CN111128144A - Voice power grid dispatching system and method - Google Patents
Voice power grid dispatching system and method Download PDFInfo
- Publication number
- CN111128144A CN111128144A CN201910985383.5A CN201910985383A CN111128144A CN 111128144 A CN111128144 A CN 111128144A CN 201910985383 A CN201910985383 A CN 201910985383A CN 111128144 A CN111128144 A CN 111128144A
- Authority
- CN
- China
- Prior art keywords
- voice
- information
- power grid
- module
- analysis
- 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.)
- Pending
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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- 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
- G10L15/08—Speech classification or search
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
Abstract
The invention relates to a voice power grid dispatching system and a method, wherein the system comprises a voice receiving module, a voice output module, a voice engine and a display, wherein the voice engine comprises a voice synthesis module, a voice recognition module, a standard term conversion module, a semantic understanding and analyzing module rule base, an information searcher and a processor. The method comprises the steps of receiving a voice instruction, identifying the received voice instruction and returning an analysis result to a display; and after the staff selects the required analysis result, returning the selected analysis result to the rule base, and adjusting the rule base according to the received analysis result. The invention has the advantages that: information recording and instruction issuing are carried out through voice, manual input is not needed, and operation is convenient and fast; after the voice is analyzed, a plurality of analysis results are returned for worker staff to select, and errors in information recording and instruction issuing are avoided; and sorting the analysis results according to the selection times of the analysis results, so that the selection is convenient for the staff.
Description
Technical Field
The invention relates to the field of power grid dispatching, in particular to a voice power grid dispatching system and method.
Background
The power dispatching is an effective management means which is adopted for ensuring safe and stable operation of a power grid, reliable external power supply and orderly operation of various power production works. The specific work content of power dispatching is that according to data information fed back by various information acquisition devices or information provided by monitoring personnel, the actual operation parameters of the power grid, such as voltage, current, frequency, load and the like, are combined, the development conditions of various production works are comprehensively considered, the safe and economic operation states of the power grid are judged, operation instructions are issued through a telephone or an automatic system, and field operators or automatic control systems are instructed to adjust, such as adjusting the output of a generator, adjusting load distribution, switching capacitors, reactors and the like, so that the continuous safe and stable operation of the power grid is ensured.
With the comprehensive popularization of the ultra-high voltage technology, the scale of a power grid is continuously enlarged, large-scale alternating current and direct current series-parallel power grid power transmission is formed, the workload and complexity of power grid operation monitoring and scheduling control are continuously increased, a traditional power grid scheduling system and method need workers to manually input and output information, and the traditional power grid scheduling system and method cannot meet the high efficiency of power grid scheduling under the condition of the current large-scale power transmission network.
Disclosure of Invention
The invention mainly solves the problems and provides a voice power grid dispatching system and a voice power grid dispatching method which utilize voice to input and output information, do not need workers to record information manually and can effectively improve the dispatching efficiency of a power grid.
The technical scheme adopted by the invention for solving the technical problem is that the voice power grid dispatching system comprises: the system comprises a voice receiving module for receiving voice information, a voice output module for sending voice, a voice engine for processing the voice information and a display for displaying scheduling information.
The voice receiving module receives voice, the received voice is converted and analyzed in the voice engine, the analysis result is output in a text or voice mode, and the staff selects the analysis result on the display to achieve power grid information acquisition and control over power grid equipment, so that the workload of the staff is reduced, and the power grid dispatching efficiency is improved.
As a preferable solution of the above solution, the speech engine includes a speech synthesis module for converting text information into speech, a speech recognition module for converting speech information into text, a standard term conversion module for converting spoken language into professional terms, and a semantic understanding and parsing module for parsing user input information.
As a preferable solution of the foregoing solution, the semantic understanding and analyzing module includes:
the rule base is used for storing the semantic analysis rules and increasing and modifying the voice analysis rules according to the analysis result finally selected by the user;
the information searcher receives the voice information and the text information, searches in the rule base according to the received information and sends a search result to the processor;
and the processor is used for receiving the search results sent by the information searcher, classifying the search results and transmitting the classified search results to the display for selection by the user. The rule base corrects the stored voice analysis rule according to the analysis result for final selection, so that the semantic understanding accuracy can be improved, and the power grid dispatching efficiency is further improved.
