CN-121983043-A - AI voice broadcast signal processing device and method

Abstract

The invention belongs to the technical field of voice interaction and broadcast control, and particularly relates to an AI voice broadcast signal processing device and method. The system comprises a telephone interaction information processing module, a broadcast demand collection and classification processing module and a broadcast system control and broadcast information transmission module, wherein the telephone interaction information processing module is used for receiving a telephone of a user and carrying out voice recognition to convert the user demand into text information, the broadcast demand collection and classification processing module is used for analyzing the text information and extracting key information required by broadcasting, and the broadcast system control and broadcast information transmission module is used for generating broadcast audio and initiating a broadcast instruction to a broadcast terminal. The invention is especially suitable for emergency broadcasting and information release scenes in factories, and long-distance high-quality signal transmission is realized by adopting the audio optical transceiver, so that signal attenuation is avoided, and the tone quality and coverage range of broadcasting are ensured.

Inventors

• Xue Jiaen
• ZHANG KAIPENG
• LI SI
• WANG TAO
• CHEN ZHIGEN
• Kou Hanxue
• XIE BIN
• WEI WEIHUA
• WANG HENG

Assignees

• 福建福清核电有限公司

Dates

Publication Date

20260505

Application Date

20260112

Claims (7)

1. 1. A voice broadcast AI signal processing apparatus, comprising: The telephone interaction information processing module is used for receiving a telephone of a user and carrying out voice recognition so as to convert the user requirement into text information; the broadcasting demand collecting and classifying processing module is used for analyzing text information and extracting key information required by broadcasting; And the broadcasting system control and broadcasting information transmission module is used for generating broadcasting audio and initiating broadcasting instructions to the broadcasting terminals.
2. 2. A method for processing an AI signal of a voice broadcast, comprising the steps of: Receiving a telephone dialed by a user through a telephone interaction information processing module, performing voice recognition, and converting the broadcasting requirement of the user into text information; analyzing the converted text information by utilizing a broadcast demand collection and classification processing module, and extracting key information, wherein the key information comprises names, departments and people of broadcast objects; and the broadcasting system control and broadcasting information transmission module is used for carrying out voice synthesis on the extracted key information, generating broadcasting content and broadcasting the broadcasting content through the broadcasting system.
3. 3. The method of claim 2, wherein the telephone interaction information processing module performs voice recognition by using a deep learning model to ensure that the user voice is accurately converted into text in real time.
4. 4. The method for processing an AI signal of a voice broadcast as set forth in claim 2 wherein said broadcast demand collection and classification processing module analyzes the text information using a natural language processing algorithm.
5. 5. The method for processing an AI signal for a voice broadcast as set forth in claim 4 wherein the intent recognition and information extraction is performed.
6. 6. The method for processing an AI signal for voice broadcast as set forth in claim 2 wherein said broadcast information delivery module generates broadcast content in audio format by speech synthesis.
7. 7. The method for processing an AI signal for voice broadcast of claim 6 wherein the broadcast information delivery module initiates a broadcast command to a plurality of broadcast terminals.

Description

AI voice broadcast signal processing device and method Technical Field The invention belongs to the technical field of voice interaction and broadcast control, and particularly relates to an AI voice broadcast signal processing device and method. Background Most of the existing nuclear power plants already build a cable broadcast system. And answering the call of the request broadcast through the manual position of each factory area, and then initiating the broadcast to the appointed area by the manual position. This approach has the following problems: 1. the efficiency is low, when the user answers the call manually, the user can not broadcast, and when the user sends the broadcast, he can not answer the call; 2. the time is limited, the work cannot be carried out for 24 hours without interruption, and the broadcasting requirement of overtime during overhaul is difficult to meet; 3. The place is limited, the broadcasting station is required to initiate the broadcasting, and other places cannot initiate the broadcasting; 4. The broadcast has no record, namely, the number of broadcast is sent, the broadcast is broadcast to the people, and the broadcast is not recorded, and in special cases, the broadcast can only be traced back by the brain of the people; during heavy overhaul, the manual broadcasting mode is difficult to meet heavy broadcasting requirements, and the overall working efficiency is affected. The nuclear power unit normally operates for one day, and millions or even tens of millions of economic benefits are created. The working efficiency of nuclear power overhaul is improved, the cost of the overhaul can be reduced, and the unit can be operated normally early. Disclosure of Invention The invention aims to provide an AI voice broadcast signal processing device and method, which answer an incoming call through an IP telephone system, recognize the broadcast intention of a user through intelligent voice interaction, extract broadcast information, generate a broadcast instruction through a broadcast control system and control the subareas of a plurality of broadcast systems to broadcast. The technical scheme of the invention is as follows, a voice broadcast AI signal processing device comprises: The telephone interaction information processing module is used for receiving a telephone of a user and carrying out voice recognition so as to convert the user requirement into text information; the broadcasting demand collecting and classifying processing module is used for analyzing text information and extracting key information required by broadcasting; And the broadcasting system control and broadcasting information transmission module is used for generating broadcasting audio and initiating broadcasting instructions to the broadcasting terminals. A voice broadcast AI signal processing method, comprising the steps of: Receiving a telephone dialed by a user through a telephone interaction information processing module, performing voice recognition, and converting the broadcasting requirement of the user into text information; analyzing the converted text information by utilizing a broadcast demand collection and classification processing module, and extracting key information, wherein the key information comprises names, departments and people of broadcast objects; and the broadcasting system control and broadcasting information transmission module is used for carrying out voice synthesis on the extracted key information, generating broadcasting content and broadcasting the broadcasting content through the broadcasting system. The telephone interaction information processing module adopts a deep learning model to carry out voice recognition, so that the real-time accurate conversion of the voice of the user into a text is ensured. The broadcast demand collection and classification processing module analyzes text information by using a natural language processing algorithm and performs intention recognition and information extraction. The broadcast information transmission module generates broadcast content in an audio format through voice synthesis and initiates broadcast instructions to a plurality of broadcast terminals. The invention is especially suitable for emergency broadcasting and information release scenes in factories, and long-distance high-quality signal transmission is realized by adopting the audio optical transceiver, so that signal attenuation is avoided, and the tone quality and coverage range of broadcasting are ensured. Drawings FIG. 1 is a flow chart of interactions between an IP telephony system and a broadcast control system; Fig. 2 is a flow chart of a broadcast control system issuing control signals to a plurality of broadcast adapters. Detailed Description The invention will be described in further detail with reference to the accompanying drawings and specific examples. The invention provides an AI voice broadcasting signal processing device, which comprises a telephone int