CN115622774A - Data encryption transmission electronic commerce transaction system based on improved particle swarm optimization support vector machine - Google Patents
Data encryption transmission electronic commerce transaction system based on improved particle swarm optimization support vector machine Download PDFInfo
- Publication number
- CN115622774A CN115622774A CN202211235708.6A CN202211235708A CN115622774A CN 115622774 A CN115622774 A CN 115622774A CN 202211235708 A CN202211235708 A CN 202211235708A CN 115622774 A CN115622774 A CN 115622774A
- Authority
- CN
- China
- Prior art keywords
- particles
- particle
- transaction
- time
- class
- 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.)
- Granted
Links
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 11
- 230000005540 biological transmission Effects 0.000 title claims abstract description 10
- 239000002245 particle Substances 0.000 title claims description 268
- 238000005457 optimization Methods 0.000 title description 17
- 230000000739 chaotic effect Effects 0.000 claims abstract description 69
- 238000013528 artificial neural network Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 230000000694 effects Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 230000006399 behavior Effects 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 5
- 230000001131 transforming effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000013139 quantization Methods 0.000 abstract 1
- 210000002569 neuron Anatomy 0.000 description 59
- 239000011159 matrix material Substances 0.000 description 14
- 230000000946 synaptic effect Effects 0.000 description 7
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 6
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 6
- 230000002964 excitative effect Effects 0.000 description 6
- 230000002401 inhibitory effect Effects 0.000 description 6
- 238000010304 firing Methods 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 238000005311 autocorrelation function Methods 0.000 description 2
- 230000003376 axonal effect Effects 0.000 description 2
- 238000005314 correlation function Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005281 excited state Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 210000000225 synapse Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Neurology (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Bioethics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An electronic commerce transaction system with data encryption transmission comprises an intelligent parameter setting module, a block chain module, an encryption module, an electronic commerce transaction evaluation module and a transaction module, wherein the intelligent parameter setting module is used for setting quantization requirements of a user, the block chain module is used for safely storing, updating and recording data and transaction activities, the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence and an asymmetric encryption algorithm based on a neural network chaotic attractor to carry out secondary encryption on the data, the electronic commerce transaction evaluation module selects a support vector machine, selects a proper electronic commerce transaction type for the user, and completes transactions in the transaction module. The invention has the beneficial effects that: the method can effectively prevent the leakage of personal information and transaction information of the client, and guarantee the electronic commerce transaction of the client.
Description
Technical Field
The invention relates to the field of electronic commerce, in particular to an electronic commerce transaction system for data encryption transmission.
Background
With the development of internet technology, network space has become the basis of people's survival and development in modern society, however, due to the insecurity of the internet, various information security problems exist, and network attacks include disguise, deception, eavesdropping, illegal access, tampering, repudiation, counterfeiting, denial of service, spreading viruses, and the like. The block chain is a new data structure, has dispersivity, does not need trust, is owned, managed and supervised by all nodes in the network, is not controlled by a single party, is a novel financial mode of commercial banks at present, mainly takes a core enterprise in electronic commerce as an entry point, provides related financial products and electronic commerce services through the contact of a plurality of enterprises in the electronic commerce, and can improve the business structure of the commercial banks to a certain extent, so that the commercial banks have stronger competitive advantages. Generally, the authenticity of data depends on the trust of a system center or a third-party entity, such as a master node, a central database, a system leader, a database administrator and the like, once the system center is not trusted any more, the authenticity of the data is damaged and is difficult to find, so that it is necessary to encrypt the data of an e-commerce platform, the encrypted data of the e-commerce platform does not have the centralization of nodes, servers and databases, the operation and maintenance of the system do not depend on management personnel, network nodes strictly package digital fingerprints of transaction information in a specific time into blocks and quickly broadcast the blocks to the whole network, and a hash technology is combined to form a tightly-linked chain among the blocks so as to form a highly secure public account, namely a block chain, so that the block chain technology has a good effect on data encryption.
Disclosure of Invention
In view of the above problems, the present invention is directed to an e-commerce transaction system with encrypted data transmission.
The purpose of the invention is realized by the following technical scheme:
an electronic commerce transaction system for data encryption transmission is characterized by comprising an intelligent parameter setting module, a blockchain module, an encryption module, an electronic commerce transaction evaluation module and a transaction module, wherein the intelligent parameter setting module is used for quantifying the requirements of users, including transaction IDs, transaction types, timestamps, privacy levels, transaction objects, transaction addresses and transaction amounts, is established in a dictionary mode and comprises keys and key values, the quantified requirements of the users are stored in the blockchain module, the blockchain module is used for safely storing, updating, recording data and transaction activities, sorting electronic commerce transaction behaviors recorded in the blockchain, grouping data according to the transaction types, deleting completely repeated data, marking and supplementing default data in time, detecting whether the key value result of each kind of data in each group of transaction categories falls into a certain interval, wherein the intervals comprise a normal value interval, an abnormal value interval and an untrusted interval, the normal value interval indicates that the key value stored by the user is correct, the abnormal value interval indicates that the key value stored by the user is incorrect, the abnormal value is highlighted at the moment, the untrusted interval indicates that the key value stored by the user is problematic, whether the result of data input is correct or not needs to be rechecked for the storage of the key value of the user this time, if the result of the key value input by the user is incorrect, the transaction behaviors stored in the block chain are modified, and if the result of the key value input by the user is correct, the transaction behaviors of the user need to be detected again; the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence and an asymmetric encryption algorithm based on a neural network chaotic attractor to carry out secondary encryption on data, the e-commerce transaction evaluation module selects a support vector machine to select a proper e-commerce transaction type for a user, and the user completes the transaction at the transaction module.
Furthermore, the intelligent parameter setting module is used for quantifying the requirements of users, and comprises a transaction ID, a transaction type, a timestamp, a security level, a transaction object, a transaction address and a transaction amount, and the requirements are established in a dictionary mode, wherein the requirements comprise a Key and a Key Value, the Key and the Key Value are marked as { Key: value }, the timestamp is uniformly numbered through a hash function after being input according to standard time, the selected range is the combination of numbers and 26 lowercase letters, and the security level comprises three levels of open, common security and special security.
Further, by means of the block chain module, transaction behaviors in the block chain are sorted, data are distinguished according to transaction types, completely repeated data are deleted, default data need to be marked and supplemented in time, key value results of each data in each group of transaction types fall into a certain interval, the interval comprises a normal value interval, an abnormal value interval and an untrusted interval, the normal value interval indicates that key values stored by the user are correct, the abnormal value interval indicates that the key values stored by the user are incorrect, the abnormal values can be highlighted at the moment, the untrusted interval indicates that the key values stored by the user are problematic, whether data input results are correct or not needs to be rechecked for the storage of the key values of the user at this time, if the key values input by the user are incorrect, the transaction behaviors stored in the block chain are modified, and if the key values input by the user are correct, the transaction behaviors of the user need to be rechecked.