Correspondingly, the invention provides a voice power grid dispatching method, which adopts the system and comprises the following steps:
s1: receiving a voice instruction issued by a worker;
s2: the voice engine identifies the received voice command and returns an analysis result to the display;
s3: and after the staff selects the required analysis result, returning the selected analysis result to the rule base, and adjusting the rule base according to the received analysis result. The whole information recording and equipment control operation only needs to carry out voice input and analysis result selection, does not need to manually input data, and is convenient and efficient to operate.
As a preferable scheme of the above scheme, the recognizing the voice command by the voice engine includes right detection and content recognition, and the right detection includes the following steps:
s21: judging whether the equipment for receiving the voice is the specific equipment or not, if so, entering the step S22; if not, identifying the content;
s22: judging whether the acoustic features of the received voice are matched with the acoustic features corresponding to the equipment for receiving the voice, if so, performing content recognition, and if not, entering the step S23;
s23: converting the received voice into text information, judging whether the text information is matched with a using password of equipment for receiving the voice, and if so, waiting for a worker to input the voice again and carrying out content recognition; if not, prompting and no permission to use. The specific equipment only allows specific personnel to use, the non-specific equipment can be used by anyone, and the acoustic characteristics are mainly tone, speech speed, intonation and the like.
As a preferable mode of the above, the content identification includes the steps of:
s201: extracting key words in the voice;
s202: searching in a rule base by using the keywords, searching all semantic analysis rules related to the keywords, and generating corresponding analysis results according to the semantic analysis rules;
s203, judging whether the equipment for receiving the voice has specific equipment, if so, sequencing the analysis results generated this time based on the selection times of the staff belonging to the equipment for all the analysis results of the keywords in the voice in the past; if not, sorting the analysis results of the time based on the selection times of all the staff for all the analysis results of the keywords in the voice in the past. And sorting the analysis results according to the overall analysis result selection tendency, so that the control instruction with higher utilization rate is in front, and the selection by the staff is facilitated.
The invention has the advantages that: information recording and instruction issuing are carried out through voice, manual input is not needed, and operation is convenient and fast; after the voice is analyzed, a plurality of analysis results are returned for worker staff to select, and errors in information recording and instruction issuing are avoided; and sorting the analysis results according to the selection times of the analysis results, so that the selection is convenient for the staff.
Drawings
Fig. 1 is a block diagram of a voice power grid dispatching system in embodiment 1.
Fig. 2 is a schematic flow chart of the voice power grid scheduling method in embodiment 1.
Fig. 3 is a schematic flowchart of the permission detection in embodiment 1.
Fig. 4 is a schematic flow chart of content identification in embodiment 1.
1-a voice receiving module 2-a voice output module 3-a voice engine 4-a display 5-a voice synthesis module 6-a voice recognition module 7-a standard term conversion module 8-a semantic understanding and analyzing module 9-a rule base 10-an information searcher 11-a processor.
Detailed Description
The technical solution of the present invention is further described below by way of examples with reference to the accompanying drawings.
Example 1:
a voice power grid dispatching system of this embodiment, as shown in fig. 1, a voice receiving module 1 for receiving voice information, a voice output module 2 for sending voice, a voice engine 3 for processing the voice information, and a display 4 for displaying dispatching information, wherein the voice engine includes a voice synthesis module 5 for converting text information into voice, a voice recognition module 6 for converting voice information into text, a standard term conversion module 7 for converting spoken language into professional terms, and a semantic understanding and parsing module 8 for parsing user input information, the semantic understanding and parsing module includes a rule base 9, an information searcher 10, and a processor 11, the rule base is used for storing semantic parsing rules and adding and modifying the voice parsing rules according to parsing results finally selected by users, the information searcher is used for receiving voice information and text information, and the processor is used for receiving the search results sent by the information searcher, classifying the search results and transmitting the classified search results to the display for the user to select.
