WO2017101266A1

WO2017101266A1 - Voice control method and system

Info

Publication number: WO2017101266A1
Application number: PCT/CN2016/084619
Authority: WO
Inventors: 王云华
Original assignee: 深圳Tcl数字技术有限公司
Priority date: 2015-12-15
Filing date: 2016-06-03
Publication date: 2017-06-22
Also published as: CN105551488A

Abstract

A voice control method and system for a smart television, the method comprising the following steps: upon receiving a voice instruction from a user, the smart television acquires an executable control of a current application that matches the voice instruction, wherein the current application is an application operating at a front end (S10); the smart television determines whether information pertaining to a to-be-executed object corresponding to the executable control is stored in the current application (S20); and when the information pertaining to the to-be-executed object is stored in the current application, the smart television invokes the executable control to execute an object corresponding to the information pertaining to the to-be-executed object (S30). The method could improve the efficiency of voice control.

Description

Voice control method and system

Technical neighborhood

The present invention relates to the field of smart television technologies, and in particular, to a voice control method and system.

Background technique

With the rapid development of smart TV technology, the voice control of smart TV is becoming more and more popular. Users only need to directly speak the favorite programs in front of the smart TV. Smart TV can return the user's needs to the page of the smart TV through semantic recognition. No need for users to find remote controls everywhere. However, in the prior art, the semantic recognition is completed based on a cloud-sized database. After receiving the voice command of the user, the smart TV transmits the voice command of the user to the cloud, and the cloud performs a large number of search and match, and often needs to wait very much. For a long time, the smart TV end can present the result of semantic recognition for the user. In addition, semantic recognition will not be completed when the smart TV is not connected to the cloud server. For example, Xiao Zhang opened the video application of iQiyi, and said that the smart TV said that the 10th episode of Huaqian TV series, the smart TV waited for 3 minutes to display a bunch of information, such as news, TV series and movies, etc. Play a TV show with thousands of bones. For another example, Xiaomei downloaded the first episode of the TV series that was spent on the smart TV local. Yesterday, the cloud server was suspended. At this time, Xiaomei said that the first episode of the flower bones, the smart TV prompts the current cloud server. Unable to connect, the first set of flowers and bones downloaded to the local can not be played, causing little beauty confusion. In the prior art, there is a problem that voice control efficiency is low.

Summary of the invention

The main object of the present invention is to provide a voice control method and system aiming at improving the efficiency of voice control.

To achieve the above object, the present invention provides a voice control method applied to a smart television, the voice control method comprising the following steps:

Upon receiving the voice command of the user, the smart television extracts an acoustic feature of the voice command and performs a verification operation on the user according to the acoustic feature;

When the verification is passed, the smart TV acquires an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end;

Determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control, and determining whether the cloud server corresponding to the current application stores the to-be-executed object information;

When the current application stores the to-be-executed object information, the smart TV invokes the executable control to execute an execution object corresponding to the to-be-executed object information;

When the current application does not store the to-be-executed object information, and the cloud server stores the to-be-executed object information, the smart television outputs prompt information.

The invention also provides a voice control method, which is applied to a smart television, and the voice control method comprises the following steps:

Upon receiving the voice instruction of the user, the smart TV acquires an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end;

Determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control;

When the current application stores the to-be-executed object information, the smart TV invokes the executable control to execute an execution object corresponding to the to-be-executed object information.

Preferably, while performing the step of determining whether the current application stores the to-be-executed object information corresponding to the executable control, the smart TV further performs the following steps:

Determining, by the smart TV, whether the cloud server corresponding to the current application stores the to-be-executed object information;

Preferably, when the current application is multiple, the step of determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control comprises:

The smart television determines whether each of the current applications stores the to-be-executed object information;

Correspondingly, after the step of determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control, the method further includes:

When the at least two of the current applications store the to-be-executed object information, the smart TV displays the current application of the current application that stores the to-be-executed object information in descending order according to the running time of the current application. Executable controls for the user to choose to execute.

