Voice control method and chip system

Abstract

The embodiment of the invention provides a voice control method and a chip system, and relates to the technical field of data processing. The voice control method applied to the voice module chip comprises the steps that when the voice module chip is powered on, a query instruction is sent to a main control chip, wake-up words are determined based on first information fed back by the main control chip, the first information at least comprises information used for indicating a target theme, and different themes have corresponding wake-up words; and then, in response to a wake-up operation carrying the wake-up word, entering a voice control mode, and executing the received voice instruction based on the voice entry table matched with the wake-up word. In the embodiment of the invention, the voice module chip can replace the wake-up words corresponding to different themes through a power-on mechanism, so that the voice module chip can be applied to voice interaction scenes of different themes, the universality of the voice module chip is improved, and the production and control costs are reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular, to a voice control method and a chip system. Background Art

[0002] With the development of intelligence, in order to improve the convenience of users' interaction with intelligent devices, some voice control systems are provided in the prior art. For example, in the field of smart home, users can control home lights, smart clothes drying machines, smart locks, smart curtains and other devices through voice commands.

[0003] However, the existing voice module chips used to realize voice interaction are developed by manufacturers for their own brands and products. As a result, the voice module chips are only suitable for voice interaction of specific products of the specific brand developed, and cannot be used across brands and products. The versatility is very poor, and different voice module chips need to be developed for different brands and products, and the production and control costs are very high. Summary of the invention

[0004] In order to solve at least one of the above technical problems, the embodiments of the present disclosure provide a voice control method and a chip system. The technical solution is as follows: In a first aspect, an embodiment of the present disclosure provides a voice control method, which is applied to a voice module chip, and the method includes: When powered on, a query instruction is sent to the main control chip, and a wake-up word is determined based on first information fed back by the main control chip; the first information at least includes information for indicating a target topic, and different topics have their own corresponding wake-up words; In response to a wake-up operation carrying the wake-up word, a voice control mode is entered, and a received voice instruction is executed based on a voice word table matching the wake-up word.

[0005] In a feasible embodiment, the method further includes: Acquire a preset voice word table, wherein the preset voice word table matches each topic indicated by the main control chip through feedback information; A sub-entry table associated with the wake-up word is established based on a preset voice entry table; the sub-entry table is used to store keywords associated with the target topic and store resource information associated with the keyword; The executing the received voice instruction based on the voice word table matching the wake-up word includes: In response to second information input by voice, determining a control intention of the second information; If the control intention matches at least one keyword in the sub-item table, resource information associated with the at least one keyword is obtained for feedback.

[0006] In a feasible embodiment, executing the received voice instruction based on the voice word table matching the wake-up word includes: In response to third information of voice input, determining fourth information corresponding to the third information based on a voice word table associated with the wake-up word; Sending the fourth information to the main control chip, so that the main control chip controls the device and feeds back corresponding playback information according to the fourth information; The playing information is controlled to be played to prompt the operation object that the voice instruction corresponding to the third information has been executed.

[0007] In a feasible embodiment, determining the wake-up word based on the first information fed back by the main control chip includes: Acquire first information and parameter setting instructions for controlling the voice module chip sent by the main control chip, wherein the first information also includes wake-up control information and / or volume control information; Determining a wake-up word corresponding to the target topic based on the information indicating the target topic in the first information; Based on the wake-up control information, a wake-up control parameter associated with the wake-up word is set, and the wake-up control parameter is used to control the wake-up time; and / or, based on the volume control information, a volume control parameter associated with the wake-up word is set, and the volume control parameter is used to control the playback volume.

[0008] In a feasible embodiment, executing the received voice instruction based on the voice word table matching the wake-up word includes: In response to first volume adjustment information input by voice, updating the volume control parameter based on the first volume adjustment information to adjust the playback volume; And / or, the method further comprises: A volume adjustment instruction sent by the main control chip is received, and the volume control parameter is updated based on the second volume adjustment information carried in the volume adjustment instruction.

[0009] In a feasible embodiment, the method further includes: In response to the pause operation, within a first time period, refusing to respond to the received voice command or controlling to shut down the voice collection module; The suspend operation includes at least one of the following: In the second time period, at least two operation objects send voice messages; Voice input is used to trigger a keyword for pausing the voice control mode; On the device interaction interface configured with the voice module chip, a control for pausing acquisition of voice input information is triggered.

[0010] In a feasible embodiment, the method further includes: In the case of entering the voice control mode, if no information inputted by voice is received for a preset exit time, then exiting the voice control mode; The preset exit duration includes a first duration associated with the wake-up word, or a second duration set by the operation object; the second duration has a higher priority than the first duration; The second duration includes the duration set by the operation object through voice control in the voice control mode and / or the duration set through the exit duration setting page provided by the display of the device configured with the voice module chip.

