A voice recognition system for the power industry

Abstract

This invention provides a speech recognition system for the power industry, comprising: a speech acquisition model for collecting speech data from a designated area; a speech processing module for converting the speech data into general power industry text based on a pre-set speech dictionary in a database and outputting it to the speech recognition module; a speech recognition module for performing semantic recognition on the general power industry text based on input speech key information, recognizing general power industry semantics in the text, determining keywords, and outputting the recognition result; and a determination module for determining the recognition result based on input control specifications and determining the semantic recognition accuracy based on the determination result. This invention can perform speech recognition online or offline, can convert different power problems and solutions into text for storage and recording, and can simultaneously process the recorded text to extract key semantics and build models.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a voice recognition system for the power industry. Background Technology

[0002] With the continuous improvement of my country's power infrastructure, the power network consists of substations and transmission lines of different voltage levels. After long-term operation, the power network often needs to be inspected and repaired, which requires grassroots power maintenance personnel to carry out fault repair. However, the records of fault repair are mostly just simple shorthand notes in writing, which are not convenient to organize or search, and are not conducive to quickly dealing with the same power problem. Summary of the Invention

[0003] The purpose of this invention is to propose a voice recognition system for the power industry, which solves the technical problem of how to efficiently and quickly record different power problems in order to improve the efficiency of fault information processing.

[0004] On the one hand, a voice recognition system for the power industry is provided, including:

[0005] A voice acquisition model is used to collect voice data from a specified area.

[0006] The speech processing module is used to convert speech data into general text for the power industry based on the preset speech dictionary in the database, and then output it to the speech recognition module.

[0007] The speech recognition module is used to perform semantic recognition on the general text used in the power industry based on the input speech key information, recognize the general power industry semantics in the text, perform keyword recognition and judgment, and output the recognition result.

[0008] The judgment module is used to judge the recognition results according to the input control specifications, and determine the semantic recognition accuracy based on the judgment results.

[0009] Preferably, it also includes a learning module, which is used to learn the correct semantic recognition based on a preset neural network and record it for the next automatic semantic judgment, and to classify different industry problems through learning;

[0010] The model generation module is used for semantic recognition of completed judgments. It builds parent and subset models according to different levels based on preset power industry requirements and stores them in the database for quick extraction through semantic recognition and hierarchical processing according to different problems.

[0011] Preferably, it also includes a database for storing the collected and generated data;

[0012] The image acquisition module is used to record video of the power maintenance and troubleshooting process.

[0013] Preferably, the voice processing module includes at least one processor, which processes the received voice data to obtain corresponding general text for the power industry.

[0014] Preferably, it further includes an interactive front end, used to receive and display the recognition results, and to determine whether each recognition item in the recognition results meets a preset standard; if an item meets the standard, it is determined that the item is appropriate, and if an item does not meet the standard, it is determined that the item is inappropriate.

[0015] Preferably, the interactive front end is further configured to input corresponding question information when it is determined that a certain item is inappropriate, and output the question information to the voice processing module.

[0016] Preferably, the voice processing module is further configured to convert the problem information into corresponding problem text information according to a preset voice dictionary in the database, and store the problem text information as a relevant maintenance record or guidance information in the database.

[0017] In summary, implementing the embodiments of the present invention has the following beneficial effects:

[0018] The speech recognition system for the power industry provided by this invention can perform speech recognition directly online or offline. It can convert different power problems and solutions into text and store the records. At the same time, it can process the recorded text, extract key semantics, and build models. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, obtaining other drawings based on these drawings without creative effort still falls within the scope of the present invention.

[0020] Figure 1 This is a schematic diagram of a voice recognition system for the power industry according to an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0022] like Figure 1 The diagram shown is a schematic representation of an embodiment of a voice recognition system for the power industry provided by the present invention. This embodiment includes:

[0023] The system comprises a voice acquisition model for collecting voice data from a designated area; a voice processing module for converting voice data into general power industry text based on a pre-set voice dictionary in a database, and outputting it to a voice recognition module; a voice recognition module for performing semantic recognition on the general power industry text based on input voice key information, identifying general power industry semantics in the text, determining keywords, and outputting the recognition result; and a determination module for determining the recognition result based on input control specifications and determining the semantic recognition accuracy. As you can understand, this system uses a microphone for voice input; the voice processing module processes the input voice, converting it into general power industry text based on a database voice dictionary; the voice recognition module automatically identifies key information in the input voice, performs semantic recognition, identifies general power industry semantics in the text, and determines keywords; and the determination module can connect to the front end for voice recognition confirmation, verifying the system's semantic recognition accuracy. The determination module connects to the front end, causing a pop-up window to perform the recognition judgment.

