CN113378149B - Artificial intelligence-based two-way mobile communication identity verification method and system - Google Patents

Artificial intelligence-based two-way mobile communication identity verification method and system Download PDF

Info

Publication number
CN113378149B
CN113378149B CN202110649413.2A CN202110649413A CN113378149B CN 113378149 B CN113378149 B CN 113378149B CN 202110649413 A CN202110649413 A CN 202110649413A CN 113378149 B CN113378149 B CN 113378149B
Authority
CN
China
Prior art keywords
encoder
neuron
mobile communication
information
code
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110649413.2A
Other languages
Chinese (zh)
Other versions
CN113378149A (en
Inventor
李一方
汪文杰
黄贤青
张强强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Marine Science And Technology Center
Original Assignee
Qingdao National Laboratory for Marine Science and Technology Development Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao National Laboratory for Marine Science and Technology Development Center filed Critical Qingdao National Laboratory for Marine Science and Technology Development Center
Priority to CN202110649413.2A priority Critical patent/CN113378149B/en
Publication of CN113378149A publication Critical patent/CN113378149A/en
Application granted granted Critical
Publication of CN113378149B publication Critical patent/CN113378149B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/44—Program or device authentication
    • G06F21/445—Program or device authentication by mutual authentication, e.g. between devices or programs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/602—Providing cryptographic facilities or services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computer Security & Cryptography (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Bioethics (AREA)
  • Neurology (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention provides a bidirectional mobile communication identity authentication method and system based on artificial intelligence. The method comprises the following steps: processing the verification information by using an encryption model at a first mobile communication device to obtain first activated neuron information and an initial ciphertext, and sending the first activated neuron output data and the initial ciphertext to a second mobile communication device; obtaining a second activated neuron by using the decryption model and coding the second activated neuron to generate a second code in the second mobile communication equipment, and if the output information of the second activated neuron is consistent with the output information of the first activated neuron, passing the identity authentication and sending the second code to the first mobile communication equipment; if the first code is the same as the second code, the bidirectional identity authentication is passed. The invention is used for bidirectional identity authentication, improves the authentication efficiency and enhances the authentication safety.