[0011] In a second aspect, an embodiment of the present disclosure provides a voice control method, which is applied to a main control chip, and the method includes: Receive the query command sent by the voice module chip when it is powered on; Feedback the first information to the voice module chip, so that the voice module chip determines the wake-up word based on the first information, and enters the voice control mode in response to the wake-up operation carrying the wake-up word, so as to execute the received voice command based on the voice word table matching the wake-up word; The first information at least includes information for indicating a target topic, and different topics have their own corresponding wake-up words.

[0012] In a feasible embodiment, the method further includes: Receive fourth information sent by the voice module chip; the fourth information is information determined by the voice module chip based on the voice entry table associated with the wake-up word, and corresponds to the third information of the voice input; The device is controlled according to the fourth information, and corresponding playback information is fed back to the voice module chip, so that the voice module chip controls the playback of the playback information, prompting the operation object that the voice instruction corresponding to the third information has been executed.

[0013] In a feasible embodiment, the first information further includes volume control information, which is used for the voice module chip to set a volume control parameter associated with the wake-up word, and the volume control parameter is used to control the playback volume; The method further comprises: In response to a volume adjustment operation triggered by a volume adjustment button, a volume adjustment instruction is sent to the voice module chip, wherein the volume adjustment instruction carries second volume adjustment information, so that the voice module chip updates the volume control parameter based on the second volume adjustment information.

[0014] In the third aspect, an embodiment of the present disclosure provides a chip system, which is applied to an electronic device, and the chip system includes one or more processors, and the one or more processors are used to call computer instructions so that the electronic device executes the steps of the method provided by the first aspect and any embodiment thereof or the second aspect and any embodiment thereof.

[0015] In a fourth aspect, an embodiment of the present disclosure provides an electronic device, comprising at least one transceiver and at least one processor coupled to the at least one transceiver, wherein the at least one processor is configured to execute the steps of the method provided in the first aspect and any embodiment thereof or the second aspect and any embodiment thereof.

[0016] In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect and any embodiment thereof or the second aspect and any embodiment thereof.

[0017] In a sixth aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the steps of the method provided in the first aspect and any embodiment thereof or the second aspect and any embodiment thereof are implemented.

[0018] The technical solution provided by the embodiments of the present disclosure has the following beneficial effects: In the first aspect, the embodiment of the present disclosure provides a voice solution, which can be applied to a voice module chip. Specifically, when powered on, a query instruction can be sent to the main control chip, and the wake-up word can be determined based on the first information fed back by the main control chip. Among them, the first information at least includes information for indicating the target theme, and different themes have their own corresponding wake-up words. Then, when the voice module chip responds to the wake-up operation carrying the wake-up word, it enters the voice control mode, and executes the received voice command based on the voice entry table that matches the determined wake-up word. That is, the voice module chip can determine the wake-up word currently suitable for the target theme based on the information provided by the main control chip when powered on, and can provide voice interaction functions under different themes. The implementation of the present disclosure realizes that the voice module chip is universal for different themes through the replacement of the wake-up word, that is, it can be used across brands and products, reducing the cost of production and control of voice module chips.

[0019] On the second aspect, the embodiment of the present disclosure provides a voice control solution, which can be applied to the main control chip. Specifically, after receiving the query instruction sent by the voice module chip when it is powered on, the first information can be fed back to the voice module chip, so that the voice module chip determines the wake-up word based on the first information, and enters the voice control module in response to the wake-up operation carrying the wake-up word, so as to execute the received voice instruction based on the voice entry table matching the wake-up word. Among them, the first information at least includes information for indicating the target theme, and different themes have their own corresponding wake-up words. The implementation of the present disclosure feeds back the first information to the voice module chip through the main control chip when it is powered on, so that the voice module chip adapts to the target theme to determine the wake-up word, provides voice interaction function for applications under different themes, and realizes that the voice module chip is universal for different themes, that is, it can be used across brands and products, reducing the cost of production and control of voice module chips. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for describing the embodiments of the present disclosure are briefly introduced below.

[0021] Figure 1 A flow chart of a voice control method provided by an embodiment of the present disclosure; Figure 2 A flowchart of another voice control method provided by an embodiment of the present disclosure; Figure 3 A schematic diagram of a system architecture provided for an embodiment of the present disclosure; Figure 4 Another schematic diagram of a system architecture provided for an embodiment of the present disclosure; Figure 5 A flow chart of a voice interaction method provided by an embodiment of the present disclosure; Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] The embodiments of the present disclosure are described below in conjunction with the drawings in the present disclosure. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions of the embodiments of the present disclosure.

[0023] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present disclosure refer to that the corresponding features can be implemented as the displayed features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" may be implemented as "A", or as "B", or as "A and B".

[0024] The term "based on" used in various embodiments of the present disclosure can be interpreted as the premise, condition or information based on is not unique, but at least one or part of it. That is, it indicates that there is at least one clear basis, and other possible bases are not excluded.

[0025] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0026] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present disclosure and the technical effects produced by the technical solutions of the present disclosure. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0027] In the related art, the voice module chips used to realize the voice interaction function are developed by manufacturers for their own brands and products, which results in the voice module chips often being only applicable to specific brands and specific products. For example, the voice module chip 1 developed by car company A is set to use a fixed wake-up word A1 for voice interaction, and the voice module chip 2 developed by car company B is set to use a fixed wake-up word B2 for voice interaction, which results in the voice module chips developed not being universal across brands and products.

