CN109256114B - Voice alarm method for power grid monitoring and dispatching - Google Patents
Voice alarm method for power grid monitoring and dispatching Download PDFInfo
- Publication number
- CN109256114B CN109256114B CN201811003840.8A CN201811003840A CN109256114B CN 109256114 B CN109256114 B CN 109256114B CN 201811003840 A CN201811003840 A CN 201811003840A CN 109256114 B CN109256114 B CN 109256114B
- Authority
- CN
- China
- Prior art keywords
- alarm
- voice
- text
- equipment information
- conversion
- 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
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
Abstract
The invention provides a voice alarm method for monitoring and scheduling a power grid, which belongs to the field of scheduling and comprises the steps of acquiring equipment information based on a monitoring service interface; identifying the received equipment information according to different data types; and generating alarm voice for the equipment information marked as the accident, and sending the generated alarm voice to the corresponding processing personnel. By introducing the virtual customer service, the real combination of technology and service is realized, the dispatcher returns to more important work, the higher value is exerted, the increasing requirement pressure of basic level personnel is relieved, the dispatching screen monitoring operation efficiency is improved, and the work flow is standardized. The outgoing call informs the dispatcher or the field operation operator. The dispatcher and the field operation personnel confirm and feed back according to the received alarm content, execute related operations, and inform the related personnel in other multimedia forms such as short messages and pictures by the intelligent screen monitoring robot aiming at some special conditions, so that the man-machine interaction with better experience effect is realized.
Description
Technical Field
The invention belongs to the field of scheduling, and particularly relates to a voice alarm method for power grid monitoring and scheduling.
Background
With the rapid development of the domestic urbanization process, the construction of the urban power distribution network is also carried out fiercely. And further, the radiation surface of the power distribution network is wider and wider, the structure is more and more complex, the asset scale is exponentially increased, and great pressure is brought to dispatchers and field engineering personnel. In some periods (such as the period of summer meeting the peak), various signals such as alarms, out-of-limit signals, abnormity signals, deflection signals and the like on a dispatching remote monitoring large screen emerge in an explosive mode, a large amount of manpower is consumed for reading, analyzing, dispatching, following and disposing alarm information, the efficiency is low, and the real value of dispatching personnel is not exerted.
In recent years, with the continuous development of artificial intelligence technology, an AI technology is tried to replace manual processing of regular, repetitive and low-service-value work in many fields, so that on one hand, the input cost of personnel can be relieved, and on the other hand, the personnel can be liberated from the low-value work to play a greater value. At present, the power grid dispatching monitoring screen mainly depends on manpower, and dispatching personnel watch the power grid for 24 hours to process various found alarm signals.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides the voice alarm method for monitoring and dispatching the power grid, which can relieve the increasing demand pressure of basic level personnel, improve the operation efficiency of dispatching and monitoring screens and standardize the working process. .
In order to achieve the technical purpose, the invention provides a voice alarm method for power grid monitoring and scheduling, which comprises the following steps:
acquiring equipment information including alarm signal data, equipment ledger data, equipment defect data and personnel contact information based on a monitoring service interface;
identifying the received equipment information according to different data types;
and generating alarm voice for the equipment information marked as the accident, and sending the generated alarm voice to the corresponding processing personnel.
Optionally, the identifying the received device information according to different data types includes:
the equipment information including protection action, accident trip and ground fault is marked as accident signals;
marking the equipment information stored in the OMS defect library as an abnormal signal;
marking the equipment information of main transformer switches and line switch deflection stored in a D5000 equipment library as abnormal signals;
and marking the equipment information which belongs to the condition that the voltage and the system reactive power cannot be regulated when the AVC system is abnormally operated as an out-of-limit signal.
Optionally, the generating an alarm voice for the device information identified as the accident includes:
determining an alarm text according to the equipment information marked as the accident;
and obtaining the alarm voice corresponding to the alarm text by means of a neural network voice synthesis technology.
Optionally, the determining an alarm text according to the device information marked as the accident includes:
planning the content of the alarm content, and determining and constructing the alarm content and the structure to be generated;
performing word selection and optimized aggregation to generate an expression based on the details of the clearly defined planning text in the microscopic planning;
when the surface layer is generated, the structure and language of the generated text are mainly realized, namely, the text description after micro planning is mapped to the alarm text consisting of characters, punctuations and structural annotation information.
