CN111831715A - Intelligent access and certificate storage system and method based on artificial intelligence big data - Google Patents
Intelligent access and certificate storage system and method based on artificial intelligence big data Download PDFInfo
- Publication number
- CN111831715A CN111831715A CN202010450756.1A CN202010450756A CN111831715A CN 111831715 A CN111831715 A CN 111831715A CN 202010450756 A CN202010450756 A CN 202010450756A CN 111831715 A CN111831715 A CN 111831715A
- Authority
- CN
- China
- Prior art keywords
- data
- petition
- layer
- algorithm
- sample
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- 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
- H04L63/0442—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 wherein the sending and receiving network entities apply asymmetric encryption, i.e. different keys for encryption and decryption
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Abstract
The invention discloses an intelligent interview and evidence storage system and method based on artificial intelligence big data, which relates to the technical field of intelligent petition, and the method for realizing artificial intelligence comprises the following steps (S1): acquiring data, namely acquiring data information of a petition event through a data acquisition layer; (S2) data processing: screening and cleaning the acquired big data to acquire effective big data, and realizing storage, encryption, calculation and sharing of the data through a block chain system or a cloud server; (S3) data calculation: calculating the association between the data through a data mining algorithm, or classifying the petition data according to set attributes according to user requirements, mining the relation between petition events through the association algorithm model on the preprocessed big data, and realizing the classification of various petition events by using a data classification algorithm model; (S4) data application: and in the data application layer, data transmission is carried out on the calculated data for the user to use. The invention improves the management capability of the petition data.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent interview and evidence storage system and method based on artificial intelligence big data.
Background
In the prior art, the face recognition technology can only realize the identification of the identity information of a user, the early warning information is not intelligent enough, detailed information cannot be early warned, such as the number of times of petition, when the last petition is, because of what petition, who is the staff who is to be handled every time, what the result of petition processing every time is, and the like, and early warning grade marks of the petition are displayed and are difficult to identify, the big data management capability is lagged, in a related business system, the interface is complex, the data is scattered, the operation is inconvenient, a case full-flow guiding function cannot be provided, the case full-period management cannot be provided, the case can not be viewed and analyzed in a global view angle, and specific work can be implemented. For the record of the petition process, only the petition process stays in the security monitoring level, the data is easy to be falsified and congealed, and the electronic data evidence storing function of the judicial evidence storing level cannot be provided. For regional classification, time classification, core keyword classification and the like, analysis charts cannot be automatically formed through manual operation, and complete intelligent analysis and research on the petition work cannot be carried out.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an intelligent interview and evidence storage system and method based on artificial intelligence big data.
The invention adopts the following technical scheme:
an intelligent interview and evidence-storing system based on artificial intelligence big data, wherein the system comprises:
the data acquisition layer is at least internally provided with an RFID (radio frequency identification device), a computer, a mouse and a keyboard which are connected with the computer, a large-scale petition database integrated in the computer and a personal information two-dimensional code; the large petition database is at least provided with a display layer, a business logic layer, a data access layer, a cloud data interface and a block chain data interface, wherein the display layer is connected with the business logic layer, the business logic layer is connected with the data access layer, the data access layer is connected with the cloud data interface and the block chain data interface, and the data access layer is used for accessing files in the large petition database to read, store and transmit data in the large petition database; the display layer is used for displaying the large petition database and receiving petition data of the data access layer, an interactive network man-machine interaction platform is provided for petition, the business logic layer stores and identifies petition information input by a user, and the cloud data interface and the block chain data interface are used for interacting petition data with the data storage layer;
the data storage layer is at least provided with a block chain system and a cloud server, wherein:
the block chain system comprises a data layer, a network layer, a consensus layer, an excitation layer and an intelligent contract layer, wherein the data layer stores data by using a Merkle tree, the data layers are structurally connected in a chain manner through blocks, and the data structure is provided with an encryption unit and a data transmission module; the network layer is mainly composed of network nodes which are interweaved in an intricate way, data communication and connection are realized by using a point-to-point technology through different network nodes, so that different node devices in the block chain network can be intercommunicated and interconnected, a consensus mechanism is arranged in the consensus layer, and the consensus mechanism can carry out consistent interaction on data arranged in the block chain network, so that the data consensus ability and the data anti-attack ability are good; the excitation layer outputs excitation information in a block chain; the intelligent contract layer is provided with more than two big data algorithm modules, and can execute and calculate the relation between various data in the block chain network; a block chain platform is arranged in the block chain layer, and the block chain platform is a supporting platform of a modularized block chain solution based on Hyperridge Fabric;
the cloud server at least comprises a distributed storage module, a data transmission interface, a CPU, an internal memory, a disk, a bandwidth and a cloud network interface, wherein the cloud server is formed by constructing a cloud resource pool by intensively and virtualizing a scale-level bottom server and allocating computing resources from the resource pool, wherein the CPU, the internal memory, the disk or the bandwidth exist in a free combination mode;
the data calculation layer is internally provided with a data mining algorithm model, wherein the data mining algorithm model is an association algorithm model and a data classification algorithm model; the association algorithm is used for mining the relationship between the received petition data and finding out the association between different petition times, and the data classification algorithm is used for classifying different types of petition data according to classification attributes and rules so that petition managers can quickly inquire the petition data;
the data application layer is internally provided with a data transmission module and an application computer, wherein the data transmission module is a wired communication module or a wireless communication module and is used for receiving and transmitting the power grid equipment data information sensed by the data acquisition layer; the wired communication module at least comprises an RS485 communication module or an RS232 communication module, and the wireless communication module at least comprises a TCP/IP network system, a ZigBee wireless network, a GPRS communication module or a CDMA wireless communication, cloud network or Bluetooth communication module; wherein:
the output end of the data acquisition layer is connected with the input end of the data storage layer, the output end of the data storage layer is connected with the input end of the data calculation layer, and the output end of the data calculation layer is connected with the input end of the data application layer.
