CN112000938A - Power grid dispatching identity authentication method and system based on multimode identification - Google Patents

Power grid dispatching identity authentication method and system based on multimode identification Download PDF

Info

Publication number
CN112000938A
CN112000938A CN202010681725.7A CN202010681725A CN112000938A CN 112000938 A CN112000938 A CN 112000938A CN 202010681725 A CN202010681725 A CN 202010681725A CN 112000938 A CN112000938 A CN 112000938A
Authority
CN
China
Prior art keywords
client
authentication
dispatcher
voiceprint
server
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
Application number
CN202010681725.7A
Other languages
Chinese (zh)
Other versions
CN112000938B (en
Inventor
翟启
翟洪婷
张庆锐
田兵
李冬
孙丽丽
杨坤
李亮
王敏
毛恒
张茜
张化代
李青
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.)
State Grid Corp of China SGCC
Information and Telecommunication Branch of State Grid Shandong Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Information and Telecommunication Branch of State Grid Shandong Electric Power Co Ltd
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 State Grid Corp of China SGCC, Information and Telecommunication Branch of State Grid Shandong Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202010681725.7A priority Critical patent/CN112000938B/en
Publication of CN112000938A publication Critical patent/CN112000938A/en
Application granted granted Critical
Publication of CN112000938B publication Critical patent/CN112000938B/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
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • 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
    • H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
    • 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
    • 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
    • H04L67/14—Session management
    • H04L67/141—Setup of application sessions
    • 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
    • H04L67/14—Session management
    • H04L67/143—Termination or inactivation of sessions, e.g. event-controlled end of session
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Signal Processing (AREA)
  • Economics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Public Health (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Computing Systems (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Human Computer Interaction (AREA)
  • Power Engineering (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The utility model discloses a power grid dispatching identity authentication method and system based on multimode identification.A server receives a login request sent by a first client terminal of power grid dispatching, completes login authentication of the first client terminal, and sends a login authentication passing instruction to the first client terminal; the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal; the server receives a call authentication request of the second client in the call process, and completes the call authentication of the second client; the server receives a call authentication request of a first client and completes the call authentication of the first client; the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client; login, call and logout authentication are all completed through multi-mode signal identification.

