WO2020135528A1

WO2020135528A1 - Unmanned aircraft, voice system thereof, and voice interaction method

Info

Publication number: WO2020135528A1
Application number: PCT/CN2019/128381
Authority: WO
Inventors: 雷小刚
Original assignee: 深圳市道通智能航空技术有限公司
Priority date: 2018-12-25
Filing date: 2019-12-25
Publication date: 2020-07-02
Also published as: CN109637533A

Abstract

An unmanned aircraft, a voice system thereof, and a voice interaction method. The voice system is used in the unmanned aircraft, the unmanned aircraft comprising an aircraft body and a remote controller having a communication connection with the aircraft body, and comprises: a voice processor (410), the voice processor (410) being provided with at least one input end and an output end, and being used for processing and converting input signals received by the input end to form output signals outputted from the output end; the input end comprises a first input end (A) used for receiving preset audio fragments as input signals; and a speaker (420), the speaker (420) being connected to the output end, and being used for playing the output signals. The present method enriches the modes of interaction between an unmanned aircraft and a user, and implements voice interaction between the unmanned aircraft and people.

Description

Unmanned aerial vehicle, its voice system and voice interaction method

【Technical field】

The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle, its voice system and voice interaction method.

【Background technique】

With the continuous development of social technology, unmanned aerial vehicles are favored because of their advantages of small structure, flexible operation and convenient deployment, and are used in more and more occasions or fields. All kinds of unmanned aerial vehicles have begun to appear extensively in various large-scale exhibitions, entertainment shooting and even the national military level, which is a hot spot for future social development.

With the rapid development of unmanned aerial vehicles, the functions are becoming more and more powerful, and the increasing number of unmanned aerial vehicles has also caused a series of negative effects, such as fast flight speed and heavy weight unmanned aerial vehicles. ) Will cause certain safety hazards, loss of unmanned aerial vehicles and management problems. How to further improve the unmanned aerial vehicle to reduce the negative impact of the unmanned aerial vehicle is an urgent problem to be solved.

[Invention content]

In order to solve the above technical problems, the embodiments of the present invention provide an unmanned aerial vehicle, a voice system, and a voice interaction method that can enrich the interaction mode of the unmanned aerial vehicle and reduce the negative impact of the unmanned aerial vehicle.

To solve the above technical problems, the embodiments of the present invention provide the following technical solution: An unmanned aerial vehicle voice system, which is applied to an unmanned aerial vehicle, and the unmanned aerial vehicle includes an aircraft body and a remote controller communicatively connected to the aircraft body. The UAV voice system includes:

A voice processor, the voice processor is provided with at least one input terminal and an output terminal, the voice processor is used to process and convert the input signal received by the input terminal to form an output signal output from the output terminal; The input signal includes a preset audio segment, and the input terminal includes a first input terminal for receiving the audio segment;

A speaker, the speaker is connected to the output terminal, and is used for playing the output signal.

Optionally, the input signal further includes collected dynamic speech, and the input terminal further includes a second input terminal for receiving the dynamic speech.

Optionally, the UAV voice system further includes a filtering module, the filtering module is configured to filter and delete sensitive sentences in the dynamic voice according to a preset filtering condition.

Optionally, the dynamic voice includes the first dynamic voice collected by the aircraft body;

The voice processor is also used to process the first dynamic voice and send the processed first dynamic voice to a remote control of an unmanned aerial vehicle and be played by the remote control.

Optionally, the dynamic voice includes a second dynamic voice collected by the remote controller.

Optionally, the UAV voice system further includes an input controller connected to the voice processor, the input controller is configured to control whether the voice processor receives the dynamic voice and/or according to user instructions The audio clip.

Optionally, the audio segment is: an audio segment selected from a preset audio library and corresponding to the current operating state of the UAV.

Optionally, the UAV voice system further includes a power management module; the power management module is electrically connected to the voice processor and the speaker, respectively, and is used to switch into the backup power supply when the UAV is powered off The voice processor and the speaker are powered.

To solve the above technical problems, the embodiments of the present invention also provide the following technical solution: An unmanned aerial vehicle.

The unmanned aerial vehicle includes an aircraft body and a remote controller communicatively connected to the aircraft body, and a wireless communication connection is established between the aircraft body and the remote controller through a wireless transceiver module.

Wherein, the UAV body includes: a memory for storing several preset audio clips to form an audio library; a main controller for configuring the audio according to the current operating state of the UAV Select an audio segment corresponding to the current operating state of the drone aircraft from the library; a voice processor connected to the main controller for processing and converting the audio segment selected by the main controller To form an output signal; and a speaker connected to the voice processor for playing the output signal.

Optionally, the aircraft body further includes a first radio module connected to the voice processor, for collecting first dynamic voice and providing the first dynamic voice to the voice processor;

The voice processor is also used to process and convert the first dynamic voice collected by the first radio module, and send the processed and converted first dynamic voice to the remote controller through the wireless transceiver module and Played by the remote control.

