CN111291628A - Face data distributed recognition and storage architecture based on block chain technology - Google Patents
Face data distributed recognition and storage architecture based on block chain technology Download PDFInfo
- Publication number
- CN111291628A CN111291628A CN202010049817.3A CN202010049817A CN111291628A CN 111291628 A CN111291628 A CN 111291628A CN 202010049817 A CN202010049817 A CN 202010049817A CN 111291628 A CN111291628 A CN 111291628A
- Authority
- CN
- China
- Prior art keywords
- node
- face
- picture
- operation node
- nodes
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000009434 installation Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 230000000644 propagated effect Effects 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims 4
- 238000013500 data storage Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 17
- 239000000306 component Substances 0.000 description 14
- 238000013475 authorization Methods 0.000 description 8
- 210000003128 head Anatomy 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- H04L67/104—Peer-to-peer [P2P] networks
-
- 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
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- 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]
-
- 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
- H04L67/34—Network arrangements or protocols for supporting network services or applications involving the movement of software or configuration parameters
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Security & Cryptography (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Image Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a face data distributed recognition and storage architecture based on a block chain technology, which comprises a system operation node, an operation node, a camera agent node and a camera group, wherein the block chain technology is adopted to integrate idle and dispersed strange calculation resources, a face recognition task is jointly completed in a mutually untrusted network formed by the nodes and the groups, the accuracy and the reliability of a recognition result are effectively ensured, and a face recognition and data storage platform with strong practicability, low cost, high safety, good expansibility and certain advancement is constructed.
Description
Technical Field
The invention relates to the technical field of block chain technology and biological feature recognition, in particular to a distributed recognition and storage architecture for face data by using the block chain technology.
Background
The block chain technology is a novel application mode integrating computer technologies such as data distributed storage, a point-to-point transmission network, a consensus mechanism and an encryption algorithm, and plays an important role in data privacy, data security, trust construction and the like.
The face recognition technology is mainly used for analyzing and recognizing the identity of a person. The human face is the inherent physiological characteristic of the human body, and has the characteristics of uniqueness, impossibility of counterfeiting, portability, availability at any time and any place and the like. The face recognition, fingerprint recognition, voiceprint recognition, iris recognition and the like belong to biological feature recognition technologies.
Along with the rapid popularization of the current video monitoring, the video monitoring is required to be capable of rapidly identifying the identity of a shot person under the remote and uncoordinated condition of the shot person in response to increasingly complex and severe public safety situations, and further intelligent early warning is achieved. The face recognition technique is clearly the best choice relative to other biometric techniques. The method can accurately find the face from the monitoring video image in real time, and then compares the face with the face data in the face database in real time, thereby quickly confirming the identity of the shot object.
The face recognition technology can be widely applied to the field of security and protection, is also an important component of a smart city and is a core support platform of a public service and emergency smart platform for city management, spans regions and time and tracks each monitoring site in real time through a strict video monitoring network, greatly improves the rapid response capability, more effectively attacks crimes, improves the security level and the comprehensive management level of the city, and is beneficial to the rapid development of various economic industries.
The practical examination in recent years shows that the key influencing the popularization and application of the face recognition technology is not the quality of a face recognition algorithm, nor the loss of mass training sample data, but the calculation power problem which is considered to be solved subjectively. The face recognition algorithm has high requirements on computational resources, and although the performance of a processing chip is continuously improved, the power consumption and the cost are still bottlenecks faced by the development of the chip technology. With the rapid increase of the data volume of the future video images, the application of the face recognition technology is restricted by calculation force more and more obviously. The technology can realize the improvement of computing power by continuously accumulating hardware resources, but medium-sized and small enterprises are difficult to bear high cost, so that the business civilization popularization of the face recognition technology is not facilitated.
Disclosure of Invention
The invention aims to provide a face data distributed recognition and storage architecture based on a block chain technology, which has the core idea that strange calculation force resources (not calculation force resources controlled by a platform) which are idle and dispersed are integrated by using the block chain technology, face recognition tasks are jointly completed in networks which are not trusted with each other, the accuracy and the reliability of recognition results are effectively ensured, and a set of face recognition and data storage platform which is strong in practicability, low in cost, high in safety, good in expansibility and advanced to a certain extent is constructed. The platform can help small and medium-sized enterprises to build a high-computing-capacity system without investing excessive hardware overhead, thereby effectively reducing the operation cost of the enterprises and being beneficial to rapid popularization of the face recognition technology in the whole society.
In order to achieve the above object, the present invention provides a face data distributed recognition and storage architecture based on a block chain technology, which includes a system operation node, a computation node, a camera agent node, and a camera group.
The nodes formed by the system operation nodes, the operation nodes and the camera agent nodes form a distributed P2P network by operating a P2P network protocol, so that point-to-point interconnection and intercommunication among the nodes are realized. The system operation node and the camera agent node are managed and deployed by a system operator, the operation node can be any group or individual except the operator who is willing to provide self-computing resources, and the operation node can be freely added to or withdrawn from the P2P network as long as the operation node runs the P2P network protocol on the respective operation device; the compute nodes may also be operator controlled computational resources. The computing device may be a notebook or desktop computer, or may be a server with superior performance.