The voice receiving module receives the voice information and then sends the voice information to the voice recognition module, the voice recognition module converts the voice information into character information, the speech conversion module is used for replacing the character information by professional terms, the information searcher searches in the rule base according to the replaced character information and sends the searched analysis results to the processor, and the processor sorts the analysis results and then displays the analysis results on a display in a character form or broadcasts the analysis results to workers in a voice form through the voice synthesis module, the voice output module and the voice output module. The rule base stores voice analysis rules, each voice analysis rule comprises a search condition and an output result, wherein the search condition comprises one or more keywords, when a specific keyword of the information searcher is searched, if the specific keyword is contained in the search condition of a certain voice analysis rule, the voice analysis rule is searched, the output result of the voice analysis rule is returned to the processor, the equipment control instruction or the information recording instruction of the output node in the voice analysis rule, and the specific data recorded by the information recording instruction needs to be obtained through the received voice.
The embodiment also provides a voice power grid dispatching method, as shown in fig. 2, including the following steps:
s1: receiving a voice instruction issued by a worker;
s2: the speech engine recognizes the received speech instruction and returns the analysis result to the display, and the speech engine recognizes the speech instruction, including authority detection and content recognition, and the authority detection, as shown in fig. 3, includes the following steps:
s21: judging whether the equipment for receiving the voice is the specific equipment only used by specific staff, if so, entering the step S22; if not, performing content identification, as shown in fig. 4, including the following steps:
s201: extracting key words in the voice;
s202: searching in a rule base by using the keywords, searching all semantic analysis rules related to the keywords, and generating corresponding analysis results according to the semantic analysis rules;
s203, judging whether the equipment receiving the voice is specific equipment, if so, sequencing the analysis results generated this time based on the selection times of the staff belonging to the equipment for all the analysis results of the keywords in the voice in the past; if not, sorting the analysis results of the time based on the selection times of all the staff for all the analysis results of the keywords in the voice in the past. (ii) a
S22: judging whether the acoustic features of the received voice are matched with the acoustic features corresponding to the equipment for receiving the voice, wherein the acoustic features considered in the implementation are mainly timbre, if so, performing content recognition, and if not, entering the step S23;
s23: converting the received voice into text information, judging whether the text information is matched with a using password of equipment for receiving the voice, and if so, waiting for a worker to input the voice again and carrying out content recognition; if not, prompting and no permission to use;
s3: and after the staff selects the required analysis result, returning the selected analysis result to the rule base, and adjusting the rule base according to the received analysis result. If the received voice information contains two keywords and the search condition of the voice analysis rule corresponding to the analysis result finally selected by the staff only contains one of the two keywords, then another keyword is added to the search condition of the voice analysis rule to improve the accuracy of the next search.
Example 2:
compared with embodiment 1, the difference of this embodiment is that the method for detecting the authority in this embodiment is different, and specifically includes the following steps:
s21: judging whether the equipment for receiving the voice is the specific equipment only used by specific staff, if so, entering the step S22; if not, identifying the content;
s22: judging whether the acoustic features of the received voice are matched with the acoustic features corresponding to the equipment for receiving the voice, if so, performing content recognition, and if not, entering the step S23;
s23: converting the received voice into text information, judging whether the text information is matched with a using password of equipment for receiving the voice, comparing the inter-word interval time of the received voice with the inter-word interval time of the pre-recorded password voice, and waiting for a worker to input the voice again and perform content identification if the inter-word interval time of the received voice is matched with the inter-word interval time of the pre-recorded password voice; if one is not matched, prompting that no permission is available. In this embodiment, the inter-word interval does not mean a time interval of several seconds, but for the speech as a whole, for example, for a speech of four words, in the first speech, the first three words are read continuously, the interval of the first three words is set to 0.5 second, a short pause is made between the third word and the fourth word, and the pause is made to be 1.5 seconds, in the second speech, the first three words are read continuously, the interval of the first three words is set to 1 second, and the pause is made to be 1.5 seconds between the third word and the fourth word, so that the inter-word intervals of the second speech and the first speech can be considered to match.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (6)
1. A voice power grid dispatching system is characterized in that: the method comprises the following steps: the system comprises a voice receiving module (1) used for receiving voice information, a voice output module (2) used for sending out voice, a voice engine (3) used for processing the voice information and a display (4) used for displaying scheduling information.
2. The voice power grid dispatching system as claimed in claim 1, wherein: the speech engine comprises a speech synthesis module (5) for converting text information into speech, a speech recognition module (6) for converting speech information into text, a standard term conversion module (7) for converting spoken language into professional terms, and a semantic understanding and analyzing module (8) for analyzing user input information.