Optionally, the remote controller further includes a second radio module for collecting second dynamic voice and sending it to the voice processor through the wireless transceiver module;

The voice processor is used to process and convert the second dynamic voice collected by the second radio module to form an output signal to be played by the speaker.

Optionally, the speech processor further includes a filtering module; the filtering module is configured to filter and delete sensitive sentences in the first dynamic speech and the second dynamic speech according to a preset filtering condition.

Optionally, the UAV body further includes an input controller; the input controller is used to control whether the voice processor receives according to the received user instruction The first dynamic speech, the second dynamic speech, and/or the audio clip.

Optionally, the UAV body further includes a power management module, a main power supply and a backup power supply electrically connected to the power management module;

The power management module is used to switch on the standby power supply to power the voice processor and the speaker when the main power supply of the aircraft body is powered off.

To solve the above technical problems, the embodiments of the present invention also provide the following technical solution: A voice interaction method for an unmanned aerial vehicle. The voice interaction method includes:

According to the current operating state of the UAV, select the corresponding audio clip in the preset audio library;

Converting and processing the selected audio segment to generate a corresponding first analog output signal;

The first analog output signal is played through the aircraft body.

Optionally, the method further includes: receiving a second dynamic voice collected by the remote controller;

Converting and processing the first dynamic voice to generate a corresponding second analog output signal;

The second simulation output information is played through the aircraft body.

Optionally, the method further includes:

Receiving the first dynamic voice collected by the aircraft body;

Convert and process the first dynamic speech;

Sending the converted and processed first dynamic voice to the remote controller for playing.

Optionally, the method further includes: determining whether to receive the input signal according to the received user instruction;

The input signal includes an audio segment, a first dynamic voice and/or a second dynamic voice.

Optionally, the method further includes: recognizing the content of the first dynamic voice and the second dynamic voice; determining whether the content of the first dynamic voice and the second dynamic voice contains sensitive sentences; if so, deleting the sensitive Statement.

Optionally, the aircraft body further includes a power management module, a main power supply and a backup power supply electrically connected to the power management module, then the method further includes:

Determine whether the main power supply is powered off; if so, the power management module controls the backup power supply to power the aircraft body.

Compared with the prior art, the unmanned aerial vehicle speech system provided by the embodiment of the present invention enriches the interaction mode between the unmanned aerial vehicle and the user, and realizes the voice interaction between the unmanned aerial vehicle and the human. As a result, the safety and practicality of the UAV during use are improved, and the UAV can be applied to more usage scenarios.

[Description of the drawings]

One or more embodiments are exemplified by the pictures in the corresponding drawings. These exemplary descriptions do not limit the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute a scale limitation.

FIG. 1 is a schematic diagram of an unmanned aerial vehicle according to an embodiment of the invention;

2 is a functional block diagram of an aircraft body provided by an embodiment of the present invention;

3 is a functional block diagram of an aircraft body and a remote controller provided by another embodiment of the present invention;

4 is a schematic structural diagram of an unmanned aerial vehicle speech system provided by an embodiment of the present invention;

5 is a schematic structural diagram of a voice system for an unmanned aerial vehicle according to another embodiment of the present invention;

6 is a method flowchart of a voice interaction method provided by an embodiment of the present invention;

7 is a flowchart of a method for a voice interaction method provided by another embodiment of the present invention;

8 is a method flowchart of a voice interaction method according to another embodiment of the present invention.

【detailed description】

In order to facilitate understanding of the present invention, the present invention will be described in more detail with reference to the drawings and specific embodiments. It should be noted that when an element is expressed as "fixed" to another element, it may be directly on the other element, or there may be one or more centered elements in between. When an element is expressed as "connecting" another element, it may be directly connected to the other element, or one or more centered elements may be present therebetween. The terms "upper", "lower", "inner", "outer", "bottom", etc. used in this specification indicate the azimuth or positional relationship based on the azimuth or positional relationship shown in the drawings, just for the convenience of describing this The invention and the simplified description do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as limiting the present invention. In addition, the terms "first", "second", "third", etc. are for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by those skilled in the technical field of the present invention. The terms used in the description of the present invention in this specification are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The term "and/or" used in this specification includes any and all combinations of one or more related listed items.

In addition, the technical features involved in different embodiments of the present invention described below can be combined as long as they do not conflict with each other.

The unmanned aerial vehicle voice system provided by the embodiment of the present invention is used to provide the functions of voice input and voice output for the unmanned aerial vehicle, according to which the voice interaction between the unmanned aerial vehicle and the surrounding people or users can be realized so that it can satisfy more The needs of different usage scenarios. FIG. 1 is an unmanned aerial vehicle using the unmanned aerial vehicle voice system provided by an embodiment of the present invention.

As shown in FIG. 1, the UAV includes an aircraft body 10 and a remote controller 20 communicatively connected to the aircraft body 10.