The system operation node can be regarded as the only representative of the system operator, and is mainly responsible for the management of the face recognition component and the face data, the maintenance of P2P network communication and the issue of data security and economic reward, and comprises a face recognition module, a face database module, an encryption/decryption module, a service module, a network routing module, a reward module, a picture library, a picture chain and a registry. The face recognition module comprises a face data processing component and realizes two functions of face feature extraction and face feature comparison; the face database module is used for storing face data, the face data belongs to highly private information, and ownership is at a system operation node; the encryption/decryption module is responsible for encrypting and decrypting data transmitted in the P2P network, for example, human face data is transmitted to each operation node through the P2P network after being encrypted, an identification result calculated by the operation node needs to be encrypted and transmitted back to a system operation node, and the encrypted identification result needs to be decrypted to obtain a final result after reaching the system operation node; the service module is responsible for managing the face feature data and the face data processing component, monitoring the running state of the whole network and the reward issuing condition; the network routing module is responsible for nodes to join or leave the P2P network, and maintains data communication channels and connection with other nodes; the reward module mainly issues economic rewards to the operation nodes which provide computing power to complete the identification task, while the operation nodes which obtain the rewards are voted by other operation nodes, and the reward module directly issues the rewards to accounts of winning nodes; the picture library is used for storing the unrecognized face pictures propagated in the P2P network, and the recognized face pictures recorded in the picture chain are deleted from the picture library; the picture chain is used for storing the picture blocks which are identified and verified, and the picture blocks are hung behind the preamble blocks according to the hash values of the preamble blocks; the registry is used for recording the information of the online operation nodes and the camera agent nodes of the network.
The operation node comprises a network routing module, an encryption/decryption module, a face recognition module, a face database module, a picture library and a picture chain. The method adopts a workload certification mechanism to compete for the face picture recognition right, the operation node obtaining the recognition right needs to broadcast picture blocks to a P2P network, a system operation node in the network and other operation nodes together verify whether the picture blocks meet the workload certification, once the workload certification is met, the system operation node approves votes for vote, and the system operation node gives a winning operation node recognition authorization according to the voting result; with the identification authorization, the winning operation node is responsible for completing the identification task of the face picture contained in the picture block, and the task comprises face feature extraction and face feature comparison; the operation nodes without wins start to pack new picture blocks and start a new round of identification right competition; after the identification task is completed, the winning operation node sends the identification result to the system operation node and other operation nodes through the P2P network, the nodes verify and vote the received identification result, and inform the system operation node of the voting result, the system operation node judges whether to finally issue the reward to the winning operation node according to the voting result, and simultaneously informs each operation node whether to give the reward. Each operation node maintains a picture chain locally, picture blocks demonstrated by the operation nodes which obtain rewards are hung and stored, and system operation nodes can hang the picture blocks to the picture chains of the operation nodes. The picture blocks which are proved by the operation nodes which do not obtain the reward are discarded by each node, and the face pictures contained in the picture blocks are repackaged into new picture blocks to start a new competition. Each operation node is independent and equivalent, and the main work is face recognition operation, so all the operation nodes can be regarded as forming an operation resource network.
The camera proxy node contains a network routing module and an encryption/decryption module, which are managed and deployed by the system operator. The main function is to receive the face pictures from the camera group, encrypt the received face pictures and send the encrypted face pictures to the P2P network.
The camera group consists of cameras deployed in different places, and aims to send face pictures acquired on site to corresponding camera agent nodes, the face pictures are sent to an operation resource network after being processed by the agent nodes, and the face pictures finally reach system operation nodes. The camera group is managed and deployed by the system operator.
Compared with the prior art, the invention adopting the technical scheme has the following advantages:
1. the practicability is strong: the technical scheme of the invention is well suitable for the face recognition technology and can meet the requirements of practical work to the maximum extent. The node type and the function design fully consider the high efficiency and the stability of the execution of the face recognition task; the distributed P2P network guarantees arbitrary joining and exiting of nodes.
2. The cost is low: for the recognition work of a large number of face pictures, a plurality of servers with excellent performance are often required to be deployed for completion, and the investment and maintenance cost of an operator is increased invisibly. The technical scheme of the invention can attract the idle calculation power except the operator to be put into the identification task, thereby reducing the input cost of the operator; meanwhile, the rapid popularization of the face recognition technology in the whole society is promoted.
3. The safety is high: the transmission of the face database module, the reward module and the data in a network channel is protected by adopting a safe encryption mechanism, so that the data is effectively prevented from being stolen and tampered. In addition, the face data is stored locally in the system operator and also stored in other nodes in a scattered manner, and once the face data of a certain node is lost or tampered, the data can be synchronized from other nodes.
4. The expansibility is good: after the operator deploys the system operation node and the camera agent node, the operator attracts idle calculation power to join face recognition work through a reward mechanism, the operator determines a reward limit according to the actual workload of face recognition, and the higher the reward limit is, the more the attracted idle calculation power is, and the less the reward limit is. The scale of the operation resource network is in a dynamic change state.
5. The maintainability is high: the system architecture fully considers the good flexibility and expandability in the aspects of face data processing capacity, network communication capacity, local data storage capacity, data security, product upgrading and the like, and particularly an operator is not responsible for purchasing and maintaining face recognition hardware facilities any more and hands purchasing and maintaining work to an operation node controlled by a non-operator; the product upgrading is also limited to the upgrading in the aspect of software to the maximum extent, and the software upgrading message is sent to the operation node through the network, and the operation node determines whether to upgrade or not. The structure and program module adopted by the system software fully consider maintainability and portability, namely, a certain component is modified according to requirements, a new function is upgraded and the structure of the system is recombined to achieve the purpose of program reuse.
5. The method has certain advancement: the block chain technology is mainly applied to the field of financial science and technology at present, but the block chain technology is expanded to the field of security protection, and particularly provides a brand-new thought and scheme for application innovation of the face recognition technology.