Preferably, before the step of acquiring, by the smart TV, an executable control that currently matches the voice instruction, the smart television further includes:

When the verification is passed, the step of executing the smart TV to acquire an executable control that matches the current voice command is performed.

Preferably, the smart TV acquiring the executable control that the current application matches the voice instruction comprises:

Upon receiving the voice instruction of the user, the smart television converts the voice instruction into first text information, and collects second text information of the currently applied executable control;

The smart television compares the first text information with each of the second text information;

The smart television uses the executable control corresponding to the matched second text information as an executable control that matches the voice instruction.

In addition, in order to achieve the above object, the present invention further provides a voice control system, which is applied to a smart TV, and the voice control system includes:

An acquiring module, configured to acquire, when the user's voice instruction is received, an executable control that matches a current application with the voice instruction, where the current application is an application running at the front end;

a determining module, configured to determine whether the current application stores the to-be-executed object information corresponding to the executable control;

And an execution module, configured to: when the current application stores the to-be-executed object information, invoke the executable control to execute an execution object corresponding to the to-be-executed object information.

Preferably, the determining module is further configured to determine whether the cloud server corresponding to the current application stores the to-be-executed object information;

The voice control system further includes a prompting module, configured to output prompt information when the current application does not store the to-be-executed object information, and the cloud server stores the to-be-executed object information.

Preferably, when the current application is multiple, the determining module is further configured to determine whether each of the current applications stores the to-be-executed object information;

The voice control system further includes a display module, configured to display the to-be-executed object information in descending order according to the running time of the current application when at least two of the current applications store the to-be-executed object information The executable control of the current application for the user to select to execute.

Preferably, the voice control system further includes a verification module, configured to extract an acoustic feature of the voice command upon receiving a voice instruction of the user, and perform a verification operation on the user according to the acoustic feature;

The obtaining module is further configured to: when the verification passes, obtain an executable control that matches the current application with the voice instruction.

Preferably, the obtaining module is further configured to: when receiving the voice instruction of the user, convert the voice instruction into first text information, and collect second text information of the currently applied executable control; and A text message is compared with each of the second text information; and an executable control corresponding to the matched second text information is used as an executable control that matches the voice instruction.

When applied to the playback control of the smart TV, the invention completes the semantic recognition process locally in the smart TV and completes the response of the voice command. For example, Xiaomei downloaded the first episode of the TV series that was spent on the smart TV through iQiyi yesterday. After opening the iQiyi today, Xiaomei said to the smart TV, "Look at the first episode of the flower bones", love Qiyi will directly play the local storage “Flower 1000 First Set”, which does not require the network connection between Smart TV and iQiyi server. Compared with the prior art, it avoids the high latency based on cloud semantic recognition and can The smart TV completes the voice control without the network connection, and therefore, the present invention can achieve the purpose of improving the voice control efficiency.

DRAWINGS

1 is a schematic flow chart of a first embodiment of a voice control method according to the present invention;

2 is a schematic diagram of functional modules of a first embodiment of a voice control system of the present invention.

The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments.

detailed description

It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The present invention provides a voice control method. Referring to FIG. 1, in a first embodiment of the voice control method of the present invention, the voice control method includes:

Step S10, when receiving the voice instruction of the user, the smart TV acquires an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end;

It should be noted that the voice control method provided in this embodiment can be applied to a smart TV, and further, is applied to a play control of a smart TV. For example, Xiaomei downloaded a well-funded TV drama through iQiyi yesterday. The first episode is in the local area of smart TV. After opening the iQiyi today, Xiaomei said to the smart TV that “the first episode of the flower and bones”, Iqiyi will directly play the “first collection of flowers and bones” in the local storage. A network connection between Smart TV and iQiyi server is required.

