Buoy edge calculation voice service system

Abstract

The utility model discloses a buoy edge computing voice service system, which relates to the technical field of voice processing and communication and comprises a box body, a power supply, a transformer and a loudspeaker which are arranged on a buoy. An edge calculation module, a VHF voice communication module and a 4G internet access module are arranged in the box body; the VHF voice communication module is connected with a power supply through a transformer, the VHF voice communication module is connected with a tweeter, and the VHF voice communication module is connected with an edge calculation module through a network cable; the edge calculation module is also connected with the power supply and the 4G internet access module; and the 4G internet access module is connected with the cloud server. According to the utility model, the key technical problems of real-time voice processing, voice recognition, information inquiry, data interconnection and the like of a communication system in marine navigation are solved, so that the functions of real-time processing, voice recognition and answering of voice input of sailors are realized, and the capability of inquiring channel information such as water level and the like is also realized.

Description

Technical Field

[0001] The utility model relates to the field of voice processing and communication technology, and in particular to a buoy edge computing voice service system. Background Art

[0002] Since the beginning of the 21st century, the communication system of ships has become increasingly important. During maritime operations, crew members need to conduct effective voice communication to ensure the smooth and safe operation of the ship. However, traditional voice communication systems have some limitations and challenges in the marine environment, such as the degradation of voice signal quality, noise interference, and communication distance limitations. Therefore, the communication system of ships, especially VHF (Very High Frequency abbreviation, that is, very high frequency, refers to radio waves with a frequency band from 30Mhz to 300MHz, a wavelength range of 1m to 10m, mostly used for radio and television broadcasts, and also a communication channel for aviation and navigation) has attracted more and more attention from researchers. Utility Model Content

[0003] In view of this, the utility model provides a buoy edge computing voice service system, which realizes effective voice communication for crew members during offshore operations.

[0004] In order to solve the above technical problems, the technical solution adopted by the utility model is:

[0005] A buoy edge computing voice service system, comprising a box and a tweeter arranged on a buoy; an edge computing module and a VHF voice communication module are arranged in the box; the VHF voice communication module is connected to the tweeter, and the VHF voice communication module is directly connected to the edge computing module through a network cable;

[0006] The edge computing module includes a processor, a memory and a network connection submodule;

[0007] The processor is used to run the deep learning speech recognition model, word segmentation tool and answer template software to perform speech recognition, text processing and speech generation;

[0008] The memory stores speech recognition models, word segmentation tools and answer template software;

[0009] The deep learning speech recognition model is trained to accurately recognize and process voice commands in various marine environments; the word segmentation tool can effectively analyze key words and phrases in speech to ensure that voice commands can be accurately understood and executed even in noisy marine environments;

[0010] The network connection submodule is used to receive the voice signal transmitted by the VHF voice communication module.

[0011] Furthermore: the box also includes a 4G Internet access module; the edge computing module is connected to the 4G Internet access module; the 4G Internet access module is connected to the cloud server.

[0012] Furthermore: a power supply is also included; the VHF voice communication module and the edge computing module are respectively connected to the power supply.

[0013] Furthermore: a transformer is also included; the VHF voice communication module is connected to the power supply through the transformer.

[0014] Furthermore: the transformer is a 19V to 12V transformer.

[0015] Furthermore: the VHF voice communication module includes a transmission interface for receiving voice communications from crew members and a network connection submodule for transmitting voice signals to the edge computing module.

[0016] A further improvement of the technical solution of the utility model is that the transformer adopts a 19V to 12V transformer.

[0017] Due to the adoption of the above technical solution, the beneficial effects achieved by the utility model are:

[0018] The utility model is based on the local processing capability of the edge computing device, and the system can perform real-time voice processing on the buoy, reducing the dependence on cloud services and improving the response speed of the system.

[0019] In addition to the voice communication function, the system of the utility model also adds practical functions such as water level information query, which increases the flexibility and comprehensiveness of the services on the navigation mark.

[0020] Through the connection between the 4G Internet access module and the cloud server, the system can query a large amount of real-time data, such as water level information, to provide more relevant information. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the utility model or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the utility model. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 This is a connection diagram of the buoy edge computing voice service system of the utility model;

[0023] Figure 2 This is a flow chart for realizing the function of the buoy edge computing voice service system of the utility model;

[0024] Figure 3 This is a scene diagram of the interaction between the crew and the buoy intelligent terminal of the utility model;

