CN112565254B - Data transmission method, device, equipment and computer readable storage medium - Google Patents
Data transmission method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112565254B CN112565254B CN202011406764.2A CN202011406764A CN112565254B CN 112565254 B CN112565254 B CN 112565254B CN 202011406764 A CN202011406764 A CN 202011406764A CN 112565254 B CN112565254 B CN 112565254B
- Authority
- CN
- China
- Prior art keywords
- model
- data
- noise
- target
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/12—Applying verification of the received information
- H04L63/123—Applying verification of the received information received data contents, e.g. message integrity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/04—Protocols for data compression, e.g. ROHC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3236—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions
- H04L9/3239—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD
Abstract
The invention discloses a data transmission method, which comprises the following steps: acquiring target data, and coding the target data to obtain a compressed code corresponding to the target data; determining a target model corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code; determining high importance characteristics/parameters corresponding to the compressed codes based on the model results, and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise added codes; and transmitting the noise-added code. The invention also discloses a data transmission device, equipment and a computer readable storage medium. Compared with the prior art which adopts integral encryption transmission, the invention only needs to add noise to the important part in the data, reduces the transmission pressure, and simultaneously can effectively avoid the risk of leakage caused by interception of the data, and realizes the safe transmission of the data.
Description
Technical Field
The present invention relates to the field of financial technology (Fintech), and in particular, to a data transmission method, apparatus, device, and computer-readable storage medium.
Background
In recent years, with the development of financial technology (Fintech), particularly internet finance, data transmission technology has been introduced into daily services of financial institutions such as banks. In the daily service process of financial institutions such as banks, a large amount of data is generated, and some important key information may exist in the data, such as an identification number included in picture data, and therefore, when the data is transmitted, the data is often required to be protected to ensure the security of data transmission. Therefore, how to protect the transmitted data is an important task that financial institutions such as banks need to do.
In the prior art, in order to ensure the security of data transmission, an encryption mode is generally adopted, that is, data to be transmitted is encrypted, and then the encrypted data is transmitted, so that only a party with a password can acquire the data and decrypt the data to obtain information therein.
However, such a data transmission method is rigid, and aims at the data integrity, but not all information elements in the data are important, for example, in the picture data, there are not only relatively important identification numbers, but also unimportant information elements such as background images, and there is no need to protect the information elements such as background images, which is obvious that the existing data transmission method is not intelligent enough, and cannot realize targeted protection.
Disclosure of Invention
The invention mainly aims to provide a data transmission method, a data transmission device, data transmission equipment and a computer readable storage medium, and aims to realize the safe transmission of data.
In order to achieve the above object, the present invention provides a data transmission method, which includes the following steps:
acquiring target data, and coding the target data to obtain a compressed code corresponding to the target data;
determining a target model corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code;
determining high importance characteristics/parameters corresponding to the compressed codes based on the model results, and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise added codes;
and transmitting the noise-added codes.
Optionally, the step of obtaining target data and encoding the target data to obtain a compressed code corresponding to the target data includes:
acquiring target data, and determining elements of the target data and the occurrence frequency of the elements in the target data;
and determining a compressed symbol corresponding to the element based on the occurrence frequency, and encoding the target data by using the compressed symbol to obtain a compressed code corresponding to the target data.
Optionally, the step of determining, based on the model result, a high importance feature/parameter corresponding to the compression coding includes:
determining the model position of the model result in the target model, and determining a model branch corresponding to the model position;
and determining high-importance characteristics/parameters corresponding to the compression coding based on the model branches.
Optionally, the step of determining, based on the model branch, a high importance feature/parameter corresponding to the compression coding includes:
determining model nodes corresponding to the model branches of the model results according to a preset backtracking principle;
and determining high-importance characteristics/parameters corresponding to the compression coding based on the model nodes.
Optionally, the step of performing noise processing on the high importance feature/parameter to obtain a noise-added code includes:
determining the data type of the target data, and determining target noise corresponding to the data type;
and determining a noise adding position corresponding to the high-importance feature/parameter, and performing noise adding processing on the high-importance feature/parameter based on the target noise and the noise adding position.
Optionally, the step of determining the target model corresponding to the target data includes:
acquiring data content of the target data, and analyzing the number of target objects in the data content;
and determining a classification type corresponding to the target data based on the number, and determining a target model corresponding to the classification type.