Further, the petition data in the petition large database at least comprises name, gender, age, region, petition event type, petition time, petition core keyword, petition reason, petition event process description, petition period, petition number and petition processing data.
Further, the blockchain system is a blockchain system based on the Fabric architecture.
Further, the Fabric architecture comprises a system management layer, an organization management layer and a business development layer.
Further, the correlation algorithm model is a Bayesian classifier model.
Further, the data classification algorithm model is provided with a cloud data interface, a wireless communication data interface or a USB data interface.
The invention also adopts the following technical scheme:
an intelligent interview and evidence storage method based on artificial intelligence big data comprises the following steps:
(S1) data acquisition: acquiring data, namely acquiring data information of a petition event through a data acquisition layer;
(S2) data processing: screening and cleaning the acquired big data to acquire effective big data, and realizing storage, encryption, calculation and sharing of the data through a block chain system or a cloud server;
(S3) data calculation: calculating the association between the data through a data mining algorithm, or classifying the petition data according to set attributes according to user requirements, mining the relation between petition events through the association algorithm model on the preprocessed big data, and realizing the classification of various petition events by using a data classification algorithm model;
(S4) data application: and in the data application layer, data transmission is carried out on the calculated data for the user to use.
Further, the correlation algorithm model formula is as follows:
assuming that the petition event data to be classified in the petition database has an attribute d, and assuming that the category of the petition event data attribute is classified into a set C, then C is { C ═ C { (C)1，c2，...，cmH, wherein the i-th classification attribute satisfies the condition: i is more than or equal to 1 and less than or equal to m, and the maximum output class of the petition event data set d to be classified is P (c)iAnd/d), then:
where C, D is expressed as a random variable, the Bayesian classification formula for document d is:
further, the data classification algorithm model is at least a decision tree algorithm model, a cluster classification algorithm model, a BP neural network algorithm model, a KNN algorithm model, a support vector machine algorithm model, a VSM method model or a k-nearest neighbor algorithm model; the k-nearest neighbor algorithm comprises the following steps:
(1) selecting information sample data in an interview database, selecting a central point of an initial cluster according to the selected interview data sample, randomly extracting K interview data sample data from the sample data, taking the selected interview data sample as the center of a sample cluster data set, and setting a threshold value T of iteration times, wherein K is more than 100, and T is more than 1 and less than 8;
(2) dividing cluster points of the petition data samples, dividing the points of each petition data sample cluster to a cluster point represented by a center closest to the petition data samples, and dividing the center point of the petition data samples closest to the center point of an initial cluster into a class;
wherein the distance formula between the nearest center of the petition data sample and the point of the represented cluster is:
wherein x and y respectively represent different types of visiting data samples, n represents the dimensionality of the visiting data samples, d (x and y) is an Euclidean distance, the distance between each visiting data sample and the parameters of the central samples is calculated according to the central point of the clustering sample of each visiting data sample, and the corresponding visiting data samples are divided again according to the minimum distance;
(3) representing the center point of the sample cluster of the petition data sample by the center point of each sample data point in different petition data sample clusters, calculating the distance between the center point of each petition data sample cluster and the clustering information data centers again according to the center points of different parameter data or different clustering information sample data, and dividing the corresponding petition data sample data again according to the minimum distance, and forming a matrix D by the minimum data calculated each time, wherein the matrix D is as follows:
wherein x is the set of minimum values found;
(4) and (3) judging whether iterative computation is carried out or not, if the iteration number is equal to a set threshold value T, not using the iterative computation, if the iteration number is different from the set threshold value, subdividing the digital asset information sample cluster points, returning to the step (2), and repeating the steps (2) and (3).
Further, an elliptic curve function algorithm, a mnemonic algorithm, a DES algorithm, a 3DES algorithm, a Blowfish algorithm, a Twofish algorithm, an IDEA algorithm, an RC6 algorithm, or a CAST5 algorithm.
Positive effect
According to the invention, by adopting a block chain technology, big data management is realized, an architecture system comprising a data acquisition layer, a data storage layer, a data calculation layer and a data application layer is constructed, and data interaction is realized by fully utilizing the characteristics of decentralization, non-falsification, distributed common accounting, asymmetric encryption, data safe storage and the like of the block chain technology; according to the invention, the encryption function and the decryption function are adopted, so that the encryption and decryption of the big data are realized, the stability of the data is ensured in the big data transmission process, the data is prevented from being tampered, and the safety performance of the data is improved; the method adopts a sharing algorithm, realizes data sharing in the block chain, fully utilizes a sharing mechanism, has the advantages of decentralization, distrust, data encryption and the like, and can better solve the data management problem in big data application;
the invention realizes the processing of the big data of the petition by applying a big data mining technology, realizes the classification and the processing of the big data by any one of a decision tree algorithm model, a cluster classification algorithm model, a BP neural network algorithm model, a KNN algorithm model, a support vector machine algorithm model, a VSM method model or a k-neighbor algorithm model, is convenient for searching the data types which have huge number of structures, are complex and are difficult to manage within extremely short time, the processing time is only a few seconds, preferably 0.05-1.5 seconds, and the data management capability is greatly improved.
