CN111883114A - A ship voice control method, system, device and storage medium - Google Patents

Abstract

The invention discloses a ship voice control method, system, device and storage medium. The method includes: acquiring a first voice signal collected; preprocessing the first voice signal to obtain a second voice signal; Feature extraction is performed on the second voice signal to obtain voice features; matching is performed according to the voice features to obtain corresponding voice sentences; the voice sentences are used as operation instructions, and the ship is controlled according to the operation instructions. The invention directly converts the voice signal into the operation command of the ship and sends out the ship, thereby realizing the control of the ship through the voice, and effectively reducing the workload of the driver or the helmsman. The invention can be widely used in the field of ship control.

Description

A ship voice control method, system, device and storage medium

technical field

The invention relates to the technical field of ship control, in particular to a ship voice control method, system, device and storage medium.

Background technique

Statistics, investigation and analysis of various marine accidents show that human factors account for 80% of the probability of ship collisions, capsizes, oil spills, fires and explosions, grounding and other marine accidents, and a large number of accidents involve ship management. And human factors such as human operation errors, even accidents caused by ship machinery failure, instrument failure and ship structure problems are directly related to human errors. Among the water traffic accidents in my country, 95% are responsible accidents, and most of the accidents are caused by human factors.

The statistical analysis report on ship accidents in 2018 shows that there were many ship collisions and self-sinking accidents in 2018 due to three reasons: on the one hand, some ship drivers had weak safety awareness, had a fluke mentality, and did not abide by the prohibition and restrictions on navigation; on the one hand, some ships When pilots drive ships, they make mistakes in decision-making due to fatigue or improper information processing. On the one hand, severe weather such as strong winds and fog increases the difficulty of safe navigation of ships, and brings challenges to on-site supervision and emergency response.

Language interaction is the most convenient and effective way for humans to communicate, and how to make machines understand human language, realize human-computer interaction, and complete various operations has become an urgent need in daily life. Automatic speech recognition technology is a method that takes speech as the research object, converts speech signals into text or commands that can be recognized by machines, and realizes human-computer intelligent interaction. The technology has important application prospects in voice navigation, document retrieval, indoor equipment control and so on. With the wide application of embedded systems in life and the continuous development of intelligent human-computer interaction technology, people begin to design and implement various embedded systems to complete specific applications.

Voice announcement is an effective way to help drivers process information. In the sea with changing weather, environmental parameters change in real time, such as: wind direction, wind speed, flow speed, visibility, tide, etc. When a ship pilot drives a ship, he needs to make operational decisions based on these complex information. However, in the process of collecting this information, the pilot may make decision mistakes due to fatigue or improper information processing.

SUMMARY OF THE INVENTION

In order to solve the above technical problems, the purpose of the present invention is to provide a ship voice control method, system, device and storage medium.

In a first aspect, an embodiment of the present invention provides a ship voice control method, including the following steps:

obtaining the collected first voice signal;

Preprocessing the first voice signal to obtain a second voice signal;

performing feature extraction on the second voice signal to obtain voice features;

Perform matching according to the voice feature to obtain a corresponding voice sentence;

The voice sentence is used as an operation instruction, and the ship is controlled according to the operation instruction.

In an embodiment of the present invention, the preprocessing of the first voice signal to obtain the second voice signal is specifically:

Filter and pre-emphasize the first speech signal to obtain a second speech signal.

In an embodiment of the present invention, the matching according to the voice feature to obtain a corresponding voice sentence further includes:

performing acoustic feature matching on the speech features to obtain an acoustic feature vector;

Matching the phonetic features through a preset pronunciation dictionary to obtain a corresponding phonetic vocabulary;

Sentence matching is performed according to the acoustic feature vector and the phonetic vocabulary to obtain corresponding phonetic sentences.

In an embodiment of the present invention, the ship voice control method further includes:

The navigation information of the ship is collected, and the navigation information is broadcast.