Drawings
The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a block chain technique based distributed face data recognition and storage architecture according to some embodiments of the present invention;
fig. 2 is a schematic diagram of a distributed P2P network formed by a system operation node, a computation node and a camera proxy node;
FIG. 3 is a diagram illustrating a picture library and operation of face pictures thereof;
FIG. 4 is a diagram of a tile structure and a chain of pictures;
FIG. 5 is a schematic diagram of internal modules and data flow of a system operation node;
FIG. 6 is a schematic diagram of a node voting method;
FIG. 7 is a schematic diagram of a start-up procedure of a system operation node;
FIG. 8 is a schematic diagram of the face recognition software being sent to the compute nodes;
FIG. 9 is a schematic diagram of reward data sent to winning compute nodes;
FIG. 10 is a schematic diagram of a system operating node receiving a face picture;
fig. 11 is a schematic diagram of a system operation node receiving a picture block and an identification result;
FIG. 12 is a diagram illustrating a system operation node receiving voting results;
FIG. 13 is a schematic diagram of a system operator node receiving node status information;
FIG. 14 is a schematic diagram of internal modules of a compute node;
FIG. 15 is a schematic diagram of a compute node boot flow;
FIG. 16 is a schematic diagram illustrating a process of competing picture identification rights of a compute node;
FIG. 17 is a flow chart illustrating the winning operation node awarding prize;
fig. 18 is a schematic diagram of modules within a camera proxy node;
fig. 19 is a schematic diagram of a relationship between a camera group and a camera proxy node.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily intended to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any one implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
Referring to fig. 1, according to an embodiment of the present invention, a face data distributed recognition and storage architecture based on a block chain technology includes a system operation node, a computation node, a camera agent node, and a camera group composed of a plurality of cameras.
Referring to fig. 2, the system operation node, the operation node and the camera agent node are interconnected by operating a P2P network protocol to form a distributed P2P network. In this distributed P2P network, the functions of the various nodes are as follows:
(1) the system operation node is mainly responsible for the management of the face recognition component and the face data and economic reward, and comprises a face recognition module, a face database module, an encryption/decryption module, a service module, a network routing module, a reward module, a picture library, a picture chain and a registry. The face recognition module comprises a face data processing component and realizes two functions of face feature extraction and face feature comparison; the face database module is used for storing face feature data, the face feature data belong to highly private information, and ownership is at a system operation node; the encryption/decryption module is responsible for encrypting and decrypting data transmitted in the P2P network, for example, human face data is transmitted to each operation node through the P2P network after being encrypted, an identification result calculated by the operation node needs to be encrypted and transmitted back to a system operation node, and the encrypted identification result needs to be decrypted to obtain a final result after reaching the system operation node; the service module is responsible for managing the face data and the face data processing assembly, monitoring the running state of the whole network and rewarding and issuing conditions; the network routing module is responsible for nodes to join or leave the P2P network, and maintains data communication channels and connection with other nodes; the reward module mainly issues economic rewards to the operation nodes which provide computing power to complete the identification task, the operation nodes which obtain the rewards are generated by voting of the system operation nodes and other operation nodes, and the reward module directly issues the rewards to accounts of winning nodes; the picture library is used for storing the unrecognized face pictures propagated in the P2P network, and the recognized face pictures recorded in the picture chain are deleted from the picture library; the picture chain is used for storing the picture blocks which are identified and verified, and the picture blocks are hung behind the preamble blocks according to the hash values of the preamble blocks; the registry is used for recording the information of the online operation nodes and the camera agent nodes of the network.
(2) The operation node comprises a network routing module, an encryption/decryption module, a face recognition module, a face database module, a picture library and a picture chain. The face picture recognition right is competed by adopting a workload certification mechanism, the operation node which obtains the recognition right sends the picture blocks to the system operation node and other operation nodes, the operation nodes are verified and voted, and the system operation node collects the votes and then judges whether the winning operation node is authorized to recognize; when the winning node receives the authorized identification, the winning node is fully responsible for completing the face identification task, wherein the face identification task comprises face feature extraction and face feature comparison, and other operation nodes start a new round of identification right competition; the winning operation node sends the identification result to the system operation node and other operation nodes through the P2P network, the identification result is verified and voted by the nodes, the system operation node collects the votes and then judges whether to award the winning operation node, and once the award is issued, the system operation node and other operation nodes can link the picture block to the local picture chain. The picture blocks demonstrated by the winning operation nodes which do not receive the reward are discarded by each node, and the face pictures contained in the picture blocks are repackaged into new picture blocks to start a new competition. Each operation node is independent and equivalent, and the main work is face recognition operation, so all the operation nodes form an operation resource network.
(3) The camera proxy node contains a network routing module and an encryption/decryption module, which are managed and deployed by the system operator. The function of the system is to receive the face pictures transmitted by the camera group, encrypt the received face pictures and transmit the encrypted face pictures to the operation resource network.
In addition, the camera group consists of cameras deployed at different places, and aims to send face pictures acquired on site to corresponding camera agent nodes, and the face pictures are processed by the agent nodes and then sent to an operation resource network.
As shown in fig. 3, the other nodes except the camera agent node in the entire system maintain a picture library locally, where the face pictures are temporarily stored. And the nodes put the pictures into a warehouse once receiving the face pictures, and the face pictures in the warehouse are associated together according to the time stamp sequence. Before competing for the picture block identification right each time, the operation node extracts a plurality of face pictures from the picture library and packs the face pictures into picture blocks, and then the operation node begins to compete for the identification right. All face pictures included in the picture chain are deleted from the picture library of each node.