Furthermore, the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence to encrypt data, and an assumption E is made K () Representing an encryption operation, M representing data to be encrypted, D K () Representing decryption, C representing data needing decryption after encryption, and satisfying the following conditions: e K (M)＝C，D K (C) = M, and has: d K (E K (M)) = M, wherein the symmetric block encryption algorithm based on the neural network chaotic sequence needs to satisfy that the plaintext to be encrypted is 56 bits, the check bits are 8 bits, and the total bits are 64 bits, and the method specifically comprises the following steps:
(1) Firstly, carrying out initial transformation on a plaintext, dividing an information block into two parts, and then transforming a product through a function, wherein 16 times of execution are needed;
(2) After the product transformation, combining the two parts of information to execute the inverse initial transformation operation, and changing the left-shifted message into 48 bits;
(3) Replace 32 bits of new data with the final result;
(4) And (4) executing replacement operation according to the steps (1) to (3), and finishing the encryption process after 16 execution cycles.
Further, the encryption module, assuming that a key k is given, if the sub-keys generated by k are k1, k2, and k16, then k is called a weak key, and satisfies:
DC(DC(M,k),k)＝M
DC -1 (DC -1 (M,k),k)＝M
DC(M,k)＝DC -1 (M,k)
wherein DC () represents a symmetric block encryption algorithm based on a neural network chaotic sequence, DC -1 () A decryption algorithm of a symmetric block based on a neural network chaotic sequence is shown, if C = DC (M, k), then C '= DC (M', k '), where M', C ', and k' are non-operational, a public key is used for encrypting data, and a private key is used for decrypting data, and a conventional symmetric encryption system uses the same key for encryption and decryption each time, and a public key encryption system uses two unrelated keys to ensure the security of a network, the security of data, and the security of a key itself, as shown in the following expression:
E K1 (M)＝C
D K2 (C)＝M
D K2 (E K1 (M))＝M
the symmetric block encryption algorithm based on the neural network chaotic sequence encrypts data of an electronic commerce platform, the chaotic neural network consists of chaotic neurons, external input and internal feedback input, a single chaotic neuron has feedback and external input items from the internal neuron as well as unstable items and threshold values from the neuron, and the equations of i neurons of the chaotic neural network consisting of M chaotic neurons are as follows:
wherein x is i (t + 1) is the output of the ith chaotic neuron at discrete time (t + 1), f i Is the continuous output function of the ith chaotic neuronNumber, M is the number of chaotic neurons, W i,j Is the connection weight of the jth chaotic neuron and the ith chaotic neuron, h j Is the axonal transformation transfer function of the jth chaotic neuron, N is the number of external inputs, V ij Is the connection weight of the jth input and the ith chaotic neuron, I j (t-r) is the intensity of the jth input at discrete time (t-r), g i Is the refractoriness function of the ith chaotic neuron, k is the refractoriness attenuation coefficient, r is the self-feedback coefficient, and r>0，T i Is the complete or non-firing threshold of the ith chaotic neuron if y i (t + 1) represents the internal state of the ith chaotic neuron in discrete time (t + 1), and the iteration of the chaotic neural network is represented as follows:
x i (t+1)＝f i (y i (t+1))
for all neurons, the functions h and g are defined as h (x) = g (x) = x, where f is the sign function, i.e.:
the external input intensity of each neuron at any time is set to the initial external input intensity value, i.e.:
the value is 0 or 1, assuming that all firing thresholds for each neuron are θ, there are:
wherein, y i (t) and y i (t + 1) is the internal state of the ith chaotic neuron at discrete times t and t +1, respectively, assuming W ij Can take values of 1, 0 and-1, and when they are in an excited state, W is ij = -1, when they are in the inhibited state, then W ij =1, when they are not directly connected, W ij =0 number of excitatory connections and inhibitory connections based on statistical properties of the neural networkThe quantity is equal, the unpredictability of the output sequence of the neural network is increased, and because the chaotic neural network is introduced on the basis of a Hopfield neural network model with time lag, according to the requirement of constructing a connection matrix by Hopfield, when i = j, W is assumed ij =0, to obtain the values of the connection weight matrix.
Further, for the selection of parameters k, r and i, integers are required followed by y i (t + 1) the designed chaotic neural network needs to fluctuate in a non-periodic way by taking 0 as a center, and the updating is as follows:
where α is the deskew coefficient, defining a discrete Hopfield neural network having N interconnected neurons, each neuron having a state of S i (t)＝{S 0 (t),S 1 (t),…,S N-1 (t)}，S i (t) is 0 or 1, next state S i (t + 1) depends on the current state of the neuron, i.e.
Wherein, T ij Is the connection weight of neurons i and j, which is a symmetric matrix, t i Is the threshold value of neuron i, S i (t) is the state of the ith neuron at time t, S i (t + 1) is the state of the ith neuron at time (t + 1), S j (t) is the state of the jth neuron at time t, and the energy of the neural network at time t is as follows:
along with the evolution of the system state, the energy function is monotonously reduced, and the energy of the neural network is limited, so that the neural network finally reaches a stable state and is defined as an attractor, wherein the attractor is a chaotic attractorRules between attractors and initial state are not related, unpredictable relation exists between state messages in attraction domain of each attractor, if connection weight matrix T is changed, the attractor and corresponding attraction domain are correspondingly changed, and after random transformation matrix H is introduced, original initial state S and attractor S are combined N Respectively converted into new initial states
And an attractor
Comprises the following steps:
the synaptic connection matrix between neurons consists of +1, 0 and-1, + l, 0 and-1 indicating that two neurons are in an excitatory state, no direct connection and an inhibitory state, respectively, and according to statistical probability, if there are more unpredictable attractors, the number of excitatory synaptic connections in the network is equal to the number of inhibitory synaptic connections, and assuming that the number of samples stored in the network is 8 and the convergence field element is 20, the connecting synaptic matrix is given by the following formula:
in order to ensure the encryption effect, it is necessary to perform security analysis on the symmetric block encryption algorithm based on the neural network chaotic sequence, and assuming that it is converted into a binary sequence C, it is derived by the following formula:
C＝C{C(i)＝2c(i)-1},1≤i≤m
where C (i) is E {0,1}, C (i) is E { -1,1}, and the binary autocorrelation function R is shown as follows:
the cross-correlation function for sequences x and y is given by:
on the basis, the design of a symmetric packet encryption algorithm based on a neural network chaotic sequence and an asymmetric packet encryption algorithm based on a neural network chaotic attractor is analyzed, and the method has safety in electronic commerce transaction transmission.