[0028] To solve the above problems, the embodiments of the present disclosure provide a voice control solution. By adapting to different themes and replacing the wake-up word used by the voice module chip when it is powered on for the first time, the voice module chip can provide voice interaction functions under different themes, thereby improving the versatility of the voice module chip and reducing production costs.

[0029] The voice control solution provided by the embodiment of the present disclosure can be implemented by a chip system. Specifically, the chip system can include a voice module chip and a main control chip. The chip system can be applied to electronic devices, and the electronic devices are adaptively configured with a voice module and a main control module, such as Figure 3 and Figure 4 The voice module includes a voice module chip, a voice acquisition module (such as a microphone, used to receive voice information input by the operation object), and a playback module (such as a speaker, used to play relevant voice information); the main control module includes a main control chip.

[0030] Optionally, the main control chip can be a chip that cooperates with the voice module chip in the chip system to realize voice control. Exemplarily, the voice module chip can be responsible for voice recognition, synthesis and playback, and can be adapted to different usage scenarios. The hardware options of the voice module chip can be OTP (One Time Programmable) voice chip, MP3 music chip, FLASH chip, etc. The main control chip can be responsible for the overall control and management of the device, and can be adapted to different usage scenarios. The hardware options of the main control chip can be MCU (Micro Controller Unit, microprocessor), MPU (Micro Processor Unit), Soc (System on Chip), etc.

[0031] Optional, such as Figure 4 As shown, the control module is also connected to the main control MCU. For example, when the electronic device is a smart clothes drying machine, the control module may include a motor module, a drying rod module, a drying module and other functional modules controlled by the main control MCU. For example, when the electronic device is a smart lock, the control module may include a cat's eye module, etc. In a feasible example, in the IoT scenario of home appliances, the electronic device is a smart speaker, which is associated with a smart TV, a smart curtain, and a smart clothes drying machine through a gateway. Then the control module may include relevant functional modules in the smart TV, the smart curtain and the smart clothes drying machine.

[0032] The following describes a voice control method applied to a voice module chip provided in an embodiment of the present disclosure.

[0033] Specifically, Figure 1 As shown, the method applied to the voice module chip includes S101 to S102: S101. When powered on, a query instruction is sent to the main control chip, and a wake-up word is determined based on first information fed back by the main control chip; the first information at least includes information for indicating a target topic, and different topics have their own corresponding wake-up words.

[0034] S102: In response to a wake-up operation carrying a wake-up word, enter a voice control mode, and execute a received voice instruction based on a voice word table matching the wake-up word.

[0035] Optionally, power-on can refer to the process of connecting a power source to a chip so that the chip starts to receive power and start working. The opposite operation of power-on is power-off (also called power-off), which can refer to the process of cutting off the power supply to the chip so that it stops working and enters an inactive state. For example, the car computer enters a power-off state after the engine is turned off, and the chip is powered off; when the driver restarts the car computer, the chip is powered on.

[0036] Optionally, the voice module chip can send a query command to the main control chip through the serial port to inquire which wake-up word to use. The main control chip can feedback information including the corresponding theme according to the internal settings of the program. After receiving the information fed back by the main control chip, the voice module chip can determine the wake-up word suitable for the target theme through internal logic processing. Among them, the theme can refer to different brands and products. For example, Enterprise A has developed smart clothes drying machines and smart locks. In daily applications, in order to avoid being awakened by a wake-up word at the same time when smart clothes drying machines and smart locks are installed in the same space, different wake-up words are set for different products; in this example, the theme can refer to smart clothes drying machines and smart locks. Optionally, the information used to indicate the theme can be the identity of the theme, the characteristics of the theme, and other information. As in the above example, the information used to indicate the theme can be the device identifier of the smart clothes drying machine and the smart lock, product-specific functional information (such as the smart clothes drying machine can be the adaptive up and down control of the clothes drying rod, and the smart lock can be fingerprint recognition), etc., which can be used to distinguish product information.

[0037] For example, car company A includes Brand 1, Brand 2 and Brand 3. The voice interaction function of the car computers of vehicles of different brands uses different wake-up words. In this case, car company A only needs to develop a voice module chip, which can be configured to execute the above-mentioned method steps S101 to S102, so that when used on car computers of different brands, the wake-up words set for different brands can be replaced, thereby realizing voice interaction functions on car computers of different brands.

[0038] Optionally, after the voice module chip determines the wake-up word used for the current power-on, if a wake-up operation triggered by the wake-up word is received, the voice control mode can be entered, that is, the voice module chip is in an awakened state, in which it can receive instructions input by voice from the operating object.

[0039] In the embodiments of the present disclosure, taking into account the voice interaction functions applied to different brands and products, due to the different functional operations that can be provided by different brands and products, the configured voice entries (used to match the voice information input by the operation object to determine the operation to be performed) are different, and it is also set that in the voice control mode, the voice module chip executes the received voice commands based on the voice entry table that matches the wake-up word, thereby improving the applicability of the voice module chip under different themes.

