CN112214298B - 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
- CN112214298B CN112214298B CN202011062010.XA CN202011062010A CN112214298B CN 112214298 B CN112214298 B CN 112214298B CN 202011062010 A CN202011062010 A CN 202011062010A CN 112214298 B CN112214298 B CN 112214298B
- Authority
- CN
- China
- Prior art keywords
- priority
- dispatcher
- voice
- scheduling
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- 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
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 unique identity code with a 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 a high-level dispatcher uses a low-level dispatching desk for dispatching; after receiving the request, the dispatching server sends a section of reference voice to the dispatching desk; after receiving the reference voice, the user repeats the section of voice and sends the section of voice to the scheduling server; the dispatching server carries out voiceprint recognition on the received test voice to determine the identity of the test voice, the dispatcher also needs to answer a privacy question, and the dispatcher can pass identity authentication and adjust the priority only when the voiceprint recognition passes and the answer question is correct. The invention can realize dynamic adjustment of priority, and has high safety and convenient use.
Description
Technical Field
The invention relates to a power dispatching technology, in particular to a dynamic priority dispatching method and a system based on voiceprint recognition.
Background
In the power dispatching system, each dispatching desk has own priority, and a high-level dispatching desk can perform operations such as strong insertion, strong disassembly and the like on a low-level dispatching desk. Typically, the priority is subordinate to the scheduler, independent of the user of the scheduler, i.e. the dispatcher. Because there are a large number of simple dispatch stations such as IP dispatch phones in the dispatch system, log-in and authentication of specific dispatchers are not supported. However, in some cases, a high-level dispatcher needs to go to a station to process the problem on site, and only a low-level dispatcher station of the station can be used for dispatching, so that the use is inconvenient. At this time, if the priority of the low-level dispatching desk can be temporarily improved, great convenience is brought to the dispatching work.
The biological identification is a technology for identifying the personal identity by utilizing the inherent physiological characteristics (such as fingerprints, faces, irises and the like) or the behavioral characteristics (such as handwriting, sound, gait and the like) of the human body, and has the advantages of high efficiency, safety, convenience and difficult counterfeiting. However, in the power dispatching system, many low-level dispatching desks have only voice communication function, and it is difficult to acquire image information such as human faces, so that the conventional biological recognition technology cannot be applied to the power dispatching system.
Disclosure of Invention
The invention aims to: aiming at the problems existing in the prior art, the invention provides a dynamic priority scheduling method and a system based on voiceprint recognition, which can temporarily and dynamically adjust 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 dispatcher identity code 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 adjustment request to a dispatching server through a priority adjustment key preset by the low-priority dispatching desk;
(3) After receiving the request, the dispatching server randomly selects a section from the prestored reference voices of a plurality of sections of texts and sends the section to the 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 carries out voiceprint recognition related to the text on the received test voice and a text related voiceprint model corresponding to each text of each dispatcher stored in advance to obtain dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times;
(6) The dispatching server randomly selects one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sends the privacy problem voices to the dispatching desk;
(7) The dispatching desk plays the privacy problem voice and returns the reply voice of the dispatcher to the dispatching server;
(8) The scheduling server invokes the prestored privacy question answer voice, carries out voiceprint recognition on the reply voice of the dispatcher, and verifies the correctness of the answer;
(9) If the voiceprint recognition is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to the priority of the current dispatcher with high priority, and sends a voice with successful dispatching priority adjustment to the dispatching desk; otherwise, sending voice refusing the priority adjustment request to the dispatching desk;
(10) In the subsequent dispatching work, the dispatching server continuously carries out voice recognition on the voice sent by the dispatching desk and the text irrelevant voice print model of each dispatcher stored in advance to obtain the identity code of the voice sent by the current dispatching desk, and once the identity code of the dispatcher who uses the dispatching desk is found to be changed, the priority of the dispatching desk is restored; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times.
Further, before step (1), the following information is pre-stored in the scheduling server:
the identity code and the corresponding priority of each dispatcher and the dispatcher station to which the dispatcher identity code is bound;
a plurality of text segments, each text segment corresponding 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 several privacy questions of each dispatcher, and the voices of the corresponding answers.