The invention solves a plurality of problems in the prior art, and specifically comprises the following steps:
the invention solves the problem that multiple windows easily cause withering and tearing and repeat statement appeal when revisiting by people, the system can collect the petition information in place at one time, the petition people do not need to repeat the original appeal when revisiting, the face recognition system accurately realizes the automatic matching of the petition people and petition historical data, and the petition people can read the petition data by one key, namely, the petition people are recognized and the petition data is read at the same time.
The invention solves the problems of short response to temporary interview, difficult unification of external feedback calibers of different interviewers and poor continuity, when the interviewer revisits, the system can quickly make a feedback response according to matched consultation and work instructions, namely realizing the case-based full-flow navigation guidance of the interview event, and avoiding the problems of slow understanding of the traditional interview, inconsistent external feedback content calibers, difficult continuity of interview work and difficult accurate response.
The invention solves the problem that the third party can not be invited to witness and the organization of the open listening process is complicated. The system provides a standard process of public inspection and third-party witness response, a public auditor and a third-party witness database are established in advance, public auditor or response witness is realized, the interviewer is forced to strengthen responsibility consciousness and make full explanation theorem preparation, and the authority of public response is enhanced.
The invention solves the problems of difficult trace retention in the interviewing process, difficult investigation of post-operative responsibility and difficult improvement of interviewing quality and effect. The system provides a visit-receiving full-flow video judicial evidence-keeping trace-keeping system, namely, the two parties are synchronously recorded in the whole process of the visit-receiving, the recorded data are converted into evidence to be kept, the warning of the behavior of winding and giving up the visit or illegal destruction records the whole course on a case, and the subsequent responsibility-pursuing and accountability are more efficient and convenient.
The invention solves the problems of difficult overall master and slow effective coping speed of the dynamic conditions of multi-head visit and petition. The system provides various interfaces, can be connected with various data platforms, automatically identifies the multi-head visiting condition, comprehensively knows the dynamic state of the petition, helps the visiting unit to comprehensively control, effectively solves the problems of insufficient information and difficult mastering of the total petition condition, and improves the coping speed and coping effect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of an overall architecture of an intelligent access and evidence-storing system based on artificial intelligence big data according to the present invention;
FIG. 2 is a schematic diagram of the architecture of a large petition database based on an artificial intelligence big data intelligent interview and evidence storage system according to the present invention;
FIG. 3 is a schematic diagram of a block chain system in an intelligent interview and evidence storage system based on artificial intelligence big data according to the present invention;
FIG. 4 is a schematic diagram of a fabric architecture of a blockchain system in an intelligent access and storage system based on artificial intelligence big data according to the present invention;
FIG. 5 is a schematic diagram of an embodiment of a Fabric architecture in an intelligent interview and evidence-based system according to the invention;
FIG. 6 is a schematic diagram of an intelligent interview and evidence storage method based on artificial intelligence big data according to the present invention;
FIG. 7 is a schematic flow chart illustrating a k-nearest neighbor algorithm based on an artificial intelligence big data intelligent interview and evidence storage method according to the present invention.
FIG. 8 is a schematic flow chart illustrating steps of an elliptic cryptography algorithm in an intelligent access and evidence storage method based on artificial intelligence big data according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in figures 1-5 of the drawings,
an intelligent interview and evidence-storing system based on artificial intelligence big data, wherein the system comprises:
the data acquisition layer is at least internally provided with an RFID (radio frequency identification device), a computer, a mouse and a keyboard which are connected with the computer, a large-scale petition database integrated in the computer and a personal information two-dimensional code; the large petition database is at least provided with a display layer, a business logic layer, a data access layer, a cloud data interface and a block chain data interface, wherein the display layer is connected with the business logic layer, the business logic layer is connected with the data access layer, the data access layer is connected with the cloud data interface and the block chain data interface, and the data access layer is used for accessing files in the large petition database to read, store and transmit data in the large petition database; the display layer is used for displaying the large petition database and receiving petition data of the data access layer, an interactive network man-machine interaction platform is provided for petition, the business logic layer stores and identifies petition information input by a user, and the cloud data interface and the block chain data interface are used for interacting petition data with the data storage layer;
the data storage layer is at least provided with a block chain system and a cloud server, wherein:
the block chain system comprises a data layer, a network layer, a consensus layer, an excitation layer and an intelligent contract layer, wherein the data layer stores data by using a Merkle tree, the data layers are structurally connected in a chain manner through blocks, and the data structure is provided with an encryption unit and a data transmission module; the network layer is mainly composed of network nodes which are interweaved in an intricate way, data communication and connection are realized by using a point-to-point technology through different network nodes, so that different node devices in the block chain network can be intercommunicated and interconnected, a consensus mechanism is arranged in the consensus layer, and the consensus mechanism can carry out consistent interaction on data arranged in the block chain network, so that the data consensus ability and the data anti-attack ability are good; the excitation layer outputs excitation information in a block chain; the intelligent contract layer is provided with more than two big data algorithm modules, and can execute and calculate the relation between various data in the block chain network; a block chain platform is arranged in the block chain layer, and the block chain platform is a supporting platform of a modularized block chain solution based on Hyperridge Fabric;