In this embodiment, when receiving the voice instruction of the user, the smart TV acquires an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end. It should be noted that the user can issue voice commands to the smart TV in various manners, for example, the user can directly speak the voice command “see the first set of flowers” to the smart TV; or the user touches the remote controller preset. The voice control button for voice control, after the user speaks the voice command "look at the first set of flowers", the remote controller transmits the voice command "the first set of flowers to the bones" to the smart TV. The remote controller can perform data interaction with the smart TV in a plurality of manners, including at least one of Bluetooth, Wi-Fi, infrared, and ZigBee. For example, in this embodiment, the remote controller can perform voice control. Adopt infrared communication.

Specifically, when receiving the voice instruction of the user, the smart television first hands the received voice command to the local semantic recognition engine to convert the voice command into the text information that can be compared. It should be noted that, while the smart TV transmits the received voice command to the local semantic recognition engine for identification, the received voice command can also be transmitted to the cloud semantic recognition engine for recognition; if the cloud semantic recognition engine feedback is received first, The text information is used as the recognition result of the voice instruction by the cloud semantic recognition engine; because the network semantic environment is not good, the recognition result of the cloud semantic recognition engine may have a considerable delay, if received first When the local semantic recognition engine feeds back the text information, and the confidence of the text information fed back by the local semantic recognition engine is greater than a preset threshold, the text information fed back by the local semantic recognition engine is used as the recognition result of the voice instruction. The present embodiment does not limit the voice recognition technology used by the local semantic recognition engine and the cloud semantic recognition engine, and may be selected according to actual needs.

In addition, the smart television acquires the scene information of the current application while performing the semantic recognition of the voice instruction, where the acquired scene information includes the first type of scene information and the second type of scene information, where the A type of scene information is used to identify the type of the current application, such as a video application type ID of 1, a magazine application type ID of 2, and a game application type ID of 3; the second type of scene information is a keyword of various applications. , such as the TV drama name of the film and so on. For example, the smart TV acquires the first type of scene information YU_1YI_Data(x1)=1 of the current application, and acquires the second type of scene information YU_2YI_Data(x1)=yingshi of the current application. After acquiring the scene information of the current application, the smart TV reads the package name of the current application, and associates the acquired scene information with the package name and stores the information in the preset storage area 11. At the same time, the smart TV also calls the interface control information collection algorithm to collect the control information of the interface where the current application is located, and saves the collected control information into the preset storage area 22 according to the type of the control, and then according to the storage area 22 The control information filters out the executable control of the current application, and constructs a classification control and a corresponding text information list (such as "play", "flowers").

Then, the smart TV compares the text information corresponding to the voice instruction with the text information in the foregoing classification control and the corresponding text information list, and executes the executable control with the same text information as the executable of the voice instruction. Control. It should be noted that the text information is stored in the form of encoding in the smart television. For example, the English characters are stored in ASCII code and stored, and the Chinese characters are encoded and stored in the unicode code. Correspondingly, the voice command and the voice command can be performed in this embodiment. When the control is matched, the English characters are matched based on the ASCII code, and the Chinese characters are matched based on the unicode code. For example, the encoded Data_String(x1)=\u82b1\u5343\u9aa8\u000d\u000a, and its corresponding Chinese character is “Flower Thousand Bone”.

Step S20: The smart TV determines whether the current application stores the to-be-executed object information corresponding to the executable control.

In this embodiment, after acquiring the executable control that matches the current voice command, the smart TV determines whether the current application stores the to-be-executed object information corresponding to the executable control. It should be noted that the smart TV is divided into different data storage areas for the installed applications.

Specifically, the current application running on the front end of the smart TV is an example of iQiyi. When the user issues a voice command “seeing a thousand bones”, the smart TV obtains the current application package name “iqiyi”, and identifies the current application. For the iQiyi, and obtain the executable control that matches the voice command "Looking at the Thousand Bone", the play button corresponding to the "Flower Thousand Bone" currently in the interface of iQiyi, the smart TV further retrieves the data storage corresponding to iQiyi. Whether the area stores the name data (ie, the object to be executed) of the "flowers to be executed" (ie, the object to be executed). The smart TV first reads the name data in the data storage area corresponding to the iQiyi to the storage area 33, and then matches the English characters based on the ASCII code, and matches the Chinese characters based on the unicode code. For example, if the name data Data_String(x1)=\u82b1\u5343\u9aa8\u000d\u000a is retrieved (Unicode corresponds to the Chinese character "Hua Qian Bone"), ie, iQiyi (the current application) stores the executable The object to be executed corresponding to the control (corresponding to the play button of "Flower Thousand Bone").

