WO2022247156A1

WO2022247156A1 - Voice interaction system and method, and intelligent device

Info

Publication number: WO2022247156A1
Application number: PCT/CN2021/130287
Authority: WO
Inventors: 李刚; 董飞; 曲国健; 赵锬鸿; 李响; 王伯长; 严韶明; 陈亚伟
Original assignee: 京东方科技集团股份有限公司; 北京京东方显示技术有限公司
Priority date: 2021-05-28
Filing date: 2021-11-12
Publication date: 2022-12-01
Also published as: CN113192509A

Abstract

A voice interaction system and method, and an intelligent device. The voice interaction system comprises: a voice interaction unit (100) used for acquiring and recognizing a target voice instruction of a user; a photoelectric sensing unit (200) connected to the voice interaction unit (100) and used for receiving and recognizing a target limb instruction of the user and controlling the voice interaction unit (100) to be turned on and off according to the target limb instruction; and an instruction control unit (300) connected to the voice interaction unit (100) and used for determining whether the voice interaction unit (100) is in an on state: if yes, receiving and recognizing the target voice instruction of the user according to the voice interaction unit (100), and controlling the intelligent device to execute an action corresponding to the target voice instruction. An intelligent voice loudspeaker box can be turned on by means of limb sensing, and interaction with the whole intelligent device can be achieved.

Description

Voice interaction system and method, smart device

Cross References to Related Applications

This application claims priority to Chinese Patent Application No. 202110594436.8 filed in China on May 28, 2021, the entire contents of which are hereby incorporated by reference.

technical field

The present disclosure relates to the technical field of smart devices, in particular to a voice interaction system and method, and a smart device.

Background technique

The Internet of Things has become an important driving force for a new round of global technological revolution and industrial transformation. Now there are endless smart speakers on the market, of all kinds. The "Xiaodu" launched by Baidu and the Siri on the Apple mobile phone are all intelligent voice technologies. Its core is very simple - let the machine have the ability to be similar to human beings in the voice dialogue, and penetrate into people's daily life space. As an important part of the smart voice speaker, the microphone determines the ability of voice interaction. In related technologies, if a smart voice speaker wants to realize interaction, it needs a microphone to give instructions to tell consumers to start voice recognition.

Contents of the invention

Embodiments of the present disclosure provide a voice interaction system and method, and a smart device, which can realize body sensing to turn on the smart voice speaker, and interact with the entire smart device.

The technical solutions provided by the embodiments of the present disclosure are as follows:

An embodiment of the present disclosure provides a voice interaction system, including:

The voice interaction unit is used to collect and recognize the target voice command of the user;

A photoelectric sensing unit, the photoelectric sensing unit is connected to the voice interaction unit, and is used to receive and recognize the target limb instruction of the user, and control the switch of the voice interaction unit according to the target limb instruction;

An instruction control unit, the instruction control unit is connected with the voice interaction unit, and is used to judge whether the voice interaction unit is in an on state; The target voice commands corresponding actions.

Exemplarily, the command control unit is also used to determine whether the voice interaction unit receives a voice command within a predetermined time when the voice interaction unit is in the on state; if not, send the voice interaction unit to the voice interaction unit the close command.

Exemplarily, the voice interaction unit is further configured to: when receiving the close command of the voice interaction unit, send the close command of the photoelectric sensor unit to the photoelectric sensor unit.

Exemplarily, the instruction control unit is further configured to receive and identify the image data collected by the image acquisition unit; and when the image data includes a target gesture, send an activation instruction of the voice interaction unit to the voice interaction unit;

The voice interaction unit is further configured to send an activation instruction of the photoelectric induction unit to the photoelectric induction unit when receiving the activation instruction of the voice interaction unit.

Exemplarily, the voice interaction unit communicates with the instruction control unit through serial port instructions,

The voice interaction unit communicates with the instruction control unit through serial port instructions.

Exemplarily, the photoelectric sensing unit includes a photoelectric switch, and the photoelectric switch includes:

A casing, the interior of the casing is hollow, the casing includes a front end and a rear end, the front end is provided with an indicator mark, and the rear end is open;

a photoelectric sensor arranged in the housing;

a circuit board arranged in the casing, the circuit board is connected to the photoelectric sensor;

a rear cover snapped onto the rear end of the housing;

A signal transmission harness, one end of the signal transmission harness is connected to the circuit board, and the other end extends out of the rear cover.