Furthermore, the electronic commerce transaction evaluation module optimizes kernel function parameters and punishment factors of the support vector machine by adopting a particle swarm algorithm.
Further, the particle swarm optimization algorithm is set to perform the update of the time (t + 1) in the search space by adopting the following steps:
step (1): carrying out similar updating detection on each particle in the particle swarm: let z i Denotes the ith particle in the particle group, z l Denotes the first particle in the particle group, when the particle z i And particles z l At time t, the following conditions are satisfied: i X i (t)-X l (t) L (t) is less than or equal to | Pbest i (t)-Pbest l When (t) | is less than or equal to L (t), the particle z is judged i And particles z l At time t, the particles are similarly updated, where X i (t) represents the particle z at time t i Position in search space, X l (t) represents the particle z at time t l At the location of the search space, pbest i (t) represents the particle z at time t i In the individual optimal position of the search space, pbest l (t) represents the particle z at time t l At the individual optimal position of the search space, L (t) is a similarity detection threshold value of the particle swarm at the time t, and
wherein L is i (t) represents the particle z at time t i In the neighborhood of the search space, and
wherein the content of the first and second substances,
indicating the distance position X in the particle swarm at time t i (t) the position of the proximate particle, c is a given positive integer, and c<N is the total number of particles in the particle swarm;
classifying the particles judged as similar update particles in the particle swarm, specifically comprising the following steps: let S k (t) represents the kth class, class S, into which the particles in the population and their similar updated particles are classified at time t k The particles in (t) are selected from the group of particles in the following way: randomly selecting one particle from the unclassified particles of the current particle swarm to be added into the class S k (t) stopping selecting particles from the population and adding the class S when the randomly selected particles do not have similar updated particles in the particle swarm k (t) adding the similar renewing particles of the randomly selected particle to the class S when the similar renewing particles exist in the particle swarm k (t) and continuing to neutralize the current class S with the particle population k (t) any particle of (t) is a particle of a similarly renewed particle added with the species S k (t) up to class S k (t) stopping selecting particles from the population to join the class S when the particles in the population do not have similar updating particles in the current population k (t) in (a);
let S (t) denote the set of classes into which the particles in the particle swarm and their similarly updated particles are classified at time t, and S (t) = { S = k (t), k =1,2, \ 8230;, M (t) }, where M (t) denotes the number of classes in the set S (t);
step (2): updating the particles in each class in the set S (t) at the time (t + 1) in the following way respectively: let N k (t) represents class S k The number of particles in (t),
for a given positive integer, for determining the update mode of the particles in the class of the set S (t), and
class S k (t) the particles satisfy:
then, the following method is adopted to match class S k In (t), the particle is updated at time (t + 1):
V k,j (t+1)＝ω(t)V k,j (t)+c 1 rand 1 (Pbest k,j (t)-X k,j (t))
+c 2 rand 2 (Gbest(t)-X k,j (t))
X k,j (t+1)＝X k,j (t)+V k,j (t+1)
in the above update formula, let z k,j Represents class S k J-th particle in (t), X k,j (t + 1) and V k,j (t + 1) represents the particle z at the time of (t + 1) k,j Position and step size in search space, X k,j (t) and V k,j (t) represents particles z at time t k,j Position and step size in the search space, ω (t) represents the inertial weight factor of the particle population at time t, and
ω max and ω min Given maximum and minimum inertial weight factors, respectively, and ω max ＝0.9，ω min ＝0.4，T max Denotes the maximum number of iterations, rand 1 And rand 2 Are respectively in the interval [0,1]Internally generated random numbers, pbest k,j (t) represents the particle z at time t k,j At the individual optimal position of the search space, gbest (t) represents the global optimal position of the particle swarm in the search space at the moment t, c 1 Local learning factor representing a population of particles, c 2 Global learning factor representing a population of particles, c 1 And c 2 The value of (d) may take: c. C 1 ＝2，c 2 ＝2；
When class S k (t) the particles satisfy:
then, the following method is adopted to match class S k In (t), the particle is updated at time (t + 1):
V k,j (t+1)＝ω k,j (t)V k,j (t)+c 1 rand 1 (Pbest k,j (t)-X k,j (t))
+c 2 rand 2 (Gbest(t)-X k,j (t))
X k,j (t+1)＝X k,j (t)+V k,j (t+1)
in the above updated formula, ω k,j (t) represents the particle z at time t k,j Inertial weight factor in search space, will be ω k,j The value of (t) is set to:
wherein ρ k (t) represents class S k (t) historical similarity coefficient of particles in (t), and
wherein z is k,b Represents class S k The b-th particle in (t), X k,b (t-1) represents the particle z at the time (t-1) k,b At the position of the search space, X k,j (t-1) represents the particle z at the time (t-1) k,j At the location of the search space, rand k,j (t) is in the interval
Internally generated random numbers.
The invention has the beneficial effects that: the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence and an asymmetric encryption algorithm based on a neural network chaotic attractor to carry out secondary encryption on data, and after electronic commerce data is encrypted and decrypted, the noise in the data is small, so that the accuracy of data encryption and decryption is ensured, the loss and distortion influence of the encrypted data are reduced, and the accuracy of the encrypted and decrypted data is ensured; the electronic commerce transaction evaluation module optimizes parameters of a support vector machine by adopting an optimized particle swarm algorithm, firstly, similar update detection is carried out on particles in a particle swarm, the particles with similar update modes are classified, when the particles are updated, when the number of the particles in the similar update modes in the class of the particles is small, the particles in the class are set to be updated continuously according to the update mode of a standard particle swarm algorithm, so that the advantages of the standard particle swarm algorithm in optimization are kept, when the number of the particles in the similar update modes in the class of the particles is large, in order to ensure the diversity after updating of the particle swarm, the similarity of the previous update step length of the particles in the class is judged by detecting the similarity of the previous position of the particles in the class, when the previous position of the particles in the class has large difference, the step length when the particles in the class are updated is large difference, at the moment, the inertia weight factor of the particles in the class is strengthened in the update process, so that the particles in the class enhance the exploration of a new region, the diversity of the updated positions of the particles in the class is improved by strengthening the inertia weight factor in the particle swarm algorithm, and the optimization of the particle in the process of the particle is improved, so that the accuracy of the similarity of the particle optimization is improved after the particle swarm optimization is improved, and the particle optimization of the particle group optimization of the particle optimization is improved.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Detailed Description
The invention is further described in connection with the following examples.