Description

Bidirectional mobile communication identity verification method and system based on artificial intelligence
Technical Field
The application relates to the field of identity authentication and artificial intelligence, in particular to a bidirectional mobile communication identity authentication method based on artificial intelligence.
Background
The identity authentication means that the identity of a user is confirmed by a certain means. The method of identity verification can be basically divided into: shared key based authentication, biometric feature based authentication, and public key encryption algorithm based authentication. The existing identity authentication method needs to store a large amount of key information and characteristic information, and the data security is low in the identity authentication process.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a bidirectional mobile communication authentication method based on artificial intelligence, which adopts the following technical scheme:
in a first mobile communication device, a first encoder is used for encrypting verification information to obtain an initial ciphertext, a first decoder is used for decrypting to obtain decryption verification information, a second encoder is used for encrypting the decryption verification information, an activation neuron is selected from the second encoder to obtain a first activation neuron, a first code is generated according to the first activation neuron, and output data of the first activation neuron and the initial ciphertext are sent to a second mobile communication device;
at a second mobile communication device, decrypting an initial ciphertext received from the first mobile communication device by using a second decoder, encrypting the output of the second decoder by using a third encoder, obtaining activated neuron information from the third encoder, comparing the activated neuron information of the third encoder with the first activated neuron information, performing identity verification on the first mobile communication device, if the identity verification is passed, generating a second code according to the activated neuron information of the third encoder, and sending the second code to the second mobile communication device;
and if the first code is the same as the second code, the second mobile communication equipment passes the authentication.
Preferably, comparing the third encoder-activated neuron information with the first activated neuron information, the authenticating the first mobile communication device comprises: and if the output data of each first activated neuron belongs to the output data set of the third encoder, the first mobile communication equipment passes the identity verification.
Preferably, generating the second code according to the third encoder activation neuron information includes: a third encoder activates the neuron, which is identical in output data to the first activated neuron, to a second activated neuron, and generates a second code from the second activated neuron.
Preferably, the first encoder and the first decoder form a self-coding network structure, and the structures and weight parameters of the first encoder, the second encoder and the third encoder are the same; the first decoder and the second decoder have the same structure and weight parameters.
Preferably, the first encoder and the second encoder are implemented by the same encoder structure.
Preferably, generating the first code from the first activated neuron comprises: generating a first code based on the identity of the first activated neuron; the generating a second code from a second activated neuron comprises: a second code is generated based on the identification of the second activated neuron.
The invention also provides a bidirectional mobile communication identity verification system based on artificial intelligence, which comprises:
the first mobile communication equipment is used for encrypting the verification information by using a first encoder to obtain an initial ciphertext, decrypting the decryption verification information by using a first decoder, encrypting the decryption verification information by using a second encoder, selecting an activation neuron from the second encoder to obtain a first activation neuron, generating a first code according to the first activation neuron, sending the output data of the first activation neuron and the initial ciphertext to the second mobile communication equipment, verifying whether the first code is the same as the second code or not, and if so, passing the identity verification of the second mobile communication equipment;
and the second mobile communication equipment is used for decrypting the initial ciphertext received from the first mobile communication equipment by using the second decoder, encrypting the output of the second decoder by using the third encoder, obtaining the information of the activated neuron from the third encoder, comparing the information of the activated neuron of the third encoder with the information of the first activated neuron, carrying out identity verification on the first mobile communication equipment, if the identity verification is passed, generating a second code according to the information of the activated neuron of the third encoder, and sending the second code to the second mobile communication equipment.
The technical scheme of the invention has the following beneficial effects:
the invention carries out bidirectional identity authentication according to the activation neuron information in the encryption process, and the sending end and the receiving end do not need to store key information or characteristic information, thereby reducing the complexity of the system, ensuring safer data transmission and higher identity authentication efficiency.
Drawings
FIG. 1 is a method flow diagram.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
The first embodiment is as follows:
the embodiment provides an artificial intelligence-based two-way mobile communication identity authentication method, and the flow of the method is shown in fig. 1.
In the first mobile communication equipment, a first encoder is used for encrypting verification information to obtain an initial ciphertext, a first decoder is used for decrypting to obtain decryption verification information, a second encoder is used for encrypting the decryption verification information, an activation neuron is selected from the second encoder to obtain a first activation neuron, a first code is generated according to the first activation neuron, and output data of the first activation neuron and the initial ciphertext are sent to second mobile communication equipment.
The invention carries out data encryption and decryption recovery by a deep learning neural network mode, and the structure of the network uses a common self-coding network structure.
The self-coding network is a network for training input data as label data at the same time, namely the network achieves the effect that the input data obtains a hidden code through an encoder, the hidden code can output the data through a decoder, and the output data needs to be consistent with the input data.
After the training of the self-coding network is completed, the encoder and the decoder are in one-to-one correspondence with each other. That is, there may be a plurality of encoders E1, E2, E3, … at the transmitting end, and a plurality of decoders D1, D2, D3 at the corresponding receiving end for receiving messages transmitted by different transmitting ends.