Optionally, after the step of transmitting the noisy code, the data transmission method further includes:
if the noise-added code is detected, verifying whether the noise-added code is complete or not based on the high-importance feature/parameter;
and if the data is complete, restoring the noise-added code to obtain target data.
Optionally, before the step of verifying whether the noisy code is complete based on the high-importance feature/parameter if the noisy code is detected, the data transmission method further includes:
calculating a first verification identifier corresponding to the high-importance feature/parameter;
if the noisy code is detected, verifying whether the noisy code is complete based on the high importance feature/parameter includes:
if the noise-added code is detected, calculating a second verification identifier corresponding to the high-importance feature/parameter, and acquiring the first verification identifier;
and verifying whether the noise-added code is complete or not based on the first verification identifier and the second verification identifier, wherein if the first verification identifier is equal to the second verification identifier, the noise-added code is determined to be complete.
In addition, to achieve the above object, the present invention also provides a data transmission device, including:
the encoding module is used for acquiring target data and encoding the target data to obtain a compressed code corresponding to the target data;
the model module is used for determining a target model corresponding to the target data and inputting the compressed codes into the target model to obtain model results corresponding to the compressed codes;
the noise adding module is used for determining high importance characteristics/parameters corresponding to the compressed codes based on the model result and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise adding codes;
and the transmission module is used for transmitting the noise-added codes.
Optionally, the encoding module is further configured to:
acquiring target data, and determining elements of the target data and the occurrence frequency of the elements in the target data;
and determining a compressed symbol corresponding to the element based on the occurrence frequency, and encoding the target data by using the compressed symbol to obtain a compressed code corresponding to the target data.
Optionally, the noise adding module is further configured to:
determining the model position of the model result in the target model, and determining a model branch corresponding to the model position;
based on the model branch, high importance features/parameters corresponding to the compression encoding are determined.
Optionally, the noise adding module is further configured to:
determining model nodes corresponding to the model branches of the model results according to a preset backtracking principle;
and determining high-importance characteristics/parameters corresponding to the compression coding based on the model nodes.
Optionally, the noise adding module is further configured to:
determining the data type of the target data, and determining target noise corresponding to the data type;
and determining a noise adding position corresponding to the high-importance feature/parameter, and performing noise adding processing on the high-importance feature/parameter based on the target noise and the noise adding position.
Optionally, the model module is further configured to:
acquiring data content of the target data, and analyzing the number of target objects in the data content;
and determining a classification type corresponding to the target data based on the number, and determining a target model corresponding to the classification type.
Optionally, the data transmission apparatus includes a decoding module, and the decoding module is configured to:
if the noise-added code is detected, verifying whether the noise-added code is complete or not based on the high-importance feature/parameter;
and if the data is complete, restoring the noise-added code to obtain target data.
Optionally, the data transmission apparatus includes a verification module, and the verification module is configured to:
calculating a first verification identifier corresponding to the high-importance feature/parameter;
if the noise-added code is detected, calculating a second verification identifier corresponding to the high-importance feature/parameter, and acquiring the first verification identifier;
and verifying whether the noise-added code is complete or not based on the first verification identifier and the second verification identifier, wherein if the first verification identifier is equal to the second verification identifier, the noise-added code is determined to be complete.
In addition, to achieve the above object, the present invention also provides a data transmission device, including: a memory, a processor and a data transmission program stored on the memory and executable on the processor, the data transmission program when executed by the processor implementing the steps of the data transmission method as described above.
Furthermore, to achieve the above object, the present invention also provides a computer readable storage medium having stored thereon a data transmission program which, when executed by a processor, implements the steps of the data transmission method as described above.
The data transmission method provided by the invention comprises the steps of acquiring target data, and coding the target data to obtain a compressed code corresponding to the target data; determining a target model corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code; determining high importance characteristics/parameters corresponding to the compressed codes based on the model results, and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise added codes; and transmitting the noise-added code. Compared with the prior art which adopts encryption transmission, the invention adopts a compression mode to compress data into compression codes for transmission, only needs to add noise to important parts in the data in the process, can effectively avoid the risk of leakage caused by interception of the data while reducing the transmission pressure, and realizes the safe transmission of the data.
