CN109346077B

Movatterモバイル変換

Info

Publication number: CN109346077B
Application number: CN201811296524.4A
Authority: CN
Inventors: 汤强
Original assignee: Individual
Current assignee: Individual
Priority date: 2018-11-01
Filing date: 2018-11-01
Publication date: 2022-03-25
Anticipated expiration: 2038-11-01
Also published as: CN109346077A

Abstract

The invention relates to a voice system suitable for portable intelligent equipment and a using method thereof. The use method of the system comprises a hardware induction use method, a software one-key use method, a track recognition use method and a knocking use method. The invention has the advantages that: the voice system can be used in various modes and can be used in different occasions; different using methods can be matched for use, so that the voice system is simpler and more convenient to use; the method is provided with the recognition of chatting voice and the recognition of semantic voice, so that the voice recognition is more accurate.

Description

Voice system suitable for portable intelligent equipment and use method thereof

Technical Field

The invention relates to the field of voice recognition, in particular to a voice system suitable for portable intelligent equipment and a using method thereof.

Background

The smart device becomes an indispensable electronic product in the mass life in the modern times, the smart phone is representative, the smart phone solves the life needs of people in interconnection and intercommunication anytime and anywhere, shopping, paying, reading, understanding news facts, playing games, voice and video, doing business and the like are all realized through the smart phone, the times are changing in developing technology, smart life is more and more popularized, various technical layers are endless, and the smart voice interaction system is closest to people

The existing voice interaction system mainly comprises the following two using methods, the first method is to find a voice application point through a touch control mode and open a voice interface to start voice recognition, the second method is to wake up the voice recognition through specific sound induction when the equipment is in a wake-up state, the first method needs to wake up the system firstly, unlock the system and then start the voice recognition through touch control operation, and the operation is complicated. The second method needs specific voice and voiceprint induction to wake up, and voice recognition is waken up after recognition, so that frequent recognition and wake-up are needed during multiple operations although the waiting time is short. And the existing voice system can only recognize voice and can not recognize voice except for human speaking voice. In addition, the current voice system is mainly oriented to system operation and cannot be used for voice application of software, particularly chat software.

Disclosure of Invention

The invention mainly solves the problems and provides the voice system which has various voice system awakening modes, is convenient and quick to awaken and is suitable for the portable intelligent equipment and the use method thereof, wherein the voice system combines voice chat and voice operation.

The technical scheme adopted by the invention for solving the technical problem is that the voice system suitable for the portable intelligent device comprises a main control module, a wake-up module, a voice receiving module, a distance sensing module, a gesture track recognition module, a knocking module and a one-key voice button displayed on a screen, wherein the voice receiving module, the distance sensing module, the gesture track recognition module, the knocking module and the wake-up module are all connected with the main control module, and the distance sensing module is arranged near the voice receiving module.

The main control module controls equipment to perform various operations, the awakening module is used for awakening the equipment, the sound receiving module and the distance sensing module work in a matched mode, the distance sensing module senses the distance between a mobile phone and a human body, when the distance is reduced to a certain range, the sound receiving module works to receive voice, the gesture track recognition module is used for sensing and recognizing a track which is moved under the control of a user after the user takes up the mobile phone, whether the user needs to use a voice system or not is judged according to the track, one-key voice buttons are only displayed on an equipment screen locking interface in a default mode, and one-key voice buttons can be displayed on a mobile phone interface all the time through user setting according to user requirements.

The invention also provides a using method of the voice system suitable for the portable intelligent equipment, which comprises a hardware induction using method, a software one-key using method, a track recognition using method and a knocking using method. Each method can wake up and use the voice system, and different methods can be matched with each other to enable the voice system to be used more conveniently, efficiently and accurately.

As a preferable scheme of the above scheme, the hardware induction using method includes the following steps:

s01: the user awakens the portable intelligent device;

s02: the main control module triggers the distance sensor;

s03: the distance sensor senses whether an object exists nearby, if so, a signal is sent to the main control module, and the main control module triggers the sound receiver and wakes up the voice system; if not, continuing to detect;

s04: receiving the voice by the sound receiver;

s05: stopping receiving the voice when the distance sensor detects that the object is far away;

s06: the speech system performs speech recognition.