The dynamic priority scheduling server based on voiceprint recognition comprises:
a database;
the priority allocation module is used for binding the dispatcher identity code with a dispatcher used by the dispatcher according to the priority of each dispatcher and the unique identity code thereof stored in the database, and setting the priority of the dispatcher as the priority of the dispatcher;
the priority adjustment request receiving module is used for receiving an adjustment priority request sent by a preset priority adjustment key of the 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 a section from the prestored reference voices of a plurality of sections of texts after receiving the request for adjusting the priority, and sending the section to a dispatching desk of the request;
the voice print recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voice print recognition related to the text by using a text related voice print model corresponding to each text of each dispatcher prestored in the database, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times; the test voice is repeated voice of a high-priority dispatcher after the dispatcher station plays the reference voice;
the privacy problem selection module is used for randomly selecting one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the privacy problem voices to the dispatcher;
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 reply voice of the caller and verifying the correctness of the answer; the reply voice of the dispatcher is a reply of the dispatcher to the privacy problem sent by the dispatching desk;
the priority adjustment module is used for adjusting the priority of the dispatching desk to the priority of the current dispatcher with high priority when the voiceprint recognition passes and the answer is correct, and sending the successful voice of dispatching priority adjustment to the dispatching desk;
and the priority rejecting module is used for sending voice rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is not passed or the answer is incorrect.
Further, the method further comprises the following steps:
the system comprises an identity code monitoring module, a scheduling server and a scheduling platform, wherein the identity code monitoring module is used for continuously carrying out voice recognition on voice sent by the scheduling platform and a pre-stored text-independent voice pattern model of each scheduler in subsequent scheduling work, so as to obtain an identity code of the voice sent by the current scheduling platform, and recovering the priority of the scheduling platform once the change of the identity code of the scheduler using the scheduling platform is found; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times.
The dynamic priority dispatching desk based on voiceprint recognition comprises:
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 scheduler needs to use a low-priority scheduling station; each dispatcher has a priority and a unique identity code, the dispatcher identity code is bound with a used dispatcher station, and the priority of the dispatcher station is the priority of the dispatcher;
the reference voice playing module is used for playing the reference voice sent by the scheduling server, and sending repeated voices of the high-priority dispatcher to the scheduling server as test voices to be identified; the reference voice is a section randomly selected from the pre-stored reference voices of a plurality of sections of texts 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 reply voice of the scheduler 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 identified by the dispatching server; the process of the dispatch server identifying the dispatcher identity code is: the test voice and text-related voiceprint models corresponding to the texts of the schedulers stored in the database in advance are subjected to voiceprint recognition related to the texts, so that a scheduler identity code corresponding to the test voice is obtained; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times;
the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server, and the scheduling result voice is sent by the following modes: the scheduling server invokes the prestored privacy question answer voice, carries out voiceprint recognition on the reply voice of the dispatcher, and verifies the correctness of the answer; if the voiceprint recognition is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to the priority of the current dispatcher with high priority, and sends the voice with the successfully adjusted priority to the dispatching desk; otherwise, the voice refusing the request for adjusting the priority is sent to the dispatching desk.
The invention discloses a dynamic priority scheduling system based on voiceprint recognition, which comprises a scheduling server and a scheduling station, wherein the scheduling server comprises:
a database;
the priority allocation module is used for binding the dispatcher identity code with a dispatcher used by the dispatcher according to the priority of each dispatcher and the unique identity code thereof stored in the database, and setting the priority of the dispatcher as the priority of the dispatcher;
the priority adjustment request receiving module is used for receiving an adjustment priority request sent by a preset priority adjustment key of the 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 a section from the prestored reference voices of a plurality of sections of texts after receiving the request for adjusting the priority, and sending the section to a dispatching desk of the request;
the voice print recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voice print recognition related to the text by using a text related voice print model corresponding to each text of each dispatcher prestored in the database, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times; the test voice is repeated voice of a high-priority dispatcher after the dispatcher station plays the reference voice;
the privacy problem selection module is used for randomly selecting one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the privacy problem voices to the dispatcher;
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 reply voice of the caller and verifying the correctness of the answer;
the priority adjustment module is used for adjusting the priority of the dispatching desk to the priority of the current dispatcher with high priority when the voiceprint recognition passes and the answer is correct, and sending the voice with successfully adjusted dispatching priority to the dispatching desk;
and the priority rejecting module is used for sending voice rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is not passed or the answer is incorrect.