As shown in fig. 4, each node in the whole system maintains a picture chain locally. The picture chain is that each picture block realizes the association of the front block and the rear block according to the time stamp sequence and the head hash value of the preorder block, thus realizing the distributed storage of the face picture captured by the camera at each node. The picture block is composed of a picture block header and a picture block body, and the picture block body comprises picture data and a Merkel tree thereof. The data structure of the picture block header mainly comprises: software version number, preorder block hash value, timestamp, difficulty coefficient, random number and picture Merkel tree root; the preamble block hash value is a hash value obtained by performing SHA256 hash calculation on preamble block header data, and the unique invariant characteristic of the hash value is used for realizing the association of the front block and the rear block; the time stamp represents the time generated by the picture block header, so that the picture blocks can be conveniently traced back on the picture chain according to the time sequence; the difficulty coefficient is used for generating difficulty of the picture block, and the operation node is ensured to find a random number meeting the requirement of the difficulty coefficient within a certain time period; the random number represents a changeable numerical value, and the operation node calculates to obtain a block head hash value by changing the value so that the hash value meets the requirement of a difficulty coefficient; the picture Merkel tree root represents that all the face picture data contained in the picture block are related together through a Merkel tree structure, and a hash value is finally obtained through calculation, wherein the hash value is the picture Merkel tree root. The hash calculation in the merkel tree still uses the SHA256 hash function. The picture chain can only be accessed by the system operator node or by a third party authorized thereby.
The functions of each node and its internal modules, and the operation flow of the system are described in detail below with reference to the following drawings.
1. As shown in fig. 5, the network routing module of the system operation node provides a routing function to ensure that the node joins or exits the P2P network, and simultaneously receives and transmits data such as face pictures, picture blocks, registration information, voting results, rewards, and the like, and face recognition software (including a face recognition module and a face database module for downloading and installing by the operation node) discovers and maintains connections with other nodes.
All data received from or sent to the network via the network routing module need to be correspondingly decrypted via the encryption/decryption module, and all data are not open to the non-operator.
The picture library is a memory area for temporarily storing unidentified face pictures received from a network, and once a picture block reaches a node, the identified face pictures contained in the picture library can be deleted from the picture library after block verification and identification result verification; the picture chain stores the identified picture blocks, and the new picture block finds the associated preamble block according to the hash value of the preamble block and is hung behind the preamble block, so that the chained storage is realized.
The registry stores online operation node information and camera agent node information in the whole P2P network, and if a node is added, the node needs to be added into the registry, and if the node exits, the corresponding information is deleted from the registry. The information in the registry is dynamically changed, the registry is stored in a computer hard disk, and once the system operation node is restarted due to failure, the online node information can be directly acquired from the registry stored in the hard disk and is communicated with the registry again.
The face recognition module comprises a face feature extraction component and a face feature comparison component. The face feature extraction is to extract feature data of key regions (such as eyebrows, eyes, nose, mouth, chin, face contour, etc.) of a face, where the feature data reflects local relationships of various parts in the key regions and their mutual relationships, and is also called face feature data. The face feature comparison module searches and matches the extracted feature data of the face image with feature data stored in a database, and determines that the face matching is successful by setting a comparison threshold when the similarity reaches or exceeds the threshold. The face recognition module is one of the core functions of the whole set of system, and is provided for downloading and using by the operation node of the system.
The face database module stores face feature data of important attention people, and the data belongs to high confidentiality. The module is matched with a face recognition module to finish the recognition work of the face picture collected by the camera. The module is downloaded together with the face recognition module through a P2P network for the operation node.
The reward module confirms the legality of the operation node obtaining the picture identification right and then distributes the reward to the winning operation node through the P2P network. The method for confirming the validity adopts a node voting method, and comprises the following steps: the nodes with the face recognition module and the face database module participate in voting, the winning operation node broadcasts the recognition result in the whole network, and the face recognition module verifies the validity after other nodes receive the recognition result. Because the winning node is a go 1: and N comparison, namely identifying one image with the highest similarity from N images of the face database, and comparing the image with the N images, so that time and calculation are consumed, and the verification of other nodes only needs to perform 1: 1, the verification can be completed quickly, the operation node which proves the picture block is voted for approval if the verification is passed, the operation node is voted for disapproval if the verification is not passed, each node with the voting right sends the voting result to the system operation node, and the system operation node maintains the online operation node information in the whole set of system, so that the reward module can count the percentage of the voted for approval to the total voted number. Of course, the system operation node verifies the identification result and counts as a ticket, if the ticket is approved to be more than ninety-five percent, the winning node is deemed to obtain the identification right and the identification result is correct, and the reward module directly issues the reward to the winning node through the P2P network. The node voting method is shown in fig. 6.
The service module is connected to the inside and outside of the system. The user realizes the operation control of the system through the Web page, including the upgrading of each module in the system operation node, the updating of the face characteristic data in the face database, the monitoring of the running state of the whole system and the like, and all of the operations are normally operated through the service module.
The start-up procedure of the system operator node is shown in fig. 7. The face recognition module and the face database module are used as a static data component for downloading and installing the operation node; the picture library is stored in the memory, and the picture chain is stored in the local hard disk. The system operation node firstly starts a service component, because the service component controls the information interaction between the Web interface and other important modules in the node; then the reward module, the encryption/decryption module and the network routing module are sequentially started, so that the system operation node accesses the P2P network, establishes connection with other nodes and maintains the connection, and meanwhile waits for data interaction in the P2P network.
The data interaction between the system operation node and other nodes mainly comprises the following two aspects:
(1) from the system operation node to the P2P network side, one is the face recognition software loading, which includes a face recognition module and a face database module. When the operation node joins the P2P network for the first time or needs to upgrade the face recognition software, the latest face recognition software needs to be loaded from the system operation node through the P2P network. The face recognition software is software formed by packaging a face recognition module and a face database module together by a system operation node, and needs to be encrypted at an operation node before being sent to the operation node, so that on one hand, the face recognition software is prevented from being stolen or interfered in network transmission, and on the other hand, detailed information in a core component is shielded for the operation node, and the flow is shown in fig. 8. The reward data is sent to the operation node obtaining the reward, the reward data belongs to the core confidential data and is encrypted before being sent to the P2P network, the process is shown in FIG. 9, and other processes such as module upgrading information, identification authorization notification and reward notification are sent to relevant nodes in the P2P network through similar processes.