As a preferable mode of the above, the software one-key using method includes the steps of:

s11: the user wakes up the portable intelligent equipment, and the portable intelligent equipment displays a screen locking interface;

s12: displaying a one-key voice button on a screen locking interface of the portable intelligent equipment;

s13: pressing a one-key voice button by a user, and preparing the voice system to receive voice;

s14: the voice system receives voice;

s15: the user releases the one-key voice button, and the voice system stops receiving voice;

s16: the speech system performs speech recognition.

As a preferable solution of the above solution, the track identification using method includes the steps of:

s21: the gesture track recognition sensor recognizes the moving track of the portable intelligent device;

s22: matching the identified moving track of the portable intelligent device with a preset track;

s23: if the matching is successful, starting a voice system; if the matching fails, no processing is carried out;

s24: the voice system receives voice;

s25: the voice system performs voice recognition and executes.

The track recognition using method can be matched with a hardware sensing using method, so that the voice system is more accurate in awakening and receiving voice.

As a preferable mode of the above, the knocking using method includes the steps of:

s31: the user taps the screen according to a certain rhythm;

s32: the knocking module receives a knocking signal;

s33: the main control module matches the received knocking rhythm with a preset knocking rhythm;

s34: if the matching is successful, the main control module performs operation corresponding to a preset knocking rhythm; if the failure occurs, the processing is not carried out and prompt is carried out at the same time. The knocking module is used for receiving sound or vibration generated when a user knocks on the screen, and the user can set different knocking rhythms for different mobile phone operations.

As a preferable solution of the above solution, the speech recognition includes the steps of:

s41: receiving and analyzing voice;

s42: judging whether preset semantic recognition keyword commands exist in the initial content and the tail end content of the analyzed content, if so, analyzing the semantics, and operating according to the voice; if not, detecting the current interface state;

s43: if the current interface of the equipment is a chat software interface, performing chat voice recognition; and if the current display interface of the equipment is a non-chat software interface, performing voice sentence recognition.

All interfaces in the chat software belong to chat software interfaces, including a main chat software interface, a chat window interface, an information popup window and the like, and the voice recognition keywords are used for distinguishing whether input voice is used for voice chat or voice recognition and can be defined by a user.

As a preferable aspect of the foregoing solution, the chat speech recognition includes the steps of:

s51: judging whether the current interface of the equipment is in a chat interface, if so, judging whether the chat software supports sending voice information, and if the chat software supports sending voice information, directly sending the voice to the chat interface and a contact corresponding to a popup window of the chat information; if the chat software does not support sending voice information, converting the voice instruction into text content and sending the text content to a chat interface and a contact corresponding to the chat information popup window;

s52: if not, judging whether preset contact keywords exist in the initial content and the end content of the analyzed content;

s53: if so, sending the content except the contact name in the voice content to the contact; if not, judging whether the initial content and the end content of the analyzed content have names or not;

s54: if yes, a selection interface appears for the user to select and record the contact person; if not, the semantics are analyzed, and the operation is carried out according to the voice.

The preset contact keywords are contacts in a phone book or chatting software, and the names refer to words with similar names or nicknames in voice.

As a preferable solution of the above solution, the speech sentence recognition includes the steps of:

s61: judging whether the equipment is currently in a system interface;

s62: if so, analyzing the content semantics and operating according to the semantics; if not, detecting whether the current interface software supports receiving voice;

s63: if yes, sending the voice to the software; and if not, prompting.

The device interface state comprises a chat software interface, a system interface and other software interfaces, wherein the chat software interface comprises a chat interface and a non-chat interface.

As a preferable scheme of the above scheme, the chat interface includes an interface provided with an input window and capable of sending information to a single person or a plurality of persons, and an interface with a popup window for chat information.