Drawings
Fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a data transmission method according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of a target model in a first embodiment of the data transmission method of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
The device of the embodiment of the invention can be a mobile terminal or a server device.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration of the apparatus shown in fig. 1 is not intended to be limiting of the apparatus and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a data transmission program.
The operating system is a program for managing and controlling data transmission equipment and software resources, and supports the operation of a network communication module, a user interface module, a data transmission program and other programs or software; the network communication module is used for managing and controlling the network interface 1002; the user interface module is used to manage and control the user interface 1003.
In the data transfer apparatus shown in fig. 1, the data transfer apparatus calls a data transfer program stored in a memory 1005 by a processor 1001 and performs operations in various embodiments of the data transfer method described below.
Based on the above hardware structure, the embodiment of the data transmission method of the present invention is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a data transmission method of the present invention, where the method includes:
step S10, acquiring target data, and coding the target data to obtain a compressed code corresponding to the target data;
s20, determining a target model corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code;
step S30, determining high importance characteristics/parameters corresponding to the compressed codes based on the model results, and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise added codes;
and S40, transmitting the noise-added codes.
The data transmission method is applied to data transmission equipment, the data transmission equipment can be a terminal, a robot or PC equipment, and for convenience of description, the data transmission equipment is referred to as transmission equipment for short.
In the prior art, in order to reduce transmission pressure, data to be transmitted is generally compressed into shorter bytes for transmission; however, if the security of transmission is considered, generally, only the original data is encrypted integrally, or the data is encrypted after being compressed, and the important information in the data cannot be protected in a targeted manner, for example, when an identification card photo is transmitted, the identification card number is important information, in the prior art, the identification card number cannot be protected only by transmission, but only a relatively clumsy identification card photo can be encrypted, and in the transmission process, if the identification card number is lost, the identification card cannot be perceived in advance.
Under the background, in the embodiment, a compression mode is adopted, data to be transmitted is compressed to obtain compression codes, high-importance features/parameters in the compression codes are extracted and denoised, transmission is facilitated, meanwhile, data targeted protection is achieved, and data transmission safety is improved.
In this embodiment, the transmission device includes an encoder (an encoding module), a model layer (including multiple models, such as a decision tree model and a linear regression model), and a decoder (a decoding module), where the decoder is configured to compress data into compression encoding, the decoder is configured to perform data restoration on the compression encoding, and the model layer is configured to perform importance analysis on parameters in the compression encoding, so as to determine important parameters therein, and perform noise processing on the important parameters.
It should be noted that, the encoder and the decoder form an unsupervised neural network model, before the implementation, the transmission device learns the implicit characteristics of the input data through machine learning, such as deep neural network learning, this process is coding (coding), and at the same time, the original input data is reconstructed by using the learned characteristics, which is decoding (decoding), that is, in the training process, the data is converted into intermediate variables, that is, compression coding, and then the intermediate variables are converted into the original input data, so as to train and obtain the encoder and the decoder. In addition, an intermediate variable, i.e., compression coding, is used to train a decision tree model or a linear regression model, etc., so as to obtain a model layer. Since machine learning is a relatively sophisticated technique, the specific training process will not be described in detail here.
The respective steps will be described in detail below:
and S10, acquiring target data, and coding the target data to obtain a compression code corresponding to the target data.
In this embodiment, the transmission device acquires target data, that is, data to be transmitted, and then encodes the target data to compress the size of the target data, so as to obtain a compressed code corresponding to the target data, where the target data includes text data, picture data, video data, and the like.
Further, in an embodiment, step S10 includes:
step a1, acquiring target data, and determining elements of the target data and the occurrence frequency of the elements in the target data;
in one embodiment, a transmission device obtains target data, and first determines elements of the target data and occurrence frequencies of the elements in the target data, where an element refers to a feature in the target data, for example, there are 99 gray points and 5 white points in picture data, and then the gray points and the white points are elements of the target data, and the values 99 and 5 are the occurrence frequencies of the elements in the target data.
Step a2, determining a compressed symbol corresponding to the element based on the occurrence frequency, and encoding the target data by using the compressed symbol to obtain a compressed code corresponding to the target data;
in an embodiment, the transmission device determines, according to frequencies of elements in the target data, compression symbols corresponding to the elements, specifically, an element with a higher frequency of occurrence is represented by a first symbol, and an element with a lower frequency of occurrence is represented by a second symbol, where the first symbol is a short symbol and the second symbol is a long symbol, so that a total symbol length of the target data is shortest, that is, the target data is compressed minimally, and finally, the target data is encoded by using the compression symbols, so as to obtain compression codes corresponding to the target data, that is, the target data is represented by using the compression codes of shorter bytes, thereby achieving compression of the target data. The frequency of the elements in the target data is higher or lower, which can be obtained by comparing the elements in the target data.
