CN113920990A - Intelligent voice recognition processing system and method for power supply client - Google Patents
Intelligent voice recognition processing system and method for power supply client Download PDFInfo
- Publication number
- CN113920990A CN113920990A CN202111518647.XA CN202111518647A CN113920990A CN 113920990 A CN113920990 A CN 113920990A CN 202111518647 A CN202111518647 A CN 202111518647A CN 113920990 A CN113920990 A CN 113920990A
- Authority
- CN
- China
- Prior art keywords
- voice
- database
- language model
- voice data
- module
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title abstract description 6
- 238000010276 construction Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 3
- 239000000284 extract Substances 0.000 claims description 9
- 238000003672 processing method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of power supply system voice recognition, and relates to an intelligent voice recognition processing system and method for a power supply client, wherein the system comprises a voice acquisition module, a voice recognition module and a voice recognition module, wherein the voice acquisition module is used for acquiring a voice data signal of the client; the signal processing module is used for processing the acquired voice data signal; the characteristic extraction module is used for extracting the characteristics of the processed voice data signal and extracting characteristic value data in the voice data signal; the language model building module is used for building a language model by adopting an N-Gram algorithm and training the built language model; the database construction module is used for constructing a power grid operation service database and storing all data related to the power grid operation service into the database; and the data query module is used for inputting the characteristic value data into the trained language model, identifying the input characteristic value data by the language model, and calling the statement with the closest similarity from the database.
Description
Technical Field
The invention belongs to the technical field of power supply system voice recognition, and particularly relates to an intelligent voice recognition processing system and method for a power supply client.
Background
The voice recognition processing technology in the prior art is mature, but the voice recognition technology applied to the power supply client is not mature.
The daily processing service of the power supply system is heavy, and if the voice recognition processing can be adopted, the daily service processing efficiency can be improved.
In view of the foregoing, the present invention provides an intelligent speech recognition processing system and method for power consumers; it is very necessary to solve the technical defects existing in the prior art.
Disclosure of Invention
The invention aims to provide an intelligent voice recognition processing system and method for a power supply client, so as to improve the daily business processing efficiency of a power supply system.
In order to achieve the purpose, the invention provides the following technical scheme:
an intelligent speech recognition processing system for a powered customer, comprising:
the voice acquisition module is used for acquiring a voice data signal of a client and reading the voice data of the speaking of the client through the voice acquisition module;
the signal processing module is used for processing the acquired voice data signals and filtering noise signals in the voice data signals;
the characteristic extraction module is used for extracting the characteristics of the processed voice data signal and extracting characteristic value data in the voice data signal;
the language model building module is used for building a language model by adopting an N-Gram algorithm and training the built language model;
the database construction module is used for constructing a power grid operation service database and storing all data related to the power grid operation service into the database;
and the data query module is used for inputting the characteristic value data into the trained language model, identifying the input characteristic value data by the language model, and calling the statement with the closest similarity from the database.
Preferably, the voice acquisition module adopts a microphone, and can acquire the voice data information of the client and convert the acquired audio signal into an electric signal.
Preferably, in the feature extraction module, the voice data signal is divided into a plurality of fields according to the level of the voice data signal, and each field extracts a keyword.
Preferably, in the database construction module, all voice data related to power grid operation are stored in a database according to the power grid operation big data; to build a database rich in data base.
The invention also provides an intelligent voice recognition processing method for the power supply client, which comprises the following steps:
s1: a voice acquisition step, in which a voice data signal of a client is acquired;
s2: a signal processing step, namely processing the acquired voice data signal and filtering a noise signal in the voice data signal;
s3: a step of feature extraction, which is to extract features of the processed voice data signal and extract feature value data in the voice data signal;
s4: a step of language model construction, which is to adopt an N-Gram algorithm to construct a language model and train the constructed language model;
s5: a step of constructing a database, namely constructing a power grid operation service database, and storing all data related to the power grid operation service into the database;
s6: and a step of data query, in which the characteristic value data is input into the trained language model, the language model identifies the input characteristic value data, and the sentence with the closest similarity is called from the database.
Preferably, in step S1, the microphone is used to acquire the voice data signal of the client, so as to be able to collect the voice data information of the client and convert the collected audio signal into an electrical signal.
Preferably, in step S3, the voice data signal is divided into several fields according to the level of the voice data signal, and each field extracts a keyword.
Preferably, in step S4, all voice data related to the power grid operation are stored in a database according to the power grid operation big data; to build a database rich in data base.
The invention has the advantages that the voice recognition technology is applied to the daily processing service of the power supply system, the voice of the client is recognized, and the requirement of the client is acquired according to the characters after the voice recognition, so that the processing efficiency of the daily service of the power supply system is improved.
In addition, the invention has reliable design principle, simple structure and very wide application prospect.
Therefore, compared with the prior art, the invention has prominent substantive features and remarkable progress, and the beneficial effects of the implementation are also obvious.