Optionally, the obtaining, by using a neural network speech synthesis technology, an alarm speech corresponding to the alarm text includes:
determining a conversion strategy from the alarm text to the voice, training a neural network based on the determined conversion strategy, and obtaining a source-target conversion network of each syllable;
and converting the alarm text based on the achieved conversion network to obtain the alarm voice corresponding to the alarm text.
Optionally, the determining a conversion policy from the alert text to the speech includes:
selecting a parameter LSF representing a frequency spectrum of a current mainstream to carry out voice signal processing to obtain a frequency spectrum distribution condition;
according to the scale of the existing corpus, mapping network model construction is carried out by using syllables as units;
normalizing each parameter input into the neural network;
and when the converted parameters do not accord with the rank ordering, directly replacing the parameters by the vectors closest to the target linguistic data.
Optionally, the converting the alarm text based on the achieved conversion network to obtain the alarm voice corresponding to the alarm text includes:
selecting a corresponding deep neural network from the labeling information of the parameters to be converted for conversion, and simultaneously selecting frequency spectrums of the synthesized corpus and the original corpus for unified normalization processing;
the normalized frequency spectrum to be converted is used as an input parameter of a corresponding conversion network, and the frequency spectrum after conversion is obtained through the output of a deep neural network;
judging whether the converted frequency spectrum has the characteristic of order arrangement, if not, replacing the frame with the frequency spectrum of the original corpus to finally obtain a stable converted frequency spectrum, and finally synthesizing through a filter to obtain the alarm voice.
The technical scheme provided by the invention has the beneficial effects that:
by introducing the virtual customer service, the real combination of technology and service is realized, the dispatcher returns to more important work, the higher value is exerted, the increasing requirement pressure of basic level personnel is relieved, the dispatching screen monitoring operation efficiency is improved, and the work flow is standardized. The outgoing call informs the dispatcher or the field operation operator. The dispatcher and the field operating personnel confirm and feed back according to the received alarm content, execute related operations, and inform the related personnel of the intelligent screen monitoring robot in other multimedia forms such as short messages and pictures according to some special conditions, so that man-machine interaction with better experience effect is realized.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flow diagram of a voice alarm method for power grid monitoring and scheduling according to the present invention.
Detailed Description
To make the structure and advantages of the present invention clearer, the structure of the present invention will be further described with reference to the accompanying drawings.
Example one
The invention provides a voice alarm method for monitoring and dispatching a power grid, which comprises the following steps of:
11. acquiring equipment information including alarm signal data, equipment ledger data, equipment defect data and personnel contact information based on a monitoring service interface;
12. identifying the received equipment information according to different data types;
13. and generating alarm voice for the equipment information marked as the accident, and sending the generated alarm voice to the corresponding processing personnel.
In implementation, the voice alarm method provided by this embodiment can implement distribution network scheduling signal processing, analysis and diagnosis, and further can output a core alarm field. Specifically, a natural language generation model facing a dispatching monitor screen scene is constructed by training the language material of a service field, and conversation text in a natural language form can be automatically generated based on a structured alarm field.
In the process of realizing voice generation, based on the deep neural network voice synthesis technology, the voice synthesis of the content of the alarm text is realized, and the communication with other operators is completed. By adopting the text generation and voice synthesis technology, the remote monitoring and analysis result can be reported to related workers in the form of multimedia such as telephone, text, pictures and the like.
In addition, the voice warning method provided by the embodiment is embodied in the form of virtual customer service or an intelligent robot in the actual use process.
The intelligent robot system related to the embodiment relates to four layers
(1) The original system layer of the service: the data source of the AI engine is mainly used for providing relevant service data such as alarm signal information, equipment ledger information, equipment defect information and the like for service judgment and analysis;
(2) An artificial intelligence engine layer: as a core module of the intelligent screen monitoring robot, besides an AI basic engine, on the basis of an artificial intelligence technology, training and constructing various AI application engines facing the distribution network scheduling field under the guidance of a service expert;
(3) The AI engine invokes the service layer: various AI engine services are provided for the application functions of the upper layer;
(4) And application functional layers: a virtual monitoring robot having a service analysis function and a call receiving and making function is provided.