Wherein, the aircraft body 10 may be of any type, and can provide users with unmanned aerial vehicles capable of satisfying the load capacity, flight speed, and flight range required for use, including but not limited to four-axis unmanned aerial vehicles, fixed-wing aircraft, and Helicopter model, etc. In Figure 1, take the quadcopter unmanned aerial vehicle as an example.

The aircraft body 10 as a mobile vehicle may be equipped with one or more equipment modules to perform corresponding tasks (such as carrying a high-resolution camera to perform an aerial reconnaissance task).

2 is a functional block diagram of an aircraft body 10 provided by an embodiment of the present invention. As shown in FIG. 2, the aircraft body 10 can be equipped with at least the following equipment modules: a memory 11, a main controller 12, a voice processor 13 and a first speaker 14.

Wherein, the memory 11 may specifically use any type of non-transitory storage device, for example, SRAM. It has storage space to meet the needs of use to store data information and/or program instructions. At least one storage partition is provided on the memory 11 for storing an audio library.

The audio library consists of several pre-set audio clips. The preset audio clip is a series of audio preset by technicians for different operating states, and is used for functions such as prompting or alarming.

The main controller 12 is the control core of the entire aircraft body 10, and is used to maintain the normal flight attitude of the aircraft body 10, receive control commands to adjust the course of the aircraft body 10, or control the aircraft body 10 to move up and down. Specifically, any type of central processing unit, microcontroller or similar logic processing chip can be used. In this embodiment, the main controller 12 is also used to call corresponding audio clips in the audio library according to the current operating state of the UAV.

The voice processor 13 is a processing system for performing one or more operations (such as control, conversion, and processing) on audio. It has at least one input terminal and at least one output terminal for receiving the input signal to be processed and outputting the processed output signal, respectively.

The specific operations that the voice processor 13 can perform may be determined according to actual conditions, including but not limited to conversion between digital and analog signals, power amplification, low-pass filtering, high-pass filtering, band-pass filtering, and noise cancellation. In this embodiment, the input end of the voice processor 13 is connected to the main controller 12 and is used to process and convert the audio clip selected by the main controller to form a corresponding output signal.

In some embodiments, the voice processor 13 may be an independent chip circuit, which is set separately from the main controller 12. In other embodiments, the voice processor 13 can also be integrated into the main controller 12 and used as one of the function modules of the main controller 12.

The first speaker 14 is an electro-acoustic transducer connected to the voice processor 13 and used to play the output signal. Its installation is configured on the aircraft body 10 so that it can obtain the sound output capability. The first speaker 14 can be provided with an appropriate number to obtain a sufficient sound output effect. For example, a speaker is arranged around the body of the UAV body to form a mutually compatible speaker array to obtain a better sound output effect.

In the actual use process, after detecting and determining the current operating state of the UAV, the corresponding audio clip can be taken out from the memory 11 by the main controller 12 and processed by the voice processor 13 and provided to the first speaker 14 outward Broadcast or broadcast to achieve the effect of reminder or warning.

The operating state refers to the current operating condition of the UAV determined by one or more measurement standards. It can be determined by the main controller with a certain detection cycle and periodic detection.

"Current" refers to the result determined by the main controller in the current detection cycle. The "operation state" is the main controller used to briefly describe the operation of the UAV.

Each operating state is a series of data sets used to indicate that the current operating conditions of the UAV meet all the standards in the set.

A person skilled in the art may define or define one or more operating states according to actual needs, for example, when the aircraft body 10 is in the take-off state of the take-off stage or the aircraft body 10 is in the landing state of the landing stage.

In this way, during the take-off of the aircraft body 10, the main controller can take out the audio clip and broadcast to the first speaker 14 "The aircraft is about to take off, please pay attention to avoid" or during the descent or landing of the aircraft body 10, The main controller takes out the corresponding audio clip and broadcasts "The aircraft is landing, please pay attention to avoidance" from the first speaker 14, or it can be played when the distance between the aircraft body 10 and obstacles (such as pedestrians) is too small. The plane is approaching, please pay attention to the similar voice.

Please continue to refer to FIG. 1. The remote controller 20 is a terminal device located on the side of the operator to realize the interaction between the aircraft body 10 and the user (such as controlling the flight course of the aircraft body and controlling the camera on the aircraft body to take photos or videos). To achieve the above interaction, the remote controller 20 may be provided with one or more input/output devices, such as a display screen, buttons, touch screen, or joystick, etc., for collecting user instructions and feeding back relevant information to the user.

A communication connection is established between the remote controller 20 and the aircraft body 10 through a wireless communication network. The remote controller 20 and the aircraft body 10 are respectively provided with wireless transceiver modules 30 corresponding to the wireless communication network to realize wireless communication connection with each other, so as to realize bidirectional data transmission between the remote controller 20 and the aircraft body 10.

Generally, the number of the remote controller 20 is only one, and it can only be provided to one user for use. Moreover, the remote controller is limited by requirements such as cost and volume, and cannot provide richer input/output devices.