3. The voice power grid dispatching system as claimed in claim 2, wherein: the semantic understanding and analyzing module comprises:
the rule base (9) is used for storing the semantic analysis rules and increasing and modifying the voice analysis rules according to the analysis result finally selected by the user;
the information searcher (10) receives the voice information and the text information, searches in the rule base according to the received information and sends the search result to the processor;
and the processor (11) receives the search results sent by the information searcher, classifies the search results and transmits the classified search results to the display for the user to select.
4. A voice power grid dispatching method, which adopts the voice power grid dispatching system of any one of claims 1, 2 or 3, and is characterized in that: the method comprises the following steps:
s1: receiving a voice instruction issued by a worker;
s2: the voice engine identifies the received voice command and returns an analysis result to the display;
s3: and after the staff selects the required analysis result, returning the selected analysis result to the rule base, and adjusting the rule base according to the received analysis result.
5. The voice power grid dispatching method according to claim 4, wherein: the speech engine identifies the speech instruction, including authority detection and content identification, and the authority detection comprises the following steps:
s21: judging whether the equipment for receiving the voice is the specific equipment or not, if so, entering the step S22; if not, identifying the content;
s22: judging whether the acoustic features of the received voice are matched with the acoustic features corresponding to the equipment for receiving the voice, if so, performing content recognition, and if not, entering the step S23;
s23: converting the received voice into text information, judging whether the text information is matched with a using password of equipment for receiving the voice, and if so, waiting for a worker to input the voice again and carrying out content recognition; if not, prompting and no permission to use.
6. The voice power grid dispatching method according to claim 5, wherein: the content identification comprises the following steps:
s201: extracting key words in the voice;
s202: searching in a rule base by using the keywords, searching all semantic analysis rules related to the keywords, and generating corresponding analysis results according to the semantic analysis rules;
s203, judging whether the equipment receiving the voice is specific equipment, if so, sequencing the analysis results generated this time based on the selection times of the staff belonging to the equipment for all the analysis results of the keywords in the voice in the past; if not, sorting the analysis results of the time based on the selection times of all the staff for all the analysis results of the keywords in the voice in the past.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910985383.5A CN111128144A (en) | 2019-10-16 | 2019-10-16 | Voice power grid dispatching system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910985383.5A CN111128144A (en) | 2019-10-16 | 2019-10-16 | Voice power grid dispatching system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111128144A true CN111128144A (en) | 2020-05-08 |
Family
ID=70495412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910985383.5A Pending CN111128144A (en) | 2019-10-16 | 2019-10-16 | Voice power grid dispatching system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111128144A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160284345A1 (en) * | 2013-11-06 | 2016-09-29 | Systran International Co., Ltd. | System for grasping keyword extraction based speech content on recorded voice data, indexing method using the system, and method for grasping speech content |
| CN106057205A (en) * | 2016-05-06 | 2016-10-26 | 北京云迹科技有限公司 | Intelligent robot automatic voice interaction method |
| CN106156784A (en) * | 2015-03-30 | 2016-11-23 | 联想(北京)有限公司 | A kind of characteristic recognition method and electronic equipment |
| CN106202541A (en) * | 2016-07-26 | 2016-12-07 | 国网山东省电力公司东营供电公司 | A kind of grid maintenance comprehensive inspection method of application ticket |
| CN106992001A (en) * | 2017-03-29 | 2017-07-28 | 百度在线网络技术（北京）有限公司 | Processing method, the device and system of phonetic order |
| CN107293299A (en) * | 2017-06-16 | 2017-10-24 | 朱明增 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
| CN107452384A (en) * | 2016-04-15 | 2017-12-08 | 感官公司 | For device, media and the method for the non-invasi training for speaker verification |
| WO2018113526A1 (en) * | 2016-12-20 | 2018-06-28 | 四川长虹电器股份有限公司 | Face recognition and voiceprint recognition-based interactive authentication system and method |