Exemplarily, the rear end of the housing is connected to the rear cover through a buckle.

Exemplarily, the front end is provided with a first through hole and a second through hole;

The photoelectric sensor is provided with a receiver and an emitter, the receiver is located at the first through hole, and the emitter is located at the second through hole.

Exemplarily, the indication mark includes an engraved hollow mark.

Exemplarily, the photoelectric switch further includes: a light source disposed in the housing.

Exemplarily, the voice interaction unit includes a microphone module, and the microphone module includes:

The upper cover, the upper cover is hollow inside, the upper cover includes a front end and a rear end, the front end is provided with at least two sound receiving holes, and the rear end is open;

At least two sound-receiving microphones arranged inside the upper cover, each of the sound-receiving microphones is set corresponding to one of the sound-receiving holes, and each of the sound-receiving holes is provided with a sealing ring;

a printed circuit board arranged inside the upper cover, and the printed circuit board is connected to the sound-receiving microphone;

The bottom cover is arranged at the rear end of the upper cover.

Exemplarily, the microphone module also includes:

The signal transmission wiring harness connected to the printed circuit board, and the wire pressing plate arranged on the printed circuit board for pressing the signal transmission wiring harness.

Exemplarily, the bottom cover and the crimping plate are fixed to the upper cover through buckles, and packaged with a sealant.

An embodiment of the present disclosure also provides a voice interaction method, including:

judging whether the voice interaction unit is on;

If so, control the smart device to perform an action corresponding to the target voice command according to the user's target voice command received and recognized by the voice interaction unit;

If not, according to the user's target body instruction received and recognized by the photoelectric sensing unit, the voice interaction unit is controlled to open, and according to the voice interaction unit receiving and recognizing the user's target voice instruction, the smart device is controlled to execute the target voice instruction corresponding action.

Exemplary, the method also includes:

When the voice interaction unit is turned on, it is judged whether the voice interaction unit has received a voice instruction within a predetermined time; if not, the voice interaction unit is controlled to be turned off.

Exemplary, the method also includes:

When the voice interaction unit is turned on, it is judged whether the voice interaction unit receives a voice command within a predetermined time; if not, the photoelectric sensor unit is controlled to be turned off.

Exemplary, the method also includes:

receiving and identifying the image data collected by the image acquisition unit;

When the image data includes a target gesture, the photoelectric sensing unit and the voice interaction unit are controlled to be turned on.

The embodiment of the present disclosure also provides a smart device, on which the voice interaction system provided by the embodiment of the present disclosure is provided.

The beneficial effects brought by the embodiments of the present disclosure are as follows:

The voice interaction system and method, and the smart device provided by the embodiments of the present disclosure combine the intelligent voice interaction unit with the photoelectric sensor unit, and can control the switch of the voice interaction unit through body movements, realize interaction with the whole machine, and solve the problem of photoelectricity. How does the induction unit control the opening of the voice interaction unit and the technical problem of instructing the control unit to switch the voice interaction unit and the photoelectric induction unit.

Description of drawings

FIG. 1 is a structural block diagram of a voice interaction system provided in an embodiment of the present disclosure;

FIG. 2 is a logical block diagram of a voice interaction system provided in an embodiment of the present disclosure;

Fig. 3 is a schematic diagram of the communication mode between the command control unit, the voice interaction unit and the photoelectric sensing unit;

FIG. 4 is a schematic structural diagram of a photoelectric switch in an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of the structure of the front end of the housing of the photoelectric switch in the embodiment of the present disclosure;

FIG. 6 is an exploded diagram of the structure of the microphone module in the embodiment of the disclosure.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present disclosure. Apparently, the described embodiments are some of the embodiments of the present disclosure, not all of them. Based on the described embodiments of the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without creative effort fall within the protection scope of the present disclosure.