[0024] In one embodiment, the system further includes: a learning module, used to learn and record correctly identified semantic recognitions by the judgment module based on a preset neural network, for use in the next automatic semantic judgment, and to classify different industry problems through learning; and a model generation module, used to build parent-child set models for the completed semantic recognitions according to preset power industry requirements at different levels, and store them in a database for rapid extraction through semantic recognition, and to classify and process them according to different problems. Understandably, the automatic learning module has a built-in learning chip based on a neural network-based artificial intelligence (AI) chip, which has the ability to learn and reason autonomously. The automatic learning module automatically learns and records correctly identified semantic recognitions by the judgment module for use in the next automatic semantic judgment, and classifies different industry problems through learning; the model generation module builds parent-child set models for the completed semantic recognitions according to power industry requirements at different levels, and stores them in a database for rapid extraction through semantic recognition, and to classify and process them according to different problems, such as classifying line problems as short circuits, open circuits, etc.

[0025] In one embodiment, the system further includes a database for storing collected and generated data; an image acquisition module for recording video of the power maintenance and troubleshooting process. The database records a speech dictionary to assist in the implementation of a semantic model; and the camera can simultaneously record video of the power maintenance and troubleshooting process.

[0026] In one embodiment, the voice processing module includes at least one processor, which processes the received voice data to obtain corresponding general text for the power industry. Understandably, the voice processing module includes a circuit board and a processing chip. The circuit board is connected to a microphone to receive voice input, and the processing chip processes the voice to convert it into text.

[0027] In one embodiment, the system further includes an interactive front-end, used to receive and display the recognition results, and determine whether each item in the recognition results conforms to a preset standard; if an item conforms, it is determined to be appropriate; if an item does not conform, it is determined to be inappropriate. The interactive front-end is also used to input corresponding question information when an item is determined to be inappropriate, and output the question information to the speech processing module. Understandably, after semantic recognition is completed, feedback is provided through the front-end to confirm whether the recognition is correct. When the recognition is inappropriate, multiple semantic options appear for the correct selection. In other words, when maintenance personnel complete a maintenance task, they can directly input voice information offline or online via microphone. The voice processing module converts the input voice into general text for the power industry based on a database of voice dictionaries. The voice recognition module automatically identifies key information in the input voice and performs semantic recognition. After semantic recognition is completed, feedback is sent through the front end to confirm whether the recognition is correct. The semantic recognition of the determined voice is then learned by the learning module, and the voice-related information is stored in the database. A camera can be set up to simultaneously record video of the maintenance work. Through the model generation module, the semantic recognition of the determined voice is used to build parent and subset models according to different levels based on the requirements of the power industry, and these models are stored in the database for easy and quick retrieval.

[0028] In one embodiment, the voice processing module is further configured to convert the problem information into corresponding problem text information based on a preset voice dictionary in the database, and store the problem text information as relevant maintenance records or guidance information in the database. Understandably, when maintenance personnel need to perform maintenance, they input the problem through a microphone, and the voice processing module and voice recognition module perform semantic extraction. After semantic confirmation, relevant maintenance records or guidance are retrieved from the database model to assist in the maintenance work.

[0029] In summary, implementing the embodiments of the present invention has the following beneficial effects:

[0030] The speech recognition system for the power industry provided by this invention can perform speech recognition directly online or offline. It can convert different power problems and solutions into text and store the records. At the same time, it can process the recorded text, extract key semantics, and build models.

[0031] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A voice recognition system for the power industry, characterized in that, include: A voice acquisition model is used to collect voice data from a specified area. The speech processing module is used to convert speech data into general text for the power industry based on the preset speech dictionary in the database, and then output it to the speech recognition module. The speech recognition module is used to perform semantic recognition on the general text used in the power industry based on the input speech key information, recognize the general power industry semantics in the text, perform keyword recognition and judgment, and output the recognition result. The judgment module is used to judge the recognition results according to the input control specifications, and determine the semantic recognition accuracy based on the judgment results; The learning module is used to learn the correct semantic recognition based on the preset neural network and record it for the next automatic semantic judgment. It also classifies different industry problems through learning. The model generation module is used for semantic recognition of completed judgments. According to the preset requirements of the power industry, it builds parent and child set models according to different levels and stores them in the database for quick extraction through semantic recognition and hierarchical processing according to different problems. An interactive front end is used to receive and display the recognition results, and to determine whether each recognition item in the recognition results meets the preset standards; If a certain item is met, it is determined to be appropriate; if a certain item is not met, it is determined to be inappropriate. When an item is determined to be inappropriate, the corresponding problem information is input and the problem information is output to the speech processing module. The voice processing module is also used to convert the problem information into corresponding problem text information according to the preset voice dictionary in the database, and store the problem text information as relevant maintenance records or guidance information in the database.

2. The system as described in claim 1, characterized in that, It also includes, A database is used to store the collected and generated data; The image acquisition module is used to record video of the power maintenance and troubleshooting process.

3. The system as described in claim 2, characterized in that, The voice processing module includes at least one processor, which processes the received voice data to obtain corresponding general text for the power industry.

Images