general operational data (such as traffic readings). Personal user data is usually more sensitive than general operational data.

[0034] Data accuracy: refers to the level of detail of water data. High-precision water data may be more easily used for improper purposes, and the corresponding data sensitivity is higher. The level of detail can be determined based on the type of subject matter contained in the data, the sampling interval of the data, etc. The type of subject matter is, for example, "Flow rate of No. 1 pipe well", "Flow rate of No. 2 pipe well", "Average pipe pressure of No. 1-5 pipe wells", etc. The more the type of subject matter, the more detailed the water data is; the shorter the sampling interval of the data, the more intensive the collection of water data, and the higher the level of detail of the corresponding water data.

[0035] Data timeliness: mainly includes real-time data and historical data. Real-time data is more sensitive than historical data due to its immediacy.

[0036] Data integrity: The more complete the data is, the lower the risk of tampering or corruption, because it is easy for the data to be inconsistent. Therefore, the higher the data integrity, the lower the corresponding data sensitivity, and vice versa.

[0037] Data source: mainly refers to whether the water data comes from key equipment or ordinary equipment. Whether the water equipment is key equipment or ordinary equipment is pre-specified. The data sensitivity of water data from key equipment is significantly higher than that from ordinary equipment.

[0038] Purpose of data use: The purpose and manner in which data is used may affect its sensitivity. For example, data used for monitoring and maintenance is generally more sensitive than data used for marketing.

[0039] Furthermore, the data sensitivity analysis model is constructed based on a convolutional network, and the data sensitivity analysis model includes an input layer, a convolutional feature layer, an activation function, a pooling layer, a normalization layer, a fully connected layer, and an output layer; wherein the activation function adopts the ReLU function, and the normalization layer adopts batch normalization.

[0040] In this embodiment, the present invention constructs a data sensitivity analysis model based on a convolutional network, see Figure 7 As shown in Figure 1, the data sensitivity analysis model includes input layer, convolutional feature layer, activation function, pooling layer, normalization layer, fully connected layer, and output layer. The functions of each layer are explained as follows: Input layer: used to receive the original key features.

[0041] Convolutional feature layer: The convolutional layer is the core of CNN, which uses convolution kernels to slide on the input key feature data to extract convolution features. Each filter is responsible for detecting specific features in the key feature data, such as data type, data accuracy, data timeliness, data integrity, data source, data usage purpose, etc. The convolution operation produces a feature map, which represents the feature response of the input key feature data under the convolution kernel.

[0042] Activation function: It is set and used after the convolution layer. It is preferred to use the ReLU function to introduce nonlinearity so that the convolutional network can learn more complex features.

[0043] Pooling layer: used to reduce the spatial size of the feature map determined by the convolutional feature layer, reduce the number of parameters and the amount of calculation, while maintaining the important information of the feature. The pooling operation can be completed by using maximum pooling or average pooling.

[0044] Normalization layer: used to adjust the activation values ​​of the above feature maps to make them more evenly distributed, which helps to speed up training and improve the generalization ability of the data sensitivity analysis model. Batch Normalization technology is preferably used.

[0045] Fully connected layer: Set in the last few layers of the convolutional network, each neuron in the fully connected layer is connected to all the activation values ​​of the previous layer. The flattened feature map is classified or regressed through the fully connected layer to obtain the predicted sensitivity value.

[0046] Output layer: used to output the predicted sensitivity value.

[0047] Furthermore, the data sensitivity analysis model is trained in the following manner: collecting several groups of first data corresponding to data type, data accuracy, data timeliness, data integrity, data source, and data usage purpose, each group of first data contains a corresponding first sensitivity label; combining the above several groups of data in pairs or more to obtain several groups of second data, each group of second data contains a corresponding second sensitivity label, and the second sensitivity label is obtained by semantically analyzing all the first sensitivity labels contained in each group of second data by a general large model; using the second data to train the data sensitivity analysis model until the training termination condition is met, and the training termination condition is constructed with a minimum loss function; the calculation formula of the loss function is as follows: ; In the above formula, is the loss function, is the number of training data from the second data that have been put into training, is the second sensitivity label of the i-th training data put into training, The predicted sensitivity label of the i-th training data output by the data sensitivity analysis model; is a drop coefficient, which decreases as the amount of training data from the second data that has been put into training increases, is the weight coefficient matrix of the i-th training data.