(2) From the P2P network side to the system operation node, the six types of data, mainly face pictures, picture blocks, recognition results, voting information after the operation node verifies the picture blocks and the recognition results, and node online information, are transmitted from the P2P network to the system operation node. The face picture is generated by the camera, encrypted by the camera agent node and sent to the P2P network, and decrypted after received by the system operation node, and then the face picture is put into the local picture library, where the above-mentioned flow is shown in fig. 10. After the picture block and the identification result are transmitted to a system operation node from a network, firstly, the picture block is decrypted, for the picture block, whether the picture block meets the workload certification is judged firstly, a vote is awarded to a winning operation node which proves the picture block after the picture block passes the verification, then the system operation node waits for the voting results of other operation nodes for the picture block, judges whether the winning operation node is authorized to identify according to the results, and informs all operation nodes of the identification authorization notification; and for the identification result, the system operation node sends the face picture corresponding to the identification result into the face identification module and combines the face database module to perform identification work, judges whether the identification result is accurate or not, votes and sends the voting result to the reward module, simultaneously sends the received voting information of other operation nodes into the reward module, determines whether economic reward is given to the winning operation node or not by the reward module, and sends the reward information to all operation nodes. The image blocks for the winning operation node are linked to the local image chain, and the face images contained in the image blocks are deleted from the local image library, and the above-mentioned flow is shown in fig. 11. In a word, after the node with the voting right verifies and votes for the picture block and the identification result, the voting result is encrypted and then sent to the system operation node, and after the system operation node decrypts the voting result, whether the picture block voting result is authorized to be identified or not is judged; for the voting result of the recognition result, the voting result is sent to the reward module, and the reward module counts the number of votes and finally determines whether to issue a reward to the winning operation node, and the process is as shown in fig. 12. The other nodes except the system operation node send registration information to the system operation node when joining the network, send unbinding registration information when exiting the network, and send node keep-alive information at regular time when always in the network to let the other nodes know the connection condition, where the data flow is shown in fig. 13.
2. As shown in fig. 14, the complete operation node includes a network routing module, an encryption/decryption module, a face recognition module, and a face database module, and a memory space and a hard disk space are opened up locally for storing a picture library and a picture chain, respectively.
The working flow of the operation node is shown in fig. 15, a user willing to provide self-computing power for participating in face recognition work for the first time to earn rewards downloads an operation node installation package from an operator through the internet, the installation package comprises a network routing module and an encryption/decryption module, the operation node is started after the user is installed, the network routing module of the operation node helps the operation node to access a P2P network, then the operation node accesses the system operation node through a P2P network according to routing information of the system operation node solidified in the network routing module and registers in the system operation node, after the registration is successful, the operation node starts to download face recognition software consisting of a face recognition module and a face database module and loads the face recognition software into the operation node, and then starts to open up a space for a picture library and a picture chain. So far, the installation of the whole operation node is finished, and the competition of the picture identification right can be started. When the operation node exits from the P2P network, the operation node needs to send unbinding registration information to the system operation node, and the system operation node deletes the operation node information from the registry after receiving the unbinding registration information, so that the system can conveniently maintain the on-line operation node information of the whole network. When the operation node which is not operated for the first time is started again, the operation node only needs to be added into the network through the network routing module, then the operation node registers in the system operation node, and then competition for the picture identification right is started. If the face identification software upgrading information exists, whether the software is upgraded or not is determined by the user.
The operator can also deploy a plurality of self-controlled operation nodes, so that a stably-operating network environment can be constructed, and the face recognition work stagnation caused by the fact that all the operation nodes of the non-operator exit the network is avoided.
The method for competing picture recognition right adopts a workload proving mechanism in a block chain technology. The operation node extracts a plurality of face pictures from a local picture library, then forms a picture block, and simultaneously calculates the hash value of the head of the block by changing the random number in the head of the block to compete for the picture identification right based on the block, thereby judging whether the hash value meets the block difficulty requirement, if so, the picture identification right is obtained, the winning operation node sends the picture block to the system operation node and other operation nodes, the node judges whether the picture block meets the difficulty requirement by adopting the voting method mentioned above, and sends the voting result to the system operation node, the system operation node judges whether the winning node obtains the identification right according to the voting result of each node, once the identification right is obtained, the system operation node authorizes the identification of the winning node, and the winning node starts to identify the face pictures in the picture block if authorized, meanwhile, the system operation node also sends an authorization notification to other operation nodes, and after receiving the notification, the other operation nodes know that one operation node is authorized, so that the operation nodes start a new round of image identification right competition. The operation node which is authorized firstly needs to perform identification work, and if no other node obtains identification authorization after the identification work is completed, the operation node can be added into the round of identification right competition. The above-described flow is shown in fig. 16. After receiving the authorization notice, the operation nodes which do not obtain the accounting right need to mark and temporarily delete the pictures contained in the picture blocks in the picture library, and the pictures are permanently deleted from the picture library only after receiving the reward notice and confirming that the operation nodes finally win.