The scheduling station includes:
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 scheduler needs to use a low-priority scheduling station;
the reference voice playing module is used for playing the reference voice sent by the scheduling server, and sending repeated voices of the high-priority dispatcher to the scheduling server as test voices to be identified;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the reply voice of the scheduler 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 scheduling server further includes:
the system comprises an identity code monitoring module, a scheduling server and a scheduling platform, wherein the identity code monitoring module is used for continuously carrying out voice recognition on voice sent by the scheduling platform and a pre-stored text-independent voice pattern model of each scheduler in subsequent scheduling work, so as to obtain an identity code of the voice sent by the current scheduling platform, and recovering the priority of the scheduling platform once the change of the identity code of the scheduler using the scheduling platform is found; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times.
The beneficial effects are that: compared with the prior art, the invention has the remarkable advantages that: 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 provided by the 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 dispatcher identity code with a used dispatching desk, and sets the priority of the dispatching desk as the priority of the dispatcher.
Wherein, prior to this step, the following information is pre-stored in the scheduling server:
the identity code and the corresponding priority of each dispatcher and the dispatcher station to which the dispatcher identity code is bound;
a plurality of text segments, each text segment corresponding to a reference voice; the reference voice is generated by reading each text through 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 a plurality of times (the times are generally more than 30), and training the multi-time reading voice of each Text to obtain a Text-related voiceprint model corresponding to each Text for Text-related voiceprint recognition (TD-VPR: text-Dependent Voiceprint Recognition), so that each Text of each dispatcher corresponds to one Text-related voiceprint model; the training process of the text-independent voiceprint model is as follows: for each dispatcher, combining the read voices of all texts and training the read voices together to obtain a Text-independent voiceprint model, so that each dispatcher corresponds to one Text-independent voiceprint model and is used for Text-independent voiceprint recognition (TI-VPR: text-Independent Voiceprint Recognition);
the voices of several privacy questions of each dispatcher, and the voices of the corresponding answers. Privacy questions such as "your birth date", "your birth place (city county)", "your graduation primary school", etc. are questions known only to individuals and collect answers in the form of speech.
(2) When a dispatcher with high priority needs to use a dispatching desk with low priority, a priority adjustment key preset by the dispatching desk with low priority sends a priority adjustment request to a dispatching server.
The preset priority adjustment key may be a specific added key, or may be an existing key or a combination of keys.
(3) After receiving the request, the dispatching server randomly selects one section from the prestored reference voices of a plurality of sections of texts and sends the section to the dispatching desk.
(4) The dispatching desk plays the reference voice, and sends the repeated voice of the high-priority dispatcher to the dispatching server as the test voice to be recognized.
(5) And the dispatching server carries out voiceprint recognition related to the text on the received test voice and a pre-stored text-related voiceprint model corresponding to each text of each dispatcher to obtain a dispatcher identity code corresponding to the test voice.
It should be noted in this step that, in general, only the high priority dispatcher is allowed to use the low priority dispatcher and the low priority dispatcher is not allowed to use the high priority dispatcher, so if the dispatcher's priority is lower than the dispatcher's priority, the adjustment of the priority will not be allowed, the voice rejecting the request for adjusting the priority will be sent directly to the dispatcher, and the flow will be ended.
(6) The dispatching server randomly selects one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sends the privacy problem voices to the dispatching desk.
(7) The dispatching desk plays the privacy problem voice and returns the reply voice of the dispatcher to the dispatching server.
(8) The dispatching server calls the prestored privacy question answer voice, carries out voiceprint recognition on the reply voice of the dispatcher, and verifies the correctness of the answer.
(9) If the voiceprint recognition is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to the priority of the current dispatcher with high priority, and sends a voice with successful dispatching priority adjustment to the dispatching desk; otherwise, the voice refusing the request for adjusting the priority is sent to the dispatching desk.
(10) In the subsequent dispatching work, the dispatching server continuously carries out voice recognition on the voice sent by the dispatching desk and the text irrelevant voice print model of each dispatcher stored in advance, so as to obtain the identity code of the voice sent by the current dispatching desk, and once the identity code of the dispatcher who uses the dispatching desk is found to be changed, the priority of the dispatching desk is restored.
The embodiment further provides a dynamic priority scheduling server based on voiceprint recognition based on the method, which comprises the following steps:
a database;
the priority allocation module is used for binding the dispatcher identity code with a dispatcher used by the dispatcher according to the priority of each dispatcher and the unique identity code thereof stored in the database, and setting the priority of the dispatcher as the priority of the dispatcher;
the priority adjustment request receiving module is used for receiving an adjustment priority request sent by a preset priority adjustment key of the 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 a section from the prestored reference voices of a plurality of sections of texts after receiving the request for adjusting the priority, and sending the section to a dispatching desk of the request;
the voice print recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voice print recognition related to the text by using a text related voice print model corresponding to each text of each dispatcher prestored in the database, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times; the test voice is repeated voice of a high-priority dispatcher after the dispatcher station plays the reference voice;
the privacy problem selection module is used for randomly selecting one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the privacy problem voices to the dispatcher;
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 reply voice of the caller and verifying the correctness of the answer; the reply voice of the dispatcher is a reply of the dispatcher to the privacy problem sent by the dispatching desk;
the priority adjustment module is used for adjusting the priority of the dispatching desk to the priority of the current dispatcher with high priority when the voiceprint recognition passes and the answer is correct, and sending the successful voice of dispatching priority adjustment to the dispatching desk;
the priority rejecting module is used for sending a voice rejecting the priority adjusting request to the dispatching desk when the voiceprint recognition fails or the answer is incorrect;
the system comprises an identity code monitoring module, a scheduling server and a scheduling platform, wherein the identity code monitoring module is used for continuously carrying out voice recognition on voice sent by the scheduling platform and a pre-stored text-independent voice pattern model of each scheduler in subsequent scheduling work, so as to obtain an identity code of the voice sent by the current scheduling platform, and recovering the priority of the scheduling platform once the change of the identity code of the scheduler using the scheduling platform is found; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times.
The embodiment also provides a dynamic priority dispatching desk based on voiceprint recognition, which comprises:
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 scheduler needs to use a low-priority scheduling station; each dispatcher has a priority and a unique identity code, the dispatcher identity code is bound with a used dispatcher station, and the priority of the dispatcher station is the priority of the dispatcher;
the reference voice playing module is used for playing the reference voice sent by the scheduling server, and sending repeated voices of the high-priority dispatcher to the scheduling server as test voices to be identified; the reference voice is a section randomly selected from the pre-stored reference voices of a plurality of sections of texts 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 reply voice of the scheduler 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 identified by the dispatching server; the process of the dispatch server identifying the dispatcher identity code is: the test voice and text-related voiceprint models corresponding to the texts of the schedulers stored in the database in advance are subjected to voiceprint recognition related to the texts, so that a scheduler identity code corresponding to the test voice is obtained; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times;
the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server, and the scheduling result voice is sent by the following modes: the scheduling server invokes the prestored privacy question answer voice, carries out voiceprint recognition on the reply voice of the dispatcher, and verifies the correctness of the answer; if the voiceprint recognition is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to the priority of the current dispatcher with high priority, and sends the voice with the successfully adjusted priority to the dispatching desk; otherwise, the voice refusing the request for adjusting the priority is sent to the dispatching desk.
The embodiment also provides a dynamic priority scheduling system based on voiceprint recognition, which comprises a scheduling server and a scheduling station, wherein the scheduling server comprises:
a database;
the priority allocation module is used for binding the dispatcher identity code with a dispatcher used by the dispatcher according to the priority of each dispatcher and the unique identity code thereof stored in the database, and setting the priority of the dispatcher as the priority of the dispatcher;
the priority adjustment request receiving module is used for receiving an adjustment priority request sent by a preset priority adjustment key of the 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 a section from the prestored reference voices of a plurality of sections of texts after receiving the request for adjusting the priority, and sending the section to a dispatching desk of the request;
the voice print recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voice print recognition related to the text by using a text related voice print model corresponding to each text of each dispatcher prestored in the database, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times; the test voice is repeated voice of a high-priority dispatcher after the dispatcher station plays the reference voice;
the privacy problem selection module is used for randomly selecting one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the privacy problem voices to the dispatcher;
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 reply voice of the caller and verifying the correctness of the answer;
the priority adjustment module is used for adjusting the priority of the dispatching desk to the priority of the current dispatcher with high priority when the voiceprint recognition passes and the answer is correct, and sending the voice with successfully adjusted dispatching priority to the dispatching desk;
the priority rejecting module is used for sending a voice rejecting the priority adjusting request to the dispatching desk when the voiceprint recognition fails or the answer is incorrect;
the system comprises an identity code monitoring module, a scheduling server and a scheduling platform, wherein the identity code monitoring module is used for continuously carrying out voice recognition on voice sent by the scheduling platform and a pre-stored text-independent voice pattern model of each scheduler in subsequent scheduling work, so as to obtain an identity code of the voice sent by the current scheduling platform, and recovering the priority of the scheduling platform once the change of the identity code of the scheduler using the scheduling platform is found; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times;
the scheduling station includes:
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 scheduler needs to use a low-priority scheduling station;
the reference voice playing module is used for playing the reference voice sent by the scheduling server, and sending repeated voices of the high-priority dispatcher to the scheduling server as test voices to be identified;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the reply voice of the scheduler to the scheduling server;
and the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server.
The above disclosure is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention, which is defined by 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 dispatcher identity code 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 adjustment request to a dispatching server through a priority adjustment key preset by the low-priority dispatching desk;
(3) After receiving the request, the dispatching server randomly selects a section from the prestored reference voices of a plurality of sections of texts and sends the section to the 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 carries out voiceprint recognition related to the text on the received test voice and a text related voiceprint model corresponding to each text of each dispatcher stored in advance to obtain dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times;
(6) The dispatching server randomly selects one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sends the privacy problem voices to the dispatching desk;
(7) The dispatching desk plays the privacy problem voice and returns the reply voice of the dispatcher to the dispatching server;
(8) The scheduling server invokes the prestored privacy question answer voice, carries out voiceprint recognition on the reply voice of the dispatcher, and verifies the correctness of the answer;
(9) If the voiceprint recognition is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to the priority of the current dispatcher with high priority, and sends a voice with successful dispatching priority adjustment to the dispatching desk; otherwise, the voice refusing the request for adjusting the priority is sent to the dispatching desk.
2. The voiceprint recognition based dynamic priority scheduling method of claim 1, wherein: the step (9) further comprises the following steps:
(10) In the subsequent dispatching work, the dispatching server continuously carries out voice recognition on the voice sent by the dispatching desk and the text irrelevant voice print model of each dispatcher stored in advance to obtain the identity code of the voice sent by the current dispatching desk, and once the identity code of the dispatcher who uses the dispatching desk is found to be changed, the priority of the dispatching desk is restored; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times.
3. The voiceprint recognition based dynamic priority scheduling method of claim 1, wherein: prior to step (1), pre-storing the following information in the scheduling server:
the identity code and the corresponding priority of each dispatcher and the dispatcher station to which the dispatcher identity code is bound;
a plurality of text segments, each text segment corresponding 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 several privacy questions of each dispatcher, and the voices of the corresponding answers.