Referring to fig. 1, the electronic commerce transaction system with data encryption transmission of the embodiment is characterized by comprising an intelligent parameter setting module, a blockchain module, an encryption module, an electronic commerce transaction evaluation module and a transaction module, wherein the intelligent parameter setting module is used for quantifying user requirements, including transaction IDs, transaction types, timestamps, privacy levels, transaction objects, transaction addresses and transaction amounts, established in a dictionary manner, including keys and key values, storing the quantified user requirements to the blockchain module, the blockchain module is used for safely storing, updating, recording data and transaction activities, sorting electronic commerce transaction behaviors recorded in the blockchain, grouping data according to the transaction types, and deleting completely repeated data, labeling and supplementing default data in time, and detecting whether a key value result of each data in each group of transaction categories falls into a certain interval, wherein the intervals comprise a normal value interval, an abnormal value interval and an untrusted interval, the normal value interval indicates that the key value stored by the user is correct, the abnormal value interval indicates that the key value stored by the user is incorrect, the abnormal value is highlighted at the moment, the untrusted interval indicates that the key value stored by the user is problematic, the storage of the key value of the user at this time needs to be checked again to determine whether a data input result is correct, if the key value input result by the user is incorrect, the transaction behavior stored in the block chain is modified, and if the key value input result by the user is correct, the transaction behavior of the user needs to be detected again; the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence and an asymmetric encryption algorithm based on a neural network chaotic attractor to carry out secondary encryption on data, the e-commerce transaction evaluation module selects a proper e-commerce transaction type for a user by using a support vector machine, and the user completes transaction in the transaction module.
Specifically, the intelligent parameter setting module is used for quantifying the requirements of users, and comprises a transaction ID, a transaction type, a timestamp, a security level, a transaction object, a transaction address and a transaction amount, wherein the requirements comprise the transaction ID, the transaction type, the timestamp, the security level, the transaction object, the transaction address and the transaction amount, the requirements are established in a dictionary mode, the requirements comprise keys and Key values, the Key values are marked as { Key: value }, the timestamp is uniformly numbered through a hash function after being input according to standard time, the selection range is the combination of numbers and 26 lowercase letters, and the security level comprises three levels of open, common security and special security.
Specifically, by using the blockchain module, transaction behaviors in the blockchain are sorted, data are distinguished according to transaction types, completely repeated data are deleted, default data need to be marked and supplemented in time, the key value result of each data in each group of transaction types needs to fall into a certain interval, the interval comprises a normal value interval, an abnormal value interval and an untrusted interval, wherein the normal value interval represents that the key value stored by the user is correct, the abnormal value interval represents that the key value stored by the user is incorrect, the abnormal value can be highlighted at the moment, the untrusted interval represents that the key value stored by the user is problematic, whether the result of data input is correct or not needs to be rechecked for the storage of the key value of the user at this time, if the result of the key value input by the user is incorrect, the transaction behaviors stored in the blockchain are modified, and if the result of the key value input by the user is correct, the transaction behaviors of the user need to be redetected.
Specifically, the encryption module encrypts data by adopting a symmetric block encryption algorithm based on a neural network chaotic sequence, and assuming that E K () Representing an encryption operation, M representing data to be encrypted, D K () Representing decryption, C representing data needing decryption after encryption, and satisfying the following conditions: e K (M)＝C，D K (C) = M, and has: d K (E K (M)) = M, wherein a symmetric block encryption algorithm based on a neural network chaotic sequence needs to meet the requirements that a plaintext to be encrypted is 56 bits, check bits are 8 bits, and total bits are 64 bits, and the method specifically comprises the following steps:
(1) Firstly, carrying out initial transformation on a plaintext, dividing an information block into two parts, and then transforming a product through a function, wherein 16 times of execution are needed;
(2) After the product transformation, the two parts of information are combined to execute the inverse initial transformation operation, and the left-shifted message is changed into 48 bits;
(3) Replace 32 bits of new data with the final result;
(4) And (4) executing replacement operation according to the steps (1) - (3), and finishing the encryption process after 16 execution cycles.
Preferably, the encryption module, assuming that a given key k, if the sub-keys generated by k are k1, k2, and k16, then k is called a weak key, satisfies:
DC(DC(M,k),k)＝M
DC -1 (DC -1 (M,k),k)＝M
DC(M,k)＝DC -1 (M,k)
wherein DC () represents a symmetric block encryption algorithm based on a neural network chaotic sequence, DC -1 () The decryption algorithm of the symmetric block based on the neural network chaotic sequence is shown, if C = DC (M, k), there is C '= DC (M', k '), where M', C 'and k' are taken as non-operation, a public key is used when encrypting data, and a private key is used when decrypting data, the conventional symmetric encryption system uses the same key to encrypt and decrypt each time, and the public key encryption system uses two unrelated keys to ensure the security of the network, the security of the data and the security of the key itself, and the expression is as follows:
E K1 (M)＝C
D K2 (C)＝M
D K2 (E K1 (M))＝M
the symmetric block encryption algorithm based on the neural network chaotic sequence encrypts data of an electronic commerce platform, the chaotic neural network consists of chaotic neurons, external input and internal feedback input, a single chaotic neuron is provided with feedback and external input items from the internal neuron, unstable items and threshold values from the neuron, and equations of i neurons of the chaotic neural network consisting of M chaotic neurons are as follows:
wherein x is i (t + 1) is the output of the ith chaotic neuron at discrete time (t + 1), f i Is the continuous output function of the ith chaotic neuron, M is the number of the chaotic neurons, W i,j Is the jth chaotic neuron and the thConnection weights of i chaotic neurons, h j Is the axonal transformation transfer function of the jth chaotic neuron, N is the number of external inputs, V ij Is the connection weight of the jth input and the ith chaotic neuron, I j (t-r) is the intensity of the jth input at discrete time (t-r), g i Is the refractoriness function of the ith chaotic neuron, k is the refractoriness attenuation coefficient, r is the self-feedback coefficient, and r>0，T i Is the complete or non-firing threshold of the ith chaotic neuron if y i (t + 1) represents the internal state of the ith chaotic neuron in discrete time (t + 1), and the iteration of the chaotic neural network is represented as follows:
x i (t+1)＝f i (y i (t+1))
for all neurons, the functions h and g are defined as h (x) = g (x) = x, where f is the sign function, i.e.:
the external input intensity of each neuron at any time is set to the initial external input intensity value, i.e.:
the value is 0 or 1, assuming that all firing thresholds for each neuron are θ, there are:
wherein, y i (t) and y i (t + 1) is the internal state of the ith chaotic neuron at discrete times t and t +1, respectively, assuming W ij Can take values of 1, 0 and-1, and when they are in an excited state, W is ij = -1, when they are in the inhibited state, then W ij =1, when they are not directly connected, W ij =0, equalizing the number of excitatory and inhibitory connections based on the statistical properties of the neural network and increasing the unpredictability of the output sequence of the neural network due to chaosThe neural network is introduced on the basis of a Hopfield neural network model with time lag, so that, according to the Hopfield requirement for constructing a connection matrix, when i = j, it is assumed that W is ij =0 to obtain the value of the connection weight matrix, which is given by the following equation for the case of M =8 in the present embodiment:
specifically, for the selection of parameters k, r and i, integers are required, followed by y i (t + 1) to make the non-periodic fluctuation with 0 as the center, the chaotic neural network is designed to be updated as follows:
where α is the deskew coefficient, defining a discrete Hopfield neural network having N interconnected neurons, each neuron having a state of S i (t)＝{S 0 (t),S 1 (t),…,S N-1 (t)}，S i (t) is 0 or 1, next state S i (t + 1) depends on the current state of the neuron, i.e.