In an embodiment of the present invention, the collection of the navigation information of the ship and the broadcasting of the navigation information specifically include:

Collect the navigation information of the ship;

The navigation information is broadcast according to the navigation information and the broadcast conditions corresponding to the navigation information.

In an embodiment of the present invention, the sailing information includes at least one of the following: sailing speed, sailing direction, wind speed, wind direction, water flow velocity, water flow direction, and ship fault information.

In a second aspect, the present invention provides a ship voice control system, comprising:

an acquisition unit for acquiring the collected first voice signal;

a preprocessing unit, configured to preprocess the first voice signal to obtain a second voice signal;

a feature extraction unit, configured to perform feature extraction on the second speech signal to obtain speech features;

a matching unit for matching according to the voice feature to obtain a corresponding voice sentence;

The operation control unit is used for taking the voice sentence as an operation instruction, and controlling the ship according to the operation instruction.

In an embodiment of the present invention, the ship voice control system further includes:

The broadcasting unit is used for collecting the navigation information of the ship and broadcasting the navigation information.

In a third aspect, an embodiment of the present invention provides a ship voice control device, including:

at least one processor;

at least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor implements the one ship voice control method.

In a fourth aspect, an embodiment of the present invention provides a storage medium in which processor-executable instructions are stored, wherein the processor-executable instructions are used to execute the one when executed by the processor. Ship voice control method.

The beneficial effects of the present invention are:

The ship voice control method, system, device and storage medium of the present invention directly convert the voice signal into the ship's operation command to send out, so that the ship can be controlled by voice, and the workload of the driver or helmsman is effectively reduced.

Further, the present invention communicates various navigation information of the ship to decision makers in the form of broadcast, the data is accurate, the information is obtained conveniently and quickly, and accidents caused by errors in processing information can be effectively reduced.

Description of drawings

Fig. 1 is the step flow chart of a kind of ship voice control method of the present invention;

Fig. 2 is the module block diagram of a kind of ship voice control system of the present invention;

3 is a schematic diagram of fitting a rotating high-definition probe image and a radar in an embodiment of the present invention;

FIG. 4 is a schematic diagram of broadcast conditions in an embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The numbers of the steps in the following embodiments are only set for the convenience of description, and the sequence between the steps is not limited in any way, and the execution sequence of each step in the embodiments can be adapted according to the understanding of those skilled in the art Sexual adjustment. Furthermore, it should be noted that the embodiments in the present application and the features of the embodiments may be arbitrarily combined with each other under the condition of no conflict.

Referring to Fig. 1, an embodiment of the present invention provides a method for controlling a ship's voice, including the following steps:

S101. Acquire a collected first voice signal.

S102. Preprocess the first voice signal to obtain a second voice signal.

S103. Perform feature extraction on the second voice signal to obtain voice features.

S104. Perform matching according to the voice feature to obtain a corresponding voice sentence.

S105. Use the voice sentence as an operation instruction, and control the ship according to the operation instruction.

In this embodiment, the first voice signal may be a voice signal spoken by a human being, that is, a command spoken by the crew, and then the spoken command is converted into an operation command that the ship can recognize, so as to achieve the effect of controlling the ship by voice.

In an embodiment of the present invention, the preprocessing of the first voice signal to obtain the second voice signal is specifically:

Filter and pre-emphasize the first speech signal to obtain a second speech signal.

In this embodiment, the preprocessing may be performing operations such as filtering, pre-emphasis, etc. on the speech signal, so as to reduce the influence of environmental noise, channels, and the like on the features.

In an embodiment of the present invention, the matching according to the voice feature to obtain a corresponding voice sentence further includes:

S1041, performing acoustic feature matching on the speech feature to obtain an acoustic feature vector;

S1042, matching the phonetic features through a preset pronunciation dictionary to obtain a corresponding phonetic vocabulary;

S1043. Perform sentence matching according to the acoustic feature vector and the phonetic vocabulary to obtain a corresponding phonetic sentence.

In this embodiment, the obtained speech feature can be matched with the acoustic feature vector constructed by the preset unit model and the vocabulary set and pronunciation in the preset pronunciation dictionary, and then the language targeted by the system is modeled, and the sentence Match, and finally get the corresponding voice sentences, such as "left rudder 5", "advance 3", "broadcast flow direction, flow rate" and other voice sentences.

In an embodiment of the present invention, the ship voice control method further includes:

The navigation information of the ship is collected, and the navigation information is broadcast.

In an embodiment of the present invention, the collection of the navigation information of the ship and the broadcasting of the navigation information specifically include:

Collect the navigation information of the ship;

The navigation information is broadcast according to the navigation information and the broadcast conditions corresponding to the navigation information.

In this embodiment, the navigation information is collected by various basic instruments such as wind and flow sensors, log, magnetic compass, etc. of the ship, such as: sailing speed, sailing direction, wind speed and direction, water flow speed and water flow direction, and these information are stored in real time , broadcast according to the broadcast conditions.

Further, as shown in Figure 3, the navigation information can be combined by the 360° rotating high-definition probe 1 installed on the top of the bridge and the bridge equipment such as AIS, ECDIS, and radar. According to the radar detection area 2 in Figure 3 and the camera monitoring Area 3 can obtain the distance and orientation information of other ships and navigation marks around the ship.

The ship fault information is set by setting the safety value or safety range for various equipment of the ship before sailing. If the equipment parameters exceed the safety range during the sailing process, an alarm will be automatically issued and the information of the failure will be broadcast.

In this embodiment, AIS, ECDIS and pictures obtained by rotating high-definition probes can be fitted to obtain accurate navigation mark information, channel information and some other ship information. When radar detection is used directly, false echo signals and interference signals will be obtained. In order to prevent false information from being broadcast, the radar signal is fitted with the target information obtained by rotating the high-definition probe to determine the azimuth and distance of real obstacles and other ships.

As shown in Figure 4, taking the position coordinates of the ship as the center, taking the safe voyage 4 (safe speed refers to the time allowed to take appropriate and effective actions to avoid collision and to stop the ship within a distance suitable for the current environment and situation Speed, here the ship process from the start of stopping the ship to the speed of 0 is called the safe voyage) as the radius to draw a circle to obtain a safety circle 7 in a circular area, and the broadcast condition can be only on other ships 5, obstacles, When the beacon 6 appears in this circular area, the voice broadcast will be broadcast. The order of broadcast refers to the order of distance and distance of the objects, and broadcasts from near to far.

The navigation information broadcast in this embodiment is divided into three levels: first-level, second-level, and third-level.

The first-level information is the sailing speed, wind direction and wind speed, water flow direction, water flow speed, channel width and other information. These information are not automatically broadcast according to the period. After using the voice control system to send voice commands, the broadcast system broadcasts the selected information.

The secondary information is the information of the objects in the security circle. The content of the broadcast is the distance and orientation of the object. These information can be broadcast automatically, and the broadcast period can be set such as "broadcast every 3 minutes", "broadcast every 5 minutes".

The third-level information is alarm information such as ship fault information, predicted collision risk information, and environmental mutation information. The ship fault information is sent out when the parameters of the sensor sensing device are not within the normal range, and the predicted collision risk information is calculated by radar to calculate the PAD (collision danger area), indicating that there is a possibility of collision danger, an alarm message is issued, and the environmental mutation information is ECDIS or rotating HD Probes that alert the vessel when it is about to enter environments such as narrow waterways and high-traffic waters, and when environmental sensors sense sudden and large changes in environmental factors such as wind currents. These messages are broadcast immediately.

Referring to Figure 2, the present invention provides a ship voice control system, including:

an acquisition unit for acquiring the collected first voice signal;

a preprocessing unit, configured to preprocess the first voice signal to obtain a second voice signal;

a feature extraction unit, configured to perform feature extraction on the second speech signal to obtain speech features;

a matching unit for matching according to the voice feature to obtain a corresponding voice sentence;

The operation control unit is used for taking the voice sentence as an operation instruction, and controlling the ship according to the operation instruction.

In an embodiment of the present invention, the ship voice control system further includes:

The broadcasting unit is used for collecting the navigation information of the ship and broadcasting the navigation information.

Further, the present invention communicates various navigation information of the ship to decision makers in the form of broadcast, the data is accurate, the information is obtained conveniently and quickly, and accidents caused by errors in processing information can be effectively reduced.

The embodiment of the present invention provides a ship voice control device, including:

at least one processor;

at least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor implements a ship voice control method.

In addition, an embodiment of the present invention provides a storage medium in which processor-executable instructions are stored, wherein the processor-executable instructions are used to execute a ship voice control method when executed by the processor.

As can be seen from the above content, the present invention realizes the control of the ship through voice by directly converting the voice signal into the operation command of the ship, thereby effectively reducing the workload of the driver or helmsman.

The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments, and those skilled in the art can make various equivalent deformations or replacements without departing from the spirit of the present invention. , these equivalent modifications or substitutions are all included within the scope defined by the claims of the present application.

Claims (10)

1. a ship voice control method, is characterized in that, comprises the following steps: obtaining the collected first voice signal; Preprocessing the first voice signal to obtain a second voice signal; performing feature extraction on the second voice signal to obtain voice features; Perform matching according to the voice feature to obtain a corresponding voice sentence; The voice sentence is used as an operation instruction, and the ship is controlled according to the operation instruction. 2. a kind of ship voice control method according to claim 1, is characterized in that, described first voice signal is preprocessed to obtain second voice signal, specifically: Filter and pre-emphasize the first speech signal to obtain a second speech signal. 3. a kind of ship voice control method according to claim 1, is characterized in that, described carries out matching according to described voice feature, obtains corresponding voice sentence, also comprises: performing acoustic feature matching on the speech features to obtain an acoustic feature vector; Matching the phonetic features through a preset pronunciation dictionary to obtain a corresponding phonetic vocabulary; Sentence matching is performed according to the acoustic feature vector and the phonetic vocabulary to obtain corresponding phonetic sentences. 4. a kind of ship voice control method according to claim 1, is characterized in that, described ship voice control method also comprises: The navigation information of the ship is collected, and the navigation information is broadcast. 5. The method for controlling a ship's voice according to claim 4, wherein the collection of the navigation information of the ship and the broadcasting of the navigation information specifically include: Collect the navigation information of the ship; The navigation information is broadcast according to the navigation information and the broadcast conditions corresponding to the navigation information. 6. a kind of ship voice control method according to claim 4 or 5, is characterized in that, described sailing information at least comprises following at least one: sailing speed, sailing direction, wind speed, wind direction, water flow velocity, water flow direction and ship accident details. 7. a ship voice control system, is characterized in that, comprises: an acquisition unit for acquiring the collected first voice signal; a preprocessing unit, configured to preprocess the first voice signal to obtain a second voice signal; a feature extraction unit, configured to perform feature extraction on the second speech signal to obtain speech features; a matching unit for matching according to the voice feature to obtain a corresponding voice sentence; The operation control unit is used for taking the voice sentence as an operation instruction, and controlling the ship according to the operation instruction. 8. a kind of ship voice control system according to claim 7, is characterized in that, described ship voice control system also comprises: The broadcasting unit is used for collecting the navigation information of the ship and broadcasting the navigation information. 9. A ship voice control device, characterized in that, comprising: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a ship voice control method according to any one of claims 1-7. 10. A storage medium storing processor-executable instructions, wherein, when executed by the processor, the processor-executable instructions are used to execute any one of claims 1-7. A ship voice control method.

Images