Step S30: When the current application stores the to-be-executed object information, the smart TV invokes the executable control to execute an execution object corresponding to the to-be-executed object information.

It can be understood by those skilled in the art that when the to-be-executed object information corresponding to the executable control is stored, the executable object corresponding to the executable control exists locally, for example, the smart TV is retrieving the executable object information. When "flowers are spent", if it is retrieved, it means that the video data of "Flower Thousand Bone" is stored locally. In this embodiment, when the current application stores the to-be-executed object information, the smart TV invokes the executable control to execute an execution object corresponding to the to-be-executed object information, for example, the smart television is searching. When the executable object information "flowers and bones" is displayed, the video data of "Flower Thousand Bone" is directly played.

The voice control method proposed in this embodiment, when applied to the play control of the smart TV, completes the semantic recognition process locally on the smart TV and completes the response of the voice command. For example, Xiaomei downloaded the first episode of the TV series that was spent on the smart TV through iQiyi yesterday. After opening the iQiyi today, Xiaomei said to the smart TV, "Look at the first episode of the flower bones", love Qiyi will directly play the local storage “Flower 1000 First Set”, which does not require the network connection between Smart TV and iQiyi server. Compared with the prior art, it avoids the high latency based on cloud semantic recognition and can The smart TV completes the voice control without the network connection, and therefore, the present invention can achieve the purpose of improving the voice control efficiency. At the same time, since the present invention performs semantic recognition locally on the smart TV, it can also avoid the occupation of network bandwidth by voice control.

Further, based on the first embodiment, a second embodiment of the voice control method of the present invention is proposed. In this embodiment, while performing the step S20, the following steps are also performed:

In this embodiment, in order to ensure correct response to the user's voice command, the smart TV converts the user's voice command into text information, and obtains an executable control that matches the current voice command according to the text information. And determining whether the current application stores the to-be-executed object information corresponding to the executable control, and determining whether the cloud server corresponding to the current application stores the to-be-executed object information, so that the current application is not When the to-be-executed object information is stored, the object to be executed can be acquired according to the to-be-executed object information stored by the cloud server corresponding to the current application.

Specifically, the current application running on the front end of the smart TV is an example of iQiyi. When the user issues a voice command “seeing a thousand bones”, the smart TV obtains the current application package name “iqiyi”, and identifies the current application. For the iQiyi, and obtain the executable control that matches the voice command "Looking at the Thousand Bone", the play button corresponding to the "Flower Thousand Bone" currently in the interface of iQiyi, the smart TV further retrieves the data storage corresponding to iQiyi. For example, the name data of the object to be executed (that is, the object to be executed) is stored in the area. For details, refer to the first embodiment, and details are not described herein again. At the same time, the smart TV sends the text information “Flower Thousand Bone” to the cloud server corresponding to iQiyi, and the cloud server searches according to the received text information “Hua Qian Bone”, and feeds back to the smart TV. result. When receiving the search result fed back by the cloud server, the smart TV determines, according to the search result, whether the cloud server stores the to-be-executed object information. For example, the search result returned by the cloud server is: a movie in which the cloud currently stores "flowers and bones", a television drama, etc., at this time, if the smart TV does not retrieve "flowers" in the data storage area corresponding to iQiyi The name data of the bone, the smart TV output prompt message: the TV series with the "Flower Thousand Bones" and the movie can be played in the cloud, is it played? The user confirms whether to play according to the display interface of the prompt information, and what to play.