Drawings
Fig. 1 is a schematic block diagram of an intelligent speech recognition processing system for a power consumer according to the present invention.
Fig. 2 is a flowchart of an intelligent speech recognition processing method for a power supply client according to the present invention.
The system comprises a voice acquisition module, a 2-signal processing module, a 3-feature extraction module, a 4-language model construction module, a 5-database construction module and a 6-data query module, wherein the voice acquisition module, the 2-signal processing module, the 3-feature extraction module, the 4-language model construction module and the 6-database construction module are arranged in the same plane.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings by way of specific examples, which are illustrative of the present invention and are not limited to the following embodiments.
Example 1:
as shown in fig. 1, the present embodiment provides an intelligent speech recognition processing system for a power supply client, including:
the voice acquisition module 1 is arranged for acquiring a voice data signal of a client and reading the voice data of the speaking of the client through the voice acquisition module; the voice acquisition module adopts a microphone, can acquire the voice data information of the client and converts the acquired audio signals into electric signals.
The signal processing module 2 is used for processing the acquired voice data signals and filtering noise signals in the voice data signals;
the characteristic extraction module 3 is used for extracting the characteristics of the processed voice data signals and extracting characteristic value data in the voice data signals; in the feature extraction module, the voice data signal is divided into a plurality of fields according to the strength grade of the voice data signal, and each field extracts keywords.
The language model building module 4 builds a language model by adopting an N-Gram algorithm and trains the built language model;
the database construction module 5 is used for constructing a power grid operation service database and storing all data related to the power grid operation service into the database; in the database construction module, all voice data related to power grid operation are stored in a database according to the power grid operation big data; to build a database rich in data base.
And the data query module 6 is used for inputting the characteristic value data into the trained language model, identifying the input characteristic value data by the language model, and calling the statement with the closest similarity from the database.
Example 2:
as shown in fig. 2, the intelligent speech recognition processing method for power supply customers provided by this embodiment includes the following steps:
s1: a voice acquisition step, in which a voice data signal of a client is acquired; in step S1, the microphone is used to acquire the voice data signal of the client, so as to be able to collect the voice data information of the client and convert the collected audio signal into an electrical signal.
S2: a signal processing step, namely processing the acquired voice data signal and filtering a noise signal in the voice data signal;
s3: a step of feature extraction, which is to extract features of the processed voice data signal and extract feature value data in the voice data signal; in step S3, the voice data signal is divided into a plurality of fields according to the level of the voice data signal, and each field extracts a keyword.
S4: a step of language model construction, which is to adopt an N-Gram algorithm to construct a language model and train the constructed language model; in the step S4, according to the power grid operation big data, all voice data related to the power grid operation are stored in a database; to build a database rich in data base.
S5: a step of constructing a database, namely constructing a power grid operation service database, and storing all data related to the power grid operation service into the database;
s6: and a step of data query, in which the characteristic value data is input into the trained language model, the language model identifies the input characteristic value data, and the sentence with the closest similarity is called from the database.
The above disclosure is only for the preferred embodiments of the present invention, but the present invention is not limited thereto, and any non-inventive changes that can be made by those skilled in the art and several modifications and amendments made without departing from the principle of the present invention shall fall within the protection scope of the present invention.
Claims (8)
1. An intelligent speech recognition processing system for a powered customer, comprising:
the voice acquisition module is used for acquiring a voice data signal of a client and reading the voice data of the speaking of the client through the voice acquisition module;
the signal processing module is used for processing the acquired voice data signals and filtering noise signals in the voice data signals;
the characteristic extraction module is used for extracting the characteristics of the processed voice data signal and extracting characteristic value data in the voice data signal;
the language model building module is used for building a language model by adopting an N-Gram algorithm and training the built language model;
the database construction module is used for constructing a power grid operation service database and storing all data related to the power grid operation service into the database;
and the data query module is used for inputting the characteristic value data into the trained language model, identifying the input characteristic value data by the language model, and calling the statement with the closest similarity from the database.
2. The system of claim 1, wherein the voice capture module is a microphone capable of capturing voice data information of the client and converting the captured audio signal into an electrical signal.
3. The system of claim 2, wherein the feature extraction module divides the voice data signal into a plurality of fields according to the level of the voice data signal, and each field extracts a keyword.
4. The system of claim 3, wherein the database construction module stores all voice data related to power grid operation into the database according to the power grid operation big data.
5. An intelligent speech recognition processing method for a power supply client, comprising the steps of:
s1: a voice acquisition step, in which a voice data signal of a client is acquired;
s2: a signal processing step, namely processing the acquired voice data signal and filtering a noise signal in the voice data signal;
s3: a step of feature extraction, which is to extract features of the processed voice data signal and extract feature value data in the voice data signal;
s4: a step of language model construction, which is to adopt an N-Gram algorithm to construct a language model and train the constructed language model;
s5: a step of constructing a database, namely constructing a power grid operation service database, and storing all data related to the power grid operation service into the database;
s6: and a step of data query, in which the characteristic value data is input into the trained language model, the language model identifies the input characteristic value data, and the sentence with the closest similarity is called from the database.