the cloud server at least comprises a distributed storage module, a data transmission interface, a CPU, an internal memory, a disk, a bandwidth and a cloud network interface, wherein the cloud server is formed by constructing a cloud resource pool by intensively and virtualizing a scale-level bottom server and allocating computing resources from the resource pool, wherein the CPU, the internal memory, the disk or the bandwidth exist in a free combination mode;
the data calculation layer is internally provided with a data mining algorithm model, wherein the data mining algorithm model is an association algorithm model and a data classification algorithm model; the association algorithm is used for mining the relationship between the received petition data and finding out the association between different petition times, and the data classification algorithm is used for classifying different types of petition data according to classification attributes and rules so that petition managers can quickly inquire the petition data;
the data application layer is internally provided with a data transmission module and an application computer, wherein the data transmission module is a wired communication module or a wireless communication module and is used for receiving and transmitting the power grid equipment data information sensed by the data acquisition layer; the wired communication module at least comprises an RS485 communication module or an RS232 communication module, and the wireless communication module at least comprises a TCP/IP network system, a ZigBee wireless network, a GPRS communication module or a CDMA wireless communication, cloud network or Bluetooth communication module; wherein:
the output end of the data acquisition layer is connected with the input end of the data storage layer, the output end of the data storage layer is connected with the input end of the data calculation layer, and the output end of the data calculation layer is connected with the input end of the data application layer.
In the above embodiment, the petition data in the petition large database at least includes name, gender, age, region, petition event type, petition time, petition core keyword, petition reason, petition event process description, petition period, petition number, and petition processing data.
In the above embodiment, the blockchain system is a blockchain system based on a Fabric architecture, and the Fabric architecture includes a system management layer, an organization management layer, and a service development layer. The Fabric platform is an alliance chain structure, supports an intelligent contract technology, does not depend on tokens when the system operates, can support about hundred transactions per second and basically meets the requirement of cross-organization transactions of digital assets between alliances. In addition, Fabric adopts a modular architecture, wherein a consensus algorithm and the like can be used as a pluggable module for a user to choose. Meanwhile, the method can lead a user to redesign and develop a specific module according to the self requirement, so that the Fabric is selected as a block chain foundation platform of the digital asset transaction system. The Fabric mainly comprises member service modules (Membership Services), block chain service modules (blockchain Services) and chain code service modules (Chaincode Services). The member service module mainly provides functions of member registration, identity management, transaction examination and the like, and performs mechanism registration authentication and transaction authentication through a registration certificate issuing mechanism (ECA) and a transaction authentication center (TCA). The block chain service module is mainly responsible for point-to-point communication between nodes, consensus, and the storage of account book data. The chain code service module provides intelligent contract service, provides a safe contract running environment and the like. Meanwhile, the platform realizes asynchronous communication through an Event Stream (Event Stream) between all the components.
In the above embodiment, the association algorithm model is a bayesian classifier model.
In the above embodiment, the data classification algorithm model is provided with a cloud data interface, a wireless communication data interface or a USB data interface.
According to the invention, by adopting a block chain technology, big data management is realized, an architecture system comprising a data acquisition layer, a data storage layer, a data calculation layer and a data application layer is constructed, and data interaction is realized by fully utilizing the characteristics of decentralization, non-falsification, distributed common accounting, asymmetric encryption, data safe storage and the like of the block chain technology; according to the invention, the encryption function and the decryption function are adopted, so that the encryption and decryption of the big data are realized, the stability of the data is ensured in the big data transmission process, the data is prevented from being tampered, and the safety performance of the data is improved; the invention adopts a sharing algorithm, realizes data sharing in a block chain, makes full use of a sharing mechanism, has the advantages of decentralization, distrust, data encryption and the like, and can better solve the problem of data management in big data application.
According to the invention, the cloud server is adopted, so that the automatic processing of data can be realized, the cloud computing automatically analyzes the required data, and a metering function of a certain service level is supported. This usage can be monitored, controlled and reported, providing transparency for hosts and customers.
It is also capable of on-demand services, which is one of the important and valuable functions of cloud computing, as users can continuously monitor the uptime, functionality and allocated network storage of the server. With this functionality, the user can also monitor the computing functionality.
The cloud technology is high in safety, and is one of the best functions of the cloud servers, a snapshot for storing data is created, and therefore even if one of the servers is damaged, the data cannot be lost. The data is stored in the storage device and cannot be attacked and utilized by any other person, and the storage service is quick and reliable and can be accessed from any place only by means of the device and internet connection.
The cloud technology is easy to maintain, the cloud host is easy to maintain, and the shutdown time is very short. In some cases, there is no downtime. Cloud computing provides updates each time by progressively refining it. These updates are more compatible with the device and faster than the old version, and fix the errors.