Therefore, in the preferred embodiment, in addition to the remote controller 20, the UAV vendor or a specific service provider will additionally provide the corresponding mobile application 40 for the UAV. The mobile application 40 is implemented by an electronic computing platform composed of one or more servers.

One or more users can run the mobile application 40 through their own smart terminal device, bind or bind or register one or more aircraft bodies 10, and through the interactive interface provided by the mobile application 40, to bind or register the aircraft The body 10 sends user instructions or receives data information returned by the aircraft body, and acts as a remote controller.

In order to further enrich the voice interaction between the aircraft body and the actual user, in some embodiments, as shown in FIG. 3, the remote controller 20 is further provided with at least one second speaker 21, and at least one aircraft body 10 is provided with at least one First radio module 15.

The first sound receiving module 15 is a transducing device, such as a microphone, for collecting environmental sounds or human voices around the aircraft body 10 and converting sound and electric signals. Specifically, according to the needs of the actual situation, a corresponding type of equipment, such as a pressure microphone, a differential pressure microphone, a combined microphone, or a line microphone, may be selected and fixed at a suitable position on the aircraft body 10.

The second speaker 21 provided on the remote controller 20 may also be any suitable type of electroacoustic transducing device for playing sound to the user of the unmanned aerial vehicle. The second speaker 21 may have the same structure as the first speaker 11 on the aircraft body 10, or different electro-acoustic conversion devices may be used depending on the environment in which the remote controller is used.

In actual use, the first sound collecting module 15 on the aircraft body 10 collects ambient sound or human voice for a period of time as the first dynamic voice in real time. Here, the term “first dynamic voice” refers to the voice collected by the first radio module 15 and changing dynamically with time.

After the first dynamic voice collected by the first radio module 15 is sent to the voice processor 13 for one or more audio processing steps, it is output to the wireless transceiver module 30. The wireless transceiver module 30 loads it on the radio frequency signal and sends it to the remote controller 20 through the wireless communication channel. After receiving the first dynamic voice, the remote controller 20 plays the received dynamic voice for the user of the UAV through the second speaker 21.

Specifically, in addition to the second speaker 21, the remote controller 20 may also be provided with a headphone jack or similar audio output interface 23, thereby allowing the user to access other external audio playback devices to play the first dynamic voice.

In other embodiments, the input device of the remote controller 20 may also include a second radio module 22 for collecting the user's voice or the ambient sound around the remote controller as the second dynamic voice.

These second dynamic voices can also be provided to the voice processor 13 of the aircraft body 10 through the wireless transceiver module 30. After the voice processor 13 performs necessary processing and conversion operations (such as noise reduction, amplification, and filtering) on it, the first speaker 14 output to the aircraft body is converted into a sound signal for playback.

Please continue to refer to FIG. 2 because the audio information collected by the first radio module 15 or the second radio module 22 is live information. The specific voice content is random and variable, and there may be some voice content that is inappropriate or violates the law (such as extremes, sensitivities or splits, phrases that are harmful to national unity, etc.). Therefore, in some embodiments, a filter module 16 may also be added to the voice processor 13 of the aircraft body.

Wherein, the filtering module 16 is a speech recognition module for identifying and detecting words and sentences in the first dynamic speech and the second dynamic speech, and filtering and deleting the first radio module 15 or the first The second radio module 22 collects the sensitive sentences in the obtained first dynamic voice and second dynamic voice, so as to prevent inappropriate voice content from being played by the speaker.

The preset screening conditions are formed by one or more combined conditions. The standard for measuring and quantifying language content from a computer perspective can be configured by technical personnel according to actual needs.

In addition, as shown in FIG. 3, when a radio module is provided on the remote controller 20 and/or the aircraft body 10, the voice processor 13 has multiple channels of input signals, such as the first dynamic voice from the first radio module, The second dynamic voice from the second radio module or the audio clip from the main controller. To ensure flexible control of voice input/output, in some embodiments, the aircraft body 10 may further include an input controller 17 for managing various input signals.

The input controller 17 is connected to the voice processor 13 and used to control whether the voice processor 13 receives the first dynamic voice and the second in the form of turning on/off the input terminal according to the received user instruction Dynamic voice and/or audio clips to flexibly control different input information.

In actual use, the user can send a user instruction to the input controller 17 through the mobile application 40 or the remote controller 20 to control the opening or closing of the three voice interaction paths described in the above embodiments. For example, the user may choose to stop the interaction mode of the first dynamic voice in the interaction interface provided by the mobile application 40. When the input controller receives the instruction, it accordingly causes the voice processor 13 to stop receiving the first dynamic voice.

Of course, the input controller 17 can also adjust the relationship between the input signals according to the preset control logic stored in the memory 11. For example, when the audio clip and the second dynamic voice input are input at the same time, the input controller stops receiving dynamic voice, so that when two signals are input at the same time, the speaker is guaranteed to play the audio clip first.