[0040] In a feasible embodiment, determining the wake-up word based on the first information fed back by the main control chip in S101 includes S101a-S101c: S101a. Acquire first information and parameter setting instructions for controlling the voice module chip sent by the main control chip, where the first information also includes wake-up control information and / or volume control information.

[0041] S101b. Determine a wake-up word corresponding to the target topic based on the information indicating the target topic in the first information.

[0042] S101c. Based on the wake-up control information, a wake-up control parameter associated with the wake-up word is set, and the wake-up control parameter is used to control the wake-up time; and / or, based on the volume control information, a volume control parameter associated with the wake-up word is set, and the volume control parameter is used to control the playback volume.

[0043] Optionally, upon receiving a query instruction sent by the voice module chip, the main control module chip can send the first information and parameter setting instructions to the voice module chip according to the internal settings of the program. Among them, the internal settings of the program in the main control module chip are determined based on the applicable theme, and the main control module chip can obtain the first information of the theme corresponding to the current device according to the query instruction and feed it back to the voice module chip. Exemplarily, the first information may include theme information, wake-up control information, volume control information, etc. Among them, the parameter setting instruction is used to instruct the voice module chip to set the parameters corresponding to the target theme according to the first information, such as wake-up words, wake-up time, playback volume, etc.

[0044] Optionally, considering that the voice module chip needs to process and analyze the received voice information, such as feature extraction, pattern matching, etc., it takes a certain amount of time to complete related operations, and the setting of the wake-up time can ensure that these operations are completed within the time expected by the user. Exemplarily, by optimizing the algorithm and model, the wake-up time can be shortened and the accuracy and efficiency of the wake-up can be improved.

[0045] Optionally, when the voice module chip receives the voice command of the operating object, it can provide feedback through an appropriate volume, so that the operating object can perceive that the command has been received and processed, thereby improving the immediacy and accuracy of voice interaction. Based on this, the embodiment of the present disclosure also configures different default playback volumes for different themes, and the default playback volume is related to the size of the space where the hardware, software and equipment of the corresponding theme are located.

[0046] In a feasible embodiment, S102 executes the received voice instruction based on the voice word table matching the wake-up word, including S102a: in response to first volume adjustment information of the voice input, updating the volume control parameter based on the first volume adjustment information to adjust the playback volume.

[0047] Optionally, the operating object can adjust the volume through voice interaction. For example, if the operating object finds that the volume of the audio played by the voice module chip is too low, the operating object can input volume adjustment information through voice, such as "turn up the volume", and the voice module chip can turn up the volume based on the current playback volume; assuming that the volume control parameter indicates that the current playback volume is the third gear, when the voice command of "turn up the volume" is received, the playback volume can be adjusted to the fourth gear.

[0048] In a feasible embodiment, the method provided by the embodiment of the present disclosure further includes: receiving a volume adjustment instruction sent by the main control chip, and updating the volume control parameter based on the second volume adjustment information carried in the volume adjustment instruction.

[0049] Optionally, the playback volume can be adjusted through the provided physical buttons in addition to adjusting it through voice interaction. If a button for adjusting the volume is provided on the interactive interface and / or physical buttons of the smart volume, the operating object can trigger the volume adjustment operation through the button, and the main control chip sends a volume adjustment instruction to the voice module chip in response to the operation, so that the voice module chip updates the volume control parameters based on the second volume adjustment information carried by the volume adjustment instruction to adjust the playback volume.

[0050] In an application scenario, considering that there may be multiple contents played through voice, such as in a driving scenario, there may be navigation volume, music playback volume and vehicle-machine interaction volume (the volume of the interaction between the operating object and the voice module), you can set the priority and / or relative volume to adaptively adjust other volumes when adjusting a certain volume to avoid conflicts between various function volumes. Exemplarily, the priority of the three volumes can be sorted from high to low as navigation volume-vehicle-machine interaction volume-music playback volume (when a higher priority voice message needs to be played, the playback of a lower priority voice message is interrupted); the relative volume of the three can be that the navigation volume is greater than the vehicle-machine interaction volume and the volume playback volume. Among them, the vehicle-machine interaction volume can be set to be the same as the music playback volume.

[0051] For example, when there are multiple volumes to be adjusted, the volume for different scenes can be adjusted by voice interaction, such as voice input of "turn down the navigation volume" to adjust the specific navigation volume. The volume adjustment for different specific scenes can also be triggered by different physical buttons.

[0052] In a feasible embodiment, considering that in actual application scenarios, for different operation objects and different application devices (different devices may provide different functions), the voice information of the operation object's voice input may be different during the voice interaction process. For example, in vehicle control, if the operation object wants to close the sunshade, the voice information that the operation object may input includes "close the sunshade", "close the skylight", etc. Based on this, the embodiment of the present disclosure also sets up the use of a specific entry table to add and record entry intentions and corresponding resources, so as to effectively improve the flexibility, accuracy and efficiency of voice recognition.

[0053] Optionally, the method provided in the embodiment of the present disclosure also includes S103 to S104.

[0054] S103: Obtain a preset voice word table, where the preset voice word table matches all the topics indicated by the main control chip through feedback information.

[0055] S104: establishing a sub-entry table associated with the wake-up word based on the preset voice entry table; the sub-entry table is used to store keywords associated with the target topic and store resource information associated with the keywords.

[0056] Optionally, after the voice module chip determines the wake-up word currently used for voice control, the corresponding preset voice entry table can be obtained. Among them, the preset voice entry table is a voice entry table with universal characteristics that is adapted to the universal setting of the voice module chip in the embodiment of the present disclosure, and it can be applied to various different topics. Exemplarily, the preset voice entry table may include entries that are applicable to multiple topics such as power on, power off, light on, and light off.

[0057] Optionally, in order to improve the flexibility and adaptability of the voice entry table under various topics, a sub-entry table associated with the wake-up word can also be established on the basis of applying the preset voice entry table. In one example, the keywords included in the sub-entry table can be the entries included in the entries that are screened as the preset voice entries, or can be the entries recorded in the actual application process. Exemplarily, for the smart clothes drying machine, the voice entries provided include: power on, power off, drying, drying rod rising, drying rod falling, and disinfection. Among them, since the preset voice entry table includes the entries of "power on" and "power off", the remaining entries of "drying", "drying rod rising", "drying rod falling", and "disinfection" are recorded in the sub-entry table corresponding to the wake-up word of the smart clothes drying machine. In some smart clothes drying machines, a lighting module is also provided. In the actual application process, if the voice input information "turn on the light" of the operation object is received, the entry of "turn on the light" can be added to the sub-entry table, and it can be used as a keyword to match the voice information input by the operation object.

[0058] Optionally, in a specific scenario, under a specific function of a specific theme, voice interaction also needs to be combined with corresponding resources, so the sub-entry table can also record resource information associated with keywords. Take playing music as an example: the sub-entry table includes the keyword "play music". In the actual application scenario, the voice module chip can obtain the audio file (resource) corresponding to the keyword "play music" through the sub-entry table for playback.

[0059] For example, Figure 5 As shown, the voice module chip can use the corresponding voice entry table according to the wake-up word confirmation, which specifically includes a general voice entry table and a specific sub-entry table (such as a playback entry).

[0060] Optionally, in S102, executing the received voice instruction based on the voice word table matching the wake-up word includes steps A1 to A2: Step A1: In response to second information input by voice, determine the control intention of the second information.

[0061] Step A2: If the control intention matches at least one keyword in the sub-item table, resource information associated with the at least one keyword is obtained for feedback.

[0062] Optionally, when the voice module chip receives the second information of voice input, the voice module chip can perform voice recognition processing on the second information to determine the control intention of the second information. Exemplarily, the voice module can use a microphone or other device to convert the voice signal of the second information into an electronic signal (such as Figure 5As shown, after the pronunciation source sends out the corresponding wake-up word, when using voice entry control, the sound source can be converted into an electrical signal through a microphone), the electronic signal is filtered, denoised, and other processes are performed, and then acoustic features are extracted from the processed electronic signal. A pre-trained speech recognition model (such as a deep neural network DNN, a hidden Markov model HMM, etc.) is used to process the extracted acoustic features, and after obtaining the output of the speech recognition model, it is processed for natural language understanding to determine the voice control intention of the operation object.

[0063] Optionally, after determining the control intent of the second information, if there is at least one keyword in the sub-entry table that matches it, the resource information associated with the keyword can be obtained for feedback. Exemplarily, when the control intent of the operating object is to play songs from a specific playlist, the audio file corresponding to the played music and the specific playlist can be obtained through the sub-entry table for playback. Among them, the sub-entry table may record the mapping relationship between the audio file and the keyword (e.g., the resource information recorded in the sub-entry table may be the mapping relationship and the storage address of the audio file), and the audio file as a resource may be stored in a database and / or locally.

[0064] Optionally, during the resource acquisition process, the voice module chip may also send a resource acquisition request to the main control chip to acquire the corresponding resources through the main control chip. Figure 5 As shown, the voice module chip can obtain the playback sound source through the main control MCU, and then control the speaker to play the corresponding sound source.

[0065] In a feasible embodiment, executing the received voice instruction based on the voice word table matching the wake-up word in S102 includes steps B1 to B3: Step B1: In response to third information input by voice, fourth information corresponding to the third information is determined based on a voice word table associated with the wake-up word.

[0066] Step B2: Send the fourth information to the main control chip, so that the main control chip controls the device according to the fourth information and feeds back corresponding playback information.

[0067] Step B3: Control the playing of the playback information to prompt the operation object that the voice instruction corresponding to the third information has been executed.

[0068] Optionally, when the operating object wakes up the voice module through the wake-up word, the voice module enters the voice control mode, at which time the operating object can be controlled through the voice entry, and the voice module can receive the third information (such as voice signal) input by the operating object through the microphone and convert it into an electrical signal, and then the voice module chip can retrieve the fourth information corresponding to the third information from the voice entry table associated with the wake-up word (such as information that can be processed by the main control chip based on the control intention) and output it to the main control chip. On this basis, the main control chip can perform corresponding control according to the fourth information, and feedback the corresponding playback information (such as playback entry) to the voice module chip, and the voice module chip controls the speaker to play after receiving the playback information.

[0069] Optionally, the voice entry table associated with the wake-up word may include the preset voice entry table and sub-entry table of the above embodiment.

[0070] Optionally, the playback of the playback information can be used to prompt the operating object that the voice command output by the operating object has been executed, the execution status and the execution result, etc., so as to improve the immediacy of the operating object's perception in the voice interaction.

[0071] In the embodiments of the present disclosure, considering that in actual applications, after waking up for voice interaction, unexpected situations may occur, such as a non-operating object suddenly speaking, the operating object needs to communicate with others, etc., which may cause the voice module chip to receive and execute incorrect voice commands. In order to avoid miscontrol and reduce the situation where the voice module chip executes incorrect commands, the present disclosure also proposes a solution for pausing voice control in voice control mode.

[0072] Optionally, the method provided by the embodiment of the present disclosure further includes: in response to the pause operation, refusing to respond to the received voice command or controlling to close the voice collection module within the first time period; In one example, during the period of pausing voice control, the voice module chip can still receive voice commands but does not respond.

[0073] In one example, during the time period when voice control is suspended, the voice module chip controls the voice collection module to be turned off, that is, no voice commands input by voice input are received during this time period.

[0074] The suspension operation includes at least one of the following three items: Pause operation 1. In the second time period, at least two operation objects send voice information. Optionally, in a similar time period, if there are voice information of at least two operation objects, it indicates that the currently received voice information is not used for voice control. In order to avoid misidentification and misexecution of the voice instructions in the voice information, the pause operation can be triggered when it is determined that the received voice information includes at least two voiceprints. Exemplarily, when the parents are triggering the voice control of the smart curtains, the child keeps saying "No No No" and other contents because of playing with the puppy. The voice module chip of the smart curtains may recognize the voice content and interrupt the execution of the voice instructions triggered by the parents. In order to avoid this situation, the embodiment of the present disclosure performs voiceprint recognition on at least two received voice information in a similar time period (such as 1 second, 2 seconds, etc.). If it is determined that there are at least two voiceprints, it is determined that at least two operation objects send voice information at the same time, and the pause voice control mode is triggered. In this case, the first time period is a pre-set time period.

[0075] Pause operation 2. Voice input is used to trigger the keyword of pausing the voice control mode. Optionally, the operating object can control the pause of the voice control mode by voice inputting keywords such as "pause", so that the voice module chip refuses to respond to the received voice command or controls the shutdown of the voice acquisition module within the first time period. In this case, the operating object can synchronously set the first time period by voice input, such as inputting voice information such as "pause response within 5 seconds", and the voice module chip can set the first time period to 5 seconds.

[0076] Pause operation 3. On the device interaction interface configured with the voice module chip, trigger the control for pausing the acquisition of voice input information. Optionally, if the control is triggered by a single click, the preset duration can be determined as the first time period in the pause operation. If the control is triggered by a long press, the duration of the long press can be determined as the first time period in the pause operation. For example, the user can long press the control on the device interaction interface. During the long press of the control, the voice module chip refuses to respond to the received voice command or controls the voice acquisition module to be turned off.

[0077] In the above-mentioned various pause operations, the first time period is adaptively adjusted to meet the needs of different scenarios. Configuring different first time periods can effectively improve the experience of voice interaction.

[0078] In a feasible embodiment, the method provided by the embodiment of the present disclosure further includes: in the case of entering the voice control mode, if no information input by voice is received within a preset exit time, then exiting the voice control mode.

[0079] Among them, the preset exit duration includes a first duration associated with the wake-up word, or a second duration set by the operation object; the second duration has a higher priority than the first duration.

[0080] Among them, the second duration includes the duration set by the operation object through voice control in the voice control mode and / or the duration set by the exit duration setting page provided by the display of the device configured with the voice module chip.

[0081] Optionally, in order to reduce power consumption, the exit duration can be set to control the state of the voice module entering the voice control mode. In one example, a corresponding first duration is configured for each theme, which can be determined by the duration control information provided when the main control chip sends the first information to the voice module chip, that is, each theme is configured with a corresponding default exit wake-up duration. In one example, taking into account the different requirements of different operation objects and different application scenarios, the operation object is also provided with a function that can dynamically set the exit duration. The operation object can set the second duration corresponding to the demand by voice control or by setting the duration on the page provided by the display of the device.

[0082] Optionally, since the second duration set for the operation object is set based on dynamic demand, in order to improve the flexibility of voice control, the priority of the second duration can be set higher than the first duration, that is, when the second duration is configured, the second duration is used as the preset exit duration for exit control of the voice control mode. When the second duration is not configured, the first duration is used as the preset exit duration for exit control of the voice control mode.

[0083] For example, assuming that the preset exit time is 30 seconds, after the operating object wakes up the voice module through the wake-up word, if no voice input information is received for 30 seconds, the voice module is automatically controlled to exit the voice control mode.

[0084] The following describes a voice control method applied to a main control chip provided in an embodiment of the present disclosure.

[0085] Optionally, the voice control method applied to the main control chip provided in the embodiment of the present disclosure has the same inventive concept as the voice control method applied to the voice module chip provided in the above-mentioned embodiment. The descriptions of each embodiment can refer to each other, and the descriptions of related concepts, operations, information, etc. will not be repeated in the following embodiments.

[0086] Specifically, Figure 2 As shown, the voice control method applied to the main control chip includes S201 to S202.

[0087] S201, receiving a query instruction sent by the voice module chip when it is powered on.

[0088] S202. Feedback the first information to the voice module chip so that the voice module chip determines the wake-up word based on the first information, and enters the voice control mode in response to the wake-up operation carrying the wake-up word, so as to execute the received voice command based on the voice word table matching the wake-up word.

[0089] The first information at least includes information for indicating a target topic, and different topics have their own corresponding wake-up words.

[0090] In the embodiment of the present disclosure, in order to provide the versatility of the voice module chip, it is set to actively query the main control chip for the wake-up word currently required when the voice module is initially powered on, and determine the wake-up word based on the first information fed back by the main control chip according to the characteristics supported by the current device (the characteristics are related to the theme), and other parameters such as wake-up time, volume playback gear, etc. can also be set synchronously. On this basis, when the voice module responds to the wake-up operation triggered by the wake-up word, it can enter the voice control mode to execute the corresponding voice command based on the voice entry table associated with the wake-up word. The implementation of the present disclosure can make the voice module chip adapt to more themes, improve its versatility, and reduce the complexity of material management and production costs.

[0091] In a feasible embodiment, the method provided by the embodiment of the present disclosure also includes S203 to S204.

[0092] S203, receiving the fourth information sent by the voice module chip; the fourth information is determined by the voice module chip based on the voice entry table associated with the wake-up word, and corresponds to the third information of the voice input.

[0093] S204: Control the device according to the fourth information, and feed back corresponding play information to the voice module chip, so that the voice module chip controls the play information, prompting the operation object that the voice instruction corresponding to the third information has been executed.

[0094] In the disclosed embodiment, since the voice module chip is highly versatile, it is more convenient to maintain and upgrade compared to the prior art. For example, in the process of voice module chip and main control chip communicating to complete voice control, if the control module configured with the main control chip changes, such as changing from smart clothes drying machine 1 (model A) to smart clothes drying machine 2 (model B), the sub-entry table corresponding to the wake-up word (specific voice entry table for smart clothes drying machine 2) can be updated, and the updated theme can be supported without large-scale modification of the hardware.

[0095] Optionally, using the same preset voice entry table for different topics can simplify the material control of the voice module chip and reduce costs. Exemplarily, using the same universal voice entry table for topic A and topic B can reduce the types and quantities of materials.

[0096] In a feasible embodiment, the first information also includes volume control information, which is used for the voice module chip to set volume control parameters associated with the wake-up word, and the volume control parameters are used to control the playback volume.

[0097] Optionally, the method provided by the embodiment of the present disclosure also includes: in response to a volume adjustment operation triggered by a volume adjustment button, sending a volume adjustment instruction to the voice module chip, the volume adjustment instruction carrying second volume adjustment information, so that the voice module chip updates the volume control parameters based on the second volume adjustment information.

[0098] In the embodiments of the present disclosure, in order to enhance the user experience, a more personalized user experience is provided based on the use of corresponding wake-up words in different themes, such as supporting dynamic adjustment of the playback volume. Users can adjust the volume according to their personalized needs, thereby improving convenience and satisfaction of use.

[0099] Optionally, the objects set by the user according to personalized needs may also include wake-up time and exit duration.

[0100] It should be noted that in the optional embodiments of the present disclosure, the information involved (such as voice information, wake-up words and other related data), when the above embodiments of the present disclosure are applied to specific products or technologies, needs to obtain permission or consent from the user, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present disclosure involve data related to the object, these data need to be obtained with the authorization and consent of the object and in compliance with the relevant laws, regulations and standards of the country and region.

[0101] An embodiment of the present disclosure provides a voice control device, which is applied to a voice module chip. The device includes a wake-up word determination module and a voice control module.

[0102] Among them, the wake-up word determination module is used to send a query instruction to the main control chip when powered on, and determine the wake-up word based on the first information fed back by the main control chip; the first information includes at least information used to indicate the target topic, and different topics have their own corresponding wake-up words; the voice control module is used to respond to a wake-up operation carrying a wake-up word, enter the voice control mode, and execute the received voice command based on the voice word table matching the wake-up word.