[0048] In this embodiment, since it is difficult to determine the sensitivity value of the data to be transmitted through a single functional relationship or a comparison table, the present invention adopts a hybrid strategy when determining the training data. Specifically, several groups of first data corresponding to the data type, data accuracy, data timeliness, data integrity, data source, and data use purpose are collected, and each group of first data contains several groups of corresponding first sensitivity labels, and each group of first sensitivity labels corresponds to the above-mentioned key features. Then, a combination of two or more is adopted to obtain several groups of second data. For example, at least some groups of first data corresponding to the data type and data accuracy are combined into a group of second data, at least some groups of first data corresponding to the data type, data accuracy, and data timeliness are combined into a group of second data, and at least some groups of first data corresponding to data timeliness, data integrity, data source, and data use purpose are combined into a group of second data, and so on. It should be noted that when combining, the number of data items in each group of first data to be combined needs to be the same, which is conducive to the subsequent comprehensive analysis of the two first sensitivity labels. All the second data are then constructed into a training data set, and the data sensitivity analysis model is fully trained using the training data set until the training termination condition is met. At this time, the data sensitivity analysis model can analyze the key features of the input and obtain accurate sensitivity values.

[0049] Among them, each group of first data contains a certain number (one for each data) of first sensitivity labels, and the first sensitivity label is used to characterize the sensitivity value of the data to be transmitted when the corresponding key feature exists. The first sensitivity label is manually labeled or automatically labeled by a machine.

[0050] An example is as follows: collect several groups of first data Ai=[ai,bi], Bi, Ci, Di, Ei, Fi corresponding to the data type, data accuracy, data timeliness, data integrity, data source, and data usage purpose, respectively, where ai is a source data corresponding to the above key feature "data type", and bi is the first sensitivity label of the source data manually or automatically labeled by the machine.

[0051] Through the above combinations of two or more, several groups of second data aj=[aaj, bbj], bj, cj, dj, ej, fj are obtained, where aaj is, for example, a source data obtained by combining the data type and the data precision, and bbj is the second sensitivity label of the source data. The second sensitivity label is determined by using a general large model to perform semantic analysis on the first sensitivity label of a source data corresponding to the "data type" and the other first sensitivity label of a source data corresponding to the "data precision", and determine a new second sensitivity label, which is used to characterize the sensitivity value corresponding to the fused data (composed of the two source data) of the two when the "data type" and "data precision" exist at the same time.

[0052] The general large model can implement semantic analysis of multiple first sensitivity labels, thereby obtaining a sensitivity value of the data to be transmitted when the key features of the corresponding items are comprehensively represented. The general large model preferably uses the GPT large model, and can also use the BERT large model, Belle large model, etc., which is not specifically limited in the present invention.

[0053] Further, determining the target communication mode according to the sensitivity value includes: when the sensitivity value is higher than a sensitivity threshold, setting the target communication mode to the operator APN private network; when the sensitivity value is not higher than the sensitivity threshold, setting the target communication mode to the Internet.

[0054] In this embodiment, the sensitivity value of the data to be transmitted is predicted by the above method, and the sensitivity value is compared with the sensitivity threshold. If it is higher than the sensitivity threshold, it means that it is sensitive data, and the operator's APN private network is used for transmission to ensure data security. If it is not higher than the sensitivity threshold, it means that it is non-sensitive data, and the Internet is used for transmission to increase the data transmission rate, so that the water IoT platform can obtain the data of each water IoT device in a more real-time manner.

[0055] See also Figure 8 As shown, a method for secure transmission between a water conservancy Internet of Things device and a platform in an embodiment of the present invention is applied to a water conservancy Internet of Things device, and includes an encryption module, a sensitivity analysis module, and a communication transmission module; the encryption module is used to encrypt the data to be transmitted using an encryption chip; the sensitivity analysis module is used to call a data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted, and obtain a corresponding sensitivity value; the communication transmission module is used to determine a target communication mode according to the sensitivity value, and transmit the encrypted data to be transmitted to the water conservancy Internet of Things platform based on the target communication mode; wherein the target communication mode is the operator's APN private network or the Internet.