Unless otherwise defined, the technical terms or scientific terms used in the present disclosure shall have the usual meanings understood by those skilled in the art to which the present disclosure belongs. "First", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Likewise, words like "a", "an" or "the" do not denote a limitation of quantity, but mean that there is at least one. "Comprising" or "comprising" and similar words mean that the elements or items appearing before the word include the elements or items listed after the word and their equivalents, without excluding other elements or items. Words such as "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "Down", "Left", "Right" and so on are only used to indicate the relative positional relationship. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

The voice interaction system provided by the embodiments of the present disclosure can be applied to various smart devices, for example, smart refrigerators, smart washing machines, and smart TVs.

FIG. 1 is a structural block diagram of a speech interaction system provided in an embodiment of the present disclosure, and FIG. 2 is a logical block diagram of the speech interaction system provided in an embodiment of the present disclosure.

Referring to Fig. 1 and Fig. 2, the voice interaction system of the smart device provided by the embodiment of the present disclosure includes:

The voice interaction unit 100 is used to collect and recognize the user's target voice instruction;

A photoelectric sensing unit 200, the photoelectric sensing unit 200 is connected to the voice interaction unit 100, and is used to receive and recognize the target limb instruction of the user, and control the switch of the voice interaction unit 100 according to the target limb instruction;

An instruction control unit 300, the instruction control unit 300 is connected to the voice interaction unit 100, and is used to determine whether the voice interaction unit 100 is in an on state; if so, according to the voice interaction unit 100 receiving and recognizing the user's target voice instruction, The smart device is controlled to perform an action corresponding to the target voice instruction.

In the above solution, the photoelectric sensor unit 200, the voice interaction unit 100 and the instruction control unit 300 are connected to form a voice interaction system, which can be applied to smart devices. Combining the voice interaction unit 100 and the photoelectric sensor unit 200 can realize , to control the switch of the voice interaction unit 100, realize the interaction with the whole machine, and solve the technical problems of how the photoelectric induction unit 200 controls the opening of the voice interaction unit 100 and instructs the control unit 300 to switch the voice interaction unit 100 and the photoelectric induction unit 200.

In some embodiments, the instruction control unit 300 is also used to determine whether the voice interaction unit 100 receives a voice instruction within a predetermined time when the voice interaction unit 100 is in the on state; 100 sends an instruction to close the voice interaction unit 100 .

In some embodiments, the voice interaction unit 100 is further configured to: when receiving the close command of the voice interaction unit 100 , send the close command of the photoelectric sensor unit 200 to the photoelectric sensor unit 200 .

In some embodiments, the voice interaction system further includes an image acquisition unit 400, the instruction control unit 300 is connected to the image acquisition unit 400, and the instruction control unit 300 is also used to receive and identify the image acquisition unit 400 Collected image data; and when the image data includes a target gesture, send the voice interaction unit 100 an opening instruction to the voice interaction unit 100; the voice interaction unit 100 is also used to receive the voice interaction unit 100 When the turn-on instruction of the photoelectric sensing unit 200 is sent to the photoelectric sensing unit 200 .

The voice interaction system provided by the embodiments of the present disclosure is described in more detail below:

In the voice interaction system provided by the embodiment of the present disclosure, the voice interaction unit 100 may include a microphone module (MIC) and the like. According to different use environments and different requirements for sound quality, the voice interaction unit can choose different types of silicon microphones, and can design microphone modules with different numbers of silicon microphones. Taking the microphone module as an example, the method of collecting and recognizing the user's target voice command may be that the microphone module starts to record the user's voice, and sends the recorded audio to the command control unit 300 .

The photoelectric sensing unit 200 may include distance sensing switch devices such as a photoelectric switch, a laser sensor switch, an electromagnetic induction sensor switch, and a capacitive sensing sensor switch. Taking the photoelectric switch as an example, the photoelectric switch is based on infrared sensing technology. The principle is to use the physical properties of infrared rays, and the principle that the infrared signal encounters obstacles with different reflection intensities at different distances to detect the distance of obstacles. Combining the infrared sensor with the switch circuit forms a sensor distance switch. The method of using the photoelectric switch to receive and identify the user's target body instructions can be that the user performs some kind of body movement within the sensing distance of the photoelectric switch, for example, approaching the photoelectric switch or waving and other body movements, the photoelectric switch receives the reflected light signal, Recognize body movement commands based on light signals.

