CN112214298A - Dynamic priority scheduling method and system based on voiceprint recognition - Google Patents
Dynamic priority scheduling method and system based on voiceprint recognition Download PDFInfo
- Publication number
- CN112214298A CN112214298A CN202011062010.XA CN202011062010A CN112214298A CN 112214298 A CN112214298 A CN 112214298A CN 202011062010 A CN202011062010 A CN 202011062010A CN 112214298 A CN112214298 A CN 112214298A
- Authority
- CN
- China
- Prior art keywords
- priority
- voice
- dispatcher
- dispatching
- dispatching desk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims description 22
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 210000000887 face Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 210000000554 iris Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- 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
- 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
- G06F21/45—Structures or tools for the administration of authentication
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Telephonic Communication Services (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a dynamic priority scheduling method and a system based on voiceprint recognition, wherein the method comprises the following steps: setting a unique identity code for each dispatcher, binding the identity code with the used dispatching desk, setting the priority of the dispatching desk as the priority of the dispatcher, and sending a request for adjusting the priority to a dispatching server when the high-level dispatcher uses the low-level dispatching desk for dispatching; after receiving the request, the dispatching server sends a reference voice to the dispatching desk; after receiving the reference voice, the user repeats the voice and sends the voice to the dispatching server; the dispatching server carries out voiceprint recognition on the received test voice to determine the identity of the test voice, a dispatcher also needs to answer a privacy question, and only when the voiceprint recognition is passed and the answered question is correct, the dispatcher can pass identity authentication and adjust the priority. The invention can realize the dynamic adjustment of the priority, and has high safety and convenient use.
Description
Technical Field
The invention relates to a power scheduling technology, in particular to a dynamic priority scheduling method and system based on voiceprint recognition.
Background
In the power dispatching system, each dispatching desk has own priority, and the high-level dispatching desk can perform operations such as forcible insertion and forcible removal on the low-level dispatching desk. Typically, the priority is subordinate to the dispatch station, independent of the user of the dispatch station, i.e., the dispatcher. Because a large number of simple dispatch stations such as IP dispatch telephones exist in the dispatch system, login and authentication of a specific dispatcher are not supported. However, in some cases, a high-level dispatcher needs to go to a plant station to handle the problem on site, and can only use a low-level dispatching desk of the plant station for dispatching, which is inconvenient to use. At this time, if the priority of the low-level dispatcher station can be temporarily increased, great convenience is brought to dispatching work.
Biometric identification is a technology for personal identification by using the inherent physiological characteristics (such as fingerprints, human faces, irises and the like) or behavior characteristics (such as handwriting, voice, gait and the like) of a human body, and has the advantages of high efficiency, safety, convenience and difficulty in counterfeiting. However, in the power dispatching system, many low-level dispatching stations only have a voice communication function, and image information such as human faces is difficult to acquire, so that the traditional biological recognition technology cannot be applied to the power dispatching system.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention provides a dynamic priority scheduling method and a dynamic priority scheduling system based on voiceprint recognition, which can temporarily and dynamically adjust the priority.
The technical scheme is as follows: the dynamic priority scheduling method based on voiceprint recognition comprises the following steps:
(1) the dispatching server sets a priority and a unique identity code for each dispatcher, binds the identity code of the dispatcher with a used dispatching desk, and sets the priority of the dispatching desk as the priority of the dispatcher;
(2) when a dispatcher with high priority needs to use a low-priority dispatching desk, sending a priority regulation request to a dispatching server through a priority regulation key preset by the low-priority dispatching desk;
(3) after receiving the request, the dispatching server randomly selects one section from the reference voices of a plurality of sections of pre-stored texts and sends the selected section to a dispatching desk;
(4) the dispatching desk plays the reference voice, and sends the repeated voice of the high-priority dispatcher as the test voice to be recognized to the dispatching server;
(5) the dispatching server performs voice print identification related to the text on the received testing voice and the pre-stored text-related voice print models corresponding to the texts of the dispatchers to obtain dispatcher identity codes corresponding to the testing voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times;
(6) the dispatching server randomly selects one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sends the selected one to a dispatching desk;
(7) the dispatching desk plays the privacy question voice and returns the response voice of the dispatcher to the dispatching server;
(8) the scheduling server calls a pre-stored private question answer voice, performs voiceprint recognition on a response voice of a scheduler, and verifies the correctness of the answer;
(9) if the voiceprint identification is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to be the priority of the current high-priority dispatcher and sends a voice with the dispatching priority adjusted successfully to the dispatching desk; otherwise, sending voice for refusing to adjust the priority request to the dispatching desk;
(10) in the subsequent scheduling work, the scheduling server continuously identifies the voice sent by the scheduling station and the pre-stored text-independent voiceprint models of all the schedulers, the voiceprint is identified without the text, the identity code of the voice sent by the current scheduling station is obtained, and the priority of the scheduling station is recovered once the identity code of the dispatcher using the scheduling station is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
Further, before the step (1), the following information is pre-stored in the scheduling server:
the identity code and the corresponding priority of each dispatcher, and a dispatching desk bound with the identity code of the dispatcher;
each text corresponds to a reference voice;
the text-independent voiceprint model of each dispatcher and the text-dependent voiceprint model corresponding to each text of each dispatcher;
the voices of a plurality of privacy questions of each dispatcher and the voice of the corresponding answer.
The invention discloses a dynamic priority scheduling server based on voiceprint recognition, which comprises:
a database;
the priority distribution module is used for binding the identity codes of the dispatchers with the dispatching desks used by the dispatchers according to the priorities of the dispatchers stored in the database and the unique identity codes of the dispatchers, and setting the priorities of the dispatching desks as the priorities of the dispatchers;
the priority adjustment request receiving module is used for receiving a priority adjustment request sent by a preset priority adjustment key of a low-priority dispatching desk when a dispatcher with high priority needs to use the low-priority dispatching desk;
the voice selection module is used for randomly selecting one section from the reference voices of a plurality of sections of texts stored in advance after receiving the priority adjustment request and sending the selected section to the requesting dispatching desk;
the voiceprint recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voiceprint recognition related to the text on the test voice and the text-related voiceprint models corresponding to the texts of the dispatchers stored in the database in advance, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times; the test voice is the voice repeated by a high-priority dispatcher after the reference voice is played by the dispatching desk;
the privacy problem selection module is used for randomly selecting one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the selected one to the dispatching desk;
the privacy question answer verification module is used for calling the pre-stored privacy question answer voice from the database, carrying out voiceprint recognition on the response voice of the dispatcher and verifying the correctness of the answer; the response voice of the dispatcher is the response of the dispatcher to the privacy problem sent by the dispatching desk;
the priority adjusting module is used for adjusting the priority of the dispatching desk to be the priority of the current high-priority dispatcher when the voiceprint recognition is passed and the answer is correct, and sending the voice with the dispatching priority adjusted successfully to the dispatching desk;
and the priority rejection module is used for sending voice for rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is failed or the answer is incorrect.
Further, the method also comprises the following steps:
the identity code monitoring module is used for continuously carrying out text-independent voiceprint recognition on the voice sent by the dispatching desk and a pre-stored text-independent voiceprint model of each dispatcher by the dispatching server in the subsequent dispatching work to obtain an identity code of the voice sent by the current dispatching desk, and recovering the priority of the dispatching desk once the identity code of the dispatcher using the dispatching desk is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
The invention discloses a dynamic priority dispatching desk based on voiceprint recognition, which comprises:
the system comprises a priority adjustment request sending module, a scheduling server and a priority adjustment module, wherein the priority adjustment request sending module is used for sending a priority adjustment request to the scheduling server after a preset priority adjustment key is pressed when a high-priority dispatcher needs to use a low-priority dispatching desk; each dispatcher has a priority and a unique identity code, the identity code of the dispatcher is bound with a used dispatching desk, and the priority of the dispatching desk is the priority of the dispatcher;
the reference voice playing module is used for playing reference voice sent by the dispatching server, taking the voice repeated by the high-priority dispatcher as test voice to be recognized and sending the test voice to the dispatching server; the reference voice is a section randomly selected from reference voices of a plurality of sections of texts stored in advance after the scheduling server receives the request;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the response voice of the dispatcher to the scheduling server; the privacy problem voice is one randomly selected from a plurality of pre-stored privacy problem voices of the dispatcher after the dispatcher identity code is recognized by the dispatching server; the process of identifying the identity code of the dispatcher by the dispatching server comprises the following steps: carrying out text-related voiceprint recognition on the test voice and a text-related voiceprint model corresponding to each text of each dispatcher, which is pre-stored in a database, so as to obtain a dispatcher identity code corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times;
the scheduling result playing module is used for playing scheduling result voice sent by the scheduling server, and the scheduling result voice is sent in the following mode: the scheduling server calls a pre-stored private question answer voice, performs voiceprint recognition on a response voice of a scheduler, and verifies the correctness of the answer; if the voiceprint identification is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to be the priority of the current high-priority dispatcher and sends the voice with the successfully adjusted priority to the dispatching desk; otherwise, sending voice for refusing to adjust the priority request to the dispatching desk.