[0056] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in the above embodiment.

[0057] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0058] An embodiment of the present invention further discloses a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor of an electronic device, any of the above methods is implemented.

[0059] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0060] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable load balancing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0061] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0062] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0063] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for secure transmission between water Internet of Things devices and platforms, applied to water Internet of Things devices, It is characterized in that The method comprises the following steps: using an encryption chip to encrypt data to be transmitted; calling a data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted to obtain a corresponding sensitivity value; determining a target communication mode according to the sensitivity value, and transmitting the encrypted data to be transmitted to a water affairs Internet of Things platform based on the target communication mode; wherein the target communication mode is an operator APN private network or the Internet; The calling of the data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted to obtain a corresponding sensitivity value includes: performing feature analysis on the data to be transmitted to obtain key features, wherein the key features include data type, data accuracy, data timeliness, data integrity, data source, and data use purpose; calling the data sensitivity analysis model to perform in-depth analysis and processing on the key features to obtain the corresponding sensitivity value; The data sensitivity analysis model is constructed based on a convolutional network, and includes an input layer, a convolutional feature layer, an activation function, a pooling layer, a normalization layer, a fully connected layer, and an output layer; wherein the activation function adopts a ReLU function, and the normalization layer adopts batch normalization; The data sensitivity analysis model is trained in the following manner: collecting a number of groups of first data corresponding to data type, data accuracy, data timeliness, data integrity, data source, and data usage purpose, each group of first data contains a corresponding first sensitivity label; combining the above-mentioned groups of data in pairs or more to obtain a number of groups of second data, each group of second data contains a corresponding second sensitivity label, and the second sensitivity label is obtained by semantically analyzing all the first sensitivity labels contained in each group of second data by a general large model; using the second data to train the data sensitivity analysis model until the training termination condition is met, and the training termination condition is constructed with a minimum loss function; the calculation formula of the loss function is as follows: ; In the above formula, is the loss function, is the number of training data from the second data that have been put into training, is the second sensitivity label of the i-th training data put into training, The predicted sensitivity label of the i-th training data output by the data sensitivity analysis model; is a drop coefficient, which decreases as the amount of training data from the second data that has been put into training increases, is the weight coefficient matrix of the i-th training data.

2. A method for secure transmission between water Internet of Things devices and platforms according to claim 1, Features: The method of using an encryption chip to encrypt the data to be transmitted includes: the encryption chip uses an asymmetric encryption algorithm to encrypt the data to be transmitted, wherein the key in the encryption chip is generated by the water conservancy Internet of Things platform and written into the encryption chip.

3. A method for secure transmission between water Internet of Things devices and platforms according to claim 1, Features: The determining of the target communication mode according to the sensitivity value includes: when the sensitivity value is higher than a sensitivity threshold, setting the target communication mode to the operator APN private network; when the sensitivity value is not higher than the sensitivity threshold, setting the target communication mode to the Internet.

4. A system for secure transmission between water Internet of Things devices and platforms based on the method according to any one of claims 1 to 3, applied to water Internet of Things devices, comprising an encryption module, a sensitivity analysis module, and a communication transmission module; Features: The encryption module is used to encrypt the data to be transmitted using an encryption chip; the sensitivity analysis module is used to call the data sensitivity analysis model to perform sensitivity analysis on the data to be transmitted and obtain a corresponding sensitivity value; the communication transmission module is used to determine the target communication mode according to the sensitivity value, and transmit the encrypted data to be transmitted to the water conservancy Internet of Things platform based on the target communication mode; wherein the target communication mode is the operator's APN private network or the Internet.

5. An electronic device, include: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-3.

6. A computer storage medium having a computer program stored thereon, Features: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is executed.

7. A computer program product comprising computer program instructions, Features: When the computer program instructions are executed by a processor of an electronic device, the method according to any one of claims 1 to 3 is implemented.

Images