Further, based on the first embodiment, a third embodiment of the voice control method of the present invention is proposed. In this embodiment, when the current application is multiple, the foregoing step S20 includes:

Correspondingly, after the step S20, the method further includes:

It should be noted that with the continuous development of the multi-tasking mechanism, at present, the smart TV based on the Android system has already supported running multiple applications at the front end, for example, the smart TV runs both iQiyi and Youku at the front end, the smart TV Divide the screen into different display areas, respectively display the iQiyi interface and Youku interface, users can operate at both iQiyi and Youku. In this embodiment, when the current application is multiple, the smart TV determines whether each of the current applications stores the to-be-executed object information, that is, the smart television determines data storage corresponding to each current application. The information about the to-be-executed object is stored in the area. For details, refer to the foregoing embodiment, and details are not described herein again.

When at least two of the current applications store the to-be-executed object information, the smart TV acquires a running time of a current application that stores the to-be-executed object information, and displays the stored in descending order according to the acquired running time. The executable control of the current application of the object information to be executed is selected for execution by a user. For example, when the user gives a voice command to the smart TV, the smart TV acquires the scene information of the current application, identifies the application currently running on the front end as iQiyi and Youku, and further identifies and finds the iQiyi. The data storage area corresponding to each of Youku stores the name data of “Hua Qian Bone”. At this time, the smart TV acquires the running time of iQiyi for 30 minutes, and the running time of Youku is 20 minutes. Then, the smart TV displays the play button of the iQiyi corresponding to the “Hua Qian Bone” in front of the play button of Youku corresponding to “Hua Qian Bone”, which is convenient for the user to select “IQian bone” by using iQiyi, or adopt Youku plays "Flower Thousands of Bone".

Further, based on any of the foregoing embodiments, a fourth embodiment of the voice control method of the present invention is provided. In the embodiment, before the step S10, the method further includes:

When the verification is passed, step S10 is performed.

It should be noted that the difference between this embodiment and the foregoing embodiment is that the user authentication operation is added in the process of voice control, and only the user who performs the authentication operation can complete the voice control of the smart TV. In this embodiment, the smart television extracts an acoustic feature of the voice instruction when receiving a voice instruction of the user, wherein the extractable acoustic features include LPC (Linear Prediction Coefficient), MFCC (Mel Cepstrum Coefficient), and At least one of PLP (Perceptual Linear Prediction) can be selected according to actual needs.

In addition, the embodiment is pre-set with an acoustic feature database, and the smart TV master can record its own acoustic features into the acoustic feature database in advance, and can also record the acoustic features of friends, relatives or others into the acoustic feature database. . After extracting the acoustic features of the voice command, the smart television compares the extracted acoustic features with respective acoustic features in a preset acoustic feature database to complete a verification operation on the user, wherein If there is a match in the acoustic feature database, the verification passes, indicating that the user who issued the voice instruction is the user authorized by the owner or the owner, and the smart TV acquires the executable control that matches the current voice instruction, and starts the voice. For the control flow, refer to the foregoing embodiment, and details are not described herein. If there is no matching item in the acoustic feature database, the verification fails, indicating that the user who issued the voice command is an illegal user, and the received voice command is discarded at this time. Conduct a voice control process.

In this embodiment, the security of the voice control can be improved by adding a verification operation to the user in the voice control flow.

Further, based on any of the foregoing embodiments, a fifth embodiment of the voice control method of the present invention is proposed. In this embodiment, the foregoing step S10 includes:

In this embodiment, the user can issue a voice instruction to the smart TV in multiple manners. For example, the user can directly speak the voice command “see the first set of flowers” to the smart TV; or the user touches the remote controller preset. The voice control button for voice control, after the user speaks the voice command "look at the first set of flowers", the remote controller transmits the voice command "the first set of flowers to the bones" to the smart TV. The remote controller can perform data interaction with the smart TV in a plurality of manners, including at least one of Bluetooth, Wi-Fi, infrared, and ZigBee. For example, the implementation may be performed by using a remote controller for voice control. The way of infrared communication.