After receiving the identification authorization, the winning operation node starts to consume the own computing power to operate face identification software to identify the face picture, and after the identification is finished, the identification result is sent to other operation nodes and system operation nodes through a network; and the other nodes verify after receiving the vote, if the vote is approved by verification, the vote is approved and not approved, the voting result is fed back to the system operation node, the reward module of the system operation node determines whether to reward the winning node according to the voting result, the reward condition is notified to the operation node, and the reward module confirms that the winning operation node finally wins, so that the economic reward is directly issued to the winning operation node in a point-to-point manner. Other operation nodes obtain the reward from the winning node, link the picture block and delete the linked picture from the picture library, and the winning node can update the picture chain and the picture library; otherwise, the operation node can know that the verified picture identification result is not approved, and then repackages the pictures contained in the operation node for the next competition of identification right. The above-described flow is shown in fig. 17. The identification result theoretically should include three data of a face picture, a library picture and the similarity between the face picture and the library picture, so that other nodes can conveniently verify, but the face picture and the library picture can cause data transmitted in a network to be redundant, the invention adopts hash values obtained by applying SHA256 hash functions to the face picture and the library picture, the two hash values only have 2 x 256 bits, namely 512 bits, and the similarity value only needs 4 bits to be expressed, so that the identification result is controlled within 516 bits and is far smaller than the data quantity of the whole picture to be transmitted, and the receiving node locally finds corresponding picture data according to the hash values of the two pictures.
3. As shown in fig. 18, the camera proxy node includes a network routing module and an encryption/decryption module, and mainly plays a role in receiving and forwarding a face picture. The node receives the face picture from the camera group, then carries out encryption processing on the face picture inside, and then sends the encrypted picture into the network, and the encryption processing can effectively prevent illegal data from entering the network. After the camera agent node is started, the registration information is sent to the system operation node, the system operation node records the on-line agent node in the registration table of the system operation node, and similarly, the agent node is required to be notified to the system operation node when exiting the network, so that the agent node information is deleted from the registration table.
The camera agent node does not participate in face recognition work, so face recognition software, a picture library and a picture chain do not exist. The camera proxy node is deployed and managed by an operator.
4. As shown in fig. 19, multiple cameras form a camera group, and each camera group corresponds to one camera proxy node. According to the actual environment and the processing capacity, a plurality of camera groups can be divided, and one camera agent node can be connected with one group or a plurality of groups. The camera group is a data source, does not access the P2P network, and does not participate in face recognition work.
5. The working steps of the face recognition platform constructed based on the face data distributed recognition architecture designed by the invention are as follows.
(1) The operator first deploys the cameras to make up a camera group.
(2) And the operator deploys a system operation node, a self-controlled operation node and a camera agent node. The three nodes are started up so that they form a stable P2P network.
(3) The user-controlled operation node downloads an operation node installation package from an operator through the Internet, and the operation node installation package is accessed to a P2P network after installation; and then registering the system operation node, and downloading the face recognition software from the system operation node after the registration is successful.
Therefore, the distributed face recognition platform is successfully built.
(4) And sending the face pictures captured by the camera group to the camera proxy node, and sending the face pictures to the P2P network after the face pictures are encrypted by the camera proxy node.
(5) Firstly, sending a face picture to a node adjacent to a camera proxy node; if the adjacent node is the camera agent node, the node forwards the face picture to the adjacent node; if the adjacent node is a system operation node or a calculation node, the face picture is stored in a local picture library and is simultaneously forwarded to the adjacent node. And the face pictures are stored in the local picture library according to the sequence of the time stamps.
(6) The operation node extracts a plurality of face pictures from a local picture library and constructs a picture block header based on hash values of the face pictures; then changing the random number in the picture block head, calculating whether the hash value of the picture block head meets the difficulty requirement or not, obtaining the picture identification right by the operation node until a random number is found out to enable the hash value of the picture block head to meet the difficulty requirement, sending the picture block to other operation nodes and system operation nodes by the node through a P2P network, verifying whether the picture block meets the difficulty requirement or not by the nodes, voting, and sending the voting result to the system operation node; and the system operation node judges whether the winning node really obtains the picture identification right according to the voting results and informs each operation node of the identification right.
(7) The winning operation node is authorized by the system operation node to perform face recognition on the face picture; and other operation nodes are authorized to inform that the operation nodes fail to compete for the identification right, new face pictures are extracted from the picture library again to establish new picture blocks, and a new round of identification right competition is started.
(8) After the face recognition work of the winning operation node is finished, the recognition result is sent to a system operation node and other operation nodes, whether the recognition result is correct or not is verified by the nodes, meanwhile, the verification result is voted, and the voted result is sent to the system operation node; the reward module of the system operation node determines whether to distribute rewards to winning operation nodes or not according to the voting result and informs each operation node of the reward result; if the winning operation node obtains the reward, all operation nodes including the winning node and the system operation node can hang the picture block to a local picture chain, and simultaneously, the face picture contained in the picture block is deleted from the picture library. If the winning operation node does not obtain the reward, the image block which is proved by the winning operation node is not approved, the system operation node and other operation nodes do not hang the image block to the local image chain, and meanwhile, the other operation nodes repackage the face image contained in the image block into a new image block for the next round of identification right competition.
(9) And the winning node joins the identification right competition of the current round after receiving the reward.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims (5)
1. A human face data distributed recognition and storage architecture based on a block chain technology is characterized by comprising a system operation node, an operation node, a camera agent node and a camera group, wherein:
the system operation node comprises a face recognition module, a face database module, an encryption/decryption module, a service module, a network routing module, a reward module, a picture library, a picture chain and a registry;
the operation node comprises a network routing module, an encryption/decryption module, a face recognition module, a face database module, a picture library and a picture chain;
the camera proxy node comprises a network routing module and an encryption/decryption module;
the camera group is composed of cameras deployed at different locations.
2. The architecture of claim 1, wherein the face recognition module comprises a face data processing component for performing two functions of face feature extraction and face feature comparison; the face database module is responsible for storing face feature data; the encryption/decryption module is responsible for encrypting and decrypting data propagated in the P2P network; the service module is responsible for managing the face feature data and the face data processing component, monitoring the running state of the whole network and the reward issuing condition; the network routing module ensures that the nodes join or quit the P2P network, and simultaneously receives and transmits data such as face pictures, picture blocks, registration information, voting results, rewards and the like, and face recognition software to discover and maintain the connection with other nodes; the reward module counts the voting results and sends economic rewards to the operation nodes which provide the computing power to complete the identification task; the picture library is used for temporarily storing the unrecognized face pictures propagated in the P2P network, and once the picture blocks reach the nodes, the identified face pictures contained in the picture blocks are deleted from the picture library after block verification and recognition result verification; the picture chain is used for storing the picture blocks which are identified and verified; the registry is used for recording the information of the online operation nodes and the camera agent nodes of the network.