Wherein, T ij Is the connection weight of neurons i and j, which is a symmetric matrix, t i Is the threshold of neuron i, S i (t) is the state of the ith neuron at time t, S i (t + 1) is the state of the ith neuron at time (t + 1), S j (t) is the state of the jth neuron at time t, and the energy of the neural network at time t is as follows:
with evolution of the system stateThe energy function is monotonously reduced, the neural network finally reaches a stable state due to limited energy, the neural network is defined as an attractor, the attractor is a chaotic attractor, namely the attractor is not related to rules between the attractor and an initial state, unpredictable relation exists between state messages in an attraction domain of each attractor, if a connection weight matrix T is changed, the attractor and a corresponding attraction domain thereof are correspondingly changed, and after a random transformation matrix H is introduced, the initial state S and the attractor S are respectively changed N Respectively converted into new initial states
And an attractor
Comprises the following steps:
the matrix of synaptic connections between neurons consists of +1, 0 and-1, with + l, 0 and-1 indicating that two neurons are in an excitatory state, no direct connection and an inhibitory state, respectively, and according to statistical probabilities, if there are more unpredictable attractors, the number of excitatory synaptic connections in the network is equal to the number of inhibitory synaptic connections, assuming that the number of samples stored in the network is 8 and the convergence field element is 20, the matrix of connecting synapses is given by:
in order to ensure the encryption effect, it is necessary to perform security analysis on the symmetric block encryption algorithm based on the neural network chaotic sequence, and assuming that it is converted into a binary sequence C, it is derived by the following formula:
C＝C{C(i)＝2c(i)-1},1≤i≤m
where C (i) is E {0,1}, C (i) is E { -1,1}, and the binary autocorrelation function R is shown as follows:
the cross-correlation function for sequences x and y is given by:
on the basis, the design of a symmetric packet encryption algorithm based on a neural network chaotic sequence and an asymmetric packet encryption algorithm based on a neural network chaotic attractor is analyzed, and the method has safety in electronic commerce transaction transmission.
Furthermore, the electronic commerce transaction evaluation module optimizes kernel function parameters and punishment factors of the support vector machine by adopting a particle swarm algorithm.
Further, the particle swarm algorithm is set to update the time (t + 1) in the search space by adopting the following steps:
step (1): carrying out similar updating detection on each particle in the particle swarm: let z i Denotes the ith particle in the particle group, z l Denotes the first particle in the particle group, when the particle z i And particles z l At time t, the following conditions are satisfied: | X i (t)-X l (t) | L (t) or less and | Pbest i (t)-Pbest l When (t) | is less than or equal to L (t), the particle z is judged i And particles z l At time t, the particles are similarly updated, where X i (t) represents the particle z at time t i Position in search space, X l (t) represents the particle z at time t l At the location of the search space, pbest i (t) represents the particle z at time t i In the individual optimal position of the search space, pbest l (t) represents the particle z at time t l At the individual optimal position of the search space, L (t) is a similarity detection threshold value of the particle swarm at the time t, and
wherein L is i (t) represents the particle z at time t i In the neighborhood of the search space, and
wherein the content of the first and second substances,
indicates the distance position X in the particle swarm at time t i (t) the position of the nearest particle, c is a given positive integer, and c<N is the total number of particles in the particle swarm;
classifying the particles judged as similar update particles in the particle swarm, specifically comprising the following steps: is provided with S k (t) represents the kth class, class S, into which the particles in the population and their similar updated particles are classified at time t k (t) the particles in (t) are selected from the group of particles in the following way: randomly selecting one particle from the unclassified particles of the current particle swarm to be added into the class S k (t) stopping selecting particles from the population to add the species S when the randomly selected particles do not have similar update particles in the population k (t) adding the similar renewing particles of the randomly selected particle to the class S when the similar renewing particles exist in the particle swarm k (t) and continuing to neutralize the particle population with the current class S k (t) any particle of (t) is a particle of a similarly renewed particle added with the species S k (t) up to class S k (t) when the particles do not have similar updating particles in the current population, stopping selecting the particles in the population and adding the particles into the class S k (t) in (t);
let S (t) denote the set of classes into which the particles in the particle swarm and their similarly updated particles are classified at time t, and S (t) = { S = k (t), k =1,2, \8230;, M (t) }, where M (t) represents the number of classes in the set S (t);
step (2): updating the time (t + 1) of each particle in each class in the set S (t) in the following way respectively: let N k (t) represents class S k The number of particles in (t),
for a given positive integer, for determining the update mode of the particles in the class of the set S (t), and
class S k (t) the particles satisfy:
then, the following way is adopted to pair class S k In (t), the particles are updated at time (t + 1):
V k,j (t+1)＝ω(t)V k,j (t)+c 1 rand 1 (Pbest k,j (t)-X k,j (t))
+c 2 rand 2 (Gbest(t)-X k,j (t))
X k,j (t+1)＝X k,j (t)+V k,j (t+1)
in the above update formula, let z k,j Represents class S k (j) th particle in (t), X k,j (t + 1) and V k,j (t + 1) represents the particle z at the time of (t + 1) k,j Position and step size in search space, X k,j (t) and V k,j (t) represents particles z at time t k,j Position and step size in the search space, ω (t) represents the inertial weight factor of the particle population at time t, and
ω max and ω min Given maximum and minimum inertial weight factors, respectively, and ω max ＝0.9，ω min ＝0.4，T max Denotes the maximum number of iterations, rand 1 And rand 2 Are respectively in the interval [0,1 ]]Internally generated random numbers, pbest k,j (t) represents the particle z at time t k,j At the individual optimal position of the search space, gbest (t) represents the global optimal position of the particle swarm in the search space at the time t, c 1 Local learning factor representing particle population, c 2 Global learning factor representing a population of particles, c 1 And c 2 Can take：c 1 ＝2，c 2 ＝2；
Class S k (t) the particles satisfy:
then, the following method is adopted to match class S k In (t), the particle is updated at time (t + 1):
V k,j (t+1)＝ω k,j (t)V k,j (t)+c 1 rand 1 (Pbest k,j (t)-X k,j (t))
+c 2 rand 2 (Gbest(t)-X k,j (t))
X k,j (t+1)＝X k,j (t)+V k,j (t+1)
in the above update formula, ω k,j (t) represents the particle z at time t k,j Inertial weight factor in search space, will be ω k,j The value of (t) is set to:
where ρ is k (t) represents class S k (t) historical similarity coefficient of particles in (t), and
wherein z is k,b Represents class S k The b-th particle in (t), X k,b (t-1) represents the particle z at the time (t-1) k,b Position in search space, X k,j (t-1) represents the particle z at the time (t-1) k,j At the location of the search space, rand k,j (t) is in the interval
Internally generated random numbers.