The invention has the advantages that: the voice system can be used in various modes and can be used in different occasions; different using methods can be matched for use, so that the voice system is simpler and more convenient to use; the method is provided with the recognition of chatting voice and the recognition of semantic voice, so that the voice recognition is more accurate.

Drawings

FIG. 1 is a block diagram of an embodiment of the present invention.

FIG. 2 is a flow chart of a hardware sensing method of the present invention.

FIG. 3 is a flow chart of a software one-key usage method of the present invention.

FIG. 4 is a flow chart of a method for using trajectory recognition in the present invention.

FIG. 5 is a flow chart of a tapping method of use in the present invention.

FIG. 6 is a flow chart of speech recognition according to the present invention.

FIG. 7 is a flow chart of the chat speech recognition of the present invention.

FIG. 8 is a flow chart of speech sentence recognition according to the present invention.

The system comprises a main control module 2, a wake-up module 3, a sound receiving module 4, a distance sensing module 5, a gesture track recognition sensing module 6 and a knocking module.

Detailed Description

The technical solution of the present invention is further described below by way of examples with reference to the accompanying drawings.

Example 1:

the embodiment provides a speech system suitable for portable intelligent device, as shown in fig. 1, including host system 1, awaken module 2, sound receiving module 3, apart from response module 4, gesture orbit recognition module 5, strike module 6 and show the one key voice button on the screen, sound receiving module, apart from response module, gesture orbit recognition module, strike module and awaken the module and all link to each other with host system, near sound receiving module is located to apart from response module. In this embodiment, the distance sensing module further has a biological recognition function to reduce the misjudgment probability, the wake-up module can provide a wrist-lifting wake-up function for the mobile phone, and the knocking module can receive vibration generated by knocking and convert the vibration into an electric signal to be sent to the main control module.

Correspondingly, the embodiment provides a voice system using method suitable for portable intelligent equipment, which comprises a hardware induction using method, a software one-key using method, a track recognition using method and a knocking using method.

As shown in fig. 2, the hardware sensing using method includes the following steps:

s01: a user wakes up the intelligent equipment by using a wrist-lifting wake-up function;

s02: the main control module triggers the distance sensor;

s04: receiving the voice by the sound receiver;

s06: the speech system performs speech recognition.

As shown in fig. 3, the software one-key using method includes the following steps:

s11: a user wakes up the intelligent equipment by using a wrist-lifting wake-up function, and the portable intelligent equipment displays a screen locking interface;

s14: the voice system receives voice;

s16: the speech system performs speech recognition.

In the implementation, the one-key voice button is only displayed on the screen locking interface, and the one-key voice button disappears after the equipment is unlocked and enters the main interface.

As shown in fig. 4, the track recognition using method includes the following steps:

s24: the voice system receives voice;

s25: the voice system performs voice recognition and executes.

When the mobile phone is used, the mobile phone is usually taken up and moved to a proper position, and the track of taking up the mobile phone to place the mobile phone in front of the chest is obviously different from the track of taking up the mobile phone to place the mobile phone at the chin by using the steps of the mobile phone.

As shown in fig. 5, the tapping use method includes the steps of:

s31: the user taps the screen according to a certain rhythm;

s32: the knocking module receives a knocking signal;

s34: if the matching is successful, the main control module performs operation corresponding to a preset knocking rhythm; if the failure occurs, the processing is not carried out and prompt is carried out at the same time.

In the embodiment, a user can set different operations for different knocking rhythms according to own preference, and the user can set the knocking rhythm of knocking two times after continuous knocking and short pause as the remote controller of the mobile phone; when a user uses the mobile phone, the mobile phone directly pops up a small window on a current interface for the user to remotely control, and the user can switch the small window into a large window; after the user taps the mobile phone according to the tapping rhythm for starting the mobile phone voice system, the mobile phone starts the voice system, and the user can input voice. Here, the knocking rhythm is not limited to the above-mentioned one, and the knocking rhythm may be a plurality of continuous knocking, a plurality of knocking at a predetermined interval, a plurality of knocking, a plurality of pause, or the like.

As shown in fig. 6, the speech recognition includes the following steps:

s41: receiving and analyzing voice;

In the embodiment, two semantic recognition keywords are set, namely ' cancel ' and ' over ', when a voice instruction of ' call for A ' and ' cancel ' call for B ' is input by voice, the voice system ignores the voice before cancellation, analyzes the semantic after cancellation, and calls for B according to the semantic; when the user inputs ' opening the address list ' cancel ', the voice system ignores the voice input; when the user inputs a voice instruction and then adds over, the voice system diameter analyzes the voice semantic and operates according to the semantic.

As shown in fig. 7, the chat speech recognition includes the following steps:

As shown in fig. 8, the speech sentence recognition includes the following steps:

s61: judging whether the equipment is currently in a system interface;

s63: if yes, sending the voice to the software; and if not, prompting.

Example 2:

compared with embodiment 1, the present embodiment combines the hardware sensing method and the track finger identification method. In this embodiment, when the user picks up the mobile phone and puts the mobile phone at the chin, which is in accordance with the track for starting the voice system, the voice system does not receive the voice command at this time, only when the distance sensor senses that an object is close to the mobile phone, the voice system starts to receive the voice command, and when the distance sensor senses that the object is away from the mobile phone, the voice system stops receiving the voice and starts voice recognition.

The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.

Claims

1. A voice system using method suitable for portable intelligent equipment is characterized by comprising the following steps: the method comprises a hardware induction using method, a software one-key using method, a track identification using method and a knocking using method;

the voice system comprises a main control module (1), a wake-up module (2), a sound receiving module (3), a distance sensing module (4), a gesture track recognition module (5), a knocking module (6) and a one-key voice button displayed on a screen, wherein the sound receiving module, the distance sensing module, the gesture track recognition module, the knocking module and the wake-up module are all connected with the main control module, and the distance sensing module is arranged near the sound receiving module;

the speech system is capable of performing speech recognition, the speech recognition comprising the steps of:

s41: receiving and analyzing voice;

s42: judging whether preset semantic recognition keyword commands exist in the initial content and the tail end content of the analyzed content, if so, analyzing the semantics, and operating according to the semantics; if not, detecting the current interface state;

s43: if the current interface of the equipment is a chat software interface, performing chat voice recognition; if the current display interface of the equipment is a non-chat software interface, carrying out voice sentence recognition;

the chat voice recognition is used for judging whether the received voice belongs to chat contents; the speech statement identifies a command for determining whether the received speech belongs to an execution operation.

2. The method of claim 1, wherein the method comprises: the hardware induction using method comprises the following steps:

s01: the user awakens the portable intelligent device;

s02: the main control module triggers the distance sensor;

s04: receiving the voice by the sound receiver;

s06: the speech system performs speech recognition.

3. The method of claim 1, wherein the method comprises: the software one-key using method comprises the following steps:

s14: the voice system receives voice;

s16: the speech system performs speech recognition.

4. The method of claim 1, wherein the method comprises: the track identification and use method comprises the following steps:

s24: the voice system receives voice;

s25: the voice system performs voice recognition and executes.

5. The method of claim 1, wherein the method comprises: the knocking use method comprises the following steps:

s31: the user taps the screen according to a certain rhythm;

s32: the knocking module receives a knocking signal;

6. The method of claim 1, wherein the method comprises: the chat voice recognition comprises the following steps:

s53: if so, sending the content except the contact name in the voice content to the contact; if not, judging whether the initial content and the end content of the analyzed content have names or not; the name is a person name or a nickname which does not belong to the contact keyword;

s54: if yes, a selection interface appears for the user to select and record the contact person; if not, the semantics are analyzed, and the operation is carried out according to the semantics.

7. The method of claim 1, wherein the method comprises: the speech sentence recognition comprises the following steps:

s61: judging whether the equipment is currently in a system interface;

s63: if yes, sending the voice to the software; and if not, prompting.

8. The method of claim 6, wherein the method further comprises: the chat interface comprises an interface which is provided with an input window and can send information to a single person or a plurality of persons and an interface with a chat information popup window.