The hidden code information obtained by the encoder is information with the same dimensionality, the first encoder and the first decoder form a self-coding network structure, and the structures and weight parameters of the first encoder, the second encoder and the third encoder are the same; the first decoder and the second decoder have the same structure and weight parameters. The hidden code information can be decoded by different decoders to obtain different information, but only the encoder and the decoder which correspond to each other can finish the correct encrypted transmission of data.
The first mobile communication equipment processes the verification information to obtain encrypted transmission information:
1) and randomly generating verification information M, and reasoning by using the verification information M as input through a first encoder to obtain an initial cryptograph, namely a cryptograph Z, wherein the dimensionality of the cryptograph in the embodiment of the invention is 3-dimensional, and the cryptograph can be changed and set according to the requirements in a specific actual scene.
2) And (4) reasoning to obtain decryption verification information-recovery data C from the hidden code Z by using a first decoder.
3) The recovered data C is encrypted using a second encoder to obtain the covert code Z'. Because the neural network has a certain reconstruction error, that is, the recovered data C has an error with the original data M in a large probability, secondary encoding is required.
In the process of encrypting the recovered data C by using the second encoder, part of neurons in the second encoder are activated and part of neurons are not activated. The neurons in the second encoder are sequentially assigned IDs from top to bottom. And selecting the activated neurons from the second encoder to obtain first activated neurons, and forming activated neuron coding information, namely a first code G, by the IDs of the first activated neurons.
The output data h corresponding to all the first activated neurons constitute activated output data J.
For example: if the IDs of the activated neurons of the first layer in the second encoder are 1, 3 and 4, the IDs of the activated neurons of the second layer are 3, 5 and 7, and the IDs of the activated neurons of the third layer are 1, 4 and 7. The number of the activated neurons is 9, and the activated neurons are randomly selected to obtain the first activated neuron. A first code is generated based on the ID of the first activated neuron.
The outputs of the first layer of activated neurons are: h is1,1,h1,3,h1,4The outputs of the second layer of activated neurons are: h is2,3,h2,5,h2,7The outputs of the third layer of activated neurons are: h is3,1,h1,4,h1,7. The output data of the first activated neurons are combined to obtain activation information J.
It should be noted that the first encoder and the second encoder may use the same encoder structure, that is, the same encoder is used to implement, and the activation information J may be generated according to the identification of the activated neuron of the encoder during the secondary encoding and the output data.
4) And combining the cryptograph data Z and the activation information J to form cryptograph information S corresponding to the verification information M. Since the activation information J is changeable, it may have different contents. Therefore, there can be a plurality of representations for the authentication information M, enabling different encryption information representations of the same data.
Thus, ciphertext information S is obtained and sent to the second mobile device.
And at the second mobile communication equipment, decrypting the initial ciphertext received from the first mobile communication equipment by using a second decoder, encrypting the output of the second decoder by using a third encoder, obtaining the activated neuron information from the third encoder, comparing the activated neuron information of the third encoder with the first activated neuron information, carrying out identity verification on the first mobile communication equipment, if the identity verification is passed, generating a second code according to the activated neuron information of the third encoder, and sending the second code to the first mobile communication equipment.
And after receiving the ciphertext information S, the second mobile communication device splits the first 3 dimensions of the ciphertext information S into the cryptograph data Z and the rest is the activation information J according to the dimensions of the data.
And then, decrypting the split hidden code data Z by using a second decoder to obtain recovered data C.
And then, reasoning by using a third encoder, and taking the data C as input to obtain the crypto data Z' obtained by new reasoning. And acquiring corresponding activated neuron identification and output data h 'of the activated neuron according to the state of neuron activation when the third encoder infers the hidden code Z'.
The activation information J obtained by splitting the ciphertext data comprises a plurality of first activation neuron output data h; and if the output data h of each first activated neuron belongs to the set formed by h ', the first mobile communication equipment passes the identity verification, a third encoder which has the same output data as the first activated neuron activates the neuron to be a second activated neuron, generates a second code according to the second activated neuron and sends the second code G' to the first mobile communication equipment.
And at the first mobile communication equipment, comparing and judging the received second code G' with the first code G, and if the information is consistent, passing the authentication of the second mobile communication equipment.
The data transmitted between networks in the invention is as follows:
1) first mobile communication device to second mobile communication device: ciphertext data S comprising a hidden code Z and activation information J;
2) the second mobile communication device to the first mobile communication device: a second code G';
the two data are different, but represent the same verification data, so the encryption level is higher, and the data are difficult to be intercepted and then cracked by using a training mode.
Example two:
a bidirectional mobile communication identity verification system based on artificial intelligence comprises:
the first mobile communication equipment is used for encrypting the verification information by using a first encoder to obtain an initial ciphertext, decrypting the decryption verification information by using a first decoder, encrypting the decryption verification information by using a second encoder, selecting an activation neuron from the second encoder to obtain a first activation neuron, generating a first code according to the first activation neuron, transmitting the output data of the first activation neuron and the initial ciphertext to the second mobile communication equipment, verifying whether the first code is the same as the second code or not, and if so, passing the identity verification of the second mobile communication equipment;
and the second mobile communication equipment is used for decrypting the initial ciphertext received from the first mobile communication equipment by using the second decoder, encrypting the output of the second decoder by using the third encoder, obtaining the information of the activated neuron from the third encoder, comparing the information of the activated neuron of the third encoder with the information of the first activated neuron, carrying out identity verification on the first mobile communication equipment, if the identity verification is passed, generating a second code according to the information of the activated neuron of the third encoder, and sending the second code to the second mobile communication equipment.
The above embodiments are merely preferred embodiments of the present invention, which should not be construed as limiting the present invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (6)

1. A bidirectional mobile communication identity authentication method based on artificial intelligence is characterized by comprising the following steps:
in the first mobile communication equipment, a first encoder is used for encrypting verification information to obtain an initial ciphertext, a first decoder is used for decrypting the verification information to obtain decryption verification information, a second encoder is used for encrypting the decryption verification information, an activation neuron is selected from the second encoder to obtain a first activation neuron, a first code is generated according to the first activation neuron, and output data of the first activation neuron and the initial ciphertext are sent to second mobile communication equipment;
at a second mobile communication device, decrypting an initial ciphertext received from the first mobile communication device by using a second decoder, encrypting the output of the second decoder by using a third encoder, obtaining activated neuron information from the third encoder, comparing the activated neuron information of the third encoder with the first activated neuron information, performing identity verification on the first mobile communication device, if the identity verification is passed, generating a second code according to the activated neuron information of the third encoder, and sending the second code to the first mobile communication device;
the comparing the third encoder activated neuron information with the first activated neuron information, and the authenticating the first mobile communication device includes: if the output data of each first activation neuron belongs to the output data set of the third encoder, the first mobile communication equipment passes the identity verification;
if the first code is the same as the second code, the second mobile communication equipment passes the identity verification;
the first encoder and the first decoder form a self-encoding network structure, and the structures and the weight parameters of the first encoder, the second encoder and the third encoder are the same; the first decoder and the second decoder have the same structure and weight parameters.
2. The method of claim 1, wherein generating the second encoding from the third encoder-activated neuron information comprises: a third encoder, having the same output data as the first, activates the neuron as a second activated neuron, generating a second encoding from the second activated neuron.
3. The method of claim 1, wherein the first encoder and the second encoder are implemented by the same encoder structure.
4. The method of claim 1, wherein generating the first code from the first active neuron comprises: generating a first code based on the identity of the first activated neuron; the generating a second code from a second activated neuron comprises: a second code is generated based on the identification of the second activated neuron.
5. A bidirectional mobile communication identity authentication system based on artificial intelligence is characterized by comprising:
the first mobile communication equipment is used for encrypting the verification information by using a first encoder to obtain an initial ciphertext, decrypting the decryption verification information by using a first decoder, encrypting the decryption verification information by using a second encoder, selecting an activation neuron from the second encoder to obtain a first activation neuron, generating a first code according to the first activation neuron, sending the output data of the first activation neuron and the initial ciphertext to the second mobile communication equipment, verifying whether the first code is the same as the second code or not, and if so, passing the identity verification of the second mobile communication equipment;
the second mobile communication equipment is used for decrypting the initial ciphertext received from the first mobile communication equipment by using the second decoder, encrypting the output of the second decoder by using the third encoder, obtaining the information of the activated neuron from the third encoder, comparing the information of the activated neuron of the third encoder with the information of the first activated neuron, carrying out identity verification on the first mobile communication equipment, if the identity verification is passed, generating a second code according to the information of the activated neuron of the third encoder, and sending the second code to the second mobile communication equipment; the comparing the third encoder activated neuron information with the first activated neuron information, and the authenticating the first mobile communication device includes: if the output data of each first activation neuron belongs to the output data set of the third encoder, the first mobile communication equipment passes the identity verification;
the first encoder and the first decoder form a self-encoding network structure, and the structures and the weight parameters of the first encoder, the second encoder and the third encoder are the same; the first decoder and the second decoder have the same structure and weight parameters.
6. The system of claim 5, wherein generating the second encoding from the third encoder-activated neuron information comprises: a third encoder activates the neuron, which is identical in output data to the first activated neuron, to a second activated neuron, and generates a second code from the second activated neuron.
CN202110649413.2A 2021-06-10 2021-06-10 Artificial intelligence-based two-way mobile communication identity verification method and system Active CN113378149B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110649413.2A CN113378149B (en) 2021-06-10 2021-06-10 Artificial intelligence-based two-way mobile communication identity verification method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110649413.2A CN113378149B (en) 2021-06-10 2021-06-10 Artificial intelligence-based two-way mobile communication identity verification method and system