Example 2
On the basis of the above embodiments, the present invention further provides an intelligent access and evidence-saving method based on artificial intelligence big data, as shown in fig. 6 to 7, including the following steps:
(S1) data acquisition: acquiring data, namely acquiring data information of a petition event through a data acquisition layer;
(S2) data processing: screening and cleaning the acquired big data to acquire effective big data, and realizing storage, encryption, calculation and sharing of the data through a block chain system or a cloud server;
(S3) data calculation: calculating the association between the data through a data mining algorithm, or classifying the petition data according to set attributes according to user requirements, mining the relation between petition events through the association algorithm model on the preprocessed big data, and realizing the classification of various petition events by using a data classification algorithm model;
(S4) data application: and in the data application layer, data transmission is carried out on the calculated data for the user to use.
Further, the correlation algorithm model formula is as follows:
assuming that the petition event data to be classified in the petition database has an attribute d, and assuming that the category of the petition event data attribute is classified into a set C, then C is { C ═ C { (C)1，c2，...，cmH, wherein the i-th classification attribute satisfies the condition: i is more than or equal to 1 and less than or equal to m, and the maximum output class of the petition event data set d to be classified is P (c)iAnd/d), then:
where C, D is expressed as a random variable, the Bayesian classification formula for document d is:
in the above embodiment, the data classification algorithm model is at least a decision tree algorithm model, a cluster classification algorithm model, a BP neural network algorithm model, a KNN algorithm model, a support vector machine algorithm model, a VSM method model, or a k-nearest neighbor algorithm model; the k-nearest neighbor algorithm comprises the following steps:
(1) selecting information sample data in an interview database, selecting a central point of an initial cluster according to the selected interview data sample, randomly extracting K interview data sample data from the sample data, taking the selected interview data sample as the center of a sample cluster data set, and setting a threshold value T of iteration times, wherein K is more than 100, and T is more than 1 and less than 8;
(2) dividing cluster points of the petition data samples, dividing the points of each petition data sample cluster to a cluster point represented by a center closest to the petition data samples, and dividing the center point of the petition data samples closest to the center point of an initial cluster into a class;
wherein the distance formula between the nearest center of the petition data sample and the point of the represented cluster is:
wherein x and y respectively represent different types of visiting data samples, n represents the dimensionality of the visiting data samples, d (x and y) is an Euclidean distance, the distance between each visiting data sample and the parameters of the central samples is calculated according to the central point of the clustering sample of each visiting data sample, and the corresponding visiting data samples are divided again according to the minimum distance;
(3) representing the center point of the sample cluster of the petition data sample by the center point of each sample data point in different petition data sample clusters, calculating the distance between the center point of each petition data sample cluster and the clustering information data centers again according to the center points of different parameter data or different clustering information sample data, and dividing the corresponding petition data sample data again according to the minimum distance, and forming a matrix D by the minimum data calculated each time, wherein the matrix D is as follows:
wherein x is the set of minimum values found;
(4) and (3) judging whether iterative computation is carried out or not, if the iteration number is equal to a set threshold value T, not using the iterative computation, if the iteration number is different from the set threshold value, subdividing the digital asset information sample cluster points, returning to the step (2), and repeating the steps (2) and (3).
In the above embodiments, the elliptic curve function algorithm, the mnemonic algorithm, the DES algorithm, the 3DES algorithm, the Blowfish algorithm, the Twofish algorithm, the IDEA algorithm, the RC6 algorithm, or the CAST5 algorithm.
Wherein the equation for the elliptic curve function is:
y2＝x3+ax+b (5)
in formula (1), assuming that there are 3 focal points of the non-vertical line and the curve, on the non-vertical line, the tangent line on the non-vertical line intersects the curve at other points, and assuming that there are 2 points Q and P, and Q and P intersect at R', there are:
R＝Q+P (6)
wherein, R and R 'are symmetrical about the X axis, when the Q point and the P point are coincident, if the coincident point is D, the straight line is tangent with the curve, and R' is represented as the intersection point; then there is the formula:
D+D＝R (7)
at this point, R and R' are still symmetric about the X axis, then:
Q＝aP (8)
since there are 3 intersections, a equals 3, the formula can be transformed into:
Q＝3P (9)
when performing encryption calculation in a block chain, assuming that a modulus is p, a base point is G, and an ordinal number is n, then:
public key G as private key; (10)
the Q point and the P point represent two different points on the curve, which can be calculated by the following formula:
Rx＝d2-Px-Qx(12)
Ry＝d(Px-Qx)-Px(13)
the encryption of the public key is completed through the algorithm, and when the private key encryption is completed, the data z is encrypted by adopting the private key dA, and the method is adopted: selecting data k, let: k is more than or equal to 0 and less than or equal to 1, and then the following formula is adopted for calculation:
p(x，y)＝k*G (14)
then, calculating:
r＝x mod n (15)
when r segment 0 occurs, then reselection occurs. Then calculated using the following formula:
if s is 0 after the final calculation, recalculation is carried out, and then the data signature (r, s) is generated, so that private encryption is realized.