Specifically, when receiving the voice instruction of the user, the smart television first hands the received voice command to the local semantic recognition engine for converting the voice command into the first text information that can be compared. It should be noted that, while the smart TV transmits the received voice command to the local semantic recognition engine for identification, the received voice command can also be transmitted to the cloud semantic recognition engine for recognition; if the cloud semantic recognition engine feedback is received first, The text information is used as the recognition result of the voice instruction by the cloud semantic recognition engine; because the network semantic environment is not good, the recognition result of the cloud semantic recognition engine may have a considerable delay, if received first The local semantic recognition engine feeds back the text information, and when the confidence of the text information fed back by the local semantic recognition engine is greater than a preset threshold, the text information fed back by the local semantic recognition engine is used as the recognition result of the voice instruction. The present embodiment does not limit the voice recognition technology used by the local semantic recognition engine and the cloud semantic recognition engine, and may be selected according to actual needs.

The smart TV obtains the scene information of the current application while performing the semantic recognition of the voice instruction, where the acquired scene information includes the first type of scene information and the second type of scene information, the first type The scenario information is used to identify the type of the current application, such as a video application type ID of 1, a magazine application type ID of 2, and a game application type ID of 3; the second type of scene information is a keyword of various applications, such as TV drama names and so on. For example, the smart TV acquires the first type of scene information YU_1YI_Data(x1)=1 of the current application, and acquires the second type of scene information YU_2YI_Data(x1)=yingshi of the current application. After acquiring the scene information of the current application, the smart TV reads the package name of the current application, and associates the acquired scene information with the package name and stores the information in the preset storage area 11. In addition, the smart TV also invokes an interface control information collection algorithm to collect control information of the interface where the current application is located, and saves the collected control information into the preset storage area 22 according to the type of the control, and then according to the storage area 22 The control information filters out the executable control of the current application, and constructs a classification control and a corresponding text information list (such as "play", "flowers").

Then, the smart television compares the first text information corresponding to the voice instruction with the second text information in the foregoing classification control and the corresponding text information list, and matches the second text information with the first text information. The execution control acts as an executable control that matches the voice instruction. It should be noted that the text information is stored in the form of encoding in the smart television. For example, the English characters are stored in ASCII code and stored, and the Chinese characters are encoded and stored in the unicode code. Correspondingly, the voice command and the voice command can be performed in this embodiment. When the control is matched, the English characters are matched based on the ASCII code, and the Chinese characters are matched based on the unicode code. For example, the encoded Data_String(x1)=\u82b1\u5343\u9aa8\u000d\u000a, and its corresponding Chinese character is “Flower Thousand Bone”.

It should be noted that the matching in the foregoing embodiments of the present invention means that the two comparators are the same or the similarity reaches a preset threshold, wherein the preset threshold may be selected according to actual needs, for example, may be set to 85%.

The present invention also provides a voice control system. Referring to FIG. 2, in a first embodiment of the voice control system of the present invention, the voice control system includes:

The obtaining module 10 is configured to: when receiving the voice instruction of the user, acquire an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end;

The determining module 20 is configured to determine whether the current application stores the to-be-executed object information corresponding to the executable control;

The execution module 30 is configured to invoke the executable control to execute an execution object corresponding to the to-be-executed object information when the current application stores the to-be-executed object information.

Further, based on the first embodiment, a second embodiment of the voice control system of the present invention is proposed. In this embodiment, the determining module 20 is further configured to determine whether the cloud server corresponding to the current application stores the to-be-stored Execution object information;

Further, based on the first embodiment, a third embodiment of the voice control system of the present invention is proposed. In this embodiment, when the current application is multiple, the determining module 20 is further configured to determine each of the current Whether the application stores the to-be-executed object information;

Further, based on any of the foregoing embodiments, a fourth embodiment of the voice control system of the present invention is provided. In this embodiment, the voice control system further includes a verification module, configured to: when receiving the voice command of the user, extract An acoustic feature of the voice command, and performing a verification operation on the user according to the acoustic feature;

The obtaining module 10 is further configured to: when the verification passes, obtain an executable control that matches the current application with the voice instruction.