[0025] Figure 4 This is the architecture diagram of the buoy edge computing system of the utility model. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the utility model, the technical solution in the embodiment of the utility model will be clearly and completely described below in conjunction with the drawings in the embodiment of the utility model. Obviously, the described embodiment is only a part of the embodiment of the utility model, not all of the embodiments. Based on the embodiment of the utility model, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the utility model.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the utility model and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the utility model described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] like Figure 1 As shown, a buoy edge computing voice service system includes a box 4, a power supply 5, a transformer 6 and a tweeter 7 for playing answer content arranged on the buoy; an edge computing module 1, a VHF voice communication module 2 and a 4G Internet access module 3 are arranged in the box 4; the VHF voice communication module 2 is connected to the power supply 5 through the transformer 6, the VHF voice communication module 2 is connected to the tweeter 7, and the VHF voice communication module 2 is connected to the edge computing module 1 through a network cable; the edge computing module 1 is also connected to the power supply 5 and the 4G Internet access module 3; the 4G Internet access module 3 is connected to the cloud server.

[0029] Specifically:

[0030] (1) The VHF voice communication module 2 and the edge computing module 1 are connected via a direct network connection to achieve real-time voice processing and service functions.

[0031] (2) VHF voice communication module 2: used to receive voice communications from crew members. This is the front-end communication device of the system, responsible for transmitting voice data to the edge computing device.

[0032] (3) Edge computing module 1: runs the Linux operating system and is connected to the 4G Internet access module 3. It is responsible for receiving, processing, and responding to the crew's voice communications.

[0033] Among them, the edge computing module 1 includes a processor, a memory and a network connection submodule; the processor is used to run a speech recognition model, a word segmentation tool and an answer template software, and perform speech recognition, text processing and speech generation; the memory stores the speech recognition model, the word segmentation tool and the answer template software; the network connection submodule is used to receive the voice signal transmitted by the VHF voice communication module 2.

[0034] The speech recognition model may be an existing Wenet speech recognition model, which converts received speech signals into text for subsequent analysis and processing. The Wenet speech recognition model is trained to achieve high-accuracy speech recognition, including multiple dialects and speech types.

[0035] The word segmentation tool can use Jieba word segmentation tool to extract keyword information from the text form of speech. These keywords help to determine the content of the crew's request so as to better respond.

[0036] The speech generation can adopt the existing speech synthesis tool. The answer content obtained after extracting the keywords is played through the tweeter 7, and the tweeter 7 has sufficient sound output capacity to ensure that the crew can clearly hear the answer content of the system under various weather conditions. The final answer content is played on the buoy by connecting to the tweeter 7, and the crew can hear the answer and get the required information.

[0037] The VHF voice communication module 2 includes a transmission interface for receiving voice communications from crew members and a network connection module for transmitting voice signals to the edge computing module 1 .

[0038] The 4G Internet access module 3 has an automatic network switching function, which can achieve a stable connection to the remote cloud server in different communication network environments.

[0039] The cloud server is a remote server connected to the edge computing module 1 through the 4G Internet access module 3. The cloud server is used to query relevant real-time data, such as water level information, marine meteorological data, etc., and return the query results to the edge computing module 1.

[0040] The power supply 5 adopts a 19V power supply.

[0041] Transformer 6 uses a 19V to 12V transformer.

[0042] In the above-mentioned embodiment, a buoy edge computing voice service system connects the existing edge computing module and the VHF voice communication module together to form a new system for realizing effective voice communication of the crew. Among them, the edge computing module is composed of a processor, a memory and a network connection submodule, and the existing speech recognition model, word segmentation tool and answer template software are installed and stored in the memory. The processor runs these existing models, tools and software to realize speech recognition, text processing and speech generation, and communicates with the VHF voice communication module to realize the voice communication of the crew. Although it involves algorithms such as speech recognition, text processing and speech generation, the existing models and tools can be directly used in this application, and the algorithm has not been improved.

[0043] The voice communication and processing flow of the buoy edge computing voice service system in the above embodiment is as follows:

[0044] (1) The crew uses the VHF intercom equipment on board to communicate with the VHF voice communication module 2 on the buoy.

[0045] (2) The VHF voice communication module 2 receives the crew’s voice and transmits the voice signal to the edge computing module 1.

[0046] (3) The edge computing module 1 uses the speech recognition submodule to convert the speech signal into text form. Using the word segmentation tool, the system analyzes the speech in text form and extracts keyword information. Based on the keyword information, the system calls the speech generation interface to generate a reply protocol. The generated reply protocol is played on the buoy through the tweeter interface.

[0047] (4)Data query and cloud server connection:

[0048] a. When the voice contains a query request, such as "What is the current water level", the edge computing module 1 is connected to the cloud server through the 4G Internet access module 3.

[0049] b. The cloud server receives the query request and retrieves relevant data such as water level information from the relevant database.

[0050] c. The query results include text data of water level information.

[0051] d. The cloud server returns the query results to the edge computing module 1.

[0052] e. The edge computing module 1 integrates the water level information into the answering protocol to realize the comprehensive function of voice answering.

[0053] Functions that this system can achieve:

[0054] (1) Crew voice communication: Crew members use the ship's VHF intercom equipment for voice communication. They can ask questions or make requests in natural language, such as checking the current sea conditions or obtaining navigation advice.

[0055] (2) Voice transmission to the buoy: The VHF intercom equipment on board transmits the crew’s voice to the VHF voice communication module 2 on the buoy.

[0056] (3) Speech recognition and word segmentation: After receiving the speech, the VHF speech communication module 2 transmits it to the edge computing module 1 in real time through a direct network connection, and then uses the speech recognition submodule on the edge computing module 1 to convert the speech into text. Subsequently, the word segmentation tool analyzes the text-based speech and extracts keyword information.

[0057] (4) Query request: Based on the extracted keyword information, the system identifies the crew’s query request, for example, “query the current water level.” This request requires additional data to respond.

[0058] (5) Cloud server connection: In order to obtain real-time data such as water level information, the edge computing module 1 is connected to the cloud server through the 4G Internet access module 3. The cloud server stores a central database of a large amount of ocean and meteorological data.

[0059] (6) Data query: The edge computing module 1 sends a query request to the cloud server, requesting data related to water level information. The cloud server retrieves relevant information from the database, including the current water level, ocean tides, etc., to meet the needs of the crew.

[0060] (7) Query results: The cloud server sends the query results back to the edge computing module 1, which include text data of the water level information.

[0061] (8) Reply protocol generation: After receiving the query results returned by the cloud server, the edge computing module 1 integrates these data into the reply protocol. The protocol constructs a text reply including water level information, such as "The current water level is 4.5 meters and the tide is at high tide."

[0062] (9) Reply transmission: The constructed reply protocol is sent to the VHF voice communication module 2, ready for reply.

[0063] (10) Answer playback: By connecting to the tweeter 7, the VHF voice communication module 2 plays the answer content on the buoy, and the crew can answer and get the required information.

[0064] In summary, the utility model provides an efficient and accurate voice communication solution, which enhances the voice communication effect during maritime navigation. The crew can interact with the intelligent terminal on the buoy through voice, obtain real-time question and answer and service support, and improve navigation safety and work efficiency. Compared with the traditional voice processing system based on the central server, the system uses the buoy as a node for calculation and processing, which significantly reduces the data transmission time. By using advanced technology and algorithms, it can process and convert the voice input of the crew in real time. In addition, the system reduces the dependence on remote cloud services through its own processing power, and enhances the stability and reliability in harsh marine environments. It combines key technologies such as speech recognition, text processing and speech generation to provide efficient voice communication and service functions. This technology fills the gap in the interaction between crew members and maritime beacons through natural language, provides a more efficient and reliable voice communication solution for maritime navigation, and has broad application prospects, and is expected to play an important role in the marine field.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the utility model, rather than to limit it. Although the utility model has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the utility model.

Claims

1. A buoy edge computing voice service system, characterized by: It comprises a box (4) and a tweeter (7) arranged on a buoy; an edge computing module (1) and a VHF voice communication module (2) are arranged in the box (4); the VHF voice communication module (2) is connected to the tweeter (7), and the VHF voice communication module (2) is directly connected to the edge computing module (1) via a network cable; The edge computing module (1) comprises a processor, a memory and a network connection submodule; The memory stores speech recognition models, word segmentation tools and answer template software; The processor runs the speech recognition model, word segmentation tool and answer template software stored in the memory; The network connection submodule is used to receive the voice signal transmitted by the VHF voice communication module (2).

2. The buoy edge computing voice service system according to claim 1 is characterized by: The box (4) also includes a 4G Internet access module (3); the edge computing module (1) is connected to the 4G Internet access module (3); and the 4G Internet access module (3) is connected to a cloud server.

3. The buoy edge computing voice service system according to claim 1 is characterized by: It also includes a power supply (5); the VHF voice communication module (2) and the edge computing module (1) are respectively connected to the power supply (5).

4. The buoy edge computing voice service system according to claim 3 is characterized by: It also includes a transformer (6); the VHF voice communication module (2) is connected to the power supply (5) via the transformer (6).

5. The buoy edge computing voice service system according to claim 4 is characterized by: The transformer (6) is a 19V to 12V transformer.

6. The buoy edge computing voice service system according to claim 1 is characterized by: The VHF voice communication module (2) comprises a transmission interface for receiving voice communications from crew members and a network connection submodule for transmitting voice signals to the edge computing module (1).

Images