In the above embodiment, when processing big data, it is usually necessary to perform dimension reduction on the big data to make complex data easier to process, and in one data dimension reduction calculation, a principal component analysis method is adopted, and the steps of the principal component analysis method are as follows:
(1) normalizing the data; suppose the latitude of the data sample of the petition data is p, and the random vector is x ═ x1，x2，...，xp) (ii) a Then for i data samples there are: x is the number ofi＝(xi1，xi2，...，xip) Wherein i is 1, 2.. times.n; when n is more than p, carrying out normalized transformation on the sample array element, wherein the normalized transformation formula is as follows:
wherein i is 1, 2.. times.n; j is 1, 2,. said, p; in equation (3), there is also:
(2) solving a correlation coefficient matrix of the normalized matrix Z in the step (1);
R＝[rij]p； (20)
wherein:
wherein i, j ═ 1, 2.., p;
(3) determining principal components, and solving a characteristic equation of a correlation matrix R to obtain the principal components, wherein the equation is as follows:
|R-λIp|＝0 (23)
in determining the value of n, by the following equation:
each λ in the formula (10)j1, 2., n, solving the system of equations yields:
Rb＝λjb (25)
deriving feature vectors by equation (11)
(4) Then, the normalized index variable is converted into a principal component
Wherein j is 1, 2.. multidot.n; and U1Referred to as the first principal component, U2Referred to as the second principal component, UjReferred to as jth principal component;
(5) and then carrying out comprehensive evaluation on the n principal components, and carrying out weighted summation on the n principal components to obtain a final evaluation value, wherein the weight is the variance contribution rate of each principal component.
In the above embodiments, Principal Component Analysis (PCA) is also called Principal Component Analysis, and aims to convert multiple indexes into a few comprehensive indexes by using the idea of dimension reduction. In statistics, principal component analysis is a technique that simplifies the data set. It is a linear transformation. This transformation transforms the data into a new coordinate system such that the first large variance of any data projection is at the first coordinate (called the first principal component), the second large variance is at the second coordinate (the second principal component), and so on. Principal component analysis is often used to reduce the dimensionality of the data set while maintaining the features of the data set that contribute most to the variance. This is done by keeping the lower order principal components and ignoring the higher order principal components. Such low order components tend to preserve the most important aspects of the data. However, this is not necessary and will depend on the particular application.
Although specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are merely illustrative and that various omissions, substitutions and changes in the form of the detail of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the steps of the above-described methods to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is to be limited only by the following claims.
Claims (10)
1. The utility model provides a visit and deposit certificate system based on artificial intelligence big data wisdom which characterized in that: the system comprises:
the data acquisition layer is at least internally provided with an RFID (radio frequency identification device), a computer, a mouse and a keyboard which are connected with the computer, a large-scale petition database integrated in the computer and a personal information two-dimensional code; the large petition database is at least provided with a display layer, a business logic layer, a data access layer, a cloud data interface and a block chain data interface, wherein the display layer is connected with the business logic layer, the business logic layer is connected with the data access layer, the data access layer is connected with the cloud data interface and the block chain data interface, and the data access layer is used for accessing files in the large petition database to read, store and transmit data in the large petition database; the display layer is used for displaying the large petition database and receiving petition data of the data access layer, an interactive network man-machine interaction platform is provided for petition, the business logic layer stores and identifies petition information input by a user, and the cloud data interface and the block chain data interface are used for interacting petition data with the data storage layer;
the data storage layer is at least provided with a block chain system and a cloud server, wherein:
the block chain system comprises a data layer, a network layer, a consensus layer, an excitation layer and an intelligent contract layer, wherein the data layer stores data by using a Merkle tree, the data layers are structurally connected in a chain manner through blocks, and the data structure is provided with an encryption unit and a data transmission module; the network layer is mainly composed of network nodes which are interweaved in an intricate way, data communication and connection are realized by using a point-to-point technology through different network nodes, so that different node devices in the block chain network can be intercommunicated and interconnected, a consensus mechanism is arranged in the consensus layer, and the consensus mechanism can carry out consistent interaction on data arranged in the block chain network, so that the data consensus ability and the data anti-attack ability are good; the excitation layer outputs excitation information in a block chain; the intelligent contract layer is provided with more than two big data algorithm modules, and can execute and calculate the relation between various data in the block chain network; a block chain platform is arranged in the block chain layer, and the block chain platform is a supporting platform of a modularized block chain solution based on Hyperridge Fabric;
the cloud server at least comprises a distributed storage module, a data transmission interface, a CPU, an internal memory, a disk, a bandwidth and a cloud network interface, wherein the cloud server is formed by constructing a cloud resource pool by intensively and virtualizing a scale-level bottom server and allocating computing resources from the resource pool, wherein the CPU, the internal memory, the disk or the bandwidth exist in a free combination mode;
the data calculation layer is internally provided with a data mining algorithm model, wherein the data mining algorithm model is an association algorithm model and a data classification algorithm model; the association algorithm is used for mining the relationship between the received petition data and finding out the association between different petition times, and the data classification algorithm is used for classifying different types of petition data according to classification attributes and rules so that petition managers can quickly inquire the petition data;
the data application layer is internally provided with a data transmission module and an application computer, wherein the data transmission module is a wired communication module or a wireless communication module and is used for receiving and transmitting the power grid equipment data information sensed by the data acquisition layer; the wired communication module at least comprises an RS485 communication module or an RS232 communication module, and the wireless communication module at least comprises a TCP/IP network system, a ZigBee wireless network, a GPRS communication module or a CDMA wireless communication, cloud network or Bluetooth communication module; wherein:
the output end of the data acquisition layer is connected with the input end of the data storage layer, the output end of the data storage layer is connected with the input end of the data calculation layer, and the output end of the data calculation layer is connected with the input end of the data application layer.
2. The system according to claim 1, wherein the system comprises:
the petition data in the petition large database at least comprises petition personnel names, sexes, ages, regions, petition events, petition event types, petition time, petition core keywords, petition reasons, petition event process description, petition periods, petition numbers and petition processing data.
3. The system according to claim 1, wherein the system comprises: the blockchain system is a blockchain system based on the Fabric architecture.
4. The system according to claim 3, wherein the system comprises: the Fabric architecture comprises a system management layer, an organization management layer and a business development layer.
5. The system according to claim 1, wherein the system comprises: the correlation algorithm model is a Bayesian classifier model.
6. The system according to claim 1, wherein the system comprises: the data classification algorithm model is provided with a cloud data interface, a wireless communication data interface or a USB data interface.
7. An intelligent interview and evidence storage method based on artificial intelligence big data is characterized in that: the method comprises the following steps:
(S1) data acquisition: acquiring data, namely acquiring data information of a petition event through a data acquisition layer;
(S2) data processing: screening and cleaning the acquired big data to acquire effective big data, and realizing storage, encryption, calculation and sharing of the data through a block chain system or a cloud server;
(S3) data calculation: calculating the association between the data through a data mining algorithm, or classifying the petition data according to set attributes according to user requirements, mining the relation between petition events through the association algorithm model on the preprocessed big data, and realizing the classification of various petition events by using a data classification algorithm model;
(S4) data application: and in the data application layer, data transmission is carried out on the calculated data for the user to use.
8. The intelligent interview and evidence storage method based on artificial intelligence big data as claimed in claim 7, wherein: the associated algorithm model formula is as follows:
assuming that the petition event data to be classified in the petition database has an attribute d, and assuming that the category of the petition event data attribute is classified into a set C, then C is { C ═ C { (C)1，c2，...，cmH, wherein the i-th classification attribute satisfies the condition: i is more than or equal to 1 and less than or equal to m, and the maximum output class of the petition event data set d to be classified is P (c)iAnd/d), then:
where C, D is expressed as a random variable, the Bayesian classification formula for document d is:
9. the intelligent interview and evidence storage method based on artificial intelligence big data as claimed in claim 7, wherein: the data classification algorithm model is at least a decision tree algorithm model, a cluster classification algorithm model, a BP neural network algorithm model, a KNN algorithm model, a support vector machine algorithm model, a VSM method model or a k-nearest neighbor algorithm model; the k-nearest neighbor algorithm comprises the following steps:
(1) selecting information sample data in an interview database, selecting a central point of an initial cluster according to the selected interview data sample, randomly extracting K interview data sample data from the sample data, taking the selected interview data sample as the center of a sample cluster data set, and setting a threshold value T of iteration times, wherein K is more than 100, and T is more than 1 and less than 8;
(2) dividing cluster points of the petition data samples, dividing the points of each petition data sample cluster to a cluster point represented by a center closest to the petition data samples, and dividing the center point of the petition data samples closest to the center point of an initial cluster into a class;
wherein the distance formula between the nearest center of the petition data sample and the point of the represented cluster is:
wherein x and y respectively represent different types of visiting data samples, n represents the dimensionality of the visiting data samples, d (x and y) is an Euclidean distance, the distance between each visiting data sample and the parameters of the central samples is calculated according to the central point of the clustering sample of each visiting data sample, and the corresponding visiting data samples are divided again according to the minimum distance;
(3) representing the center point of the sample cluster of the petition data sample by the center point of each sample data point in different petition data sample clusters, calculating the distance between the center point of each petition data sample cluster and the clustering information data centers again according to the center points of different parameter data or different clustering information sample data, and dividing the corresponding petition data sample data again according to the minimum distance, and forming a matrix D by the minimum data calculated each time, wherein the matrix D is as follows:
wherein x is the set of minimum values found;
(4) and (3) judging whether iterative computation is carried out or not, if the iteration number is equal to a set threshold value T, not using the iterative computation, if the iteration number is different from the set threshold value, subdividing the digital asset information sample cluster points, returning to the step (2), and repeating the steps (2) and (3).