If there are three ABC elements in the target data, and the frequency of the three ABC elements is a > B > C, a =1, B =01, C =001, that is, a with a higher frequency of occurrence is represented by a shorter symbol 1, B with a second highest frequency of occurrence is represented by a second shorter symbol 01, C with a lower frequency of occurrence is represented by a longer symbol 001, and so on.
And S20, determining a target model corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code.
In this embodiment, after obtaining the compressed code corresponding to the target data, the transmission device further determines a target model corresponding to the target data, and then inputs the compressed code into the target model, so as to obtain a model result corresponding to the compressed code, that is, the transmission device extracts important parameters in the compressed code, that is, high-importance features/parameters, through the target model. Before the specific implementation, a large number of compressed codes are used as the input of the target model in advance, the labeled model result is used as the output of the target model, and the target model is obtained through training, and a decision tree model or a linear regression model is specifically trainable, which is not described in detail herein.
Further, in an embodiment, the step of determining the target model corresponding to the target data includes:
step b1, acquiring data content of the target data, and analyzing the number of target objects in the data content;
in an embodiment, the transmission device first obtains data content of the target data, if the target data is picture data, obtains data content in the picture data, such as people and things in the picture data, and analyzes the number of target objects in the data content, wherein the target objects specifically refer to identification purposes of the target data, such as judging whether the current picture data is a cat image; and judging whether the current picture data is man or not, wherein the number of the target objects is the number of the identification targets.
And b2, determining the classification type corresponding to the target data based on the number, and determining the target model corresponding to the classification type.
Then, determining classification types corresponding to the target data according to the number of the target objects, wherein the classification types comprise a two-classification problem and a multi-classification problem, and finally determining a corresponding target model according to the classification types corresponding to the target data, wherein if the two-classification problem exists, the corresponding target model is determined to be a decision tree model; and if the multi-classification problem exists, determining the corresponding target model to be a linear regression model and the like. Specifically, the mapping relationship between the classification type and the target model may be established in advance, so that after the classification type corresponding to the target data is determined, the target model corresponding to the target data may be determined according to the mapping relationship.
And finally, inputting the compressed codes into a target model so as to obtain a model result, wherein if the target data is picture data, animals exist in the picture data, and the target model finally outputs a result of 'cat'.
And S30, determining high importance characteristics/parameters corresponding to the compressed codes based on the model results, and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise added codes.
In this embodiment, the transmission device determines, according to the model result, the high-importance features/parameters corresponding to the compressed codes, that is, determines which parameters are important for the model result, for example, if the model result is "cat", then it needs to find the high-importance features/parameters that are important for "cat" from all the compressed codes, that is, which parameters are related to the "cat" information, and then perform noise processing on the high-importance features/parameters, so as to obtain the noise-added codes, so that even if the target data is intercepted halfway in the transmission process, other devices cannot restore to the original "cat" due to the noise addition.
Further, in an embodiment, the step of determining the high importance feature/parameter corresponding to the compression encoding based on the model result comprises:
step c1, determining the model position of the model result in the target model, and determining a model branch corresponding to the model position;
in an embodiment, in the process of determining the high-importance feature/parameter, the transmission device determines a model position of a model result in the target model, and then determines a corresponding model branch according to the model position of the model result, it should be noted that the target model is a tree model, as shown in fig. 3, each circle represents one node, each node represents one parameter, the lowest node is the model result, that is, the model result is diverse, if the picture data includes both a cat and a tree, the finally output model result has both a "cat" and a "tree", that is, corresponds to two model results, and the model branch refers to a path traced back to a model root node according to the model result, as shown in fig. 3, 1 → 2 → 3 constitutes a model branch.
And c2, determining high-importance characteristics/parameters corresponding to the compression coding based on the model branches.
Then, the transmission device determines the high importance characteristic/parameter corresponding to the compression coding according to the model branch where the model result is located.