Description

Power grid dispatching identity authentication method and system based on multimode identification
Technical Field
The disclosure relates to the technical field of communication, in particular to a power grid dispatching identity authentication method and system based on multi-mode identification.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The power grid dispatching is a command and decision brain for safe and stable operation of each level of power grid and is mainly responsible for work such as power grid operation mode adjustment, power outage and power transmission maintenance, new energy consumption, power plant output adjustment, handling of power grid emergency accidents and the like. As a main means of power grid dispatching and commanding, the power dispatching and commanding system is an effective means for dispatching and command uploading and issuing. At present, with the increasing number of extra-high voltage and 500kV transformer substations, the operation mode of a power grid is increasingly complex, and the number of dispatching instructions uploaded and issued by a power dispatching command system in a provincial dispatching hall is increasing. Therefore, the requirements of power grid dispatching and commanding on the dispatching and commanding system are higher and higher, and the current traditional dispatching and commanding system operation and maintenance mode cannot meet the current intelligent, efficient and rapid requirements under the new situation.
In the course of implementing the present disclosure, the inventors found that the following technical problems exist in the prior art:
firstly, the existing power grid dispatching command system lacks a dispatcher identity authentication mechanism. At present, a power grid dispatching command system mainly uses terminal devices such as a dispatching desk, an IP phone, an IAD/AG (integrated access device/access gateway), calls and answers can be carried out by off-hook, the identity authentication function of a dispatcher is not supported, and the safety requirement of the power grid dispatching command is difficult to meet.
Secondly, the common identity authentication mechanism only has login and logout identity authentication, and the identity authentication in the use process is lacked. In a power grid dispatching command scene, except that a dispatcher has identity authentication requirements for logging in and logging out, the risk of identity being falsely used also exists in the conversation process.
Thirdly, the common identity authentication mechanism only confirms the identity of the user through a single signal acquisition means. In a power grid dispatching command system, terminal equipment such as a dispatching desk and the like is provided with a camera, an earphone, a sound, a telephone handle and other various signal acquisition modules, and abundant user discriminant information is not fully utilized.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a power grid dispatching identity authentication method and system based on multi-mode identification; by researching the dispatcher identity authentication system with a dispatcher login authentication mechanism, a call process authentication mechanism and a logout authentication mechanism, the identity of the dispatcher and a responder under the power dispatching command scene is reliably identified, and the compliance and the validity of dispatching instruction issuing are ensured.
In a first aspect, the present disclosure provides a power grid dispatching identity authentication method based on multi-mode identification;
the power grid dispatching identity authentication method based on multi-mode identification comprises the following steps:
the method comprises the steps that a server receives a login request sent by a first client scheduled by a power grid, completes login authentication of the first client, and sends a login authentication passing instruction to the first client;
the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal;
in the conversation process, the server receives a conversation authentication request of the second client, and the server completes the conversation authentication of the second client; the server receives a call authentication request of the first client, and completes the call authentication of the first client;
the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client;
the login authentication, the call authentication and the logout authentication are all completed through multi-mode signal identification.
In a second aspect, the present disclosure provides a power grid dispatching identity authentication system based on multi-mode identification;
power grid dispatching identity authentication system based on multimode identification comprises: the system comprises a telephone exchange network and a server connected with the telephone exchange network, wherein the server is connected with a first client, and the telephone exchange network is connected with a second client; the server is also connected with a camera, a microphone, a display or a sound box;
the method comprises the steps that a server receives a login request sent by a first client scheduled by a power grid, completes login authentication of the first client, and sends a login authentication passing instruction to the first client;
the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal;
in the conversation process, the server receives a conversation authentication request of the second client, and the server completes the conversation authentication of the second client; the server receives a call authentication request of the first client, and completes the call authentication of the first client;
the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client;
the login authentication, the call authentication and the logout authentication are all completed through multi-mode signal identification.
Compared with the prior art, the beneficial effect of this disclosure is:
1. the dispatcher identity authentication system is sound in authentication mechanism and high in safety. The invention provides an identity identification model construction method, a dispatcher login authentication mechanism, a dispatcher communication process authentication mechanism, a dispatcher logout authentication mechanism and other means, which can provide identity authentication for any link in the whole dispatching process, ensure safe dispatching instruction issuing and prevent identity misuse.
2. The dispatcher identity authentication system has strong reliability of an authentication mechanism. The method disclosed by the invention realizes mutual evidence of recognition results in a mode of multi-model fusion of face recognition, action recognition, voiceprint recognition and voice recognition.
3. The dispatcher identity authentication system has the advantages of high expandability and high flexibility. The authentication mechanism disclosed by the invention does not depend on special hardware equipment, and the recognition models adopted by face recognition, action recognition, voiceprint recognition and voice recognition can be continuously iterated, optimized or replaced according to the development of related technologies.
4. The dispatcher identity authentication system authentication mechanism has small influence on the use efficiency of the user. The face recognition, the action recognition, the voiceprint recognition and the voice recognition are operated in a parallel mode, the time consumption of identity authentication is short, and the influence on the use efficiency of a user is small.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a functional architecture diagram of an identity authentication system according to a first embodiment of the present disclosure;
fig. 2(a) is a method for constructing a voiceprint recognition model of an identity authentication system according to a first embodiment of the present disclosure;
fig. 2(b) is a method for constructing a voice recognition model of an identity authentication system according to a first embodiment of the present disclosure;
fig. 2(c) is a method for constructing a face recognition model of an identity authentication system according to a first embodiment of the present disclosure;
fig. 2(d) is a method for constructing an identity authentication system action recognition model according to a first embodiment of the present disclosure;
fig. 3 is a dispatcher login authentication mechanism of an identity authentication system according to an embodiment of the present disclosure;
fig. 4 is an authentication mechanism of a dispatcher communication process of the identity authentication system according to a first embodiment of the disclosure;
fig. 5 is a dispatcher logout authentication mechanism of an identity authentication system according to an embodiment of the disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The first embodiment provides a power grid dispatching identity authentication method based on multi-mode identification;
the power grid dispatching identity authentication method based on multi-mode identification comprises the following steps:
s101: the method comprises the steps that a server receives a login request sent by a first client scheduled by a power grid, completes login authentication of the first client, and sends a login authentication passing instruction to the first client;
the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal;
s102: in the conversation process, the server receives a conversation authentication request of the second client, and the server completes the conversation authentication of the second client; the server receives a call authentication request of the first client, and completes the call authentication of the first client;
s103: the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client;
the login authentication, the call authentication and the logout authentication are all completed through multi-mode signal identification.
Preferably, the first client is a client for a power grid dispatching dispatcher; and the second client is a client for a power grid dispatching responder.
Further, as shown in fig. 3, the server completes login authentication of the first client, and the specific steps include:
s1011: the server randomly calls a verification text from the alternative text library, and displays the verification text through a display, wherein the verification text is used for guiding a dispatcher to read after; the method comprises the steps that a server obtains a follow-up reading process video captured by a camera, and the server obtains a follow-up reading process audio captured by a microphone;
s1012: extracting the face features of the video in the follow-up reading process by using a face recognition model, matching the similarity of the extracted face features and the face features in a dispatcher face database, and acquiring a dispatcher number k corresponding to the face feature with the maximum similarity and the maximum value of the matching similarity of the first face feature from the dispatcher face database;
for the video in the follow-up reading process, the action characteristic extraction is carried out by utilizing the action recognition model, and the starting time t of the voice sending action is obtained1And an end time t2；
S1013: for the audio frequency in the follow-up reading process, voiceprint feature recognition is carried out by utilizing a voiceprint recognition model, similarity matching is carried out on the extracted voiceprint features and voiceprint features in a dispatcher voiceprint database, and a dispatcher number j corresponding to the voiceprint feature with the maximum similarity and the maximum value of the first voiceprint feature matching similarity are obtained from the dispatcher voiceprint database;
for the audio frequency in the follow-up reading process, the voice feature recognition is carried out by utilizing the voice recognition model, and the starting time t of the voice feature sending is obtained3And an end time t4；
Converting the audio in the follow-up reading process into characters, performing similarity matching on the converted characters and the verification text, and calculating a text similarity matching score;
s1014: if the dispatcher number k is not equal to the dispatcher number j, judging that the identity authentication fails, ending the identity login authentication process, and rejecting the user login request; if the dispatcher number k is equal to the dispatcher number j, then go to S1015;
s1015: if | t1-t3|+|t2-t4|>T, if the difference between the starting and ending time of the voice in the audio and the starting and ending time of the voice action in the video is larger than a preset judgment threshold value T, the suspected fake recording is judged, and S1016 is skipped; if | t1-t3|+|t2-t4|<T, judging that the operation is normal, and jumping to S1017;
s1016: the server randomly selects a head action from the alternative action library, presents the head action on a display and guides a user to make the action; the server acquires an action process video captured by the camera; extracting action characteristics of the action process video by using an action recognition model, and judging the action process video to be a non-fake recording if the extracted action characteristics are consistent with the specified head action; jumping to S1017; if the extracted motion characteristics are inconsistent with the specified head motion, determining to be a fake recording; ending the identity login authentication process and rejecting the user login request;
s1017: if the maximum value of the first face feature matching similarity, the maximum value of the first voiceprint feature matching similarity and the text similarity matching score are all within the set threshold value range, the identity authentication is passed, and the identity authentication process is ended; otherwise, it indicates that the authentication fails, and returns to S1011.
It should be understood that, as shown in fig. 2(a), the voiceprint recognition model is obtained by performing neural network training based on a dispatcher voiceprint database; in the training process of the neural network, the input value of the training is voiceprint data, and the output value is a voiceprint label;
as shown in fig. 2(b), the speech recognition model is obtained by performing neural network training based on a speech database of a dispatcher; in the training process of the neural network, the input value of the training is voice data, and the output value is a voice label;
as shown in fig. 2(c), the face recognition model is obtained by performing neural network training based on a dispatcher face database; in the training process of the neural network, the input value of the training is a face image, and the output value is a face label;
as shown in fig. 2(d), the action recognition model is obtained by performing neural network training based on a dispatcher action database; in the training process of the neural network, the input value of the training is a motion video, and the output value is a motion label.
The alternative text library is used for storing a plurality of Chinese texts.
The alternative motion library is used for storing a plurality of head motions, including but not limited to blinking, nodding, sideways heading and the like.
Further, as shown in fig. 4, the step of completing the call authentication of the second client by the server includes:
the server receives the audio from the second client of the responder, performs voiceprint feature extraction on the audio of the second client by using a voiceprint recognition model, performs similarity matching on the extracted voiceprint features and the voiceprint features in the voiceprint database of the dispatcher, and acquires the dispatcher number i corresponding to the voiceprint feature with the maximum similarity and the maximum matching similarity of the second voiceprint feature from the voiceprint database of the dispatcher;
if the maximum value of the second acoustic pattern feature matching similarity is smaller than a first set threshold, the identity authentication of the user of the second client is illegal, and acousto-optic alarm is performed;
if the maximum value of the second acoustic pattern feature matching similarity is larger than a first set threshold and smaller than a second set threshold, the identity authentication of the user of the second client is suspected to be illegal, and acousto-optic prompt is carried out;
and if the maximum value of the second voiceprint feature matching similarity is larger than a second set threshold, acquiring the identity information of the second client user from the dispatcher voiceprint database according to the dispatcher number i, and displaying the identity information.
Further, the server completes the call authentication of the first client, and the specific steps include:
the server receives the audio from a first client used by a dispatcher, performs voiceprint feature extraction on the audio of the first client by using a voiceprint recognition model, performs similarity matching on the extracted voiceprint features and voiceprint features in a dispatcher voiceprint database, and acquires a dispatcher number m corresponding to the voiceprint feature with the maximum similarity and a third voiceprint feature matching similarity maximum value from the dispatcher voiceprint database;
if the maximum value of the third voiceprint feature matching similarity is smaller than a third set threshold, the identity authentication of the user of the first client is illegal, and acousto-optic alarm is performed;
if the maximum value of the third voiceprint feature matching similarity is larger than a third set threshold and smaller than a fourth set threshold, the identity authentication of the user of the first client is suspected to be illegal, and acousto-optic prompt is carried out;
if the maximum value of the third voiceprint feature matching similarity is larger than a fourth set threshold value and m is equal to j, judging that the user identity of the current first client is legal;
and if the maximum value of the third voiceprint feature matching similarity is larger than a fourth set threshold value and m is not equal to j, judging that the identity of the user of the current first client is illegal, and carrying out acousto-optic alarm.
Further, in the process of communication, periodically performing communication authentication of the second client and communication authentication of the first client; and ending the call until the first client or the second client hangs up.
Furthermore, the first client is connected with the server, the server is connected with a telephone exchange network, and the telephone exchange network is connected with the second client.
Further, the first client includes: a first phone handle; the first phone handle is connected with the server. And the user of the first client is a dispatcher of the power grid dispatching.
Further, the second client includes: a second phone handle; and the second telephone handle is connected with the server through a telephone switching network. And the user of the second client is a responder for power grid dispatching.
Further, as shown in fig. 5, the server completes logout authentication of the first client, and the specific steps include:
s1031: the method comprises the steps that a server receives a logout authentication request from a first client used by a dispatcher;
the server randomly calls a verification text from the alternative text library, and displays the verification text through a display, wherein the verification text is used for guiding a dispatcher to read after; the method comprises the steps that a server obtains a follow-up reading process video captured by a camera, and the server obtains a follow-up reading process audio captured by a microphone;
s1032: extracting the face features of the video in the follow-up reading process by using a face recognition model, matching the similarity of the extracted face features and the face features in a dispatcher face database, and acquiring a dispatcher number p corresponding to the face feature with the maximum similarity and a second face feature matching similarity maximum value from the dispatcher face database;
s1033: for the audio frequency in the follow-up reading process, voiceprint feature recognition is carried out by utilizing a voiceprint recognition model, similarity matching is carried out on the extracted voiceprint features and voiceprint features in a dispatcher voiceprint database, and a dispatcher number q corresponding to the voiceprint feature with the maximum similarity and the maximum value of the matching similarity of the fourth voiceprint feature are obtained from the dispatcher voiceprint database;
s1034: if the dispatcher number k is equal to the dispatcher number p and the dispatcher number k is equal to the dispatcher number q; judging that the identity authentication is passed, ending the identity logout authentication process, and successfully logging out the user; otherwise, judging that the identity authentication fails, ending the identity logout authentication process, and rejecting the user logout request;
s1035: if the maximum value of the second face feature matching similarity and the maximum value of the fourth voiceprint feature matching similarity are both in the set value range, the identity authentication is passed, the identity logout authentication process is ended, and the user logout is successful; otherwise, the identity authentication is judged to be failed, the identity logout authentication process is ended, and the user logout request is refused.
The second embodiment provides a power grid dispatching identity authentication system based on multi-mode identification;
as shown in fig. 1, the power grid dispatching identity authentication system based on multi-mode identification includes: the system comprises a telephone exchange network and a server connected with the telephone exchange network, wherein the server is connected with a first client, and the telephone exchange network is connected with a second client; the server is also connected with a camera, a microphone, a display or a sound box;
the method comprises the steps that a server receives a login request sent by a first client scheduled by a power grid, completes login authentication of the first client, and sends a login authentication passing instruction to the first client;
the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal;
in the conversation process, the server receives a conversation authentication request of the second client, and the server completes the conversation authentication of the second client; the server receives a call authentication request of the first client, and completes the call authentication of the first client;
the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client;
the login authentication, the call authentication and the logout authentication are all completed through multi-mode signal identification.
Further, the first client is a first phone handle, and the second client is a second phone handle.
Further, the multi-modal signal includes: one or more of voiceprint features, face features, speech features and action features.
The display is a touch capacitive screen and is used for displaying the identity authentication result of the core data processing unit, and the display content is controlled by the graphical interface display module.
The SIP phone is an IP phone and is used for sending and receiving SIP messages, meeting the call requirements of dispatchers and being linked with the call module.
The camera is a CMOS monocular camera and is used for capturing real-time video streams of dispatchers.
The microphone is a built-in microphone of the touch display and is used for capturing real-time audio streams of the dispatcher.
The sound box is arranged in the touch display and is used for playing sound prompt signals and alarm signals.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (10)

1. The power grid dispatching identity authentication method based on multi-mode identification is characterized by comprising the following steps:
the method comprises the steps that a server receives a login request sent by a first client scheduled by a power grid, completes login authentication of the first client, and sends a login authentication passing instruction to the first client;
the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal;
in the conversation process, the server receives a conversation authentication request of the second client, and the server completes the conversation authentication of the second client; the server receives a call authentication request of the first client, and completes the call authentication of the first client;
the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client;
the login authentication, the call authentication and the logout authentication are all completed through multi-mode signal identification.
2. The method as claimed in claim 1, wherein the server performs login authentication of the first client, the specific steps comprising:
guiding a dispatcher to follow and read: the server randomly calls a verification text from the alternative text library, and displays the verification text through a display, wherein the verification text is used for guiding a dispatcher to read after; the method comprises the steps that a server obtains a follow-up reading process video captured by a camera, and the server obtains a follow-up reading process audio captured by a microphone;
extracting the face features of the video in the follow-up reading process by using a face recognition model, matching the similarity of the extracted face features and the face features in a dispatcher face database, and acquiring a dispatcher number k corresponding to the face feature with the maximum similarity and the maximum value of the matching similarity of the first face feature from the dispatcher face database;
for the video in the follow-up reading process, the action characteristic extraction is carried out by utilizing the action recognition model, and the starting time t of the voice sending action is obtained1And an end time t2；
For the audio frequency in the follow-up reading process, voiceprint feature recognition is carried out by utilizing a voiceprint recognition model, similarity matching is carried out on the extracted voiceprint features and voiceprint features in a dispatcher voiceprint database, and a dispatcher number j corresponding to the voiceprint feature with the maximum similarity and the maximum value of the first voiceprint feature matching similarity are obtained from the dispatcher voiceprint database;
for the audio frequency in the follow-up reading process, the voice feature recognition is carried out by utilizing the voice recognition model, and the starting time t of the voice feature sending is obtained3And an end time t4；
Converting the audio in the follow-up reading process into characters, performing similarity matching on the converted characters and the verification text, and calculating a text similarity matching score;
if the dispatcher number k is not equal to the dispatcher number j, judging that the identity authentication fails, ending the identity login authentication process, and rejecting the user login request; if the dispatcher number k is equal to the dispatcher number j, the next step is carried out;
if | t1-t3|+|t2-t4|>T, if the difference between the starting and ending time of the voice in the audio and the starting and ending time of the voice action in the video is larger than a preset judgment threshold value T, judging that the voice is suspected to be a fake record, and skipping to the step of guiding action; if | t1-t3|+|t2-t4|<If the judgment result is normal, skipping to the judgment step;
a guiding action step: the server randomly selects a head action from the alternative action library, presents the head action on a display and guides a user to make the action; the server acquires an action process video captured by the camera; extracting action characteristics of the action process video by using an action recognition model, and judging the action process video to be a non-fake recording if the extracted action characteristics are consistent with the specified head action; skipping to the next step; if the extracted motion characteristics are inconsistent with the specified head motion, determining to be a fake recording; ending the identity login authentication process and rejecting the user login request;
a judging step: if the maximum value of the first face feature matching similarity, the maximum value of the first voiceprint feature matching similarity and the text similarity matching score are all within the set threshold value range, the identity authentication is passed, and the identity authentication process is ended; otherwise, the identity authentication is not passed, and the step of guiding the dispatcher to follow the reading is returned.
3. The method of claim 1, wherein the voiceprint recognition model is derived from neural network training based on a dispatcher voiceprint database; in the training process of the neural network, the input value of the training is voiceprint data, and the output value is a voiceprint label;
the voice recognition model is obtained by carrying out neural network training based on a voice database of a dispatcher; in the training process of the neural network, the input value of the training is voice data, and the output value is a voice label;
the face recognition model is obtained by carrying out neural network training based on a dispatcher face database; in the training process of the neural network, the input value of the training is a face image, and the output value is a face label;
the action recognition model is obtained by carrying out neural network training based on a dispatcher action database; in the training process of the neural network, the input value of the training is a motion video, and the output value is a motion label.
4. The method as claimed in claim 1, wherein the server completes the call authentication of the second client, and the specific steps include:
the server receives the audio from the second client of the responder, performs voiceprint feature extraction on the audio of the second client by using a voiceprint recognition model, performs similarity matching on the extracted voiceprint features and the voiceprint features in the voiceprint database of the dispatcher, and acquires the dispatcher number i corresponding to the voiceprint feature with the maximum similarity and the maximum matching similarity of the second voiceprint feature from the voiceprint database of the dispatcher;
if the maximum value of the second acoustic pattern feature matching similarity is smaller than a first set threshold, the identity authentication of the user of the second client is illegal, and acousto-optic alarm is performed;
if the maximum value of the second acoustic pattern feature matching similarity is larger than a first set threshold and smaller than a second set threshold, the identity authentication of the user of the second client is suspected to be illegal, and acousto-optic prompt is carried out;
and if the maximum value of the second voiceprint feature matching similarity is larger than a second set threshold, acquiring the identity information of the second client user from the dispatcher voiceprint database according to the dispatcher number i, and displaying the identity information.
5. The method as claimed in claim 1, wherein the server completes the call authentication of the first client, and the specific steps include:
the server receives the audio from a first client used by a dispatcher, performs voiceprint feature extraction on the audio of the first client by using a voiceprint recognition model, performs similarity matching on the extracted voiceprint features and voiceprint features in a dispatcher voiceprint database, and acquires a dispatcher number m corresponding to the voiceprint feature with the maximum similarity and a third voiceprint feature matching similarity maximum value from the dispatcher voiceprint database;
if the maximum value of the third voiceprint feature matching similarity is smaller than a third set threshold, the identity authentication of the user of the first client is illegal, and acousto-optic alarm is performed;
if the maximum value of the third voiceprint feature matching similarity is larger than a third set threshold and smaller than a fourth set threshold, the identity authentication of the user of the first client is suspected to be illegal, and acousto-optic prompt is carried out;
if the maximum value of the third voiceprint feature matching similarity is larger than a fourth set threshold value and m is equal to j, judging that the user identity of the current first client is legal;
and if the maximum value of the third voiceprint feature matching similarity is larger than a fourth set threshold value and m is not equal to j, judging that the identity of the user of the current first client is illegal, and carrying out acousto-optic alarm.
6. The method of claim 1, wherein during the call, the call authentication of the second client and the call authentication of the first client are performed periodically; and ending the call until the first client or the second client hangs up.
7. The method of claim 1, wherein the first client is coupled to a server, the server is coupled to a telephone switching network, and the telephone switching network is coupled to the second client;
the first client includes: a first phone handle; the first phone handle is connected with the server; the user of the first client is a dispatcher of the power grid dispatching;
the second client includes: a second phone handle; the second telephone handle is connected with the server through a telephone switching network; and the user of the second client is a responder for power grid dispatching.
8. The method as claimed in claim 1, wherein the server performs logout authentication of the first client, the specific steps comprising:
the method comprises the steps that a server receives a logout authentication request from a first client used by a dispatcher;
the server randomly calls a verification text from the alternative text library, and displays the verification text through a display, wherein the verification text is used for guiding a dispatcher to read after; the method comprises the steps that a server obtains a follow-up reading process video captured by a camera, and the server obtains a follow-up reading process audio captured by a microphone;
extracting the face features of the video in the follow-up reading process by using a face recognition model, matching the similarity of the extracted face features and the face features in a dispatcher face database, and acquiring a dispatcher number p corresponding to the face feature with the maximum similarity and a second face feature matching similarity maximum value from the dispatcher face database;
for the audio frequency in the follow-up reading process, voiceprint feature recognition is carried out by utilizing a voiceprint recognition model, similarity matching is carried out on the extracted voiceprint features and voiceprint features in a dispatcher voiceprint database, and a dispatcher number q corresponding to the voiceprint feature with the maximum similarity and the maximum value of the matching similarity of the fourth voiceprint feature are obtained from the dispatcher voiceprint database;
if the dispatcher number k is equal to the dispatcher number p and the dispatcher number k is equal to the dispatcher number q; judging that the identity authentication is passed, ending the identity logout authentication process, and successfully logging out the user; otherwise, judging that the identity authentication fails, ending the identity logout authentication process, and rejecting the user logout request;
if the maximum value of the second face feature matching similarity and the maximum value of the fourth voiceprint feature matching similarity are both in the set value range, the identity authentication is passed, the identity logout authentication process is ended, and the user logout is successful; otherwise, the identity authentication is judged to be failed, the identity logout authentication process is ended, and the user logout request is refused.
9. Power grid dispatching identity authentication system based on multimode identification is characterized by comprising: the system comprises a telephone exchange network and a server connected with the telephone exchange network, wherein the server is connected with a first client, and the telephone exchange network is connected with a second client; the server is also connected with a camera, a microphone, a display or a sound box;
the method comprises the steps that a server receives a login request sent by a first client scheduled by a power grid, completes login authentication of the first client, and sends a login authentication passing instruction to the first client;
the server sends a communication connection establishment request to a second client terminal dispatched by the power grid through a telephone exchange network according to the communication connection instruction of the first client terminal, and establishes communication connection between the second client terminal and the first client terminal;
in the conversation process, the server receives a conversation authentication request of the second client, and the server completes the conversation authentication of the second client; the server receives a call authentication request of the first client, and completes the call authentication of the first client;
the server receives a login authentication request of the first client, finishes login authentication of the first client and disconnects communication connection between the first client and the second client;
the login authentication, the call authentication and the logout authentication are all completed through multi-mode signal identification.
10. The system of claim 9, wherein the first client is a first phone handset and the second client is a second phone handset; the multi-modal signal, comprising: one or more of voiceprint features, face features, speech features and action features.
CN202010681725.7A 2020-07-15 2020-07-15 Power grid dispatching identity authentication method and system based on multimode identification Active CN112000938B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010681725.7A CN112000938B (en) 2020-07-15 2020-07-15 Power grid dispatching identity authentication method and system based on multimode identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010681725.7A CN112000938B (en) 2020-07-15 2020-07-15 Power grid dispatching identity authentication method and system based on multimode identification