10. The intelligent interview and evidence storage method based on artificial intelligence big data as claimed in claim 7, wherein: the encryption method in the block chain is any one of the following encryption algorithms:
elliptic curve function algorithm, mnemonic algorithm, DES algorithm, 3DES algorithm, Blowfish algorithm, Twofish algorithm, IDEA algorithm, RC6 algorithm or CAST5 algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010450756.1A CN111831715A (en) | 2020-05-25 | 2020-05-25 | Intelligent access and certificate storage system and method based on artificial intelligence big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010450756.1A CN111831715A (en) | 2020-05-25 | 2020-05-25 | Intelligent access and certificate storage system and method based on artificial intelligence big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111831715A true CN111831715A (en) | 2020-10-27 |
Family
ID=72914018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010450756.1A Pending CN111831715A (en) | 2020-05-25 | 2020-05-25 | Intelligent access and certificate storage system and method based on artificial intelligence big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111831715A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396341A (en) * | 2020-11-30 | 2021-02-23 | 河海大学 | Block chain localization cloud computing big data application analysis method |
| CN113158227A (en) * | 2021-03-08 | 2021-07-23 | 重庆邮电大学 | Database access log chaining method and system based on Fabric |
| CN113420015A (en) * | 2021-06-07 | 2021-09-21 | 浙江嘉兴数字城市实验室有限公司 | Automatic classification method of social management events based on neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287268A (en) * | 2019-06-30 | 2019-09-27 | 智慧谷(厦门)物联科技有限公司 | A kind of digital asset processing method and system based on block chain |
| CN110532329A (en) * | 2019-09-02 | 2019-12-03 | 智慧谷(厦门)物联科技有限公司 | A kind of Intelligent bracelet data processing and sharing method based on block chain technology |
| EP3579494A1 (en) * | 2018-06-08 | 2019-12-11 | Deutsche Telekom AG | Blockchain based roaming |
| CN111027087A (en) * | 2019-12-16 | 2020-04-17 | 智慧谷(厦门)物联科技有限公司 | Enterprise information management system and method for encrypting mnemonics by applying block chain |
-
2020
- 2020-05-25 CN CN202010450756.1A patent/CN111831715A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3579494A1 (en) * | 2018-06-08 | 2019-12-11 | Deutsche Telekom AG | Blockchain based roaming |
| CN110287268A (en) * | 2019-06-30 | 2019-09-27 | 智慧谷(厦门)物联科技有限公司 | A kind of digital asset processing method and system based on block chain |
| CN110532329A (en) * | 2019-09-02 | 2019-12-03 | 智慧谷(厦门)物联科技有限公司 | A kind of Intelligent bracelet data processing and sharing method based on block chain technology |
| CN111027087A (en) * | 2019-12-16 | 2020-04-17 | 智慧谷(厦门)物联科技有限公司 | Enterprise information management system and method for encrypting mnemonics by applying block chain |
Non-Patent Citations (3)
| Title |
|---|
| 焦李成: "《人工智能前沿技术丛书 简明人工智能》", 30 September 2019, 西安电子科技大学出版社 * |
| 王和勇: "《面向大数据的高维数据控掘技术》", 31 March 2018, 西安电子科技大学出版社 * |
| 王文海: "《密码学理论与应用基础》", 30 September 2009, 国防工业出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396341A (en) * | 2020-11-30 | 2021-02-23 | 河海大学 | Block chain localization cloud computing big data application analysis method |
| CN113158227A (en) * | 2021-03-08 | 2021-07-23 | 重庆邮电大学 | Database access log chaining method and system based on Fabric |
| CN113158227B (en) * | 2021-03-08 | 2022-10-11 | 重庆邮电大学 | Database access log uplink method and system based on Fabric |
| CN113420015A (en) * | 2021-06-07 | 2021-09-21 | 浙江嘉兴数字城市实验室有限公司 | Automatic classification method of social management events based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220343197A1 (en) | Systems and methods for providing machine learning model explainability information | |
| Elgendy et al. | Big data analytics: a literature review paper | |
| Hussain et al. | Classification, clustering and association rule mining in educational datasets using data mining tools: A case study | |
| WO2022105115A1 (en) | Question and answer pair matching method and apparatus, electronic device and storage medium | |
| Rodger | Discovery of medical Big Data analytics: Improving the prediction of traumatic brain injury survival rates by data mining Patient Informatics Processing Software Hybrid Hadoop Hive | |
| WO2021174944A1 (en) | Message push method based on target activity, and related device | |
| CN111831715A (en) | Intelligent access and certificate storage system and method based on artificial intelligence big data | |
| El Morr et al. | Descriptive, predictive, and prescriptive analytics | |
| US20170018030A1 (en) | System and Method for Determining Credit Worthiness of a User | |
| CA2481432A1 (en) | Processing mixed numeric and/or non-numeric data | |
| CN104866831B (en) | The face recognition algorithms of characteristic weighing | |
| CN108269331A (en) | A kind of intelligent video big data processing system | |
| US8719191B2 (en) | Training and verification using a correlated boosted entity model | |
| CN109829721B (en) | Online transaction multi-subject behavior modeling method based on heterogeneous network characterization learning | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| Prasad | Big data analytics made easy | |
| Cifci et al. | Data mining usage and applications in health services | |
| Rentzmann et al. | Unsupervised learning: What is a sports car? | |
| Li et al. | Fuzzy clustering-based financial data mining system analysis and design | |
| WO2021189908A1 (en) | Image classification method based on deep learning, image classification apparatus, server and medium | |
| Batmaz et al. | Overview of knowledge discovery in databases process and data mining for surveillance technologies and EWS | |
| Venkat et al. | Clustering of huge data with fuzzy c-means and applying gravitational search algorithm for optimization | |
| CN113762703A (en) | Method and device for determining enterprise portrait, computing equipment and storage medium | |
| CN114443409A (en) | Payment business system monitoring method, device and equipment and computer storage medium | |
| Al Aghbari | Mining big data |
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 |