Specifically, in an embodiment, step c2 includes:
step c21, determining model nodes corresponding to the model branches of the model results according to a preset backtracking principle;
in an embodiment, the transmission device determines the model node corresponding to the model result at the model branch according to a preset backtracking principle, where the backtracking principle refers to performing backtracking according to a judgment path of the model result at the target model, as shown in fig. 3, if the model result is 1, backtracking obtains 2 and 3 as key model nodes.
And c22, determining high-importance characteristics/parameters corresponding to the compression coding based on the model nodes.
Then, according to the model node, determining a high importance feature/parameter corresponding to the compression coding, as shown in fig. 3, the features corresponding to 2 and 3 are the high importance feature/parameter, for example, when "cat" is judged, "tail" is the high importance feature/parameter, etc.
In another embodiment, in order to reduce the workload of noise addition on the high-importance features/parameters subsequently, when determining the high-importance features/parameters, only the starting node and the ending node of the model branch may be selected, the features corresponding to the starting node and the ending node are used as the high-importance features/parameters, and the features of the intermediate nodes are ignored, etc.
Further, in an embodiment, the step of performing noise processing on the high importance feature/parameter to obtain a noise-added code includes:
step c3, determining the data type of the target data, and determining target noise corresponding to the data type;
in an embodiment, the transmission device determines a data type of target data, where the data type includes text data, picture data, video data, and the like, and determines corresponding target noise according to the data type, and taking the picture data as an example, the target noise corresponding to the picture data may be salt-pepper noise or gaussian noise, and the like.
And c4, determining a noise adding position corresponding to the high-importance feature/parameter, and performing noise adding processing on the high-importance feature/parameter based on the target noise and the noise adding position.
Then, determining a noise adding position corresponding to the high importance feature/parameter, and performing noise adding processing on the high importance feature/parameter according to the target noise and the noise adding position, specifically, taking the target data as picture data, taking the target noise as salt-pepper noise as an example, firstly specifying a signal-to-noise ratio (SNR) with a value range of [0,1], then calculating the total pixel number (SP) in the picture data to obtain the pixel number (NP = SP (1-SNR) to be added with noise, then obtaining each pixel position (P (i, j) to be added with noise, namely the noise adding position of the high importance feature/parameter, and specifying the pixel value to be 255 or 0, thereby completing the noise adding processing on the high importance feature/parameter. And obtaining the noise-added code after noise-adding treatment.
And S40, transmitting the noise-added codes.
In this embodiment, after the noisy codes are obtained, the noisy codes may be transmitted, so that the transmission device may perform data transmission with a shorter code, and since the high importance features/parameters are processed by the noisy codes, there is no need to worry about the risk of data leakage.
The embodiment acquires target data and encodes the target data to obtain a compressed code corresponding to the target data; determining a target model corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code; determining high importance characteristics/parameters corresponding to the compressed codes based on the model results, and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise added codes; and transmitting the noise-added code. Compared with the prior art which adopts encryption transmission, the invention adopts a compression mode to compress data into compression codes for transmission, only needs to add noise to important parts in the data in the process, can effectively avoid the risk of leakage caused by interception of the data while reducing the transmission pressure, and realizes the safe transmission of the data.
Further, a second embodiment of the data transmission method of the present invention is proposed based on the first embodiment of the data transmission method of the present invention.
The second embodiment of the data transmission method differs from the first embodiment of the data transmission method in that after step S40, the data transmission method further comprises:
step S50, if the noise-added code is detected, verifying whether the noise-added code is complete or not based on the high-importance characteristic/parameter;
and S60, if the data is complete, restoring the noise-added code to obtain target data.
The transmission device of the embodiment comprises an encoder, a model layer and a decoder, wherein when the noise-added code is detected, the transmission device performs data restoration through the decoder, and in the decoding process, whether important information in target data is lost or not can be verified through high-importance characteristics/parameters, so that the target data can be well restored.
The respective steps will be described in detail below:
and S50, if the noise-added code is detected, verifying whether the noise-added code is complete or not based on the high-importance characteristic/parameter.
In this embodiment, if the transmission device detects the noisy code, it verifies whether the noisy code is complete, that is, whether important information in the target data is lost, according to the high-importance feature/parameter corresponding to the noisy code.