The unmanned aerial vehicle provided by the embodiment of the present invention has voice input and voice output functions, can realize voice interaction with one or more users, and plays a role of prompting or alarming by playing sound, which expands the use of unmanned aerial vehicles and Application areas.

Of course, those skilled in the art can also add or save one or more functional modules for the UAV according to different application scenarios, and cooperate with the voice input/output functions. As shown in FIG. 3, when the aircraft body 10 is an electrically driven flight vehicle, the aircraft body 10 may further include a backup battery 18 and a power management module 19.

Wherein, the power management module is a functional circuit for managing and distributing power supply for various electronic devices in the aircraft body 10. It can have multiple input and output terminals, access multiple power supplies and provide the working voltage required by each electronic device.

In the electrically-driven aircraft body 10, there is at least one main power source to supply power for the entire aircraft body 10. The main power supply can supply power to the electronic components (such as the main controller, voice processor, and speakers) in the aircraft body 10 through the power management module 19.

The backup battery 18 is relatively compact and independent of the backup power source other than the main power source. In some embodiments, as an optional component, the backup battery 18 is detachably mounted on the aircraft body 10. When the main power supply is cut off, the power management module 19 can switch into the backup power supply to power the voice processor 13 and the first speaker 14 to maintain a minimum voice output function.

With the additional backup battery, the aircraft body 10 can maintain the voice output function when the main power supply is cut off due to some abnormal conditions (such as battery disconnection, battery failure, or serious power shortage) caused by the impact, so that the aircraft body can Be better managed.

Part of the functional modules of the aircraft body shown in Figures 2 and 3 can form a complete unmanned aircraft voice system and be installed in other different types of flight vehicles. As an independent system component, it is added to the unmanned aircraft. Voice input and voice output functions.

4 is a schematic structural diagram of an unmanned aerial vehicle speech system provided by an embodiment of the present invention. In FIG. 4, the entire UAV voice system is described in the form of functional modules. It can be understood by those skilled in the art that these functional modules may be implemented not only by the original hardware system of the unmanned aerial vehicle, but also by a newly added hardware device in the unmanned aerial vehicle.

As shown in FIG. 4, the UAV voice system includes: a voice processor 410 and a speaker 420.

The voice processor 410 is an audio processing chip provided with at least one input terminal and an output terminal, and is used to process and convert the input signal received by the input terminal to form an output signal output from the output terminal.

The processing and conversion may specifically consist of one or more logical operation steps. For different input signals or processing requirements, the voice processor 410 may adopt different processing and conversion methods (for example, adjusting the frequency of noise reduction filtering) to obtain an output signal that meets the requirements.

Wherein, the voice processor 410 at least includes a first input terminal A for receiving a preset audio segment as an input signal. The audio clip refers to standardized audio data with fixed content, which is written into the memory 11 by a technician in a manner such as recording speech or synthesized speech in advance.

Specifically, the audio segment may be preset by a technician for different operating states. It can be selected from the preset audio library by the UAV control system according to the current operating state of the UAV.

The current operating state of the UAV is that the main controller detects and determines the operating conditions of the UAV through one or more measurement standards. "Current operating state" is a classification mark used to indicate that the current operating conditions of the UAV meet all the requirements contained in this operating state.

The speaker 420 is an electroacoustic transducing device connected to the output terminal and used for playing the output signal. It can be driven by the voice processor 410 to play the converted and processed audio clips outward at an appropriate volume.

In order to further enrich the manner of voice interaction, as shown in FIG. 4, the voice processor 410 may further include a second input terminal B. The second input terminal B is used to receive the collected dynamic voice as an input signal and provide it to the voice processor.

The dynamic voice is collected by a radio module such as a microphone in real time, and the content will change audio data. Because its content is determined by the user or the surrounding environment, it is in the process of real-time change. Therefore, it is called dynamic speech.

Since the content of dynamic speech is always uncertain, inappropriate or inappropriate content may appear. To avoid such a situation, in the preferred embodiment, as shown in FIG. 5, at least one filter module 430 may also be added. In FIG. 5, taking the filtering module 430 independently disposed outside the voice processor as an example. Of course, those skilled in the art can understand that the filtering module 430 can also be integrated into the voice processor as part of the voice processor 410.

The filtering module 430 is a functional module with voice recognition and judgment capabilities. It can filter the content of the dynamic voice according to the pre-set screening conditions set by the technician, and delete the sensitive sentences therein.

The sensitive sentence is a voice content that is not suitable for transmission or broadcasting, such as extreme, insulting, and divisive words that violate national laws and regulations. The filtering conditions are set from the perspective of the computer and can be understood by the computer. For example, a large number of basic data can be obtained through crawling and other methods, and an appropriate model can be constructed to quantify the sensitivity of language content.

Specifically, the dynamic voice may specifically include the first dynamic voice collected by the first radio module on the UAV body 10 or the second dynamic voice collected by the second radio module on the remote controller.

In other embodiments, as shown in FIG. 5, the UAV voice system may further include an input controller 440 connected to the voice processor 410.

The input controller 440 is used to control whether the voice processor 410 receives the first dynamic voice, the second dynamic voice and/or a preset audio segment according to user instructions, so that the user can independently turn on or Turning off the playback of the first dynamic voice, the second dynamic voice, or the audio clip has better flexibility.

In addition, a complete unmanned aerial vehicle usually consists of a remote control located on the ground and an aircraft body located in the air. In order to satisfy more usage scenarios, the dynamic voice may be derived from the ambient sound collected by the aircraft body or the surrounding human voice (ie, the first dynamic voice), or the voice of the operating user collected from the remote control (ie The second dynamic voice).

For dynamic speech from different sources, the speech processor 410 can perform different processing and conversion operations, and output to different devices for playback, respectively. To facilitate the presentation and differentiation of dynamic speech from different sources. Here, the first dynamic voice represents the dynamic voice collected by the radio module of the aircraft body, and the second dynamic voice represents the dynamic voice collected by the remote controller.

Please continue to refer to FIG. 5, the first dynamic voice collected by the first radio module provided in the aircraft body is used as an input signal, and is processed by the filter module 430 and then transmitted to the voice processor 410 from the second input terminal. After the voice processor 410 performs analog-to-digital conversion and noise reduction filtering, it is loaded onto the radio frequency signal, and then sent to the remote control of the unmanned aerial vehicle by wireless transmission or the like for playback.

The second dynamic voice from the second radio module of the remote control of the UAV is also provided to the voice processor 410 through the second input terminal B of the filter module 430. After the voice processor 410 performs processing such as noise reduction filtering and digital-to-analog conversion to obtain an output signal, it is output from the output terminal and played by the speaker 420.

In order to provide certain power supply redundancy, in some embodiments, as shown in FIG. 5, the aircraft voice system may further include a power management module 450.

The power management module 450 is respectively connected to the main power supply and the backup power supply of the UAV. Under normal circumstances, it is powered by the main power supply and can charge the backup power supply. When the main power supply is cut off due to special circumstances, the backup power supply is switched on to provide power for the entire UAV voice system.

It should be noted that although in the embodiments of the present invention, only the functional naming and description methods are used to describe the UAV voice interaction system (such as the voice processor 410, the filtering module 430, and the input controller 440). However, those skilled in the art can use different methods to implement the described functions for each specific application according to actual needs (such as power consumption, chip area cost, circuit implementation difficulty, etc.), such as choosing to use hardware and software Or a combination of software and hardware to implement one or more functions of the UAV voice interaction system disclosed in the embodiments of the present invention, such implementation should not be considered beyond the scope of the present invention. On the premise that the functions that need to be performed are known, the hardware circuit combinations or software programs used to implement these functions are well known to those skilled in the art.

During the operation of the entire UAV voice system shown in FIG. 5, the multiple input and output terminals provided by the voice processor cooperate with peripheral devices to implement at least the following three different voice interaction methods to support different scenes to be used. 6 to 8 are the execution flow of the voice interaction mode respectively.

Among them, as shown in FIG. 6, the voice interaction method based on the fixed audio segment includes the following steps:

601. According to the current operating state of the unmanned aerial vehicle, select a corresponding audio segment from a preset audio library.

One or more situations in which the operating state is divided by a series of judgment conditions or measurement standards. Each situation can be used to represent the surrounding environment of the UAV or its own operating conditions. For example, the power of the aircraft body is too low, and the aircraft body is in the process of takeoff/landing.

According to the characteristics of different operating states, one or more audio clips can be pre-set by a technician to form an audio library.

602. Convert and process the selected audio segment to generate a corresponding first analog output signal.

Conventional pre-set and stored audio clips may use a specific encoding format or data format in order to meet the requirements of easy storage and so on. At this time, the voice processor may integrate a corresponding function module to process and convert it to generate an analog output signal suitable for being played by the speaker.

603. Play the first analog output signal through a speaker on the aircraft body.

The sound of the first analog output signal played by the speaker can be heard by people located on the side of the aircraft body, so as to realize mutual voice interaction.

The voice interaction method shown in FIG. 6 can be used in various scenarios and achieve good technical effects. For example, when the unmanned aerial vehicle is flying or flying in an area with a large number of pedestrians, when the unmanned aerial vehicle is in the operating state of takeoff, landing, or abnormality, etc., a corresponding voice prompt is issued to remind the pedestrian to pay attention to avoidance and collision, reduce The risk of a security accident.

Or when the UAV has abnormal crashes or power loss, and the aircraft body 10 is far from the operator and exceeds the control range, it can play the prompt voice through the speaker (such as taking pictures, please do not move, etc.) To a certain deterrent or prompt function, to prevent the aircraft body from being taken away by passersby and lost.

In some embodiments, as shown in FIG. 7, the voice interaction method based on dynamic voice may include the following steps:

701. Receive the first dynamic voice collected by the remote control.

The remote controller collects the first dynamic voice generated by the user or operator in real time, and the content may change. The first dynamic voice can be acquired through a built-in microphone or an external radio equipment.

702. Convert and process the first dynamic voice to generate a corresponding second analog output signal.

Similarly, the first dynamic voice can also be processed by the voice processor to perform noise reduction and format conversion, and then generate a corresponding second analog output signal and provide it to the speaker for playback.

703. Play the second analog output signal through a speaker on the aircraft body.

Through this kind of voice interaction, the UAV can be expanded into a speaker that can be easily moved to play a role in many special scenarios. For example, when a problem occurs in front of a freeway or a curved winding mountain road (such as a collapse accident), which affects driving safety, rescue or firefighters can fly through the unmanned aerial vehicle to the scene of the accident for investigation, and enter the voice through the remote control to prompt the rear Vehicles pay attention to the situation ahead or issue traffic control messages.

Or, at some large-scale event sites, deploy unmanned aerial vehicles at the intersection of people flow. Relevant organization personnel spoke broadcast traffic guidance or event notification information on the remote control side, and broadcast it to people through unmanned aerial vehicles to better facilitate the management and control of people flow and avoid the occurrence of safety accidents.

In other embodiments, as shown in FIG. 8, the dynamic voice-based voice interaction method may also be the reverse process shown in FIG. 7, including the following steps:

801. Receive second dynamic speech collected by the aircraft body.

The second dynamic voice can be collected by an additional microphone or other radio equipment on the aircraft body, which is sound information located on the side of the aircraft body.

802. The second dynamic voice after conversion and processing.

803. Send the converted and processed second dynamic voice to the remote controller through wireless communication.

Similarly, the second dynamic voice collected and processed or converted (such as analog-to-digital conversion, noise reduction filter, etc.) by the voice processor can be loaded on the radio frequency signal, sent to the remote controller through wireless communication and played .

Such a voice interaction mode can enable the operator on the remote control side to learn the environmental status or personnel status on the UAV side by voice. For example, in the case of accidents or disasters where certain rescuers cannot quickly enter or arrive in time, the unmanned aerial vehicle can play a high-quality maneuverability, enter the accident or disaster scene, and collect the voice information of the personnel (such as the scene) Description, required help, etc.) and feedback to the rescuer located at the end of the remote control to facilitate the rescue work.

Of course, the voice interaction methods shown in FIGS. 7 and 8 can also be used in combination to achieve voice communication and communication between the remote control side and the UAV side.

In addition to the three basic voice interaction functions shown in Figures 6-8. In the entire voice interaction process, it can also provide more functions to meet the needs of use.

In some embodiments, the user or operator may send one or more control instructions through a remote control or a corresponding mobile application. The voice interaction system determines whether to receive the input signal according to the control instruction. The input signal includes an audio segment, a first dynamic voice and/or a second dynamic voice. The three voice interaction functions can be selectively turned off, turned on or partially turned off by receiving and controlling the input signal.

In other embodiments, in order to prevent unmanned aerial vehicles from spreading bad voice content, before the dynamic voice is played by the speaker, the voice processor first recognizes the sentences of the first dynamic voice and the second dynamic voice. Then, according to the preset filtering conditions, it is determined whether the sentences of the first dynamic speech and the second dynamic speech are sensitive sentences. Finally, the sensitive sentence is deleted and then provided to the speaker for playback.

The "deletion" refers to a process of avoiding sensitive sentences from being played. Specifically, it can be implemented in any form, such as eliminating the audio signal corresponding to the sensitive sentence or adding a background sound to the audio signal corresponding to the sensitive sentence to cover the original audio signal.

In summary, the voice interaction system provided by the embodiments of the present invention enriches the interaction mode of the unmanned aerial vehicle, and adds voice input/output functions to the unmanned aerial vehicle. Such voice interaction expands the application scenarios of the UAV, and improves the safety and usability when using the UAV.

The above embodiments are only used to illustrate the technical solution of the present invention, not to limit it; under the idea of the present invention, the technical features in the above embodiments or different embodiments may also be combined, and the steps may be implemented in any order There are many other variations of the different aspects of the present invention as described above, and for simplicity, they are not provided in the details; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some of the technical features can be equivalently replaced; and these modifications or replacements do not deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

An unmanned aerial vehicle speech system is applied to an unmanned aerial vehicle. The unmanned aerial vehicle includes an aircraft body and a remote controller communicatively connected to the aircraft body.

A voice processor, the voice processor is provided with at least one input terminal and an output terminal, the voice processor is used to process and convert the input signal received by the input terminal to form an output signal output from the output terminal; The input signal includes a preset audio segment, and the input terminal includes a first input terminal for receiving the audio segment;

A speaker, the speaker is connected to the output terminal, and is used for playing the output signal.
The voice system of an unmanned aerial vehicle according to claim 1, characterized in that the input signal further includes dynamic voice acquired, and the input terminal further includes a second input terminal for receiving the dynamic voice.
The UAV voice system according to claim 2, wherein the UAV voice system further comprises a filtering module, the filtering module is configured to filter and delete the dynamic voice according to a preset filtering condition Sensitive statement.
The unmanned aerial vehicle voice system according to claim 2, wherein the dynamic voice includes a first dynamic voice acquired by the aircraft body;

The voice processor is also used to process the first dynamic voice and send the processed first dynamic voice to the remote controller and play it by the remote controller.
The UAV voice system according to claim 2, wherein the dynamic voice includes a second dynamic voice collected by the remote controller.
The UAV voice system according to claim 2, wherein the UAV voice system further includes an input controller connected to the voice processor, the input controller is used to control the Whether the speech processor receives the dynamic speech and/or the audio segment.
The voice system for an unmanned aerial vehicle according to any one of claims 1-6, wherein the audio segment is selected from a preset audio library and corresponds to the current operating state of the unmanned aerial vehicle Audio clip.
The UAV voice system according to any one of claims 1-7, wherein the UAV voice system further includes a power management module;

The power management module is electrically connected to the voice processor and the speaker, respectively, and is used to cut in a backup power supply to power the voice processor and the speaker when the UAV is powered off.
An unmanned aerial vehicle includes an aircraft body and a remote controller communicatively connected to the aircraft body. A wireless communication connection is established between the aircraft body and the remote controller through a wireless transceiver module. The aircraft body includes:

Memory, used to store several preset audio clips to form an audio library;

The main controller is used to select an audio segment corresponding to the current operating state of the drone aircraft from the audio library according to the current operating state of the unmanned aerial vehicle;

A voice processor, the voice processor is connected to the main controller, and is used to process and convert the audio segment selected by the main controller to form an output signal; and

A speaker, the speaker is connected to the voice processor, and is used to play the output signal.
The unmanned aerial vehicle according to claim 9, wherein the aircraft body further includes a first radio module connected to the voice processor for collecting first dynamic voice and providing the voice processor with Describe the first dynamic voice;

The voice processor is also used to process and convert the first dynamic voice collected by the first radio module, and send the processed and converted first dynamic voice to the remote controller through the wireless transceiver module and Played by the remote control.
The UAV according to claim 9, wherein the remote controller further includes a second radio module for collecting second dynamic voice and sending it to the voice processor through the wireless transceiver module;

The voice processor is used to process and convert the second dynamic voice collected by the second radio module to form an output signal to be played by the speaker.
The UAV according to claim 10 or 11, wherein the voice processor further includes a filter module; the filter module is configured to filter and delete the first dynamic voice and all Describe the sensitive sentences in the second dynamic speech.
The UAV according to claim 10 or 11, wherein the aircraft body further includes an input controller;

The input controller is configured to control whether the voice processor receives the first dynamic voice, the second dynamic voice, and/or the audio segment according to the received user instruction.
The UAV according to claim 9, wherein the aircraft body further includes a power management module, a main power supply and a backup power supply electrically connected to the power management module;

The power management module is used to switch on the standby power supply to power the voice processor and the speaker when the main power supply of the aircraft body is powered off.
A voice interaction method for an unmanned aerial vehicle. The unmanned aerial vehicle includes an aircraft body and a remote controller communicatively connected to the aircraft body. The voice interaction method includes:

According to the current operating state of the UAV, select the corresponding audio clip in the preset audio library;

Converting and processing the selected audio segment to generate a corresponding first analog output signal;

The first analog output signal is played through the aircraft body.
The voice interaction method according to claim 15, wherein the method further comprises:

Receiving the second dynamic voice collected by the remote controller;

Converting and processing the first dynamic voice to generate a corresponding second analog output signal;

The second simulation output information is played through the aircraft body.
The voice interaction method according to claim 16, wherein the method further comprises:

Receiving the first dynamic voice collected by the aircraft body;

Convert and process the first dynamic speech;

Sending the converted and processed first dynamic voice to the remote controller for playing.
The voice interaction method according to claim 17, wherein the method further comprises:

According to the received user instructions, determine whether to receive the input signal;

The input signal includes an audio segment, a first dynamic voice and/or a second dynamic voice.
The voice interaction method according to claim 17 or 18, wherein the method further comprises:

Recognizing the content of the first dynamic voice and the second dynamic voice;

Determine whether the content of the first dynamic speech and the second dynamic speech contains sensitive sentences;

If yes, delete the sensitive sentence.
The voice interaction method according to claims 15-19, wherein the aircraft body further includes a power management module, a main power supply and a backup power supply electrically connected to the power management module, then the method further includes:

Determine whether the main power supply is powered off;

If yes, the power management module controls the backup power supply to power the aircraft body.