The real combination of technology and service is realized by introducing the virtual customer service at the front edge; from the social perspective, the dispatching personnel can return to more important work, so that the greater value is exerted, the increasing demand pressure of basic level personnel is relieved, the dispatching screen monitoring operation efficiency is improved, and the working process is standardized; basically, more than 90% of the manual processing work of the alarm information can be replaced, and the labor intensity of the manual screen monitoring work is greatly reduced. And through the deployed telephone system and the acquired personnel information, the out-calling telephone informs a dispatcher or a field operation operator. The dispatcher and the field operation personnel confirm and feed back according to the received alarm content, execute related operations, and inform the related personnel in other multimedia forms such as short messages and pictures by the intelligent screen monitoring robot aiming at some special conditions, so that the man-machine interaction with better experience effect is realized.
Specifically, the identifying the received device information in step 12 according to different data types includes:
121. the equipment information including protection action, accident trip and ground fault is marked as accident signals;
122. marking the equipment information stored in the OMS defect library as an abnormal signal;
123. marking the main transformer switch and line switch deflection equipment information stored in a D5000 equipment library as abnormal signals;
124. and marking the equipment information which belongs to the condition that the voltage and the system reactive power cannot be regulated when the AVC system is abnormally operated as an out-of-limit signal.
In implementation, service data is acquired through a data interface developed by a service system, different alarm types are identified according to the acquired alarm data and a known service rule, and the current processing logic is as follows:
accident signals mainly comprise signals of protection actions, accident tripping, grounding faults and the like, and are directly informed to personnel of equipment operation units for inspection and to current value regulators;
comparing the abnormal signals with an OMS defect library, wherein the signals belong to automatic skipping of defect processing on the way, and the signals do not belong to personnel inspection of notification equipment operation units for on-the-way processing, and informing a current value regulator;
the displacement signal is compared with a D5000 equipment library, the displacement signals (capacitor, reactor switching and main transformer gear adjustment) which do not belong to the main transformer switch and the line switch are automatically skipped, and the belonging notification equipment operation unit personnel checks and notifies a current value regulator;
the out-of-limit signal mainly aims at two types of voltage out-of-limit and reactive out-of-limit, and generally, an AVC system can automatically adjust the voltage out-of-limit and reactive out-of-limit, but when the AVC system is abnormally operated, the voltage and the reactive of the system cannot be accurately and effectively adjusted. In the intelligent monitoring screen, the intelligent robot tracks the out-of-limit signal, and informs a regulator to perform manual regulation after the continuous out-of-limit time is longer than a set value (delay processing).
Optionally, the generating of the alarm voice for the device information identified as the accident in step 13 includes:
131. determining an alarm text according to the equipment information marked as the accident;
132. and obtaining the alarm voice corresponding to the alarm text by means of a neural network voice synthesis technology.
Wherein step 131 comprises:
1311. planning the content of the alarm content, and determining and constructing the alarm content and the structure to be generated;
1312. performing word selection and optimization aggregation to generate an expression based on the details of the clearly defined planning text in the microscopic planning;
1313. when the surface layer is generated, the structure and language of the generated text are mainly realized, namely, the text description after micro planning is mapped to the alarm text consisting of characters, punctuations and structural annotation information.
In implementation, the intelligent screen monitoring robot mainly monitors four types of alarm signals, namely accidents, abnormity, out-of-limit and displacement. And automatically generating corresponding alarm voice texts according to different alarm types according to the semantics and rules of the scheduling monitoring service based on the acquired signal data, the ledger data, the defect information and the like. The method applies the classical pipeline model in NLG, and has better robustness, independence and reusability. The steps of generating the alarm voice text are as follows:
1) And determining and constructing the alarm content and structure to be generated through content planning.
2) The details of a planning text, such as ledger information, position information, defect information and the like of alarm equipment, are clearly defined in the microscopic planning, and further word selection, optimized aggregation and expression generation are required to be submitted. The contents studied by the device generate an expression (template) as follows:
XX operation and maintenance class, XX time is XX minute, XX changes XX signal and please go to the site for inspection;
XX power supply station, XX time is XX division, XX line protection action, switch tripping, success (or failure) of reclosing, XX time is XX division, and accident line patrol is allowed;
when the XX signal appears, the XX operation and maintenance class is informed to check;
when the XX line protection action, the switch trip and the coincidence are successful (or fail), the XX operation and maintenance class is informed to check, and the XX accident line inspection is allowed;
when the XX variable voltage exceeds the limit, the regulation is required in time.
…
In the step, the pipeline model is simultaneously referred, and the microscopic content planning is completed by selecting words, aggregating and submitting to generate expressions.
a) Selecting words: the context environment, the interaction target, the actual factor and the like need to be considered when selecting words in the application, the words selected in the device need to meet the scheduling and monitoring service scene, such as equipment name, alarm type and the like, and the grammatical structure needs to meet the daily conversation habit of a scheduler;
b) Polymerization: redundant information among sentences is eliminated, readability of texts is increased, grammatical structures of alarm contents have general standard format requirements, and the short sentences are combined by directly utilizing connecting words in a simple connection mode.
c) Submitting and generating an expression: after the two steps are realized, the submitted and generated expression mainly makes the expression of the alarm content have more language colors, for example, repeated reference is reduced, and the readability of the whole sentence is increased.
3) When the surface layer is generated, the structure and language of the generated text are mainly realized, namely the text description after micro planning is mapped to the surface layer text consisting of characters, punctuations and structural annotation information.
And forming the final text content to be alarmed through the three large steps.
Optionally, step 132 includes:
1321. determining a conversion strategy from the alarm text to the voice, training a neural network based on the determined conversion strategy, and obtaining a source-target conversion network of each syllable;
1322. and converting the alarm text based on the achieved conversion network to obtain the alarm voice corresponding to the alarm text.
The step 1311 of determining the conversion policy from the alert text to the voice includes:
selecting a parameter LSF (least squares) representing a frequency spectrum of a current mainstream to perform voice signal processing to obtain a frequency spectrum distribution condition;
according to the scale of the existing corpus, mapping network model construction is carried out by using syllables as units;
normalizing each parameter input into the neural network;
and when the converted parameters do not accord with the rank ordering, directly replacing the parameters by the vectors closest to the target linguistic data.
In the implementation, the frequency spectrum parameters of the parallel linguistic data with the same syllable are selected from the synthesized voice and the original linguistic data according to the marking information of the parameters to be converted, the normalization processing is uniformly carried out after time alignment, and the obtained normalization parameters are respectively used as the input parameters and the output parameters of the deep neural network to learn. And obtaining a source-target conversion network of each syllable.
A corresponding step 1312 includes:
selecting a corresponding deep neural network from the labeling information of the parameters to be converted for conversion, and simultaneously selecting frequency spectrums of the synthesized corpus and the original corpus for unified normalization processing;
the normalized frequency spectrum to be converted is used as an input parameter of a corresponding conversion network, and the frequency spectrum after conversion is obtained through the output of a deep neural network;
judging whether the converted frequency spectrum has the characteristic of order arrangement, if not, replacing the frame with the frequency spectrum of the original corpus to finally obtain a stable converted frequency spectrum, and finally synthesizing through a filter to obtain the alarm voice.
In the implementation, the corresponding deep neural network is selected from the labeled information of the parameters to be converted for conversion, and the frequency spectrums of the synthesized corpus and the original corpus are simultaneously selected for unified normalization processing. And the normalized frequency spectrum to be converted is used as an input parameter of the corresponding conversion network, and the frequency spectrum after conversion is obtained through the output of the deep neural network. Judging whether the converted frequency spectrum has the characteristic of order arrangement, if not, replacing the frame with the frequency spectrum of the original corpus to finally obtain a stable converted frequency spectrum, and finally synthesizing through a filter. Therefore, under the condition of limited training parameters, the steps of training, conversion and synthesis can be completed, and the effect of improving the tone quality is achieved.
The invention provides a voice alarm method for monitoring and scheduling a power grid, which comprises the steps of acquiring equipment information based on a monitoring service interface; identifying the received equipment information according to different data types; and generating alarm voice for the equipment information marked as the accident, and sending the generated alarm voice to the corresponding processing personnel. By introducing the virtual customer service, the real combination of technology and service is realized, the dispatcher returns to more important work, the higher value is exerted, the increasing requirement pressure of basic level personnel is relieved, the dispatching screen monitoring operation efficiency is improved, and the work flow is standardized. The outgoing call informs the dispatcher or the field operation operator. The dispatcher and the field operating personnel confirm and feed back according to the received alarm content, execute related operations, and inform the related personnel of the intelligent screen monitoring robot in other multimedia forms such as short messages and pictures according to some special conditions, so that man-machine interaction with better experience effect is realized.
The above embodiments have been described with reference to the accompanying drawings, which are not intended to limit the scope of the invention.
The above description is intended to be illustrative of the present invention and should not be taken as limiting the invention, as the invention is intended to cover various modifications, equivalents, improvements, and equivalents, which may be made within the spirit and scope of the present invention.
Claims (5)
1. The voice alarm method for power grid monitoring and dispatching is characterized by comprising the following steps:
acquiring equipment information including alarm signal data, equipment ledger data, equipment defect data and personnel contact information based on a monitoring service interface;
identifying the received equipment information according to different data types;
generating alarm voice for the equipment information marked as the accident, and sending the generated alarm voice to corresponding processing personnel;
the generating of the alarm voice for the equipment information marked as the accident includes:
determining an alarm text according to the equipment information marked as the accident;
obtaining an alarm voice corresponding to the alarm text by means of a neural network voice synthesis technology;
the determining of the alarm text according to the equipment information marked as the accident comprises the following steps:
planning the content of the alarm content, and determining and constructing the alarm content and the structure to be generated;
performing word selection and optimization aggregation to generate an expression based on the details of the clearly defined planning text in the microscopic planning;
when the surface layer is generated, the structure and language of the generated text are realized, namely the text description after micro planning is mapped to the alarm text consisting of characters, punctuations and structural annotation information.
2. The voice alarm method for power grid monitoring and dispatching according to claim 1, wherein the identifying the received device information according to different data types comprises: equipment information including protection actions, accident tripping and ground faults is marked as accident signals.
3. The method for voice alarm of power grid monitoring and dispatching according to claim 1, wherein obtaining the alarm voice corresponding to the alarm text by means of a neural network voice synthesis technology comprises:
determining a conversion strategy from the alarm text to the voice, training a neural network based on the determined conversion strategy, and obtaining a source-target conversion network of each syllable;
and converting the alarm text based on the achieved conversion network to obtain the alarm voice corresponding to the alarm text.
4. The voice alarm method for power grid monitoring and dispatching according to claim 3, wherein the determining of the conversion strategy from the alarm text to the voice comprises:
selecting a parameter LSF (least squares) representing a frequency spectrum of a current mainstream to perform voice signal processing to obtain a frequency spectrum distribution condition;
according to the scale of the existing corpus, mapping network model construction is carried out by using syllables as units;
normalizing each parameter input into the neural network;
and when the converted parameters do not accord with the rank ordering, directly replacing the parameters by the vectors closest to the target linguistic data.