Specifically, in an embodiment, before step S50, the data transmission method further includes:
step d, calculating a first verification identifier corresponding to the high-importance feature/parameter;
that is, after the high-importance feature/parameter is determined, the first verification identifier corresponding to the high-importance feature/parameter, such as the MD5 value, is calculated and used as a basis for subsequent verification, and it can be understood that if the high-importance feature/parameter is lost or lost during transmission, the MD5 value will change accordingly, so that the MD5 value can be used as the first verification identifier corresponding to the high-importance feature/parameter.
Step S50 includes:
step e1, if the noise-added code is detected, calculating a second verification identifier corresponding to the high-importance feature/parameter, and acquiring the first verification identifier;
in an embodiment, if the transmission device detects the noisy code, the transmission device calculates a second verification identifier of the high-importance feature/parameter corresponding to the noisy code, and obtains a first verification identifier calculated before transmission.
And e2, verifying whether the noise-added code is complete or not based on the first verification identifier and the second verification identifier, wherein if the first verification identifier is equal to the second verification identifier, the noise-added code is determined to be complete.
And then, comparing the first verification identification with the second verification identification, judging whether the first verification identification is equal to the second verification identification, if so, determining that the noise-added code is complete, and data loss or loss phenomenon does not occur in the transmission process, otherwise, determining that the noise-added code is incomplete, and data loss or loss phenomenon occurs in the transmission process, thereby sending prompt information to prompt related personnel to make corresponding actions.
And S60, if the data is complete, restoring the noise-added code to obtain target data.
In this embodiment, if it is determined that the noisy codes are complete, the transmission device performs data reduction on the loaded codes to obtain target data, where a specific reduction process is opposite to a coding process, and details are not described herein.
According to the embodiment, target data to be transmitted is compressed through encoding, high-importance features/parameters corresponding to the compressed encoding are further determined, so that important parameters hidden in the compressed encoding are extracted, then noise processing is performed on the high-importance features/parameters, the high-importance features/parameters are protected pertinently, information leakage risks are reduced, the quality of restored data can be tracked in the decoding process, whether important features are lost or not is judged, and safe transmission of the data is achieved.
The invention also provides a data transmission device. The data transmission device of the present invention includes:
the encoding module is used for acquiring target data and encoding the target data to obtain a compressed code corresponding to the target data;
the model module is used for determining a target model corresponding to the target data and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code;
the noise adding module is used for determining high importance characteristics/parameters corresponding to the compressed codes based on the model result and carrying out noise adding processing on the high importance characteristics/parameters to obtain noise adding codes;
and the transmission module is used for transmitting the noise-added codes.
Optionally, the encoding module is further configured to:
acquiring target data, and determining elements of the target data and the occurrence frequency of the elements in the target data;
and determining a compressed symbol corresponding to the element based on the occurrence frequency, and encoding the target data by using the compressed symbol to obtain a compressed code corresponding to the target data.
Optionally, the noise adding module is further configured to:
determining the model position of the model result in the target model, and determining a model branch corresponding to the model position;
based on the model branch, high importance features/parameters corresponding to the compression encoding are determined.
Optionally, the noise adding module is further configured to:
determining model nodes corresponding to the model branches of the model results according to a preset backtracking principle;
and determining high-importance characteristics/parameters corresponding to the compression coding based on the model nodes.
Optionally, the noise adding module is further configured to:
determining the data type of the target data, and determining target noise corresponding to the data type;
and determining a noise adding position corresponding to the high-importance feature/parameter, and performing noise adding processing on the high-importance feature/parameter based on the target noise and the noise adding position.
Optionally, the model module is further configured to:
acquiring data content of the target data, and analyzing the number of target objects in the data content;
and determining a classification type corresponding to the target data based on the number, and determining a target model corresponding to the classification type.
Optionally, the data transmission apparatus includes a decoding module, and the decoding module is configured to:
if the noise-added code is detected, verifying whether the noise-added code is complete or not based on the high-importance feature/parameter;
and if the data is complete, restoring the noise-added code to obtain target data.
Optionally, the data transmission apparatus includes a verification module, and the verification module is configured to:
calculating a first verification identifier corresponding to the high-importance feature/parameter;
if the noise-added code is detected, calculating a second verification identifier corresponding to the high-importance feature/parameter, and acquiring the first verification identifier;
and verifying whether the noise-added code is complete or not based on the first verification identifier and the second verification identifier, wherein if the first verification identifier is equal to the second verification identifier, the noise-added code is determined to be complete.
The invention also provides a computer readable storage medium.
The computer-readable storage medium of the present invention has stored thereon a data transmission program which, when executed by a processor, implements the steps of the data transmission method as described above.
The method implemented when the data transmission program running on the processor is executed may refer to each embodiment of the data transmission method of the present invention, and details are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A data transmission method, characterized in that the data transmission method comprises the steps of:
acquiring target data, and coding the target data to obtain a compressed code corresponding to the target data;
determining a corresponding target model according to the classification type corresponding to the target data, and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code;
determining the model position of the model result in the target model, and determining a model branch corresponding to the model position;
determining model nodes corresponding to the model branches of the model results according to a preset backtracking principle;
determining the characteristics corresponding to the starting node and the end node of the model branch as high-importance characteristics/parameters corresponding to the compressed codes based on the model nodes, and performing noise processing on the high-importance characteristics/parameters to obtain noise-added codes;
and transmitting the noise-added codes.
2. The data transmission method according to claim 1, wherein the step of obtaining the target data and encoding the target data to obtain the compressed code corresponding to the target data comprises:
acquiring target data, and determining elements of the target data and the occurrence frequency of the elements in the target data;
and determining a compressed symbol corresponding to the element based on the occurrence frequency, and encoding the target data by using the compressed symbol to obtain a compressed code corresponding to the target data.
3. The data transmission method as claimed in claim 1, wherein the step of performing noise processing on the high importance features/parameters to obtain noise-added codes comprises:
determining the data type of the target data, and determining target noise corresponding to the data type;
and determining a noise adding position corresponding to the high-importance feature/parameter, and performing noise adding processing on the high-importance feature/parameter based on the target noise and the noise adding position.
4. The data transmission method according to claim 1, wherein the step of determining the corresponding object model according to the classification type corresponding to the object data comprises:
acquiring data content of the target data, and analyzing the number of target objects in the data content;
and determining a classification type corresponding to the target data based on the number, and determining a target model corresponding to the classification type.
5. The data transmission method of any of claims 1-4, wherein after the step of transmitting the noisy encoding, the data transmission method further comprises:
if the noise-added code is detected, verifying whether the noise-added code is complete or not based on the high-importance feature/parameter;
and if the data is complete, restoring the noise-added code to obtain target data.
6. The data transmission method as claimed in claim 5, wherein before the step of verifying whether the noisy codes are complete based on the high importance features/parameters if the noisy codes are detected, the data transmission method further comprises:
calculating a first verification identifier corresponding to the high-importance feature/parameter;
if the noise-added code is detected, verifying whether the noise-added code is complete based on the high-importance feature/parameter includes:
if the noise-added code is detected, calculating a second verification identifier corresponding to the high-importance feature/parameter, and acquiring the first verification identifier;
and verifying whether the noise-added code is complete or not based on the first verification identifier and the second verification identifier, wherein if the first verification identifier is equal to the second verification identifier, the noise-added code is determined to be complete.
7. A data transmission apparatus, characterized in that the data transmission apparatus comprises:
the encoding module is used for acquiring target data and encoding the target data to obtain a compressed code corresponding to the target data;
the model module is used for determining a corresponding target model according to the classification type corresponding to the target data and inputting the compressed code into the target model to obtain a model result corresponding to the compressed code;
a noise adding module, configured to determine, based on the model result, a high-importance feature/parameter corresponding to the compressed code, and perform noise adding processing on the high-importance feature/parameter to obtain a noise added code, where the noise adding module is specifically configured to determine a model position of the model result in the target model, and determine a model branch corresponding to the model position; determining model nodes corresponding to the model branches of the model results according to a preset backtracking principle; determining the characteristics corresponding to the starting node and the end node of the model branch as high-importance characteristics/parameters corresponding to the compression coding based on the model node;
and the transmission module is used for transmitting the noise-added codes.
8. A data transmission device, characterized in that the data transmission device comprises: memory, processor and data transmission program stored on the memory and executable on the processor, which data transmission program, when executed by the processor, implements the steps of the data transmission method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that a data transmission program is stored thereon, which when executed by a processor implements the steps of the data transmission method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011406764.2A CN112565254B (en) | 2020-12-04 | 2020-12-04 | Data transmission method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011406764.2A CN112565254B (en) | 2020-12-04 | 2020-12-04 | Data transmission method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112565254A CN112565254A (en) | 2021-03-26 |
| CN112565254B true CN112565254B (en) | 2023-03-31 |
Family
ID=75048064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011406764.2A Active CN112565254B (en) | 2020-12-04 | 2020-12-04 | Data transmission method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112565254B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004064041A1 (en) * | 2003-01-09 | 2004-07-29 | Dilithium Networks Pty Limited | Method and apparatus for improved quality voice transcoding |
| CN109325584A (en) * | 2018-08-10 | 2019-02-12 | 深圳前海微众银行股份有限公司 | Federation's modeling method, equipment and readable storage medium storing program for executing neural network based |
| CN111860727A (en) * | 2020-07-30 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Two-dimensional code generation method, verification method, device and computer-readable storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020076049A1 (en) * | 2000-12-19 | 2002-06-20 | Boykin Patrick Oscar | Method for distributing perceptually encrypted videos and decypting them |
| US20030079222A1 (en) * | 2000-10-06 | 2003-04-24 | Boykin Patrick Oscar | System and method for distributing perceptually encrypted encoded files of music and movies |
| US7433815B2 (en) * | 2003-09-10 | 2008-10-07 | Dilithium Networks Pty Ltd. | Method and apparatus for voice transcoding between variable rate coders |
| CN101409830B (en) * | 2007-10-10 | 2010-10-13 | 华为技术有限公司 | Method and apparatus for judging DCT coefficient block similarity, and encrypting and deciphering image |
| CN111160043B (en) * | 2019-12-31 | 2024-04-30 | 科大讯飞股份有限公司 | Feature encoding method, device, electronic equipment and readable storage medium |
-
2020
- 2020-12-04 CN CN202011406764.2A patent/CN112565254B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004064041A1 (en) * | 2003-01-09 | 2004-07-29 | Dilithium Networks Pty Limited | Method and apparatus for improved quality voice transcoding |
| CN109325584A (en) * | 2018-08-10 | 2019-02-12 | 深圳前海微众银行股份有限公司 | Federation's modeling method, equipment and readable storage medium storing program for executing neural network based |
| CN111860727A (en) * | 2020-07-30 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Two-dimensional code generation method, verification method, device and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112565254A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109558748B (en) | Data processing method and device, electronic equipment and storage medium | |
| US20080178286A1 (en) | Rendered Image Collection of Potentially Malicious Web Pages | |
| CN109902475B (en) | Verification code image generation method and device and electronic equipment | |
| CN111931188A (en) | Vulnerability testing method and system under login scene | |
| CN111628866B (en) | Neural network verification method, device and equipment and readable storage medium | |
| CN111612079A (en) | Data right confirming method, equipment and readable storage medium | |
| CN112884075A (en) | Traffic data enhancement method, traffic data classification method and related device | |
| CN113628116B (en) | Training method and device for image processing network, computer equipment and storage medium | |
| CN112565254B (en) | Data transmission method, device, equipment and computer readable storage medium | |
| CN112348627A (en) | Application pushing method, device, equipment and computer readable storage medium | |
| CN112633200A (en) | Human face image comparison method, device, equipment and medium based on artificial intelligence | |
| CN115314268B (en) | Malicious encryption traffic detection method and system based on traffic fingerprint and behavior | |
| JP7445753B2 (en) | Computer-implemented method for optical character recognition | |
| CN115203674A (en) | Automatic login method, system, device and storage medium for application program | |
| CN113569083A (en) | Intelligent sound box local end digital evidence obtaining system and method based on data traceability model | |
| CN112165594A (en) | Service handling method and device based on video communication and computer equipment | |
| CN106156235A (en) | A kind of picture method for down loading based on Android platform and system | |
| CN105227518A (en) | Server, client, interactive system and information method of sending and receiving | |
| CN115250199B (en) | Data stream detection method and device, terminal equipment and storage medium | |
| CN116740540B (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN112235255B (en) | Voice data processing method and device and server | |
| CN115712887B (en) | Picture verification code identification method and device, electronic equipment and storage medium | |
| CN111294326B (en) | Method, apparatus, device and medium for confirming system data security | |
| CN115862159A (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| Nene | Deep learning approaches to universal and practical steganalysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |