SUMMERY OF THE UTILITY MODEL
In view of this, the present invention provides a strip mine card voice intercom system based on dispatching instruction set, which can perform adaptive denoising on incoming voice signals, and reduce the adverse effect of dialect on voice recognition by using the interconversion of "voice-text instruction"; data loss caused by network fluctuation is solved; therefore, the system realizes efficient and accurate real-time voice communication between the trucks in the strip mine.
In order to achieve the above purpose, the utility model provides a following technical scheme:
a strip mine card voice intercom system based on a dispatching instruction set comprises a plurality of vehicle-mounted terminals and a server, wherein,
each in-vehicle terminal includes:
the device comprises a voice conversion module for realizing voice text conversion and self-adaptive denoising, a storage module for information caching, a wireless network communication module for receiving and sending signals, a first processor module for data calculation tasks in the voice conversion module, a microphone and external broadcasting;
the server includes:
the system comprises a text information management module for selecting a target vehicle-mounted terminal, a communication scheduling module for controlling channel scheduling, a group management module for realizing vehicle-mounted terminal division, a wireless network communication module for receiving and sending signals and a second processor module;
in the system: the method comprises the following steps that a voice signal is transmitted to a voice conversion module through a microphone, the voice conversion module is internally provided with an adaptive denoising module, an open-pit mine card dispatching instruction set and a voice sample set thereof, the adaptive denoising module acquires environmental noise in real time, and voice data are adaptively denoised according to real-time noise after arriving;
the strip mine card dispatching instruction set and the voice sample set thereof are used for filtering effective instructions and outputting corresponding text instruction phrase information;
the first processor module is used for transmitting the voice signal of the microphone to the voice conversion module and transmitting the text instruction phrase generated by the voice conversion module to the storage module or the wireless network module;
the wireless network module sends the text information to a server;
the server receives a text signal and transmits the text signal to the text information management module for text analysis and processing, and text forwarding is realized through the communication scheduling module, the group management module and the second processor module;
finally, the wireless network communication module sends text information to the target vehicle-mounted terminal;
and the target vehicle-mounted terminal receives the text information, converts the text information into voice through the voice conversion module, and then sends the voice to an external broadcast to finish voice broadcast.
The storage module adopts an SD card.
The wireless network module adopts the SIM card to receive or send signals under the 2G/3G/4G condition.
The strip mine card dispatching instruction set covers a dispatching instruction phrase complete set of the strip mine card, the core part of the strip mine card dispatching instruction set is a library used for placing sound waveforms, instruction phrases and corresponding relations between the sound waveforms and the instruction phrases, and each instruction phrase text of the library stores sound waveform samples of at least one common dialect besides a mandarin sound waveform sample.
The text information management module is used for automatically selecting an intercom mode according to the text information, and the intercom mode comprises designated intercom, one-to-many intercom or intra-group intercom.
The group management module divides a plurality of vehicle-mounted terminals into groups according to the automatic selection result of the text information management module so as to realize a forwarding mode corresponding to the talkback mode, wherein the forwarding mode comprises three modes of designated transmission, multicast and broadcast.
The communication scheduling module divides channels according to the required forwarding mode and coordinates the use of the channels.
The beneficial effects of the utility model reside in that:
1. the voice conversion module realizes the conversion function of voice information and text information, reduces the data transmission bandwidth and lightens the network load.
2. The self-adaptive denoising function of the voice conversion module improves the voice talkback recognition rate.
3. The keyword matching technology realized by the built-in scheduling instruction set of the voice module reduces the influence of environmental noise and dialect, screens information, only outputs effective information texts, and greatly reduces the data transmission amount and the calculation burden.
4. The existence of the storage module solves the problem of data loss caused by network interruption.
5. Because the wireless network module adopted by the system supports data transmission under 2G/3G/4G, the problem of data transmission interruption caused by network instability is solved.
6. The voice talkback mode selection function provided by the text message pipe module of the server side solves the problem of information disorder caused by the fact that multiple people share a channel in the traditional voice talkback process.
Detailed Description
The technical solution of the present invention will be further specifically described with reference to the accompanying drawings.
As shown in fig. 1, the utility model discloses a pronunciation intercom system structure schematic diagram, the utility model discloses a strip mine card pronunciation intercom system based on dispatch instruction set comprises a plurality of vehicle mounted terminals and a server, wherein each vehicle mounted terminal includes the voice conversion module that is used for realizing voice text interconversion, the storage module that is used for information cache, the wireless network module that is used for receiving and sending signals, the processor module that is used for data calculation, microphone, external broadcast and power; the server side comprises a text information management module for selecting a target vehicle-mounted terminal, a communication scheduling module for controlling channel scheduling, a group management module for realizing vehicle-mounted terminal division, a wireless network communication module for receiving and sending signals and a processor module; the information transmission between the two is completed by adopting a network communication mode and is realized by a wireless network module.
The truck driver inputs voice to the system through the vehicle-mounted terminal microphone, and voice information enters the system and is transmitted to the voice conversion module.
Ambient noise is collected in real time before speech input, and is removed from the speech before it is converted into text according to noise frequency bands.
The voice module is internally provided with a dispatching instruction set which covers a phrase complete set of the strip mine card dispatching instruction and corresponding sound waveform information, effective instructions can be filtered out from the voice information after denoising by adopting a keyword matching technology, corresponding text instruction phrases are output, and the text information is transmitted to the storage module or the wireless network module after the voice information conversion is finished.
If the network state is normal, the text message is transmitted to the wireless network module, and the wireless network module is sent to the server, wherein the wireless network module is an SIM card arranged on the system and simultaneously supports data transmission under a 2G/3G/4G network, so that the problem of transmission interruption caused by network fluctuation can be avoided.
When the network is interrupted, the text information is transmitted to the storage module, the SD card of the storage module realizes cache, and the text information is transmitted to the wireless network module after the network is recovered.
The server end can enter a text information management module after receiving the transmitted text information, the module can analyze and process the text information and automatically select an intercom mode according to the text information, and the intercom mode comprises a point-to-point intercom mode, an intra-group intercom mode and a one-to-many intercom mode. The selection of the talkback mode determines the range of the vehicle-mounted terminal for data return.
And the group management module of the server performs group division on the plurality of vehicle-mounted terminals according to the selection result of the text management module to realize corresponding forwarding modes, wherein the forwarding modes comprise three modes of designated transmission, multicast and broadcast.
After the vehicle-mounted terminal equipment in the voice talkback range receives the text information transmitted by the server, the text information is synthesized into voice information through the voice conversion module again, and the voice information is sent to an external broadcast to be automatically played, so that talkback is completed.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the scope of the claims of the present invention.