5. The voice alarm method for power grid monitoring and scheduling according to claim 4, wherein the converting the alarm text based on the achieved conversion network to obtain the alarm voice corresponding to the alarm text comprises:
selecting a corresponding deep neural network from the labeling information of the parameters to be converted for conversion, and simultaneously selecting frequency spectrums of the synthesized corpus and the original corpus for unified normalization processing; the normalized frequency spectrum to be converted is used as an input parameter of a corresponding conversion network, and the frequency spectrum after conversion is obtained through the output of a deep neural network; judging whether the converted frequency spectrum has the characteristic of order arrangement, if not, replacing the frame with the frequency spectrum of the original corpus to finally obtain a stable converted frequency spectrum, and finally synthesizing through a filter to obtain the alarm voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811003840.8A CN109256114B (en) | 2018-08-30 | 2018-08-30 | Voice alarm method for power grid monitoring and dispatching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811003840.8A CN109256114B (en) | 2018-08-30 | 2018-08-30 | Voice alarm method for power grid monitoring and dispatching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109256114A CN109256114A (en) | 2019-01-22 |
| CN109256114B true CN109256114B (en) | 2022-12-13 |
Family
ID=65049815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811003840.8A Active CN109256114B (en) | 2018-08-30 | 2018-08-30 | Voice alarm method for power grid monitoring and dispatching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109256114B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111128144A (en) * | 2019-10-16 | 2020-05-08 | 国网浙江省电力有限公司金华供电公司 | Voice power grid dispatching system and method |
| CN112468668A (en) * | 2020-11-24 | 2021-03-09 | 国网河南省电力公司南阳供电公司 | Telephone alarming method and system of power dispatching monitoring system |
| CN113205799A (en) * | 2021-03-24 | 2021-08-03 | 合肥佳讯科技有限公司 | Alarm processing method based on voice recognition |
| CN113447744A (en) * | 2021-06-28 | 2021-09-28 | 国网福建省电力有限公司福州供电公司 | Equipment abnormity alarm event synthesis method of power monitoring system based on signal analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750795A (en) * | 2012-06-21 | 2012-10-24 | 江苏省电力公司苏州供电公司 | Acousto-optic alarm device |
| CN104811327A (en) * | 2014-01-26 | 2015-07-29 | 中国移动通信集团江西有限公司 | Monitoring warning voice automatic notification method and device |
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
-
2018
- 2018-08-30 CN CN201811003840.8A patent/CN109256114B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750795A (en) * | 2012-06-21 | 2012-10-24 | 江苏省电力公司苏州供电公司 | Acousto-optic alarm device |
| CN104811327A (en) * | 2014-01-26 | 2015-07-29 | 中国移动通信集团江西有限公司 | Monitoring warning voice automatic notification method and device |
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109256114A (en) | 2019-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109256114B (en) | Voice alarm method for power grid monitoring and dispatching | |
| CN105574652B (en) | Intelligent power distribution network planning big data management and control system and method | |
| CN111326153A (en) | Power grid intelligent regulation and control auxiliary robot interaction method based on semantic understanding | |
| CN108830745A (en) | Power grid cascading fault diagnosis, early warning, assessment system based on monitoring information | |
| CN110888973B (en) | Method for automatically structuring and carding monitoring information table | |
| CN110852697B (en) | Automatic generation system for switching operation ticket of transformer substation | |
| CN109345072A (en) | Dispatching method for distribution branch line scheduling scenario | |
| CN106356850B (en) | The generation method of safety and stability control device failure Off-line control Policy model | |
| CN110336375A (en) | A kind of processing method and system of power system monitor warning information | |
| CN107611969A (en) | Possess the regulation and control anti-error system and method for transfer order binding function | |
| CN113314106A (en) | Electric power information query and regulation function calling method based on voice and intention recognition | |
| CN110276516A (en) | Distribution monitoring analysis and repairing command methods based on power grid GIS | |
| CN111291148A (en) | Method and system for generating protection fixed value visual configuration diagram based on GIS (geographic information System) | |
| CN110086166B (en) | Method and system for representing stable operation quota of power grid | |
| CN113409162A (en) | Centralized control station equipment monitoring system and control method based on intelligent event processing | |
| CN105278955A (en) | Management report system for terminal facilities | |
| CN116804691A (en) | Fault monitoring method for dispatching automation equipment of power system | |
| CN116094174A (en) | Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium | |
| CN116108203A (en) | Method, system, storage medium and equipment for constructing power grid panoramic dispatching knowledge graph and managing power grid equipment | |
| CN116109068A (en) | Operation portrait tag management method and system based on digital transformation | |
| Xiang et al. | Design of Intelligent Dispatching System Based on Human Voice Adaptive Speech Recognition | |
| CN114398773A (en) | Coal mine dispatching robot system based on artificial intelligence technology | |
| CN114626440A (en) | Monitoring signal objectification analysis method and device | |
| CN109494882B (en) | Method and system for diagnosing state of substation switch equipment | |
| CN115800528A (en) | Intelligent power grid dispatching monitoring terminal based on artificial intelligence and communication technology |
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 |