The dynamic priority scheduling system based on voiceprint recognition comprises a scheduling server and a scheduling platform, wherein the scheduling server comprises:
a database;
the priority distribution module is used for binding the identity codes of the dispatchers with the dispatching desks used by the dispatchers according to the priorities of the dispatchers stored in the database and the unique identity codes of the dispatchers, and setting the priorities of the dispatching desks as the priorities of the dispatchers;
the priority adjustment request receiving module is used for receiving a priority adjustment request sent by a preset priority adjustment key of a low-priority dispatching desk when a dispatcher with high priority needs to use the low-priority dispatching desk;
the voice selection module is used for randomly selecting one section from the reference voices of a plurality of sections of texts stored in advance after receiving the priority adjustment request and sending the selected section to the requesting dispatching desk;
the voiceprint recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voiceprint recognition related to the text on the test voice and the text-related voiceprint models corresponding to the texts of the dispatchers stored in the database in advance, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times; the test voice is the voice repeated by a high-priority dispatcher after the reference voice is played by the dispatching desk;
the privacy problem selection module is used for randomly selecting one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the selected one to the dispatching desk;
the privacy question answer verification module is used for calling the pre-stored privacy question answer voice from the database, carrying out voiceprint recognition on the response voice of the dispatcher and verifying the correctness of the answer;
the priority adjusting module is used for adjusting the priority of the dispatching desk to be the priority of the current high-priority dispatcher when the voiceprint identification is passed and the answer is correct, and sending the voice with the successfully adjusted dispatching priority to the dispatching desk;
and the priority rejection module is used for sending voice for rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is failed or the answer is incorrect.
The dispatch station includes:
the system comprises a priority adjustment request sending module, a scheduling server and a priority adjustment module, wherein the priority adjustment request sending module is used for sending a priority adjustment request to the scheduling server after a preset priority adjustment key is pressed when a high-priority dispatcher needs to use a low-priority dispatching desk;
the reference voice playing module is used for playing reference voice sent by the dispatching server, taking the voice repeated by the high-priority dispatcher as test voice to be recognized and sending the test voice to the dispatching server;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the response voice of the dispatcher to the scheduling server;
and the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server.
Further, the dispatch server further includes:
the identity code monitoring module is used for continuously carrying out text-independent voiceprint recognition on the voice sent by the dispatching desk and a pre-stored text-independent voiceprint model of each dispatcher by the dispatching server in the subsequent dispatching work to obtain an identity code of the voice sent by the current dispatching desk, and recovering the priority of the dispatching desk once the identity code of the dispatcher using the dispatching desk is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
Has the advantages that: compared with the prior art, the invention has the following remarkable advantages: the invention adopts voiceprint recognition and privacy problem recognition to judge the identity of the dispatcher, thereby dynamically adjusting the priority of the used dispatching desk to be the priority of the current dispatcher, realizing the flexibility of dispatching, and having the advantages of high safety, low cost, low algorithm complexity and convenient use.
Drawings
Fig. 1 is a schematic flow chart of a dynamic priority scheduling method based on voiceprint recognition according to the present invention.
Detailed Description
The embodiment provides a dynamic priority scheduling method based on voiceprint recognition, as shown in fig. 1, including:
(1) the dispatching server sets a priority and a unique identity code for each dispatcher, binds the identity code of the dispatcher with the used dispatching desk, and sets the priority of the dispatching desk as the priority of the dispatcher.
Wherein, before this step, the following information is pre-stored in the scheduling server:
the identity code and the corresponding priority of each dispatcher, and a dispatching desk bound with the identity code of the dispatcher;
each text corresponds to a reference voice; the reference speech is generated by reading each text with standard pronunciation;
the text-independent voiceprint model of each dispatcher and the text-dependent voiceprint model corresponding to each text of each dispatcher; the training process of the text-related voiceprint model comprises the following steps: for each dispatcher, reading each Text for multiple times (the times are generally more than 30), training the multiple-reading voice of each Text to obtain a Text-related Voiceprint model corresponding to each Text, and using the Text-Dependent Voiceprint Recognition (TD-VPR) to recognize the Voiceprint related to the Text, so that each Text of each dispatcher corresponds to one Text-related Voiceprint model; the training process of the text-independent voiceprint model comprises the following steps: for each dispatcher, the reading voices of all texts are integrated and trained together to obtain a Text-Independent Voiceprint model, so that each dispatcher corresponds to one Text-Independent Voiceprint model and is used for carrying out Text-Independent Voiceprint Recognition (TI-VPR);
the voices of a plurality of privacy questions of each dispatcher and the voice of the corresponding answer. Privacy questions such as "your year, month and day of birth", "your place of birth (province, city, county)", "your graduate elementary school", and the like, which are only known to the individual, and collect answers in the form of voices.
(2) When a dispatcher with high priority needs to use the low-priority dispatching desk, a priority adjusting request is sent to the dispatching server through a priority adjusting key preset by the low-priority dispatching desk.
The preset priority adjustment key may be a certain key which is added in particular, or may be a certain existing key or a combination of certain keys.
(3) After receiving the request, the dispatching server randomly selects one section from the reference voices of a plurality of sections of pre-stored texts and sends the selected section to the dispatching desk.
(4) And the dispatching desk plays the reference voice, and sends the repeated voice of the high-priority dispatcher as the test voice to be recognized to the dispatching server.
(5) And the dispatching server performs voice print identification related to the text on the received testing voice and the pre-stored voice print model related to the text of each dispatcher so as to obtain the dispatcher identity code corresponding to the testing voice.
It should be noted in this step that, in general, only the high-priority dispatcher is allowed to use the low-priority dispatcher station, and the low-priority dispatcher is not allowed to use the high-priority dispatcher station, so if the priority of the dispatcher is lower than that of the dispatcher station, the adjustment of the priority is not allowed, a voice refusing to adjust the priority request is directly sent to the dispatcher station, and the flow is ended.
(6) And the dispatching server randomly selects one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sends the selected one to the dispatching desk.
(7) The dispatching desk plays the privacy question voice and returns the response voice of the dispatcher to the dispatching server.
(8) The dispatching server calls the pre-stored private question answer voice, performs voiceprint recognition on the response voice of the dispatcher and verifies the correctness of the answer.
(9) If the voiceprint identification is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to be the priority of the current high-priority dispatcher and sends a voice with the dispatching priority adjusted successfully to the dispatching desk; otherwise, sending voice for refusing to adjust the priority request to the dispatching desk.
(10) In the subsequent dispatching work, the dispatching server continuously identifies the voice sent by the dispatching desk and the text-independent voiceprint models of all the dispatchers, wherein the text-independent voiceprint models are stored in advance, so that the identity code of the voice sent by the current dispatching desk is obtained, and the priority of the dispatching desk is recovered once the identity code of the dispatcher using the dispatching desk is found to be changed.
Based on the above method, the present embodiment further provides a dynamic priority scheduling server based on voiceprint recognition, including:
a database;
the priority distribution module is used for binding the identity codes of the dispatchers with the dispatching desks used by the dispatchers according to the priorities of the dispatchers stored in the database and the unique identity codes of the dispatchers, and setting the priorities of the dispatching desks as the priorities of the dispatchers;
the priority adjustment request receiving module is used for receiving a priority adjustment request sent by a preset priority adjustment key of a low-priority dispatching desk when a dispatcher with high priority needs to use the low-priority dispatching desk;
the voice selection module is used for randomly selecting one section from the reference voices of a plurality of sections of texts stored in advance after receiving the priority adjustment request and sending the selected section to the requesting dispatching desk;
the voiceprint recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voiceprint recognition related to the text on the test voice and the text-related voiceprint models corresponding to the texts of the dispatchers stored in the database in advance, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times; the test voice is the voice repeated by a high-priority dispatcher after the reference voice is played by the dispatching desk;
the privacy problem selection module is used for randomly selecting one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the selected one to the dispatching desk;
the privacy question answer verification module is used for calling the pre-stored privacy question answer voice from the database, carrying out voiceprint recognition on the response voice of the dispatcher and verifying the correctness of the answer; the response voice of the dispatcher is the response of the dispatcher to the privacy problem sent by the dispatching desk;
the priority adjusting module is used for adjusting the priority of the dispatching desk to be the priority of the current high-priority dispatcher when the voiceprint recognition is passed and the answer is correct, and sending the voice with the dispatching priority adjusted successfully to the dispatching desk;
the priority rejection module is used for sending voice for rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is failed or the answer is incorrect;
the identity code monitoring module is used for continuously carrying out text-independent voiceprint recognition on the voice sent by the dispatching desk and a pre-stored text-independent voiceprint model of each dispatcher by the dispatching server in the subsequent dispatching work to obtain an identity code of the voice sent by the current dispatching desk, and recovering the priority of the dispatching desk once the identity code of the dispatcher using the dispatching desk is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
This embodiment also provides a dynamic priority dispatching desk based on voiceprint recognition, including:
the system comprises a priority adjustment request sending module, a scheduling server and a priority adjustment module, wherein the priority adjustment request sending module is used for sending a priority adjustment request to the scheduling server after a preset priority adjustment key is pressed when a high-priority dispatcher needs to use a low-priority dispatching desk; each dispatcher has a priority and a unique identity code, the identity code of the dispatcher is bound with a used dispatching desk, and the priority of the dispatching desk is the priority of the dispatcher;
the reference voice playing module is used for playing reference voice sent by the dispatching server, taking the voice repeated by the high-priority dispatcher as test voice to be recognized and sending the test voice to the dispatching server; the reference voice is a section randomly selected from reference voices of a plurality of sections of texts stored in advance after the scheduling server receives the request;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the response voice of the dispatcher to the scheduling server; the privacy problem voice is one randomly selected from a plurality of pre-stored privacy problem voices of the dispatcher after the dispatcher identity code is recognized by the dispatching server; the process of identifying the identity code of the dispatcher by the dispatching server comprises the following steps: carrying out text-related voiceprint recognition on the test voice and a text-related voiceprint model corresponding to each text of each dispatcher, which is pre-stored in a database, so as to obtain a dispatcher identity code corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times;
the scheduling result playing module is used for playing scheduling result voice sent by the scheduling server, and the scheduling result voice is sent in the following mode: the scheduling server calls a pre-stored private question answer voice, performs voiceprint recognition on a response voice of a scheduler, and verifies the correctness of the answer; if the voiceprint identification is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to be the priority of the current high-priority dispatcher and sends the voice with the successfully adjusted priority to the dispatching desk; otherwise, sending voice for refusing to adjust the priority request to the dispatching desk.
The embodiment further provides a dynamic priority scheduling system based on voiceprint recognition, which includes a scheduling server and a scheduling platform, where the scheduling server includes:
a database;
the priority distribution module is used for binding the identity codes of the dispatchers with the dispatching desks used by the dispatchers according to the priorities of the dispatchers stored in the database and the unique identity codes of the dispatchers, and setting the priorities of the dispatching desks as the priorities of the dispatchers;
the priority adjustment request receiving module is used for receiving a priority adjustment request sent by a preset priority adjustment key of a low-priority dispatching desk when a dispatcher with high priority needs to use the low-priority dispatching desk;
the voice selection module is used for randomly selecting one section from the reference voices of a plurality of sections of texts stored in advance after receiving the priority adjustment request and sending the selected section to the requesting dispatching desk;
the voiceprint recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voiceprint recognition related to the text on the test voice and the text-related voiceprint models corresponding to the texts of the dispatchers stored in the database in advance, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times; the test voice is the voice repeated by a high-priority dispatcher after the reference voice is played by the dispatching desk;
the privacy problem selection module is used for randomly selecting one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the selected one to the dispatching desk;
the privacy question answer verification module is used for calling the pre-stored privacy question answer voice from the database, carrying out voiceprint recognition on the response voice of the dispatcher and verifying the correctness of the answer;
the priority adjusting module is used for adjusting the priority of the dispatching desk to be the priority of the current high-priority dispatcher when the voiceprint identification is passed and the answer is correct, and sending the voice with the successfully adjusted dispatching priority to the dispatching desk;
the priority rejection module is used for sending voice for rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is failed or the answer is incorrect;
the identity code monitoring module is used for continuously carrying out text-independent voiceprint recognition on the voice sent by the dispatching desk and a pre-stored text-independent voiceprint model of each dispatcher by the dispatching server in the subsequent dispatching work to obtain an identity code of the voice sent by the current dispatching desk, and recovering the priority of the dispatching desk once the identity code of the dispatcher using the dispatching desk is found to be changed; the text-independent voiceprint model is obtained by training voices of all the dispatchers when reading all the texts for multiple times;
the dispatch station includes:
the system comprises a priority adjustment request sending module, a scheduling server and a priority adjustment module, wherein the priority adjustment request sending module is used for sending a priority adjustment request to the scheduling server after a preset priority adjustment key is pressed when a high-priority dispatcher needs to use a low-priority dispatching desk;
the reference voice playing module is used for playing reference voice sent by the dispatching server, taking the voice repeated by the high-priority dispatcher as test voice to be recognized and sending the test voice to the dispatching server;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the response voice of the dispatcher to the scheduling server;
and the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (8)
1. A dynamic priority scheduling method based on voiceprint recognition is characterized by comprising the following steps:
(1) the dispatching server sets a priority and a unique identity code for each dispatcher, binds the identity code of the dispatcher with a used dispatching desk, and sets the priority of the dispatching desk as the priority of the dispatcher;
(2) when a dispatcher with high priority needs to use a low-priority dispatching desk, sending a priority regulation request to a dispatching server through a priority regulation key preset by the low-priority dispatching desk;
(3) after receiving the request, the dispatching server randomly selects one section from the reference voices of a plurality of sections of pre-stored texts and sends the selected section to a dispatching desk;
(4) the dispatching desk plays the reference voice, and sends the repeated voice of the high-priority dispatcher as the test voice to be recognized to the dispatching server;
(5) the dispatching server performs voice print identification related to the text on the received testing voice and the pre-stored text-related voice print models corresponding to the texts of the dispatchers to obtain dispatcher identity codes corresponding to the testing voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times;
(6) the dispatching server randomly selects one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sends the selected one to a dispatching desk;
(7) the dispatching desk plays the privacy question voice and returns the response voice of the dispatcher to the dispatching server;
(8) the scheduling server calls a pre-stored private question answer voice, performs voiceprint recognition on a response voice of a scheduler, and verifies the correctness of the answer;
(9) if the voiceprint identification is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to be the priority of the current high-priority dispatcher and sends a voice with the dispatching priority adjusted successfully to the dispatching desk; otherwise, sending voice for refusing to adjust the priority request to the dispatching desk.
2. The dynamic priority scheduling method based on voiceprint recognition according to claim 1, wherein: after the step (9), the method further comprises the following steps:
(10) in the subsequent scheduling work, the scheduling server continuously identifies the voice sent by the scheduling station and the pre-stored text-independent voiceprint models of all the schedulers, the voiceprint is identified without the text, the identity code of the voice sent by the current scheduling station is obtained, and the priority of the scheduling station is recovered once the identity code of the dispatcher using the scheduling station is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
3. The dynamic priority scheduling method based on voiceprint recognition according to claim 1, wherein: pre-storing the following information in the scheduling server before step (1):
the identity code and the corresponding priority of each dispatcher, and a dispatching desk bound with the identity code of the dispatcher;
each text corresponds to a reference voice;
the text-independent voiceprint model of each dispatcher and the text-dependent voiceprint model corresponding to each text of each dispatcher;
the voices of a plurality of privacy questions of each dispatcher and the voice of the corresponding answer.
4. A dynamic priority scheduling server based on voiceprint recognition, comprising:
a database;
the priority distribution module is used for binding the identity codes of the dispatchers with the dispatching desks used by the dispatchers according to the priorities of the dispatchers stored in the database and the unique identity codes of the dispatchers, and setting the priorities of the dispatching desks as the priorities of the dispatchers;
the priority adjustment request receiving module is used for receiving a priority adjustment request sent by a preset priority adjustment key of a low-priority dispatching desk when a dispatcher with high priority needs to use the low-priority dispatching desk;
the voice selection module is used for randomly selecting one section from the reference voices of a plurality of sections of texts stored in advance after receiving the priority adjustment request and sending the selected section to the requesting dispatching desk;
the voiceprint recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voiceprint recognition related to the text on the test voice and the text-related voiceprint models corresponding to the texts of the dispatchers stored in the database in advance, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times; the test voice is the voice repeated by a high-priority dispatcher after the reference voice is played by the dispatching desk;
the privacy problem selection module is used for randomly selecting one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the selected one to the dispatching desk;
the privacy question answer verification module is used for calling the pre-stored privacy question answer voice from the database, carrying out voiceprint recognition on the response voice of the dispatcher and verifying the correctness of the answer; the response voice of the dispatcher is the response of the dispatcher to the privacy problem sent by the dispatching desk;
the priority adjusting module is used for adjusting the priority of the dispatching desk to be the priority of the current high-priority dispatcher when the voiceprint recognition is passed and the answer is correct, and sending the voice with the dispatching priority adjusted successfully to the dispatching desk;
and the priority rejection module is used for sending voice for rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is failed or the answer is incorrect.
5. The voiceprint recognition based dynamic priority scheduling server of claim 4 further comprising:
the identity code monitoring module is used for continuously carrying out text-independent voiceprint recognition on the voice sent by the dispatching desk and a pre-stored text-independent voiceprint model of each dispatcher by the dispatching server in the subsequent dispatching work to obtain an identity code of the voice sent by the current dispatching desk, and recovering the priority of the dispatching desk once the identity code of the dispatcher using the dispatching desk is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
6. A dynamic priority scheduler based on voiceprint recognition, comprising:
the system comprises a priority adjustment request sending module, a scheduling server and a priority adjustment module, wherein the priority adjustment request sending module is used for sending a priority adjustment request to the scheduling server after a preset priority adjustment key is pressed when a high-priority dispatcher needs to use a low-priority dispatching desk; each dispatcher has a priority and a unique identity code, the identity code of the dispatcher is bound with a used dispatching desk, and the priority of the dispatching desk is the priority of the dispatcher;
the reference voice playing module is used for playing reference voice sent by the dispatching server, taking the voice repeated by the high-priority dispatcher as test voice to be recognized and sending the test voice to the dispatching server; the reference voice is a section randomly selected from reference voices of a plurality of sections of texts stored in advance after the scheduling server receives the request;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the response voice of the dispatcher to the scheduling server; the privacy problem voice is one randomly selected from a plurality of pre-stored privacy problem voices of the dispatcher after the dispatcher identity code is recognized by the dispatching server; the process of identifying the identity code of the dispatcher by the dispatching server comprises the following steps: carrying out text-related voiceprint recognition on the test voice and a text-related voiceprint model corresponding to each text of each dispatcher, which is pre-stored in a database, so as to obtain a dispatcher identity code corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times;
the scheduling result playing module is used for playing scheduling result voice sent by the scheduling server, and the scheduling result voice is sent in the following mode: the scheduling server calls a pre-stored private question answer voice, performs voiceprint recognition on a response voice of a scheduler, and verifies the correctness of the answer; if the voiceprint identification is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to be the priority of the current high-priority dispatcher and sends the voice with the successfully adjusted priority to the dispatching desk; otherwise, sending voice for refusing to adjust the priority request to the dispatching desk.
7. A dynamic priority scheduling system based on voiceprint recognition is characterized in that: the system comprises a dispatching server and a dispatching desk, wherein the dispatching server comprises:
a database;
the priority distribution module is used for binding the identity codes of the dispatchers with the dispatching desks used by the dispatchers according to the priorities of the dispatchers stored in the database and the unique identity codes of the dispatchers, and setting the priorities of the dispatching desks as the priorities of the dispatchers;
the priority adjustment request receiving module is used for receiving a priority adjustment request sent by a preset priority adjustment key of a low-priority dispatching desk when a dispatcher with high priority needs to use the low-priority dispatching desk;
the voice selection module is used for randomly selecting one section from the reference voices of a plurality of sections of texts stored in advance after receiving the priority adjustment request and sending the selected section to the requesting dispatching desk;
the voiceprint recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voiceprint recognition related to the text on the test voice and the text-related voiceprint models corresponding to the texts of the dispatchers stored in the database in advance, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voice of each dispatcher when reading each text for multiple times; the test voice is the voice repeated by a high-priority dispatcher after the reference voice is played by the dispatching desk;
the privacy problem selection module is used for randomly selecting one of a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the selected one to the dispatching desk;
the privacy question answer verification module is used for calling the pre-stored privacy question answer voice from the database, carrying out voiceprint recognition on the response voice of the dispatcher and verifying the correctness of the answer;
the priority adjusting module is used for adjusting the priority of the dispatching desk to be the priority of the current high-priority dispatcher when the voiceprint identification is passed and the answer is correct, and sending the voice with the successfully adjusted dispatching priority to the dispatching desk;
the priority rejection module is used for sending voice for rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is failed or the answer is incorrect;
the dispatch station includes:
the system comprises a priority adjustment request sending module, a scheduling server and a priority adjustment module, wherein the priority adjustment request sending module is used for sending a priority adjustment request to the scheduling server after a preset priority adjustment key is pressed when a high-priority dispatcher needs to use a low-priority dispatching desk;
the reference voice playing module is used for playing reference voice sent by the dispatching server, taking the voice repeated by the high-priority dispatcher as test voice to be recognized and sending the test voice to the dispatching server;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the response voice of the dispatcher to the scheduling server;
and the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server.
8. The voiceprint recognition based dynamic priority scheduling system of claim 7 wherein: the dispatch server further comprises:
the identity code monitoring module is used for continuously carrying out text-independent voiceprint recognition on the voice sent by the dispatching desk and a pre-stored text-independent voiceprint model of each dispatcher by the dispatching server in the subsequent dispatching work to obtain an identity code of the voice sent by the current dispatching desk, and recovering the priority of the dispatching desk once the identity code of the dispatcher using the dispatching desk is found to be changed; the text-independent voiceprint model is obtained by training voices of all the texts read by each dispatcher for multiple times.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011062010.XA CN112214298B (en) | 2020-09-30 | 2020-09-30 | Dynamic priority scheduling method and system based on voiceprint recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011062010.XA CN112214298B (en) | 2020-09-30 | 2020-09-30 | Dynamic priority scheduling method and system based on voiceprint recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112214298A true CN112214298A (en) | 2021-01-12 |
CN112214298B CN112214298B (en) | 2023-09-22 |
Family
ID=74051668
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011062010.XA Active CN112214298B (en) | 2020-09-30 | 2020-09-30 | Dynamic priority scheduling method and system based on voiceprint recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112214298B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106790054A (en) * | 2016-12-20 | 2017-05-31 | 四川长虹电器股份有限公司 | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition |
WO2018149077A1 (en) * | 2017-02-16 | 2018-08-23 | 平安科技(深圳)有限公司 | Voiceprint recognition method, device, storage medium, and background server |
-
2020
- 2020-09-30 CN CN202011062010.XA patent/CN112214298B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106790054A (en) * | 2016-12-20 | 2017-05-31 | 四川长虹电器股份有限公司 | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition |
WO2018149077A1 (en) * | 2017-02-16 | 2018-08-23 | 平安科技(深圳)有限公司 | Voiceprint recognition method, device, storage medium, and background server |
Non-Patent Citations (1)
Title |
---|
侯勇;王铮;舒乔晔;傅山;: "一种防范电网调度员语音失误的语音辅助系统", 微型电脑应用, no. 12 * |
Also Published As
Publication number | Publication date |
---|---|
CN112214298B (en) | 2023-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0746846B1 (en) | Voice-controlled account access over a telephone network | |
EP0953972B1 (en) | Simultaneous speaker-independent voice recognition and verification over a telephone network | |
CN101697514B (en) | A kind of method and system of authentication | |
AU2006306790B2 (en) | System and method of subscription identity authentication utilizing multiple factors | |
US5127043A (en) | Simultaneous speaker-independent voice recognition and verification over a telephone network | |
AU2004300140B2 (en) | System and method for providing improved claimant authentication | |
CN101467204B (en) | Method and system for bio-metric voice print authentication | |
JP2003058190A (en) | Personal authentication system | |
KR20190045099A (en) | Voice Authentication System and Method | |
CN104426998A (en) | Vehicle telematics unit and method of operating the same | |
CN101494540A (en) | Remote voice identification authentication system and method | |
CN109785834B (en) | Voice data sample acquisition system and method based on verification code | |
Beigi | Challenges of LargeScale Speaker Recognition | |
US7246061B2 (en) | Method for the voice-operated identification of the user of a telecommunications line in a telecommunications network in the course of a dialog with a voice-operated dialog system | |
ATE340399T1 (en) | PATTERN PROCESSING SYSTEM SPECIFIC TO A GROUP OF USERS | |
CN112214298B (en) | Dynamic priority scheduling method and system based on voiceprint recognition | |
US20220366916A1 (en) | Access control system | |
Kim | User experience validation using the honeycomb model in the requirements development stage | |
KR20210117827A (en) | Voice service supply system and supply method using artificial intelligence | |
US20220139402A1 (en) | Voice authentication apparatus, voice authentication method, and a recording medium | |
KR101876262B1 (en) | Multi-factor user authentication system | |
JP2004177663A (en) | Method of identifying person taking course | |
JP5436951B2 (en) | User authentication device and user authentication method | |
KR20220138925A (en) | System of Self-participation Authentication and Concentration Induction in Online Education through Voice Recognition and Voiceprint Recognition | |
EP1016075B1 (en) | Method and arrangement for providing speaker reference data for speaker verification |
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 |