The instruction control unit 300 may be a computer, an MCU, etc., for example, the instruction control unit 300 may be a PC terminal of a smart device.

In the voice interaction system of the embodiment of the present disclosure, the voice interaction unit 100 communicates with the instruction control unit 300 through serial port instructions, and the voice interaction unit 100 communicates with the instruction control unit 300 through serial port instructions. to communicate.

The specific structures of the voice interaction unit 100 , the photoelectric sensor unit 200 and the command control unit 300 will be further described later, and the voice interaction implementation process of the voice interaction system will be explained in more detail below.

As shown in Figure 2, the voice interaction method of the voice interaction system of the smart device provided in the embodiment of the present disclosure may include the following process:

1) The user independently turns on the voice interaction unit 100, the command control unit 300 receives the target voice command sent by the voice interaction unit 100, and controls the smart device according to the target voice command received and recognized by the voice interaction unit 100 Executing an action corresponding to the target voice instruction, so as to realize voice interaction. The process in the logic block diagram is sequence number B→sequence number C.

2) When the voice interaction unit 100 is in the open state, the command control unit 300 judges whether the voice interaction unit 100 receives a voice command within a predetermined time; if not, sends the voice command to the voice interaction unit 100 A closing command of the interactive unit 100;

Specifically, for example, according to the algorithm, when the instruction control unit 300 detects that the voice interaction unit 100 does not input a voice within a certain period of time, the instruction control unit 300 will send a shutdown instruction to the voice interaction unit 100 (serial number ②) , the voice interaction unit 100 stops recording, and will no longer send a voice command (serial number ③) to the command control unit 300. At the same time, the voice interaction unit 100 sends a shutdown command (sequence number ④) to the photoelectric sensor unit 200, and the photoelectric sensor unit 200 is turned off.

It should be noted that after the user's voice command is completed, and there is no voice command for a period of time, the command control unit 300 will send a shutdown command to the voice interaction unit 100. At this time, the voice interaction unit 100 can be in a standby state, so that not only can save power , and can also play a role in protecting privacy. At this time, the voice of the user will not be recorded and saved by the voice interaction unit 100 .

3) When the voice interaction unit 100 is in the off state, when the photoelectric sensor unit 200 senses the user's target limb instruction, it sends an instruction to the voice interaction unit 100 to control the voice interaction unit 100 to be turned on, and the The command control unit 300 receives the target voice command sent by the voice interaction unit 100, and according to the voice interaction unit 100 receiving and recognizing the user's target voice command, controls the smart device to perform an action corresponding to the target voice command, so as to realize the voice interact;

For example, when the user is close to the photosensitive unit 200 (that is, the distance between the user and the photosensitive unit 200 is less than a predetermined distance) or the user makes a target body movement (for example, waving) in front of the sensor of the photosensitive unit 200, the photosensitive unit 200 sends a signal to the photosensitive unit 200. The voice interaction unit 100 sends the start command, the voice interaction unit 100 starts recording, and sends the recording data to the command control unit 300, the command control unit 300 recognizes the text according to the recorded audio, and makes corresponding actions according to the user's voice. In the logic block diagram The middle is serial number A→serial number B→serial number C.

4) The command control unit 300 can autonomously send an activation command (serial number Y) to the voice interaction unit 100, the voice interaction unit 100 is turned on, and sends the received audio data including the target voice command to the command control unit 300 (serial number Z), The voice interaction unit 100 sends an opening command to the photoelectric sensing unit 200, and the photoelectric sensing unit 200 is turned on.

For example, taking the smart refrigerator as an example, the voice interaction system also includes an image acquisition unit 400. When the user is far away from the photoelectric sensing unit 200 and exceeds the threshold, or the sensing is affected and the sensitivity is disturbed, at this time It may not be possible to turn on the photoelectric sensor unit 200 and the voice interaction unit 100 through body movements. Then, the instruction control unit 300 can be based on the images collected by the image acquisition unit 400. For example, when the collected images include target gestures, then the instruction control unit 300 The unit 300 judges that the user has the intention to open the voice interaction unit 100, thereby sending an opening instruction (serial number V) to the voice interaction unit 100, and at the same time, the voice interaction unit 100 sends an opening instruction to the photoelectric sensor unit 200 to open the voice interaction unit 100 and Photoelectric sensing unit 200.

3 is a schematic diagram of the communication mode between the command control unit 300, the voice interaction unit and the photoelectric sensor unit 200. The command control unit 300 is used as the host (PC end) of the smart device, and the voice interaction unit 100 includes a microphone module (MIC). The photoelectric sensing unit 200 includes a photoelectric switch LED light as a specific embodiment, and the specific work flow is described as follows:

1) Connect as shown in Figure 3, the photoelectric sensor unit 200 is connected to the voice interaction unit 100, and the voice interaction unit 100 is connected to the command control unit 300; the MIC defaults to the MUTE ON state. At this time, the MIC remains in the standby state and does not output voice commands. Send the corresponding MUTE ON state to the photoelectric sensing unit 200, the photoelectric switch remains closed (MUTE ON state), and the LED light goes out;

2) When the PC sends the MUTE ON command to the MIC through UART (Universal Asynchronous Receiver/Transmitter), the MIC is turned off, and at the same time the MIC sends the current state to the photoelectric sensor unit 200 through the serial port, and the photoelectric switch is turned off (MUTE ON state), the LED light is off;

3) When the PC sends the MUTE OFF command to the MIC through the UART, the MIC is turned on, and at the same time, the MIC sends the current state to the photoelectric sensor unit 200 through the serial port, the photoelectric switch is turned on (MUTE OFF state), and the LED light is turned on; the photoelectric switch only In the MUTE ON state (LED is off), the user's body commands can be received, and in the MUTE OFF state (LED is on), the user's body commands cannot be received.

Specifically, the control instructions in the voice interaction system are shown in Table 1:

Table 1: PC-MIC-photoelectric switch control command

The above is the description of the logical design of the voice interaction system for smart devices provided by the embodiments of the present disclosure. The structure of each unit in the voice interaction system for smart devices provided by the embodiments of the present disclosure will be described in detail below.

In some embodiments, as shown in FIG. 4 and FIG. 5, the photoelectric sensing unit 200 includes a photoelectric switch, and the photoelectric switch includes: a housing 210, a photoelectric sensor 220, a circuit board 230, a rear cover 240 and a first signal transmission Wire harness (not shown in the figure), the interior of the housing 210 is hollow, the housing 210 includes a front end and a rear end, the front end is provided with an indicator mark 211, and the rear end is open; the photoelectric sensor 220 is arranged in the housing 210; The circuit board 230 is arranged in the housing 210, and the circuit board 230 is connected to the photoelectric sensor 220; the rear cover 240 is buckled on the rear end of the housing 210; one end of the first signal transmission harness is connected to the circuit The board 230 is connected, and the other end protrudes from the back cover 240 , and the photoelectric switch also includes a light source arranged in the housing 210 . For example, the light source may comprise LED lights.

In some embodiments, as shown in FIG. 4 , the rear end of the housing 210 is connected to the rear cover 240 through buckling. For example, the rear end of the housing 210 can be provided with a buckle groove, the rear cover 240 is provided with a buckle 241, and the buckle 241 on the back cover 240 is stuck in the buckle groove of the housing 210, and the After the rear cover 240 covers the casing 210, it can prevent it from falling off.

In addition, in some embodiments, as shown in FIG. 5 , the front end is provided with a first through hole 213 and a second through hole 214; the photoelectric sensor 220 is provided with a receiving electrode and an emitter electrode, and the receiving electrode The emitter is located at the first through hole 213 , and the emitter is located at the second through hole 214 , so that the receiver and emitter of the photosensor 220 are exposed.

In the above solution, the size of the first through hole 213 and the second through hole 214 is aligned to expose the receiving electrode and the emitter, for example, the diameter of the first through hole 213 and the second through hole 214 can be is 2.8mm.

In addition, in some embodiments of the present disclosure, the indication mark includes an engraved hollow mark. In this way, the front surface of the housing 210 has an engraved hollow logo, which can clearly display the mark on the surface of the photoelectric switch housing 210. For example, the mark is text, such as "Wave Hand To Speak", reminding the user to turn on the photoelectric switch by waving his hand to wake up the microphone. Make a recording.

The depth of the embossed design of the engraved hollow mark on the front surface of the housing 210 may be about 0.3 mm. Compared with the hollow mark engraved in the sun, the font is clearer. The engraved font is thicker. If the casing 210 is formed by injection molding and the surface is painted, the light transmission of the casing 210 is not good. The thicker the font, the darker the display and the worse the contrast effect. If the form of intaglio and hollowing is adopted, the font will be thinner, the brighter the display, the better the contrast effect, and the technical problem that the mark of the shell 210 is not clearly displayed when the photoelectric switch is working is solved.

In addition, it should be noted that the surface of the housing 210 can be painted. For example, if Pantone 656C color is selected, the thickness of the paint can be 0.7-0.12 μm, so as to ensure that the light of the LED is evenly transmitted, and the handwriting of the engraved hollow logo is clearly displayed.

In addition, in the embodiment of the present disclosure, the photoelectric sensor 220 in the photoelectric switch can be an infrared sensor, and the infrared sensor can determine the range of the energizing current and the sensing distance of the infrared sensor through the size of the peripheral resistance. For example, according to the actual use environment, the sensing distance of the photoelectric switch may be about 80 mm, but it is not limited thereto.

The emitter of the infrared sensor emits infrared light. When the user performs physical movements (for example, approaching the photoelectric switch or waving) within the sensing distance, the emitted infrared light will reflect the light under the reflection of blocking obstacles. At this time, the receiving pole of the infrared sensor will receive the light signal and convert the light signal into an electrical signal. The photoelectric switch controls the LED light to light up according to the electrical signal of the infrared sensor, and at the same time wakes up the microphone module according to the UART command.

In addition, in a specific exemplary embodiment, the circuit board 230 in the photoelectric switch includes a first surface and a second surface opposite to each other, and an LED light is provided on the first surface to provide the photoelectric switch with As a light source, after the LED light is turned on, the light can pass through the casing 210 to display the engraved hollow logo on the front end of the casing 210 .

The infrared sensor and peripheral resistors are also arranged on the first surface.

A photoelectric sensor main chip and a first signal transmission harness are arranged on the second surface, and the photoelectric sensor main chip receives the signal sent by the infrared sensor, processes the signal, and sends an activation signal to the microphone module. instruction. One end of the first signal transmission wire harness is connected to the circuit board 230, and the other end passes through the through hole provided in the center of the rear cover 240, and is connected with the first signal transmission wire harness of the microphone module, and the photoelectric switch receives Both the signal transmission harness and the sending instruction are transmitted.

In addition, in some embodiments, the voice interaction unit includes a microphone module. The figure shows an exploded view of the structure of an embodiment of the microphone module.

As shown in Figure 6, the microphone module includes: an upper cover 110, at least two radio microphones (not shown in the figure), a printed circuit board 120, a sealing ring 130 and a bottom cover 140, wherein the inside of the upper cover 110 Hollow, the upper cover 110 includes a front end and a rear end, the front end is provided with at least two sound-receiving holes, and the rear end is open; at least two sound-receiving microphones are arranged inside the upper cover 110, each of the sound-receiving microphones Corresponding to one of the sound receiving holes, and each of the sound receiving holes is provided with a sealing ring 130; the printed circuit board 120 is arranged inside the upper cover 110, and the printed circuit board 120 is connected to the sound receiving microphone; The bottom cover 140 is disposed on the rear end of the upper cover 110 .

In some embodiments, the microphone module further includes: a second signal transmission wire harness connected to the printed circuit board 120, and a wiring harness arranged on the printed circuit board 120 for pressing the second signal transmission wire harness. The wire harness plate 150. The bottom cover 140 and the pressure plate are fixed on the upper cover 110 by buckles, and sealed by a sealant.

As an exemplary embodiment, the upper cover 110 of the microphone module is silk-screened with a black mark (LOGO), which is convenient for users to identify. The location is more conducive to the collection of sound.

As an exemplary embodiment, the printed circuit board 120 includes a front side and a back side. Taking two microphones as an example, the two microphones are arranged at two ends of the front side. Taking the number of microphones in the microphone module as an example, after the ambient noise is sampled, the sound waveform is analyzed and phase-operated, and superimposed on the sampling waveform of the main microphone to form a phase cancellation, so that one of the microphones can keep a stable and clear recording, and the other One microphone actively eliminates physical noise, and after algorithm processing, the recorded sound is clearer, which solves the technical problem of poor recording effect of the microphone in a noisy environment. Dual microphones can improve the signal when dealing with changing and complex sound environments. The noise ratio keeps the recording sound pure, and the post-algorithm processing is more accurate.

The front of the printed circuit board 120 is also provided with a voice signal main chip, which can perform processing such as noise reduction and algorithm optimization according to the sound data entered by the two microphones. At the same time, the voice signal main chip includes a serial port interface for sending And receive instructions from photoelectric switches and PC terminals.

A reset key is provided on the back of the printed circuit board 120 for subsequent software upgrade operations.

The back of the printed circuit board 120 is also provided with a connecting line jack for connecting the second signal transmission harness to maintain signal data transmission between the photoelectric switch and the PC terminal.

The bottom cover 140 and the wire crimping cover can be connected to the upper cover 110 by a buckle, and encapsulated by a sealant to prevent damage from external force.

Judging whether the voice interaction unit 100 is in an open state;

If yes, according to the user's target voice command received and recognized by the voice interaction unit 100, control the smart device to perform an action corresponding to the target voice command;

If not, the voice interaction unit 100 is controlled to be turned on according to the user's target body instruction received and recognized by the photoelectric sensing unit 200, and the smart device is controlled to perform the same operation as described above according to the voice interaction unit 100 receiving and recognizing the user's target voice instruction. The target voice commands the corresponding action.

In some exemplary embodiments, the method also includes:

When the voice interaction unit 100 is turned on, it is judged whether the voice interaction unit 100 receives a voice command within a predetermined time; if not, the voice interaction unit 100 is controlled to be turned off.

In some exemplary embodiments, the method also includes:

When the voice interaction unit 100 is turned on, it is determined whether the voice interaction unit 100 receives a voice command within a predetermined time; if not, the photoelectric sensor unit 200 is controlled to be turned off.

In some exemplary embodiments, the method also includes:

Receiving and identifying the image data collected by the image collection unit 400 in the smart device;

When the image data includes the target gesture, the photoelectric sensing unit 200 and the voice interaction unit 100 are controlled to be turned on.

The specific voice interaction process of the voice interaction method is the same as the specific voice interaction process of the voice interaction system provided in the present disclosure, and will not be repeated here.

The smart devices provided by the embodiments of the present disclosure may include smart refrigerators, smart washing machines, smart TVs, etc., and the application scenarios are not limited to household appliances, but can also be applied to application scenarios such as shopping guides in clothing shopping malls and self-service convenience stores.

The following points need to be explained:

(1) The drawings of the embodiments of the present disclosure only relate to the structures involved in the embodiments of the present disclosure, and other structures may refer to general designs.

(2) For the sake of clarity, in the drawings used to describe the embodiments of the present disclosure, the thicknesses of layers or regions are exaggerated or reduced, that is, the drawings are not drawn in actual scale. It will be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, it can be "directly on" or "under" the other element, or Intermediate elements may be present.

(3) In the case of no conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other to obtain new embodiments.

The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

A voice interaction system is characterized in that it comprises:

The voice interaction unit is used to collect and recognize the target voice command of the user;

A photoelectric sensing unit, the photoelectric sensing unit is connected to the voice interaction unit, and is used to receive and recognize the target limb instruction of the user, and control the switch of the voice interaction unit according to the target limb instruction;

An instruction control unit, the instruction control unit is connected with the voice interaction unit, and is used to judge whether the voice interaction unit is in an on state; The target voice commands corresponding actions.
The voice interactive system according to claim 1, wherein,

The command control unit is also used to judge whether the voice interaction unit has received a voice command within a predetermined time when the voice interaction unit is in an on state; if not, send a shutdown command of the voice interaction unit to the voice interaction unit.
The voice interactive system according to claim 2, wherein,

The voice interaction unit is further configured to: when receiving the closing command of the voice interaction unit, send the closing command of the photoelectric sensing unit to the photoelectric sensing unit.
The voice interaction system according to claim 1, wherein,

The voice interaction system also includes an image acquisition unit, the instruction control unit is connected to the image acquisition unit, and is used to receive and identify the image data collected by the image acquisition unit, and when the image data includes a target gesture, send The voice interaction unit sends an activation instruction of the voice interaction unit;

The voice interaction unit is further configured to send an activation instruction of the photoelectric induction unit to the photoelectric induction unit when receiving the activation instruction of the voice interaction unit.
The voice interaction system according to claim 1, wherein,

The voice interaction unit communicates with the instruction control unit through serial port instructions,

The voice interaction unit communicates with the instruction control unit through serial port instructions.
The voice interaction system according to claim 1, wherein,

The photoelectric sensing unit includes a photoelectric switch, and the photoelectric switch includes:

A casing, the interior of the casing is hollow, the casing includes a front end and a rear end, the front end is provided with an indicator mark, and the rear end is open;

a photoelectric sensor arranged in the housing;

a circuit board arranged in the casing, the circuit board is connected to the photoelectric sensor;

a rear cover snapped onto the rear end of the housing;

A signal transmission harness, one end of the signal transmission harness is connected to the circuit board, and the other end extends out of the rear cover.
The voice interaction system according to claim 6, wherein,

The rear end of the housing is connected to the rear cover through buckles.
The voice interaction system according to claim 6, wherein,

The front end is provided with a first through hole and a second through hole; the photoelectric sensor is provided with a receiver and an emitter, the receiver is located at the first through hole, and the emitter is located at the second At the second through hole.
The voice interaction system according to claim 6, wherein,

The indication mark includes an engraved hollow mark.
The voice interaction system according to claim 6, wherein,

The photoelectric switch also includes: a light source arranged in the housing.
The voice interaction system according to claim 1, wherein,

The voice interaction unit includes a microphone module, and the microphone module includes:

The upper cover, the upper cover is hollow inside, the upper cover includes a front end and a rear end, the front end is provided with at least two sound receiving holes, and the rear end is open;

At least two sound-receiving microphones arranged inside the upper cover, each of the sound-receiving microphones is set corresponding to one of the sound-receiving holes, and each of the sound-receiving holes is provided with a sealing ring;

a printed circuit board arranged inside the upper cover, and the printed circuit board is connected to the sound-receiving microphone;

The bottom cover is arranged at the rear end of the upper cover.
The voice interaction system according to claim 11, wherein,

The microphone module also includes:

The signal transmission wiring harness connected to the printed circuit board, and the wire pressing plate arranged on the printed circuit board for pressing the signal transmission wiring harness.
The voice interaction system according to claim 12, wherein,

The bottom cover and the pressure plate are fixed to the upper cover through buckles, and sealed with a sealant.
A voice interaction method, characterized in that it is applied to the voice interaction system according to any one of claims 1 to 13, said method comprising:

judging whether the voice interaction unit is on;

If so, control the smart device to perform an action corresponding to the target voice command according to the user's target voice command received and recognized by the voice interaction unit;

If not, according to the user's target body instruction received and recognized by the photoelectric sensing unit, the voice interaction unit is controlled to open, and according to the voice interaction unit receiving and recognizing the user's target voice instruction, the smart device is controlled to execute the target voice instruction corresponding action.
The voice interaction method according to claim 14, wherein:

The method also includes:

When the voice interaction unit is turned on, it is judged whether the voice interaction unit has received a voice instruction within a predetermined time; if not, the voice interaction unit is controlled to be turned off.
The voice interaction method according to claim 14, wherein:

The method also includes:

When the voice interaction unit is turned on, it is judged whether the voice interaction unit receives a voice command within a predetermined time; if not, the photoelectric sensor unit is controlled to be turned off.
The voice interaction method according to claim 15, wherein,

The method also includes:

receiving and identifying the image data collected by the image acquisition unit;

When the image data includes a target gesture, the photoelectric sensing unit and the voice interaction unit are controlled to be turned on.
An intelligent device, characterized in that the voice interaction system according to any one of claims 1 to 13 is provided on the intelligent device.