| CN109256114A (en) * | 2018-08-30 | 2019-01-22 | 国网浙江省电力有限公司杭州供电公司 | Phonic warning method for power system monitor scheduling |
| CN109345072A (en) * | 2018-08-30 | 2019-02-15 | 国网浙江省电力有限公司杭州供电公司 | Dispatching method for distribution branch line scheduling scenario |
| CN109783808A (en) * | 2018-12-20 | 2019-05-21 | 出门问问信息科技有限公司 | A kind of method, apparatus and electronic equipment for correcting natural language understanding module |
-
2019
- 2019-10-16 CN CN201910985383.5A patent/CN111128144A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160284345A1 (en) * | 2013-11-06 | 2016-09-29 | Systran International Co., Ltd. | System for grasping keyword extraction based speech content on recorded voice data, indexing method using the system, and method for grasping speech content |
| CN106156784A (en) * | 2015-03-30 | 2016-11-23 | 联想(北京)有限公司 | A kind of characteristic recognition method and electronic equipment |
| CN107452384A (en) * | 2016-04-15 | 2017-12-08 | 感官公司 | For device, media and the method for the non-invasi training for speaker verification |
| CN106057205A (en) * | 2016-05-06 | 2016-10-26 | 北京云迹科技有限公司 | Intelligent robot automatic voice interaction method |
| CN106202541A (en) * | 2016-07-26 | 2016-12-07 | 国网山东省电力公司东营供电公司 | A kind of grid maintenance comprehensive inspection method of application ticket |
| WO2018113526A1 (en) * | 2016-12-20 | 2018-06-28 | 四川长虹电器股份有限公司 | Face recognition and voiceprint recognition-based interactive authentication system and method |
| CN106992001A (en) * | 2017-03-29 | 2017-07-28 | 百度在线网络技术（北京）有限公司 | Processing method, the device and system of phonetic order |
| CN107293299A (en) * | 2017-06-16 | 2017-10-24 | 朱明增 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
| CN109256114A (en) * | 2018-08-30 | 2019-01-22 | 国网浙江省电力有限公司杭州供电公司 | Phonic warning method for power system monitor scheduling |
| CN109345072A (en) * | 2018-08-30 | 2019-02-15 | 国网浙江省电力有限公司杭州供电公司 | Dispatching method for distribution branch line scheduling scenario |
| CN109783808A (en) * | 2018-12-20 | 2019-05-21 | 出门问问信息科技有限公司 | A kind of method, apparatus and electronic equipment for correcting natural language understanding module |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111651609A (en) | Multi-turn dialogue method and system integrating knowledge graph and emotion supervision | |
| US8825661B2 (en) | Systems and methods for two stream indexing of audio content | |
| CN112053007B (en) | Distribution network fault first-aid repair prediction analysis system and method | |
| CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
| CN112035626A (en) | Rapid identification method and device for large-scale intentions and electronic equipment | |
| CN116860925A (en) | LLMs prompt word optimization-based intelligent power grid dispatching question-answering system and method | |
| CN113112236A (en) | Intelligent distribution network scheduling system and method based on voice and voiceprint recognition | |
| CN113326678A (en) | Method and device for generating conference summary, terminal equipment and computer storage medium | |
| CN112382276A (en) | Power grid material information acquisition method and device based on voice semantic recognition | |
| CN112417996A (en) | Information processing method and device for industrial drawing, electronic equipment and storage medium | |
| CN111128144A (en) | Voice power grid dispatching system and method | |
| CN110555199B (en) | Article generation method, device, equipment and storage medium based on hotspot materials | |
| JP6571231B1 (en) | Search apparatus and method | |
| CN113096654B (en) | Computer voice recognition system based on big data | |
| CN113656579B (en) | Text classification method, device, equipment and medium | |
| CN102541284A (en) | Method and system for carrying out combination through target quantity in character input | |
| CN109446520A (en) | For constructing the data clustering method and device of knowledge base | |
| CN112270922B (en) | Automatic filling method and device for scheduling log | |
| CN114942981A (en) | Question-answer query method and device, electronic equipment and computer readable storage medium | |
| CN112925889A (en) | Natural language processing method, device, electronic equipment and storage medium | |
| Zou et al. | Design of intelligent customer service report system based on automatic speech recognition and text classification | |
| KR101132469B1 (en) | System and method for providing search result according to automatically completed an initial sound and the automatically completed an initial sound | |
| CN111274399A (en) | Common data grading method based on natural language preprocessing | |
| CN109522356B (en) | Nuclear reactor digital experiment system | |
| CN115438142B (en) | Conversational interactive data analysis report system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |