Voice control method and device, vehicle and computer readable storage medium

Abstract

The application provides a voice control method and device, a vehicle and a computer readable storage medium. The method comprises the following steps: receiving a voice control instruction; determining a target inert field according to the voice control instruction; when the time of the received voice control instruction exceeds a preset time, judging whether the received voice control instruction falls into the target inert field; if yes, performing a corresponding voice control action in response to the received voice control instruction. The application does not need to perform re-awakening and re-domain every time, thereby simplifying the user voice control process, realizing continuous voice control in the target inert field, and improving the user experience.

Description

Technical Field

[0001] This invention relates to the field of speech recognition technology, and in particular to a voice control method and device, a vehicle, and a computer-readable storage medium. Background Technology

[0002] With the continuous development of speech recognition technology, the application scenarios of voice control are becoming more and more common, and delayed listening technology is widely used in various fields.

[0003] Currently, when issuing a voice wake-up command, delayed listening technology can maintain the context recording during the listening process, allowing users to input commands concisely. However, once delayed listening is exited, the next voice wake-up will restart the dialogue and fall back to the previous context, and will not be able to respond to concise input commands. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0005] Therefore, one objective of this invention is to propose a voice control method that eliminates the need for repeated wake-up and re-reentry, thereby simplifying the user's voice control process, enabling continuous voice control within the target inertial domain, and improving the user experience.

[0006] Therefore, a second objective of the present invention is to provide a voice control device.

[0007] Therefore, a third objective of the present invention is to provide a vehicle.

[0008] Therefore, a fourth objective of the present invention is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, an embodiment of the first aspect of the present invention provides a voice control method, the method comprising: receiving a voice control command; determining a target inertial domain based on the voice control command; determining whether the voice control command received again falls within the target inertial domain after a preset time has elapsed since the voice control command was received again; and if so, performing a corresponding voice control action in response to the voice control command received again.

[0010] According to the voice control method of the present invention, a target inertial domain is determined based on the received voice control command. If the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0011] In some embodiments, determining a target inertial region based on the voice control command includes: determining whether the voice control command is in a preset region; if so, determining whether the voice control command and the previously received voice control command fall into the same preset region; if so, counting the number of times the voice control command falls into the same preset region consecutively until the number reaches a preset number, and determining the same preset region as the target inertial region.

[0012] In some embodiments, determining whether the voice control command is within a preset domain includes: determining a preset voice control command set within the preset domain; and determining that the voice control command is within the preset domain when the voice control command matches the preset voice control command set.

[0013] In some embodiments, after determining that the same preset domain is the target inert domain, the method further includes: storing the target inert domain.

[0014] In some embodiments, the voice control method further includes: if it is determined that the voice control command received again is not in the preset domain, then it is further determined whether the voice control command received again lacks feature data; if so, it is determined whether the voice control command received again matches the feature data in the target inert domain; if so, it is determined that the voice control command received again falls into the target inert domain.

[0015] In some embodiments, the voice control method further includes: if it is determined that the voice control command received again does not lack feature data, then issuing a prompt message reminding the user to issue the voice control command again, or issuing a prompt message indicating that the target inertial domain determination has failed.

[0016] In some embodiments, after the voice control command does not fall into the same preset area as the previously received voice control command, the method further includes: determining a new preset area.

[0017] To achieve the above objectives, a second aspect of the present invention provides a voice control device, comprising: a receiving module for receiving voice control commands; a determining module for determining a target inertial region based on the voice control commands; a judging module for judging whether a voice control command received again falls within the target inertial region after a preset time has elapsed since the voice control command was received again; and an execution module for performing a corresponding voice control action in response to the voice control command received again when it is determined that the voice control command received again falls within the target inertial region.

[0018] According to the voice control device of the present invention, a target inertial domain is determined based on the received voice control command. When the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0019] To achieve the above objectives, a third aspect of the present invention provides a vehicle including a voice control device as described in the above embodiments, the voice control device being executed to implement the voice control method as described in the above embodiments.

[0020] According to the vehicle of the present invention, a target inertial domain is determined based on the received voice control command. If the time between receiving the voice control command again and the time between receiving the voice control command and the voice control command received when the target inertial domain was determined is longer than a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is longer and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-fall into the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0021] To achieve the above objectives, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium storing a voice control program, which, when executed by a processor, implements the voice control method as described in the above embodiments.

[0022] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0023] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0024] Figure 1 This is a flowchart of a voice control method according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of a voice control method according to another embodiment of the present invention;

[0026] Figure 3 This is a block diagram of a voice control device according to an embodiment of the present invention;

[0027] Figure 4 This is a block diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0028] The embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. The embodiments of the present invention are described in detail below.

[0029] In voice simplex mode, the voice must be reactivated each time it is used. After completing the voice control command, the control program is exited. In voice duplex mode, a delayed listening technology is used. After completing the voice control command, the program continues to listen for a preset time. If a concise control command identical to the above voice control command is received again within the preset time, the corresponding voice control action is executed. If no voice control command is received within the preset time, the program exits after the preset listening time has elapsed.

[0030] Therefore, the present invention determines the target inertial domain based on the previously received voice control command, and when the time of the received voice control command exceeds the preset time and the received voice control command falls into the target inertial domain, it directly responds and executes the corresponding voice control action, thereby eliminating the need for re-wake-up and re-landing in the domain, thus achieving simple voice control.

[0031] The following is combined with Figure 1 The voice control method of this invention will be illustrated by example.

[0032] like Figure 1 As shown, the voice control method of this embodiment includes at least steps S1-S3.

[0033] Step S1: Receive voice control commands.

[0034] Among them, voice control commands are instructions issued by users to control related devices. After the user issues a voice control command, the voice control command is recognized by ASR (Automatic Speech Recognition) and converted into text information. By analyzing the text information, it is determined whether the preset domain is the target inert domain.

[0035] In this embodiment, when the relevant device is woken up, if the user issues a voice control command, such as an instruction to open the car window, the relevant device receives the user's voice control command to open the car window, converts the voice control command into corresponding text information through ASR speech recognition, and performs a domain determination based on the text information after obtaining the text information.

[0036] Step S2: Determine the target inertial area based on the voice control command.

[0037] The target lazy domain refers to the domain that users use frequently and that is closely related to the context. Understandably, the determination of the target lazy domain will change depending on the user's usage. When the received voice control commands hit the same preset domain multiple times, for example, when multiple received voice control commands fall into the multimedia domain, the multimedia domain is determined to be the target lazy domain.

[0038] In this embodiment, when determining the target inertial domain based on the voice control command, the preset domain in which the received voice control command is located is determined. For example, when a voice control command to play the next song is received from the driver, it is determined that the voice control command is in the multimedia domain. When the voice control command is determined to be in the multimedia domain, it is determined whether the previously received voice control command is also in the multimedia domain. If the previously received voice control command was also in the multimedia domain, for example, a voice control command to increase the volume of the current song was received, it is considered that the currently received voice control command to play the next song and the previously received voice control command to increase the volume of the current song fall into the same preset domain, for example, the multimedia domain. The number of consecutive times falling into the multimedia domain is counted. If the number of consecutive times falling into the multimedia domain reaches a preset number, for example, three times, the multimedia domain is determined to be the target inertial domain. When counting the consecutive times falling into the same preset domain, if the preset number is not exceeded or there is an interruption, the preset domain is not the target inertial domain.

[0039] Understandably, after receiving a voice control command, the system determines the target inertial domain by judging the relationship between the voice control command and the preset domain, as well as the number of times the voice control command falls into the same preset domain consecutively. This allows for the determination of the target inertial domain and the subsequent control based on the received voice control command, eliminating the need for repeated wake-up calls and simplifying the voice control process.

[0040] Step S3: If the time for receiving the voice control command again exceeds a preset time, determine whether the received voice control command falls into the target inertial domain.

[0041] The voice control command received again can be a concise voice control command or a command different from the currently received voice control command. For example, if the currently received voice control command is to open the car window, the next received voice control command can be to close the car window.

[0042] In this embodiment, if the time between the received voice control command and the currently received voice control command exceeds a preset time, it is considered that the interval between the received voice control command and the current voice control command is too long and does not fall within the delayed listening time range. At this time, it is determined whether the received voice control command falls into the target inertial domain. For example, if the target inertial domain is determined to be the vehicle control domain, the preset domain in which the received voice control command is located is compared with the target inertial domain. If the received voice control command is a voice control command to adjust the window height, it is determined that the received voice control command belongs to the vehicle control domain, and it is considered that the received voice control command falls into the target inertial domain. By analyzing whether the received voice control command falls into the target inertial domain, it is easier to perform concise voice control in the future.

[0043] Step S4: If the voice control command received again falls into the target inertial domain, then the corresponding voice control action is executed in response to the voice control command received again.

[0044] In this embodiment, after determining the target inertial domain based on the voice control command, the context of the target inertial domain is preserved. When a voice control command is received again, it is determined whether the received voice control command is within a preset domain. It is understood that the received voice control command can be a concise voice control command, such as a voice control command to increase volume. By determining the preset domain in which the received concise voice control command is located, it is easier to match the voice control command to increase volume with the feature data in the target inertial domain. If the match is successful and it is determined that the received voice control command falls within the target inertial domain, the received voice control command is directly responded to to execute the voice control action corresponding to the received voice control command, thereby achieving the purpose of inputting concise voice control commands.

[0045] For example, after determining that the multimedia domain is the target inertial domain, when the user says the voice control command to turn up the volume again, the voice control command is matched with the multimedia domain. If the match is successful, it is considered that turning up the volume falls into the multimedia domain, and the song volume is directly increased.

[0046] According to the voice control method of the present invention, a target inertial domain is determined based on the received voice control command. If the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0047] In some embodiments, when determining whether a voice control command is within a preset area, a preset voice control command set for the preset area is determined; when a voice control command matches a preset voice control command set, the voice control command is determined to be within the preset area.

[0048] In this embodiment, a preset voice control command set is stored in a preset area. Users can collect a large number of voice control commands in advance in the preset voice control command set and perform regular matching so that the voice control commands correspond to their corresponding operations. For example, if the voice control command is to open the car window, then the corresponding operation is to open the car window.

[0049] After determining the preset voice control command set within the preset domain, the received voice control command is matched against the preset voice control command set, and a match is determined. If the match is successful, the received voice control command is determined to be within the preset domain; if the match fails, the received voice control command is determined to be outside the preset domain. Similarly, the previously received voice control command is matched against the preset voice control command set, and a match is determined. If the match is successful, the previously received voice control command is determined to be within the preset domain; if the match fails, the previously received voice control command is determined to be outside the preset domain.

[0050] If both the received voice control command and the previously received voice control command match the preset voice control command set, it is determined that the received voice control command and the previously received voice control command fall into the same preset area. The number of times the voice control command falls into the same preset area consecutively is counted. If the number of consecutive falls into the same preset area reaches a preset number, such as three consecutive falls into the same preset area, the same preset area is determined as the target area. The target area is designated as the target lazy area and stored. By determining the target lazy area, the user can quickly reach the target lazy area by simply speaking the control command next time, simplifying the operation of voice control and improving the responsiveness of voice control.

[0051] For example, after the multimedia system starts playing a song, the user gives a voice control command to turn up the volume. The system determines that the voice control command matches the preset voice control command set and that the voice control command to turn up the volume falls within the vehicle's multimedia domain. Similarly, the system determines that the previously received voice control command to play the next song falls within the vehicle's multimedia domain. When the number of times the voice control command falls within the vehicle's multimedia domain consecutively reaches 3 times, the vehicle's multimedia domain is determined to be the target inertial domain.

[0052] In some embodiments, after determining the same preset domain as the target lazy domain, the target lazy domain is stored.

[0053] In this embodiment, after determining that the same preset area is a target lazy area, the target lazy area is stored. The received voice control command is matched with a preset voice control command set in the target lazy area. If it is determined that the received voice command matches the preset voice control command set in the target lazy area, then the received voice control command is determined to fall into the target lazy area.

[0054] If the command set matching fails, the system exits the target inertial domain. The target inertial domain is stored so that subsequent received voice control commands will fall into it. Based on the preset voice control command set in the target inertial domain, the voice control commands are then executed.

[0055] The commands and operations are matched one-to-one. The system responds to the received voice control commands by executing the corresponding voice control actions, thereby improving the response speed of voice control.

[0056] For example, after determining that the vehicle control domain is the target lazy domain, the vehicle control domain is stored, and when the user...

[0057] The system will then issue the command to raise the car window. The command will be matched with the preset voice control command set 0 in the vehicle control domain. If the match is successful, the system will consider that raising the car window has fallen into the vehicle control domain, and the car window will be raised.

[0058] In some embodiments, if it is determined that the voice control command received again is not in a preset domain, it is further determined whether the voice control command received again lacks feature data; if so, it is determined whether the voice control command received again matches the feature data in the target lazy domain; if so, it is determined that the voice control command received again falls into the target lazy domain.

[0059] 5. In this embodiment, when a voice control command is received again but is not within the preset area, i.e., it cannot successfully fall within the area,

[0060] Determine if the received voice control command lacks feature data, such as a subject. If it is determined that the received voice control command lacks a subject, for example, if the received voice control command is for the next song, determine if the received voice control command matches the feature data in the target lazy domain. If it matches the target...

[0061] If feature matching is performed in the lazy domain, feature corpus retrieval is conducted. For example, if the song in the target lazy domain is retrieved as subject 0, the voice control command for the next song received will be matched with the song in the target lazy domain.

[0062] Adjust the playback order of songs on the vehicle's multimedia system.

[0063] In some embodiments, if it is determined that the voice control command received again does not lack feature data, a prompt message is issued reminding the user to issue the voice control command again, or a prompt message is issued indicating that the target lazy domain determination has failed.

[0064] In this embodiment, if the received voice control command is complete and does not lack feature data, and if it still fails to fall into the control domain, then a fallback domain is entered, and a chat mode with the user is initiated to remind the user to receive the command again.

[0065] The received voice control commands are rich in characteristic language data and will issue reminder messages, such as reminding the user to send a domain failure message, or issuing reminder messages such as "I didn't hear you clearly, please say it again" or "Control failed, please check if the device is working properly", so as to remind the user to re-enter the voice or test the device until the voice control command is correct and the user can perform subsequent control operations.

[0066] 0 In some embodiments, the voice control command and the previously received voice control command do not fall into the same preset area.

[0067] Then, determine the new preset area.

[0068] In the embodiment, when determining the target inertial domain, after receiving a voice control command, if the voice control command and the previously received voice control command do not fall into the same preset domain, for example, the currently received voice control command is to open the car window, while the previously received voice control command was to turn up the song volume, then the multimedia domain is exited and a new preset domain is determined, such as the vehicle control domain.

[0069] The following is for reference. Figure 2 The voice control method of this invention will be illustrated by example.

[0070] like Figure 2 The diagram shown is a flowchart of a voice control method according to another embodiment of the present invention.

[0071] Step S11: Input voice control command.

[0072] Step S12, ASR recognition.

[0073] Step S13: NLU model judgment or rule-based judgment.

[0074] Step S14: Determine if the domain is available. If yes, proceed to step S15; otherwise, proceed to step S21.

[0075] Step S15: Determine whether the area falls within the preset area. If yes, proceed to step S16; otherwise, proceed to step S17.

[0076] Step S16: Count the number of times the object falls into the same preset area consecutively.

[0077] Step S17: Determine the new preset area.

[0078] Step S18: Determine whether the number of attempts has reached the preset number. If yes, proceed to step S19; otherwise, proceed to step S20.

[0079] Step S19: Determine the preset domain as the target inert domain.

[0080] Step S20: The preset area is not marked as the target lazy area.

[0081] Step S21: Determine whether the voice control command lacks feature data. If yes, proceed to step S22; otherwise, proceed to step S23.

[0082] Step S22: Determine whether it matches the feature corpus in the target lazy domain. If yes, proceed to step S24; otherwise, proceed to step S25.

[0083] Step S23: Issue a prompt message reminding the user to issue the voice control command again, or issue a prompt message indicating that the target inertial area has failed to be identified.

[0084] Step S24: Recall the feature corpus.

[0085] Step S25, entering the catch-all area.

[0086] Step S26: The dialogue ends, and the memory of the target inert domain is maintained.

[0087] According to the voice control method of the present invention, a target inertial domain is determined based on the received voice control command. If the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0088] The following is for reference. Figure 3 The voice control device 2 of this invention is described in an embodiment.

[0089] like Figure 3 The diagram shown is a block diagram of a voice control device according to an embodiment of the present invention. The device 2 includes: a receiving module 21, a determining module 22, a judging module 23, and an execution module 24, wherein...

[0090] The receiving module 21 is used to receive voice control commands; the determining module 22 is used to determine the target inertial domain based on the voice control commands; the judging module 23 is used to judge whether the voice control commands received again fall into the target inertial domain after the time exceeds a preset time; the executing module 24 is used to execute the corresponding voice control action in response to the voice control commands received again when it is determined that the voice control commands received again fall into the target inertial domain.

[0091] According to the voice control device 2 of the present invention, a target inertial domain is determined based on the received voice control command. When the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0092] In some embodiments, the determining module 22 is specifically used to: determine whether the voice control command is in a preset area; if so, determine whether the voice control command and the previously received voice control command fall into the same preset area; if so, count the number of times the voice control command falls into the same preset area consecutively until the number reaches a preset number, and determine the same preset area as the target inertial area.

[0093] In some embodiments, the determining module 22 is further specifically used to: determine a preset voice control instruction set in a preset area; and determine that the voice control instruction is in the preset area when the voice control instruction matches the preset voice control instruction set.

[0094] In some embodiments, the execution module 23 is specifically used to: after determining that the same preset domain is a target lazy domain, store the target lazy domain.

[0095] In some embodiments, the execution module 24 is specifically used to: if it is determined that the voice control command received again is not in the preset domain, then further determine whether the voice control command received again lacks feature data; if so, determine whether the voice control command received again matches the feature data in the target lazy domain; if so, determine that the voice control command received again falls into the target lazy domain.

[0096] In some embodiments, the execution module 24 is specifically used to: if it is determined that the voice control command received again does not lack feature data, issue a prompt message reminding the user to issue the voice control command again, or issue a prompt message indicating that the target lazy domain determination has failed.

[0097] In some embodiments, the execution module 24 is further specifically configured to: determine a new preset area after the voice control command and the received voice control command do not fall into the same preset area.

[0098] According to the voice control device 2 of the present invention, a target inertial domain is determined based on the received voice control command. When the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the received voice control command and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the received voice control command falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0099] The following is for reference. Figure 4 Vehicle 3, as described in an embodiment of the present invention.

[0100] like Figure 4 As shown, the vehicle 3 of this embodiment includes the voice control device 2 of the above embodiment. When executed, the voice control device 2 implements the voice control method as described in the above embodiment.

[0101] According to the vehicle 3 of the present invention, a target inertial domain is determined based on the received voice control command. If the time for receiving the voice control command again exceeds a preset time, it is considered that the interval between the voice control command received again and the voice control command received when the target inertial domain was determined is relatively long and does not fall within the delayed listening time range. Then, it is determined whether the voice control command received again falls into the target inertial domain. When it falls into the target inertial domain, the corresponding voice control action is executed. There is no need to re-wake up and re-land in the domain each time, thereby simplifying the user's voice control process, realizing continuous voice control within the target inertial domain, and improving the user experience.

[0102] The following describes a non-transitory computer-readable storage medium according to embodiments of the present invention.

[0103] The storage medium of this invention stores a voice control program, which, when executed by a processor, implements the voice control method described in the above embodiments.

[0104] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0105] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A voice control method, characterized by, The method comprises: receiving a voice control instruction; judging whether the voice control instruction is in a preset field; if yes, judging whether the voice control instruction falls into the same preset field as the last received voice control instruction; if yes, counting the number of times the voice control instruction continuously falls into the same preset field until the number of times reaches a preset number, determining that the same preset field is a target field, and taking the target field as a target inert field; if the voice control instruction received again falls into the target inert field, responding to the voice control instruction received again to perform a corresponding voice control action.

2. The voice control method of claim 1, wherein, The judging whether the voice control instruction is in a preset field comprises: determining a preset voice control instruction set of the preset field; when the voice control instruction matches the preset voice control instruction set, determining that the voice control instruction is in the preset field.

3. The voice control method according to claim 1, characterized by, After taking the target field as the target inert field, the method further comprises: storing the target inert field.

4. The voice control method according to claim 1, characterized by, The method further comprises: if it is judged that the voice control instruction is not in the preset field, further judging whether the voice control instruction lacks a feature corpus; if yes, judging whether the voice control instruction lacking the feature corpus matches a feature corpus in the target inert field; if yes, determining that the preset field where the voice control instruction is located is the target inert field.

5. The voice control method of claim 4, wherein, The method further comprises: if it is judged that the voice control instruction does not lack the feature corpus, issuing prompt information prompting a user to issue the voice control instruction again, or issuing prompt information reminding of a failure of determining the target inert field.

6. The voice control method of claim 1, wherein, After the voice control instruction and the voice control instruction received again do not fall into the same preset field, the method further comprises: determining a new target field.

7. A voice control device, characterized in that The method comprises: a receiving module configured to receive a voice control instruction; a determining module configured to judge whether the voice control instruction is in a preset field; if yes, judging whether the voice control instruction falls into the same preset field as the last received voice control instruction; if yes, counting the number of times the voice control instruction continuously falls into the same preset field until the number of times reaches a preset number, determining that the same preset field is a target field, and taking the target field as a target inert field; an executing module configured to, when the voice control instruction received again falls into the target inert field, respond to the voice control instruction received again to perform a corresponding voice control action.

8. An electronic device, comprising: The voice control device comprises: the voice control device according to claim 7.

9. A non-transitory computer-readable storage medium, comprising: The non-transitory computer readable storage medium stores a voice control program, and the voice control program is executed by a processor to implement the voice control method according to any one of claims 1-6.

Images