6. The intelligent speech recognition processing method for power supply customers according to claim 5, wherein the step S1 employs a microphone to acquire the customer speech data signal, so as to collect the customer speech data information and convert the collected audio signal into an electrical signal.
7. The intelligent speech recognition processing method for power supply customers according to claim 6, wherein in step S3, the speech data signal is divided into a plurality of fields according to the intensity level of the speech data signal, and each field extracts a keyword.
8. The intelligent voice recognition processing method for the power supply customers according to claim 7, wherein in step S4, all voice data related to the power grid operation are stored in the database according to the power grid operation big data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111518647.XA CN113920990A (en) | 2021-12-14 | 2021-12-14 | Intelligent voice recognition processing system and method for power supply client |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111518647.XA CN113920990A (en) | 2021-12-14 | 2021-12-14 | Intelligent voice recognition processing system and method for power supply client |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113920990A true CN113920990A (en) | 2022-01-11 |
Family
ID=79248988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111518647.XA Pending CN113920990A (en) | 2021-12-14 | 2021-12-14 | Intelligent voice recognition processing system and method for power supply client |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113920990A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108447475A (en) * | 2018-03-02 | 2018-08-24 | 国家电网公司华中分部 | A kind of method for building up of the speech recognition modeling based on electric power dispatching system |
| CN109147768A (en) * | 2018-09-13 | 2019-01-04 | 云南电网有限责任公司 | A kind of audio recognition method and system based on deep learning |
| US20200035233A1 (en) * | 2019-07-29 | 2020-01-30 | Lg Electronics Inc. | Intelligent voice recognizing method, voice recognizing apparatus, intelligent computing device and server |
| CN111489754A (en) * | 2019-01-28 | 2020-08-04 | 国家电网有限公司客户服务中心 | Telephone traffic data analysis method based on intelligent voice technology |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
-
2021
- 2021-12-14 CN CN202111518647.XA patent/CN113920990A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108447475A (en) * | 2018-03-02 | 2018-08-24 | 国家电网公司华中分部 | A kind of method for building up of the speech recognition modeling based on electric power dispatching system |
| CN109147768A (en) * | 2018-09-13 | 2019-01-04 | 云南电网有限责任公司 | A kind of audio recognition method and system based on deep learning |
| CN111489754A (en) * | 2019-01-28 | 2020-08-04 | 国家电网有限公司客户服务中心 | Telephone traffic data analysis method based on intelligent voice technology |
| US20200035233A1 (en) * | 2019-07-29 | 2020-01-30 | Lg Electronics Inc. | Intelligent voice recognizing method, voice recognizing apparatus, intelligent computing device and server |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102522084B (en) | Method and system for converting voice data into text files | |
| CN104679729A (en) | Recorded message effective processing method and system | |
| CN103258535A (en) | Identity recognition method and system based on voiceprint recognition | |
| CN105261356A (en) | Voice recognition system and method | |
| CN101320560A (en) | Method for speech recognition system improving discrimination by using sampling velocity conversion | |
| Gao et al. | Discriminative multiple canonical correlation analysis for multi-feature information fusion | |
| CN106776880A (en) | A kind of paper based on picture and text identification reviews system and method | |
| CN103892821A (en) | Emotion recognition model generating device based on electrocardiosignals and method thereof | |
| CN112542156A (en) | Civil aviation maintenance worker card system based on voiceprint recognition and voice instruction control | |
| CN103258531A (en) | Harmonic wave feature extracting method for irrelevant speech emotion recognition of speaker | |
| CN113920990A (en) | Intelligent voice recognition processing system and method for power supply client | |
| CN102831890A (en) | Method for recognizing text-independent voice prints | |
| CN208000464U (en) | A kind of intelligent sound robot adjusting volume based on the age | |
| CN113468395A (en) | Internet asset fingerprint identification method and system based on inverted index | |
| Zhao et al. | Research on end-to-end voiceprint recognition model based on convolutional neural network | |
| CN103247316B (en) | The method and system of index building in a kind of audio retrieval | |
| CN209265517U (en) | A kind of vocal print punch card system based on speech recognition | |
| Zhang et al. | Research on spectrum sensing system based on composite neural network | |
| CN107180629B (en) | Voice acquisition and recognition method and system | |
| CN102521762A (en) | Customer information acquisition system | |
| CN110688473A (en) | Method for robot to dynamically acquire information | |
| CN116230020A (en) | Speech emotion recognition and classification method | |
| CN114792518A (en) | Voice recognition system based on scheduling domain technology, method thereof and storage medium | |
| CN114049879A (en) | Speech recognition method based on artificial intelligence algorithm | |
| CN113704430A (en) | Intelligent auxiliary receiving method and device, electronic equipment and storage 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220111 |