The invention has the beneficial effects that: the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence and an asymmetric encryption algorithm based on a neural network chaotic attractor to carry out secondary encryption on data, after electronic commerce data is encrypted and decrypted, the noise in the data is small, the accuracy of data encryption and decryption is ensured, the loss and distortion influence of the encrypted data are reduced, and the accuracy of the encrypted and decrypted data is ensured; the electronic commerce transaction evaluation module optimizes parameters of a support vector machine by adopting an optimized particle swarm algorithm, firstly, similar update detection is carried out on particles in a particle swarm, the particles with similar update modes are classified, when the particles are updated, when the number of the particles in the similar update modes in the class of the particles is small, the particles in the class are set to be updated continuously according to the update mode of a standard particle swarm algorithm, so that the advantages of the standard particle swarm algorithm in optimization are kept, when the number of the particles in the similar update modes in the class of the particles is large, in order to ensure the diversity after updating of the particle swarm, the similarity of the previous update step length of the particles in the class is judged by detecting the similarity of the previous position of the particles in the class, when the previous position of the particles in the class has large difference, the step length when the particles in the class are updated is large difference, at the moment, the inertia weight factor of the particles in the class is strengthened in the update process, so that the particles in the class enhance the exploration of a new region, the diversity of the updated positions of the particles in the class is improved by strengthening the inertia weight factor in the particle swarm algorithm, and the optimization of the particle in the process of the particle is improved, so that the accuracy of the similarity of the particle optimization is improved after the particle swarm optimization is improved, and the particle optimization of the particle group optimization of the particle optimization is improved.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (3)
1. An electronic commerce transaction system for data encryption transmission is characterized by comprising an intelligent parameter setting module, a blockchain module, an encryption module, an electronic commerce transaction evaluation module and a transaction module, wherein the intelligent parameter setting module is used for quantifying user requirements, including transaction ID, transaction types, timestamps, privacy levels, transaction objects, transaction addresses and transaction amounts, is established in a dictionary mode and comprises keys and key values, the quantified user requirements are stored in the blockchain module, the blockchain module is used for safely storing, updating, recording data and transaction activities, electronic commerce transaction behaviors recorded in the blockchain are sorted, data are grouped according to the transaction types, completely repeated data are deleted, and default data are marked and supplemented in time, detecting whether the key value result of each kind of data in each group of transaction categories falls into a certain interval, wherein the intervals comprise a normal value interval, an abnormal value interval and an untrusted interval, the normal value interval indicates that the key value stored by the user is correct, the abnormal value interval indicates that the key value stored by the user is incorrect, the abnormal value is highlighted at the moment, the untrusted interval indicates that the key value stored by the user is problematic, whether the result of data input is correct or not needs to be rechecked for the storage of the key value of the user this time, if the result of the key value input by the user is incorrect, the transaction behavior stored in the block chain needs to be modified, and if the result of the key value input by the user is correct, the transaction behavior of the user needs to be redetected; the encryption module adopts a symmetric block encryption algorithm based on a neural network chaotic sequence and an asymmetric encryption algorithm based on a neural network chaotic attractor to carry out secondary encryption on data, the e-commerce transaction evaluation module selects a proper e-commerce transaction type for a user by using a support vector machine, and the user completes transaction in the transaction module;
the intelligent parameter setting module is used for quantifying the requirements of users, and comprises a transaction ID, a transaction type, a timestamp, a security level, a transaction object, a transaction address and a transaction amount, wherein the requirements are established in a dictionary mode, the requirements comprise a Key and a Key Value, and the Key Value are marked as { Key: value }, the timestamp is uniformly numbered through a hash function after being input according to standard time, the selection range of the timestamp is the combination of numbers and 26 lowercase letters, and the security level comprises three levels of open, common security and special security;
the electronic commerce transaction evaluation module optimizes kernel function parameters and punishment factors of the support vector machine by adopting a particle swarm algorithm.
2. The system of claim 1, wherein the encryption module encrypts the data using a symmetric block encryption algorithm based on a neural network chaotic sequence, assuming E K () Representing an encryption operation, M representing data to be encrypted, D K () Representing decryption, C representing data needing decryption after encryption, and satisfying the following conditions: e K (M)＝C，D K (C) = M, and has: d K (E K (M)) = M, wherein a symmetric block encryption algorithm based on a neural network chaotic sequence needs to meet the requirements that a plaintext to be encrypted is 56 bits, check bits are 8 bits, and total bits are 64 bits, and the method specifically comprises the following steps:
(1) Firstly, carrying out initial transformation on a plaintext, dividing an information block into two parts, and then transforming a product through a function, wherein 16 times of execution are needed;
(2) After the product transformation, the two parts of information are combined to execute the inverse initial transformation operation, and the left-shifted message is changed into 48 bits;
(3) Replacing 32-bit new data with the final result;
(4) And (4) executing replacement operation according to the steps (1) - (3), and finishing the encryption process after 16 execution cycles.
3. The system of claim 1 or 2, wherein the particle swarm algorithm is configured to perform the update at time (t + 1) in the search space by the following steps:
step (1): performing similar updating detection on each particle in the particle swarm: let z i Denotes the ith particle in the particle population, z l Denotes the first particle in the population, when particle z i And particles z l At time t, the following conditions are satisfied: i X i (t)-X l (t) | L (t) or less and | Pbest i (t)-Pbest l When (t) | is less than or equal to L (t), the particle z is judged i And particles z l At time t, the particles are similarly updated, where X i (t) represents the particle z at time t i Position in search space, X l (t) represents the particle z at time t l At the location of the search space, pbest i (t) represents the particle z at time t i In the individual optimal position of the search space, pbest l (t) represents the particle z at time t l At the individual optimal position of the search space, L (t) is a similarity detection threshold value of the particle swarm at the time t, and
wherein L is i (t) represents the particle z at time t i In the neighborhood of the search space, and
wherein the content of the first and second substances,
indicating the distance position X in the particle swarm at time t i (t) the position of the proximate particle, c is a given positive integer, and c<N is the total number of particles in the particle swarm;
classifying the particles judged as similar update particles in the particle swarm, specifically comprising the following steps: let S k (t) represents the kth class, class S, into which the particles in the population and their similar updated particles are classified at time t k (t) the particles in (t) are selected from the group of particles in the following way: randomly selecting one particle from the unclassified particles of the current particle swarm to be added into the class S k (t) stopping selecting particles from the population to add the species S when the randomly selected particles do not have similar update particles in the population k (t) adding the like renewing particles of the randomly selected particles to the class S when the like renewing particles exist in the particle group k (t) and continuing to neutralize the current class S with the particle population k (t) any one of the particlesAdding S-like substances to particles of similarly renewed particles k (t) up to class S k (t) stopping selecting particles from the population to join the class S when the particles in the population do not have similar updating particles in the current population k (t) in (a);
let S (t) denote a set of classes into which particles in a particle swarm and their similarly updated particles are classified at time t, and S (t) = { S = { (S) } k (t), k =1,2, \8230;, M (t) }, where M (t) represents the number of classes in the set S (t);
step (2): updating the time (t + 1) of each particle in each class in the set S (t) in the following way respectively: let N k (t) represents class S k The number of particles in (t),
for a given positive integer, for determining the update mode of the particles in the class of the set S (t), and
class S k (t) the particles satisfy:
then, the following method is adopted to match class S k In (t), the particles are updated at time (t + 1):
V k,j (t+1)＝ω(t)V k,j (t)+c 1 rand 1 (Pbest k,j (t)-X k,j (t))+c 2 rand 2 (Gbest(t)-X k,j (t))
X k,j (t+1)＝X k,j (t)+V k,j (t+1)
in the above update formula, let z k,j Represents class S k J-th particle in (t), X k,j (t + 1) and V k,j (t + 1) represents the particle z at the time of (t + 1) k,j Position and step size in search space, X k,j (t) and V k,j (t) represents particles z at time t k,j At the position and step size of the search space, ω (t) represents the inertial weight factor of the particle population at time t, and
ω max and ω min Given maximum and minimum inertial weight factors, respectively, and ω max ＝0.9，ω min ＝0.4，T max Denotes the maximum number of iterations, rand 1 And rand 2 Are respectively in the interval [0,1 ]]Internally generated random numbers, pbest k,j (t) represents the particle z at time t k,j At the individual optimal position of the search space, gbest (t) represents the global optimal position of the particle swarm in the search space at the time t, c 1 Local learning factor representing a population of particles, c 2 Global learning factor representing a population of particles, c 1 And c 2 The value of (d) may take: c. C 1 ＝2，c 2 ＝2；
Class S k (t) the particles satisfy:
then, the following way is adopted to pair class S k In (t), the particle is updated at time (t + 1):
V k,j (t+1)＝ω k,j (t)V k,j (t)+c 1 rand 1 (Pbest k,j (t)-X k,j (t))+c 2 rand 2 (Gbest(t)-X k,j (t))
X k,j (t+1)＝X k,j (t)+V k,j (t+1)
in the above update formula, ω k,j (t) represents the particle z at time t k,j Inertial weight factor in search space, will be ω k,j The value of (t) is set to:
wherein ρ k (t) represents class S k (t) the historical similarity coefficient of the particles, and
wherein the content of the first and second substances,z k,b represents class S k The b-th particle in (t), X k,b (t-1) represents the particle z at the time (t-1) k,b Position in search space, X k,j (t-1) represents the particle z at the time (t-1) k,j At the location of the search space, rand k,j (t) is in the interval
Internally generated random numbers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211235708.6A CN115622774B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system based on improved particle swarm optimization and supporting data encryption transmission of vector machine |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211235708.6A CN115622774B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system based on improved particle swarm optimization and supporting data encryption transmission of vector machine |
| CN202210944450.0A CN115065458B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system with data encryption transmission |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210944450.0A Division CN115065458B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system with data encryption transmission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115622774A true CN115622774A (en) | 2023-01-17 |
| CN115622774B CN115622774B (en) | 2024-01-12 |
Family
ID=83208514
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211235695.2A Active CN115619555B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system with data encryption transmission function |
| CN202211235708.6A Active CN115622774B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system based on improved particle swarm optimization and supporting data encryption transmission of vector machine |
| CN202210944450.0A Active CN115065458B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system with data encryption transmission |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211235695.2A Active CN115619555B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system with data encryption transmission function |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210944450.0A Active CN115065458B (en) | 2022-08-08 | 2022-08-08 | Electronic commerce transaction system with data encryption transmission |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN115619555B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405283A (en) * | 2023-04-06 | 2023-07-07 | 陈俊宏 | Data encryption authentication system based on information data protection |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116308655B (en) * | 2023-03-17 | 2023-09-15 | 北京未来链技术有限公司 | Intelligent community commodity big data intelligent bill spelling and settlement system based on blockchain |
| CN116308813B (en) * | 2023-05-17 | 2023-08-08 | 青岛农村商业银行股份有限公司 | Different-industry combined financial equity safety management system |
| CN117035836A (en) * | 2023-10-08 | 2023-11-10 | 深圳市焕想科技有限公司 | Electronic commerce transaction data processing method and system based on artificial intelligence |
| CN117978362B (en) * | 2024-04-02 | 2024-06-07 | 深圳市海域达赫科技有限公司 | Data encryption method, system, computer device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485348A (en) * | 2016-09-22 | 2017-03-08 | 中国银联股份有限公司 | A kind of Forecasting Methodology of transaction data and device |
| US20190379699A1 (en) * | 2018-06-07 | 2019-12-12 | Unifyvault LLC | Systems and methods for blockchain security data intelligence |
| CN110852604A (en) * | 2019-11-08 | 2020-02-28 | 湖南商学院 | Dynamic trust calculation method based on mobile Agent |
| CN112632842A (en) * | 2020-12-23 | 2021-04-09 | 国网北京市电力公司 | Trading harmony based power grid and building energy consumption trading matching method and system |
| CN112765271A (en) * | 2020-12-31 | 2021-05-07 | 杭州趣链科技有限公司 | Block chain transaction index storage method and device, computer equipment and medium |
| CN113554511A (en) * | 2021-06-23 | 2021-10-26 | 河海大学 | Active power distribution network power trading method based on block chain and particle swarm optimization |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001144746A (en) * | 1999-11-11 | 2001-05-25 | Japan Science & Technology Corp | Enchiper system and decoding system using chaos neural network |
| JP2003023421A (en) * | 2001-07-09 | 2003-01-24 | C4 Technology Inc | Encryption method, program thereof, recording medium recorded with the program, encryption device, decoding method, and decoder |
| CN101977112B (en) * | 2010-11-04 | 2013-10-09 | 厦门大学 | Public key cipher encrypting and decrypting method based on neural network chaotic attractor |
| CN107231214B (en) * | 2017-06-12 | 2020-07-28 | 哈尔滨工程大学 | Optimal multi-user detection method based on evolutionary chaotic quantum neural network |
| CN110611701B (en) * | 2018-08-21 | 2022-10-11 | 汇链丰(北京)科技有限公司 | Parameter configuration and transaction processing method based on block chain |
| CN109165224B (en) * | 2018-08-24 | 2021-02-19 | 东北大学 | Indexing method for key words on block chain database |
| US11809896B2 (en) * | 2019-05-24 | 2023-11-07 | International Business Machines Corporation | Anomalous transaction commitment prevention for database |
| US11615272B2 (en) * | 2020-06-17 | 2023-03-28 | Capital One Services, Llc | Anomaly analysis using a blockchain, and applications thereof |
| CN112927072B (en) * | 2021-01-20 | 2023-08-29 | 北京航空航天大学 | Block chain-based money back-flushing arbitration method, system and related device |
| CN113723954A (en) * | 2021-06-15 | 2021-11-30 | 复旦大学 | Method for detecting and supervising abnormal transaction nodes in block chain |
| CN114331436A (en) * | 2021-12-30 | 2022-04-12 | 江苏九一网络科技有限公司 | E-commerce safe transaction system based on block chain |
-
2022
- 2022-08-08 CN CN202211235695.2A patent/CN115619555B/en active Active
- 2022-08-08 CN CN202211235708.6A patent/CN115622774B/en active Active
- 2022-08-08 CN CN202210944450.0A patent/CN115065458B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485348A (en) * | 2016-09-22 | 2017-03-08 | 中国银联股份有限公司 | A kind of Forecasting Methodology of transaction data and device |
| US20190379699A1 (en) * | 2018-06-07 | 2019-12-12 | Unifyvault LLC | Systems and methods for blockchain security data intelligence |
| CN110852604A (en) * | 2019-11-08 | 2020-02-28 | 湖南商学院 | Dynamic trust calculation method based on mobile Agent |
| CN112632842A (en) * | 2020-12-23 | 2021-04-09 | 国网北京市电力公司 | Trading harmony based power grid and building energy consumption trading matching method and system |
| CN112765271A (en) * | 2020-12-31 | 2021-05-07 | 杭州趣链科技有限公司 | Block chain transaction index storage method and device, computer equipment and medium |
| CN113554511A (en) * | 2021-06-23 | 2021-10-26 | 河海大学 | Active power distribution network power trading method based on block chain and particle swarm optimization |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405283A (en) * | 2023-04-06 | 2023-07-07 | 陈俊宏 | Data encryption authentication system based on information data protection |
| CN116405283B (en) * | 2023-04-06 | 2023-11-24 | 广州大有网络科技有限公司 | Data encryption authentication system based on information data protection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115619555B (en) | 2023-06-09 |
| CN115065458A (en) | 2022-09-16 |
| CN115622774B (en) | 2024-01-12 |
| CN115619555A (en) | 2023-01-17 |
| CN115065458B (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Cristofaro | An overview of privacy in machine learning | |
| CN115065458B (en) | Electronic commerce transaction system with data encryption transmission | |
| Feng et al. | Mining network data for intrusion detection through combining SVMs with ant colony networks | |
| Wazirali | An improved intrusion detection system based on KNN hyperparameter tuning and cross-validation | |
| Peddabachigari et al. | Modeling intrusion detection system using hybrid intelligent systems | |
| Suwannalai et al. | Network intrusion detection systems using adversarial reinforcement learning with deep Q-network | |
| Rawat et al. | Intrusion detection systems using classical machine learning techniques vs integrated unsupervised feature learning and deep neural network | |
| Subaira et al. | Efficient classification mechanism for network intrusion detection system based on data mining techniques: a survey | |
| Panigrahi et al. | Two-stage database intrusion detection by combining multiple evidence and belief update | |
| Kumar et al. | Network attack detection using an unsupervised machine learning algorithm | |
| Kadry et al. | Intrusion detection model using optimized quantum neural network and elliptical curve cryptography for data security | |
| Srilatha et al. | DDoSNet: A deep learning model for detecting network attacks in cloud computing | |
| Kaushik et al. | Multi-class SVM based network intrusion detection with attribute selection using infinite feature selection technique | |
| Ketepalli et al. | Data Preparation and Pre-processing of Intrusion Detection Datasets using Machine Learning | |
| Ge et al. | A review of secure federated learning: privacy leakage threats, protection technologies, challenges and future directions | |
| Hao et al. | A sequential detection method for intrusion detection system based on artificial neural networks | |
| Lee et al. | CoNN-IDS: Intrusion detection system based on collaborative neural networks and agile training | |
| US11829486B1 (en) | Apparatus and method for enhancing cybersecurity of an entity | |
| Ganeshan et al. | I-AHSDT: intrusion detection using adaptive dynamic directive operative fractional lion clustering and hyperbolic secant-based decision tree classifier | |
| Iftikhar et al. | A supervised feature selection method for malicious intrusions detection in IoT based on genetic algorithm | |
| Zhu et al. | Lightweight Cryptographic Simulation of Power IoT Fused with Bayesian Network Algorithms | |
| Babu et al. | Bat-Inspired Optimization for Intrusion Detection Using an Ensemble Forecasting Method. | |
| Selvamani et al. | An efficacious intellectual framework for host based intrusion detection system | |
| Deep et al. | Prevention and Detection of Intrusion in Cloud Using Hidden Markov Model | |
| Bangari | A comparative evaluation of machine learning models and EDA through Tableau using CICIDS2017 dataset |
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 |