Further, based on any of the foregoing embodiments, a fifth embodiment of the voice control system of the present invention is proposed. In this embodiment, the acquiring module 10 is further configured to: when receiving a voice command of a user, the voice command. Converting to the first text information, and collecting second text information of the currently applied executable control; and comparing the first text information with each of the second text information; and matching the matched second text information The executable control acts as an executable control that matches the voice instruction.

The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the invention and the drawings are directly or indirectly applied to other related technical neighbors. The domains are all included in the scope of patent protection of the present invention.

Claims

A voice control method is applied to a smart television, characterized in that the voice control method comprises the following steps:

Upon receiving the voice command of the user, the smart television extracts an acoustic feature of the voice command and performs a verification operation on the user according to the acoustic feature;

When the verification is passed, the smart TV acquires an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end;

Determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control, and determining whether the cloud server corresponding to the current application stores the to-be-executed object information;

When the current application stores the to-be-executed object information, the smart TV invokes the executable control to execute an execution object corresponding to the to-be-executed object information;

When the current application does not store the to-be-executed object information, and the cloud server stores the to-be-executed object information, the smart television outputs prompt information.
A voice control method is applied to a smart television, characterized in that the voice control method comprises the following steps:

Upon receiving the voice instruction of the user, the smart TV acquires an executable control that matches the current application with the voice instruction, where the current application is an application running at the front end;

Determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control;

When the current application stores the to-be-executed object information, the smart TV invokes the executable control to execute an execution object corresponding to the to-be-executed object information.
The voice control method according to claim 2, wherein the step of performing the smart television to determine whether the current application stores the to-be-executed object information corresponding to the executable control, and performing the following steps:

Determining, by the smart TV, whether the cloud server corresponding to the current application stores the to-be-executed object information;

When the current application does not store the to-be-executed object information, and the cloud server stores the to-be-executed object information, the smart television outputs prompt information.
The voice control method according to claim 2, wherein when the current application is multiple, the smart television determines whether the current application stores the to-be-executed object information corresponding to the executable control. include:

The smart television determines whether each of the current applications stores the to-be-executed object information;

Correspondingly, after the step of determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control, the method further includes:

When the at least two of the current applications store the to-be-executed object information, the smart TV displays the current application of the current application that stores the to-be-executed object information in descending order according to the running time of the current application. Executable controls for the user to choose to execute.
The voice control method according to claim 2, further comprising: before the step of acquiring, by the smart TV, an executable control that matches the voice command;

Upon receiving the voice command of the user, the smart television extracts an acoustic feature of the voice command and performs a verification operation on the user according to the acoustic feature;

When the verification is passed, the step of executing the smart TV to acquire an executable control that matches the current voice command is performed.
The voice control method according to claim 4, further comprising: before the step of acquiring, by the smart TV, an executable control that matches the voice command;

Upon receiving the voice command of the user, the smart television extracts an acoustic feature of the voice command and performs a verification operation on the user according to the acoustic feature;

When the verification is passed, the step of executing the smart TV to acquire an executable control that matches the current voice command is performed.
The voice control method according to claim 2, wherein the smart TV acquires executable controls that match the current application with the voice command, including:

Upon receiving the voice instruction of the user, the smart television converts the voice instruction into first text information, and collects second text information of the currently applied executable control;

The smart television compares the first text information with each of the second text information;

The smart television uses the executable control corresponding to the matched second text information as an executable control that matches the voice instruction.
The voice control method according to claim 3, wherein the smart TV acquires executable controls that match the current application with the voice command, including:

Upon receiving the voice instruction of the user, the smart television converts the voice instruction into first text information, and collects second text information of the currently applied executable control;

The smart television compares the first text information with each of the second text information;

The smart television uses the executable control corresponding to the matched second text information as an executable control that matches the voice instruction.
The voice control method according to claim 4, wherein the smart TV acquires executable controls that match the current application with the voice command, including:

Upon receiving the voice instruction of the user, the smart television converts the voice instruction into first text information, and collects second text information of the currently applied executable control;

The smart television compares the first text information with each of the second text information;

The smart television uses the executable control corresponding to the matched second text information as an executable control that matches the voice instruction.
The voice control method according to claim 5, wherein the smart TV acquires executable controls that match the current application with the voice command, including:

Upon receiving the voice instruction of the user, the smart television converts the voice instruction into first text information, and collects second text information of the currently applied executable control;

The smart television compares the first text information with each of the second text information;

The smart television uses the executable control corresponding to the matched second text information as an executable control that matches the voice instruction.
The voice control method according to claim 3, wherein the smart television determines whether the current application stores the to-be-executed object information corresponding to the executable control when the current application is multiple include:

The smart television determines whether each of the current applications stores the to-be-executed object information;

Correspondingly, after the step of determining, by the smart TV, whether the current application stores the to-be-executed object information corresponding to the executable control, the method further includes:

When the at least two of the current applications store the to-be-executed object information, the smart TV displays the current application of the current application that stores the to-be-executed object information in descending order according to the running time of the current application. Executable controls for the user to choose to execute.
A voice control system is applied to a smart television, wherein the voice control system comprises:

An acquiring module, configured to acquire, when the user's voice instruction is received, an executable control that matches a current application with the voice instruction, where the current application is an application running at the front end;

a determining module, configured to determine whether the current application stores the to-be-executed object information corresponding to the executable control;

And an execution module, configured to: when the current application stores the to-be-executed object information, invoke the executable control to execute an execution object corresponding to the to-be-executed object information.
The voice control system according to claim 12, wherein the determining module is further configured to determine whether the cloud server corresponding to the current application stores the to-be-executed object information;

The voice control system further includes a prompting module, configured to output prompt information when the current application does not store the to-be-executed object information, and the cloud server stores the to-be-executed object information.
The voice control system according to claim 12, wherein the determining module is further configured to determine whether each of the current applications stores the to-be-executed object information when the current application is multiple;

The voice control system further includes a display module, configured to display the to-be-executed object information in descending order according to the running time of the current application when at least two of the current applications store the to-be-executed object information The executable control of the current application for the user to select to execute.
The voice control system according to claim 12, wherein said voice control system further comprises a verification module for extracting an acoustic feature of said voice command upon receiving a voice command of the user, and according to said acoustic The feature performs a verification operation on the user;

The obtaining module is further configured to: when the verification passes, obtain an executable control that matches the current application with the voice instruction.
A voice control system according to claim 14 wherein said voice control system further comprises a verification module for extracting an acoustic feature of said voice command upon receipt of a user's voice command, and based on said acoustic The feature performs a verification operation on the user;

The obtaining module is further configured to: when the verification passes, obtain an executable control that matches the current application with the voice instruction.
The voice control system according to claim 12, wherein the obtaining module is further configured to: when receiving the voice instruction of the user, convert the voice instruction into the first text information, and collect the executable of the current application. a second text information of the control; and comparing the first text information with each of the second text information; and executing an executable control corresponding to the matched second text information as an executable that matches the voice instruction Control.
The voice control system according to claim 13, wherein the obtaining module is further configured to: when receiving the voice instruction of the user, convert the voice instruction into the first text information, and collect the executable of the current application. a second text information of the control; and comparing the first text information with each of the second text information; and executing an executable control corresponding to the matched second text information as an executable that matches the voice instruction Control.
The voice control system according to claim 14, wherein the obtaining module is further configured to: when receiving the voice instruction of the user, convert the voice instruction into the first text information, and collect the executable of the current application. a second text information of the control; and comparing the first text information with each of the second text information; and executing an executable control corresponding to the matched second text information as an executable that matches the voice instruction Control.
The voice control system according to claim 15, wherein the obtaining module is further configured to: when receiving the voice instruction of the user, convert the voice instruction into the first text information, and collect the executable of the current application. a second text information of the control; and comparing the first text information with each of the second text information; and executing an executable control corresponding to the matched second text information as an executable that matches the voice instruction Control.