4. A dynamic priority scheduling server based on voiceprint recognition, comprising:
a database;
the priority allocation module is used for binding the dispatcher identity code with a dispatcher used by the dispatcher according to the priority of each dispatcher and the unique identity code thereof stored in the database, and setting the priority of the dispatcher as the priority of the dispatcher;
the priority adjustment request receiving module is used for receiving an adjustment priority request sent by a preset priority adjustment key of the 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 a section from the prestored reference voices of a plurality of sections of texts after receiving the request for adjusting the priority, and sending the section to a dispatching desk of the request;
the voice print recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voice print recognition related to the text by using a text related voice print model corresponding to each text of each dispatcher prestored in the database, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times; the test voice is repeated voice of a high-priority dispatcher after the dispatcher station plays the reference voice;
the privacy problem selection module is used for randomly selecting one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the privacy problem voices to the dispatcher;
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 reply voice of the caller and verifying the correctness of the answer; the reply voice of the dispatcher is a reply of the dispatcher to the privacy problem sent by the dispatching desk;
the priority adjustment module is used for adjusting the priority of the dispatching desk to the priority of the current dispatcher with high priority when the voiceprint recognition passes and the answer is correct, and sending the successful voice of dispatching priority adjustment to the dispatching desk;
and the priority rejecting module is used for sending voice rejecting the priority adjustment request to the dispatching desk when the voiceprint recognition is not passed or the answer is incorrect.
5. The voiceprint recognition based dynamic priority scheduling server of claim 4, further comprising:
the system comprises an identity code monitoring module, a scheduling server and a scheduling platform, wherein the identity code monitoring module is used for continuously carrying out voice recognition on voice sent by the scheduling platform and a pre-stored text-independent voice pattern model of each scheduler in subsequent scheduling work, so as to obtain an identity code of the voice sent by the current scheduling platform, and recovering the priority of the scheduling platform once the change of the identity code of the scheduler using the scheduling platform is found; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many times.
6. A dynamic priority scheduler based on voiceprint recognition, comprising:
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 scheduler needs to use a low-priority scheduling station; each dispatcher has a priority and a unique identity code, the dispatcher identity code is bound with a used dispatcher station, and the priority of the dispatcher station is the priority of the dispatcher;
the reference voice playing module is used for playing the reference voice sent by the scheduling server, and sending repeated voices of the high-priority dispatcher to the scheduling server as test voices to be identified; the reference voice is a section randomly selected from the pre-stored reference voices of a plurality of sections of texts 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 reply voice of the scheduler 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 identified by the dispatching server; the process of the dispatch server identifying the dispatcher identity code is: the test voice and text-related voiceprint models corresponding to the texts of the schedulers stored in the database in advance are subjected to voiceprint recognition related to the texts, so that a scheduler identity code corresponding to the test voice is obtained; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times;
the scheduling result playing module is used for playing the scheduling result voice sent by the scheduling server, and the scheduling result voice is sent by the following modes: the scheduling server invokes the prestored privacy question answer voice, carries out voiceprint recognition on the reply voice of the dispatcher, and verifies the correctness of the answer; if the voiceprint recognition is passed and the answer is correct, the dispatching server adjusts the priority of the dispatching desk to the priority of the current dispatcher with high priority, and sends the voice with the successfully adjusted priority to the dispatching desk; otherwise, the voice refusing the request for adjusting the priority is sent to the dispatching desk.
7. A dynamic priority scheduling system based on voiceprint recognition is characterized in that: the method comprises a scheduling server and a scheduling station, wherein the scheduling server comprises the following steps:
a database;
the priority allocation module is used for binding the dispatcher identity code with a dispatcher used by the dispatcher according to the priority of each dispatcher and the unique identity code thereof stored in the database, and setting the priority of the dispatcher as the priority of the dispatcher;
the priority adjustment request receiving module is used for receiving an adjustment priority request sent by a preset priority adjustment key of the 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 a section from the prestored reference voices of a plurality of sections of texts after receiving the request for adjusting the priority, and sending the section to a dispatching desk of the request;
the voice print recognition module is used for receiving the test voice sent by the dispatching desk, carrying out voice print recognition related to the text by using a text related voice print model corresponding to each text of each dispatcher prestored in the database, and obtaining dispatcher identity codes corresponding to the test voice; the text-related voiceprint model is obtained by training voices of each dispatcher when reading each text for many times; the test voice is repeated voice of a high-priority dispatcher after the dispatcher station plays the reference voice;
the privacy problem selection module is used for randomly selecting one from a plurality of pre-stored privacy problem voices of the dispatcher according to the identified dispatcher identity code and sending the privacy problem voices to the dispatcher;
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 reply voice of the caller and verifying the correctness of the answer;
the priority adjustment module is used for adjusting the priority of the dispatching desk to the priority of the current dispatcher with high priority when the voiceprint recognition passes and the answer is correct, and sending the voice with successfully adjusted dispatching priority to the dispatching desk;
the priority rejecting module is used for sending a voice rejecting the priority adjusting request to the dispatching desk when the voiceprint recognition fails or the answer is incorrect;
the scheduling station includes:
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 scheduler needs to use a low-priority scheduling station;
the reference voice playing module is used for playing the reference voice sent by the scheduling server, and sending repeated voices of the high-priority dispatcher to the scheduling server as test voices to be identified;
the privacy problem voice playing module is used for playing the privacy problem voice sent by the scheduling server and returning the reply voice of the scheduler 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 scheduling server further includes:
the system comprises an identity code monitoring module, a scheduling server and a scheduling platform, wherein the identity code monitoring module is used for continuously carrying out voice recognition on voice sent by the scheduling platform and a pre-stored text-independent voice pattern model of each scheduler in subsequent scheduling work, so as to obtain an identity code of the voice sent by the current scheduling platform, and recovering the priority of the scheduling platform once the change of the identity code of the scheduler using the scheduling platform is found; the text-independent voiceprint model is obtained by training voices of each dispatcher when reading all texts for many 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 CN112214298A (en) | 2021-01-12 |
| CN112214298B true 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 |
|---|
| 一种防范电网调度员语音失误的语音辅助系统;侯勇;王铮;舒乔晔;傅山;;微型电脑应用(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112214298A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2003058190A (en) | Personal authentication system | |
| CN101467204B (en) | Method and system for bio-metric voice print authentication | |
| EP0746846B1 (en) | Voice-controlled account access over a telephone network | |
| AU2006306790B2 (en) | System and method of subscription identity authentication utilizing multiple factors | |
| EP0953972B1 (en) | Simultaneous speaker-independent voice recognition and verification over a telephone network | |
| US7240007B2 (en) | Speaker authentication by fusion of voiceprint match attempt results with additional information | |
| EP3159820A1 (en) | Authentication device, authentication system, authentication method, and program storage medium | |
| KR20190045099A (en) | Voice Authentication System and Method | |
| CN101494540A (en) | Remote voice identification authentication system and method | |
| CN104426998A (en) | Vehicle telematics unit and method of operating the same | |
| CN101697514A (en) | Method and system for identity authentication | |
| CN104104664A (en) | Method, server, client and system for verifying verification code | |
| US20080195395A1 (en) | System and method for telephonic voice and speech authentication | |
| CN106330983A (en) | Identity authentication method, user's client terminal and system | |
| KR20160133463A (en) | Method and device for identifying or authenticating a person and/or an object using dynamic acoustic security information | |
| CN109785834A (en) | A kind of voice data sample acquisition system and its method based on identifying code | |
| 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 | |
| CN112214298B (en) | Dynamic priority scheduling method and system based on voiceprint recognition | |
| ATE340399T1 (en) | PATTERN PROCESSING SYSTEM SPECIFIC TO A GROUP OF USERS | |
| JP2000067005A (en) | Method for confirming person himself and device using the same method and record medium recording program for controlling the same device | |
| JP2003087860A (en) | Method and system for personal identification in mobile communication, and personal identification device | |
| Kim | User experience validation using the honeycomb model in the requirements development stage | |
| KR20190050659A (en) | Method for Evaluating Response of Heterogeneous Language Speaking | |
| JP2002311992A (en) | Method and device for speaker authentication | |
| US20220139402A1 (en) | Voice authentication apparatus, voice authentication method, and a recording medium |
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 |