Publications (2)

Publication Number Publication Date
CN112000938A true CN112000938A (en) 2020-11-27
CN112000938B CN112000938B (en) 2022-11-29

Family

ID=73466959

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010681725.7A Active CN112000938B (en) 2020-07-15 2020-07-15 Power grid dispatching identity authentication method and system based on multimode identification

Country Status (1)

Country Link
CN (1) CN112000938B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112632505A (en) * 2020-12-18 2021-04-09 中国南方电网有限责任公司 Power grid dispatcher login authentication system based on big data analysis and face recognition
CN112822186A (en) * 2020-12-31 2021-05-18 国网江苏省电力有限公司信息通信分公司 Power system IP dispatching station notification broadcasting method and system based on voice authentication
CN113283695A (en) * 2021-04-19 2021-08-20 贵州电网有限责任公司 Power dispatching intelligent agent implementation method and system based on artificial intelligence
CN113298391A (en) * 2021-05-29 2021-08-24 中国南方电网有限责任公司 Power grid dispatching intelligent anti-misoperation and command method and system based on big data

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101355527A (en) * 2008-08-15 2009-01-28 深圳市中兴移动通信有限公司 Method for implementing single-point LOG striding domain name
CN103957522A (en) * 2014-04-16 2014-07-30 华为技术有限公司 Intelligent communication method, intelligent communication terminals and intelligent communication system
CN105704711A (en) * 2014-11-25 2016-06-22 中兴通讯股份有限公司 Method for ensuring call communication security, device and user terminal
CN106790260A (en) * 2017-02-03 2017-05-31 国政通科技股份有限公司 A kind of multiple-factor identity identifying method
CN107181851A (en) * 2017-04-25 2017-09-19 上海与德科技有限公司 Call control method and device
CN110557400A (en) * 2019-09-16 2019-12-10 平安科技（深圳）有限公司 Login control method and device
CN110647729A (en) * 2018-06-27 2020-01-03 深圳联友科技有限公司 Login verification method and system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101355527A (en) * 2008-08-15 2009-01-28 深圳市中兴移动通信有限公司 Method for implementing single-point LOG striding domain name
CN103957522A (en) * 2014-04-16 2014-07-30 华为技术有限公司 Intelligent communication method, intelligent communication terminals and intelligent communication system
CN105704711A (en) * 2014-11-25 2016-06-22 中兴通讯股份有限公司 Method for ensuring call communication security, device and user terminal
CN106790260A (en) * 2017-02-03 2017-05-31 国政通科技股份有限公司 A kind of multiple-factor identity identifying method
CN107181851A (en) * 2017-04-25 2017-09-19 上海与德科技有限公司 Call control method and device
CN110647729A (en) * 2018-06-27 2020-01-03 深圳联友科技有限公司 Login verification method and system
CN110557400A (en) * 2019-09-16 2019-12-10 平安科技（深圳）有限公司 Login control method and device

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112632505A (en) * 2020-12-18 2021-04-09 中国南方电网有限责任公司 Power grid dispatcher login authentication system based on big data analysis and face recognition
CN112822186A (en) * 2020-12-31 2021-05-18 国网江苏省电力有限公司信息通信分公司 Power system IP dispatching station notification broadcasting method and system based on voice authentication
CN113283695A (en) * 2021-04-19 2021-08-20 贵州电网有限责任公司 Power dispatching intelligent agent implementation method and system based on artificial intelligence
CN113298391A (en) * 2021-05-29 2021-08-24 中国南方电网有限责任公司 Power grid dispatching intelligent anti-misoperation and command method and system based on big data

Also Published As

Publication number Publication date
CN112000938B (en) 2022-11-29

Similar Documents

Publication Publication Date Title
CN112000938B (en) Power grid dispatching identity authentication method and system based on multimode identification
CN109618068B (en) Voice service pushing method, device and system based on artificial intelligence
CN111488433B (en) Artificial intelligence interactive system suitable for bank and capable of improving field experience
CN111755001A (en) Artificial intelligence-based power grid rapid dispatching and commanding system and method
WO2021051506A1 (en) Voice interaction method and apparatus, computer device and storage medium
CN108154579A (en) A kind of intelligent access control system and exchange method that can be interacted with visitor
CN110769124A (en) Electric power marketing customer communication system
CN109688276B (en) Incoming call filtering system and method based on artificial intelligence technology
CN106409283A (en) Audio frequency-based man-machine mixed interaction system and method
CN105100360A (en) Communication auxiliary method and device for voice communication
CN101998138A (en) Television channel monitoring system and real-time monitoring method thereof
CN104766608A (en) Voice control method and voice control device
CN111128241A (en) Intelligent quality inspection method and system for voice call
CN109119084A (en) A kind of dispatch call method and system based on speech recognition
CN109040723A (en) A kind of control method of conference scenario
CN103152334A (en) Method for remotely opening door by building intercom system using speech recognition of management platform
CN108510988A (en) Language identification system and method for deaf-mutes
CN110570847A (en) Man-machine interaction system and method for multi-person scene
CN107358958B (en) Intercommunication method, apparatus and system
CN111384778B (en) Intelligent operation and maintenance system for power distribution network equipment
CN106355701A (en) Intelligent door lock and unlocking method
CN114724561A (en) Voice interruption method and device, computer equipment and storage medium
CN102364965A (en) Refined display method of mobile phone communication information
CN103187062A (en) Vehicle-mounted data processing device and preservation service data processing system
CN113065879A (en) Data stream quality inspection method and system

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