Publications (2)

Publication Number Publication Date
CN113378149A CN113378149A (en) 2021-09-10
CN113378149B true CN113378149B (en) 2022-06-03

Family

ID=77573764

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110649413.2A Active CN113378149B (en) 2021-06-10 2021-06-10 Artificial intelligence-based two-way mobile communication identity verification method and system

Country Status (1)

Country Link
CN (1) CN113378149B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107301864A (en) * 2017-08-16 2017-10-27 重庆邮电大学 A kind of two-way LSTM acoustic models of depth based on Maxout neurons
CN108345934A (en) * 2018-01-16 2018-07-31 中国科学院计算技术研究所 A kind of activation device and method for neural network processor
CN111663294A (en) * 2019-03-08 2020-09-15 Lg电子株式会社 Artificial intelligence device and action method thereof
CN112329908A (en) * 2021-01-04 2021-02-05 中国人民解放军国防科技大学 Image generation method for neural network model test

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107301864A (en) * 2017-08-16 2017-10-27 重庆邮电大学 A kind of two-way LSTM acoustic models of depth based on Maxout neurons
CN108345934A (en) * 2018-01-16 2018-07-31 中国科学院计算技术研究所 A kind of activation device and method for neural network processor
CN111663294A (en) * 2019-03-08 2020-09-15 Lg电子株式会社 Artificial intelligence device and action method thereof
CN112329908A (en) * 2021-01-04 2021-02-05 中国人民解放军国防科技大学 Image generation method for neural network model test

Also Published As

Publication number Publication date
CN113378149A (en) 2021-09-10

Similar Documents

Publication Publication Date Title
CN109818739B (en) Generation type image steganography method based on countermeasure network
CN111510281B (en) Homomorphic encryption method and device
CN109146524A (en) A kind of agricultural product using block chain technology are traced to the source information security solution
CN114219483B (en) Method, equipment and storage medium for sharing block chain data based on LWE-CPBE
CN109640095B (en) Video encryption system combined with quantum key distribution
Beigi et al. Quantum achievability proof via collision relative entropy
CN110213060A (en) A kind of quantum Proxy Signature method and system that the nothing based on quantum walking is tangled
CN116471007A (en) Network information encryption transmission method based on cloud platform
CN110838907A (en) Commodity anti-counterfeiting code generation system based on block chain
CN102594551A (en) Method for reliable statistics of privacy data on radio frequency identification (RFID) tag
CN104598801B (en) A kind of Dynamic Two-dimensional code generating method based on algorithm reconstruct
CN113489591A (en) Traceable comparison attribute encryption method based on multiple authorization centers
WO2023133907A1 (en) Privacy protection biometric authentication method and apparatus, and electronic device
CN113378149B (en) Artificial intelligence-based two-way mobile communication identity verification method and system
CN111698252B (en) Cloud platform data encryption transmission method and system
CN117640069A (en) Multi-party block chain hidden communication generation model based on Markov chain
CN107507254A (en) Compression of images encryption method based on arithmetic coding
CN108011714B (en) Method and system for protecting data object body identification based on cryptology operation
CN109412754A (en) A kind of data storage, distribution and access method encoding cloud
Zhou et al. A survey of security aggregation
CN202023428U (en) Wireless encryption remote control system for automobile door lock
CN109905241A (en) A kind of short encoding of chinese characters of curve public key, coding/decoding method
Xin et al. Quantum authentication of classical messages without entangled state as authentication key
CN115296879B (en) Encryption authentication method and system for microservice
CN112583823B (en) Encoding encryption and decoding decryption processing method

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
CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: No. 168, Wenhai Middle Road, Jimo District, Qingdao City, Shandong Province 266200

Patentee after: Qingdao Marine Science and Technology Center

Address before: No. 168, Wenhai Middle Road, Jimo District, Qingdao City, Shandong Province 266200

Patentee before: QINGDAO NATIONAL LABORATORY FOR MARINE SCIENCE AND TECHNOLOGY DEVELOPMENT CENTER

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210910

Assignee: Qingdao Litu Marine Equipment Technology Co.,Ltd.

Assignor: Qingdao Marine Science and Technology Center

Contract record no.: X2023980044213

Denomination of invention: A bidirectional mobile communication identity verification method and system based on artificial intelligence

Granted publication date: 20220603

License type: Common License

Record date: 20231024