3. The distributed face data identification and storage architecture based on the blockchain technology as claimed in claim 2, wherein the reward module counts the voting results and determines the validity of the winning operation node, and a node voting method is adopted, wherein the method comprises: the node with the face recognition module and the face database module participates in voting, the winning operation node broadcasts the recognition result in the whole network, the other nodes are validated by the face recognition module after receiving the recognition result, the validation is passed, the operation node which proves the picture block is voted for, the operation node is voted for without validation, each node with the voting right sends the voting result to the reward module of the system operation node, the reward module can count the percentage of the voted for votes in the total votes, if the voted for votes exceeds ninety-five percent, the winning node is considered to obtain the recognition right and the recognition result is correct, and the reward module directly sends the reward to the winning node through the P2P network; the node voting method is also adopted for verifying the validity of the picture blocks.
4. The distributed face data identification and storage architecture based on the blockchain technology of claim 3, wherein the validation of the identification result means that three data, namely the face picture, the library picture and the similarity between the face picture and the library picture, are sent to other nodes through a P2P network for validation, the face identification module calculates the similarity between the face picture and the library picture, and then judges whether the similarity is consistent with the original similarity; the invention adopts Hash values obtained by applying SHA256 Hash function to the face picture and the library picture, wherein the two Hash values only have 2 x 256 bits, namely 512 bits, and the similarity value only needs 4 bits to be represented, so that the identification result is controlled within 516 bits and is far smaller than the data quantity of the whole picture, and a receiving node finds corresponding picture data locally according to the Hash values of the two pictures.
5. The distributed face data identification and storage architecture based on the blockchain technology of claim 1, wherein the working steps of the whole platform are as follows:
step 1, an operator firstly deploys cameras to form a camera group;
step 2, an operator deploys a system operation node, a self-controlled operation node and a camera agent node; starting the three nodes to form a stable P2P network;
step 3, downloading an operation node installation package from an operator by the operation node controlled by the user through the Internet, and accessing the operation node installation package to a P2P network after the operation node installation is finished; then registering to a system operation node, and downloading face recognition software from the system operation node after successful registration; so far, successfully building a distributed face recognition platform;
step 4, sending the face pictures captured by the camera group to a camera proxy node, encrypting the face pictures by the camera proxy node, and sending the face pictures to a P2P network;
step 5, the face picture is firstly sent to a node adjacent to the camera agent node; if the adjacent node is the camera agent node, the node forwards the face picture to the adjacent node; if the adjacent node is a system operation node or a calculation node, the face picture is stored in a local picture library and is simultaneously forwarded to the adjacent node; the face pictures are stored in a local picture library according to the sequence of the time stamps;
step 6, extracting a plurality of face pictures from a local picture library by the operation node to construct picture blocks, competing for picture identification rights based on the picture blocks constructed by the operation node, sending the picture blocks to other operation nodes and system operation nodes by the winning operation node through a P2P network, verifying whether the picture blocks meet requirements and voting by the nodes, and sending voting results to the system operation node; the system operation node judges whether the winning node really obtains the picture identification right according to the voting results and informs each operation node of the identification right;
step 7, the winning operation node is authorized by the system operation node to start face recognition on the face picture; other operation nodes are authorized to inform that the operation nodes fail to compete for the identification right, new face pictures are extracted from the picture library again to establish new picture blocks, and a new round of identification right competition is started;
step 8, after the face recognition work of the winning operation node is finished, sending the recognition result to a system operation node and other operation nodes, verifying whether the recognition result is correct by the nodes, voting the verification result and sending the voting result to the system operation node; the reward module of the system operation node determines whether to distribute rewards to winning operation nodes or not according to the voting result and informs each operation node of the reward result; if the winning operation node obtains the reward, all operation nodes including the winning node and the system operation node can hang the picture block to a local picture chain, and simultaneously, the face picture contained in the picture block is deleted from the picture library; if the winning operation node does not obtain the reward, the image block which is proved by the winning operation node is not approved, the system operation node and other operation nodes do not hang the image block to the local image chain, and meanwhile, other operation nodes repackage the face image contained in the image block into a new image block for the next round of identification right competition;
and 9, adding the identification right competition of the current round again after the winning node receives the reward.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010049817.3A CN111291628B (en) | 2020-01-17 | 2020-01-17 | Face data distributed identification and storage architecture based on block chain technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010049817.3A CN111291628B (en) | 2020-01-17 | 2020-01-17 | Face data distributed identification and storage architecture based on block chain technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291628A true CN111291628A (en) | 2020-06-16 |
| CN111291628B CN111291628B (en) | 2024-02-06 |
Family
ID=71023406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010049817.3A Active CN111291628B (en) | 2020-01-17 | 2020-01-17 | Face data distributed identification and storage architecture based on block chain technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291628B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112055067A (en) * | 2020-08-28 | 2020-12-08 | 杭州复杂美科技有限公司 | Node connection method, device and storage medium |
| CN112241684A (en) * | 2020-09-16 | 2021-01-19 | 四川天翼网络服务有限公司 | Face retrieval distributed computing method and system |
| CN113408421A (en) * | 2021-06-21 | 2021-09-17 | 湖北央中巨石信息技术有限公司 | Face recognition method and system based on block chain |
| CN117914871A (en) * | 2024-03-15 | 2024-04-19 | 海南中南标质量科学研究院有限公司 | Automatic block chain monitoring equipment for sea sewage outlet |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570087A (en) * | 2016-10-20 | 2017-04-19 | 中国电子科技集团公司第二十八研究所 | Distributed face recognition system |
| CN108509274A (en) * | 2018-03-28 | 2018-09-07 | 厦门益东智能科技有限公司 | A kind of method and system based on block chain data automatic marking and intellectual analysis |
| CN109146484A (en) * | 2018-08-31 | 2019-01-04 | 深圳付贝科技有限公司 | Common recognition verification method, digging mine machine and block catenary system based on block chain |
| CN109241111A (en) * | 2018-08-27 | 2019-01-18 | 武汉虹信技术服务有限责任公司 | A kind of distributed face identification system and method for database based on memory |
| CN109800691A (en) * | 2019-01-07 | 2019-05-24 | 深圳英飞拓科技股份有限公司 | Demographics method and system based on face recognition technology |
| CN109872152A (en) * | 2019-01-11 | 2019-06-11 | 平安科技（深圳）有限公司 | Block chain common recognition method and relevant device based on share authorisation verification mechanism |
| CN110138861A (en) * | 2019-05-15 | 2019-08-16 | 北京中星微人工智能芯片技术有限公司 | A kind of security protection Intelligentized method and device |
-
2020
- 2020-01-17 CN CN202010049817.3A patent/CN111291628B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570087A (en) * | 2016-10-20 | 2017-04-19 | 中国电子科技集团公司第二十八研究所 | Distributed face recognition system |
| CN108509274A (en) * | 2018-03-28 | 2018-09-07 | 厦门益东智能科技有限公司 | A kind of method and system based on block chain data automatic marking and intellectual analysis |
| CN109241111A (en) * | 2018-08-27 | 2019-01-18 | 武汉虹信技术服务有限责任公司 | A kind of distributed face identification system and method for database based on memory |
| CN109146484A (en) * | 2018-08-31 | 2019-01-04 | 深圳付贝科技有限公司 | Common recognition verification method, digging mine machine and block catenary system based on block chain |
| CN109800691A (en) * | 2019-01-07 | 2019-05-24 | 深圳英飞拓科技股份有限公司 | Demographics method and system based on face recognition technology |
| CN109872152A (en) * | 2019-01-11 | 2019-06-11 | 平安科技（深圳）有限公司 | Block chain common recognition method and relevant device based on share authorisation verification mechanism |
| CN110138861A (en) * | 2019-05-15 | 2019-08-16 | 北京中星微人工智能芯片技术有限公司 | A kind of security protection Intelligentized method and device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112055067A (en) * | 2020-08-28 | 2020-12-08 | 杭州复杂美科技有限公司 | Node connection method, device and storage medium |
| CN112055067B (en) * | 2020-08-28 | 2023-04-18 | 杭州复杂美科技有限公司 | Node connection method, device and storage medium |
| CN112241684A (en) * | 2020-09-16 | 2021-01-19 | 四川天翼网络服务有限公司 | Face retrieval distributed computing method and system |
| CN113408421A (en) * | 2021-06-21 | 2021-09-17 | 湖北央中巨石信息技术有限公司 | Face recognition method and system based on block chain |
| CN117914871A (en) * | 2024-03-15 | 2024-04-19 | 海南中南标质量科学研究院有限公司 | Automatic block chain monitoring equipment for sea sewage outlet |
| CN117914871B (en) * | 2024-03-15 | 2024-05-24 | 海南中南标质量科学研究院有限公司 | Automatic block chain monitoring equipment for sea sewage outlet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291628B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111291628B (en) | Face data distributed identification and storage architecture based on block chain technology | |
| Ramachandran et al. | Using blockchain and smart contracts for secure data provenance management | |
| US20180218454A1 (en) | Managing participation in a monitored system using blockchain technology | |
| CN108964926B (en) | User trust negotiation establishing method, user behavior data storage method and medium | |
| KR102002509B1 (en) | Privite blockchain system including notarizing center and notarial method thereof | |
| WO2019105189A1 (en) | Model training system and method, and storage medium | |
| CN115210741B (en) | Partially ordered blockchain | |
| WO2019010067A1 (en) | Blockchain proof of custody, proof against tampering, proof of chain of custody | |
| CN107528688A (en) | A kind of keeping of block chain key and restoration methods, device based on encryption commission technology | |
| CN114128214B (en) | Security layer for configuring blockchains | |
| CN110602217B (en) | Block chain-based alliance management method, device, equipment and storage medium | |
| EP4216077A1 (en) | Blockchain network-based method and apparatus for data processing, and computer device | |
| CN111415163A (en) | Service processing and verifying method, system and verifying node based on block chain | |
| JP2006506749A (en) | Method and apparatus for protection processing of confidential data | |
| US20220012358A1 (en) | Techniques for preventing collusion using simultaneous key release | |
| CN111291394B (en) | False information management method, false information management device and storage medium | |
| CN101496019A (en) | File system authentication | |
| CN111416709B (en) | Voting method, device, equipment and storage medium based on block chain system | |
| CN116527372B (en) | Internet-based data security interaction system and method | |
| US20180218364A1 (en) | Managing distributed content using layered permissions | |
| CN107465728A (en) | Information processing method, central server and storage medium on identification code | |
| WO2019178440A1 (en) | System and method for securing private keys behind a biometric authentication gateway | |
| CN114861211A (en) | Meta-universe scene-oriented data privacy protection method, system and storage medium | |
| CN112307440B (en) | Method for protecting online education and teaching video property by using blockchain technology | |
| Zhang et al. | Aegis: a trusted, automatic and accurate verification framework for vertical federated learning |
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 |