[0103] In another embodiment of the present disclosure, a voice control device applied to a main control chip is also provided. The device may include a receiving module and a feedback module.

[0104] Among them, the receiving module is used to receive the query instruction sent by the voice module chip when it is powered on; the feedback module is used to feedback the first information to the voice module chip, so that the voice module chip determines the wake-up word based on the first information, and enters the voice control mode in response to the wake-up operation carrying the wake-up word, so as to execute the received voice instruction based on the voice vocabulary table matching the wake-up word; wherein the first information includes at least information for indicating the target topic, and different topics have their own corresponding wake-up words.

[0105] The device of the embodiments of the present disclosure can execute the method provided by the embodiments of the present disclosure, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present disclosure correspond to the steps in the method of each embodiment of the present disclosure. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0106] The modules involved in the embodiments described in the present disclosure can be implemented by software. The name of the module does not limit the module itself in some cases. For example, the wake-up word determination module can also be described as "a module that sends a query instruction to the main control chip at power-on and determines the wake-up word based on the first information fed back by the main control chip", "a first module", etc.

[0107] In the embodiment of the present disclosure, an electronic device is provided, which can be a device with a voice module such as an Internet of Things device and a home appliance. The host of the device includes a memory, a processor and a computer program stored in the memory. The processor executes the above computer program to implement the steps of the voice control method. Compared with the related art, it can be realized: in the solution applied to the voice module chip, when powered on, a query instruction can be sent to the main control chip, and the wake-up word can be determined based on the first information fed back by the main control chip. Among them, the first information at least includes information for indicating the target theme, and different themes have their own corresponding wake-up words. Then, when the voice module chip responds to the wake-up operation carrying the wake-up word, it enters the voice control mode and executes the received voice instruction based on the voice entry table matching the determined wake-up word. That is, the voice module chip can determine the wake-up word currently suitable for the target theme based on the information provided by the main control chip when powered on, and can provide voice interaction functions under different themes. The implementation of the present disclosure realizes that the voice module chip is universal for different themes through the replacement of the wake-up word, that is, it can realize the use across brands and products, and reduce the cost of production and control of the voice module chip.

[0108] In an alternative embodiment, an electronic device is provided, such as Figure 6 As shown, Figure 6The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present disclosure.

[0109] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0110] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0111] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0112] The memory 4003 is used to store the computer program for executing the embodiment of the present disclosure, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0113] Among them, electronic devices include but are not limited to: intelligent devices equipped with voice modules.

[0114] An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0115] The embodiments of the present disclosure also provide a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiments when executed by a processor.

[0116] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than that shown or described in the text.

[0117] It should be understood that, although the flowchart of the embodiment of the present disclosure indicates each operation step by arrows, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present disclosure, the implementation steps in each flowchart can be executed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times. In scenarios with different execution times, the execution order of these sub-steps or stages can be flexibly configured according to demand, and the embodiment of the present disclosure does not limit this.

[0118] The above is only an optional implementation method for some implementation scenarios of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the scheme of the present disclosure, other similar implementation methods based on the technical ideas of the present disclosure are also within the protection scope of the embodiments of the present disclosure.

Claims

1. A voice control method, characterized in that: Applied to a voice module chip, the method comprises: When powered on, a query instruction is sent to the main control chip, and a wake-up word is determined based on first information fed back by the main control chip; the first information at least includes information for indicating a target topic, and different topics have their own corresponding wake-up words; In response to a wake-up operation carrying the wake-up word, a voice control mode is entered, and a received voice instruction is executed based on a voice word table matching the wake-up word.

2. The method according to claim 1, characterized in that: The method further comprises: Acquire a preset voice word table, wherein the preset voice word table matches each topic indicated by the main control chip through feedback information; A sub-entry table associated with the wake-up word is established based on a preset voice entry table; the sub-entry table is used to store keywords associated with the target topic and store resource information associated with the keyword; The executing the received voice instruction based on the voice word table matching the wake-up word includes: In response to second information input by voice, determining a control intention of the second information; If the control intention matches at least one keyword in the sub-item table, resource information associated with the at least one keyword is obtained for feedback.

3. The method according to claim 1 or 2, characterized in that: The executing the received voice instruction based on the voice word table matching the wake-up word includes: In response to third information of voice input, determining fourth information corresponding to the third information based on a voice word table associated with the wake-up word; Sending the fourth information to the main control chip, so that the main control chip controls the device and feeds back corresponding playback information according to the fourth information; The playing information is controlled to be played to prompt the operation object that the voice instruction corresponding to the third information has been executed.

4. The method according to claim 1, characterized in that: The determining the wake-up word based on the first information fed back by the main control chip includes: Acquire first information and parameter setting instructions for controlling the voice module chip sent by the main control chip, wherein the first information also includes wake-up control information and / or volume control information; Determining a wake-up word corresponding to the target topic based on the information indicating the target topic in the first information; Based on the wake-up control information, a wake-up control parameter associated with the wake-up word is set, and the wake-up control parameter is used to control the wake-up time; and / or, based on the volume control information, a volume control parameter associated with the wake-up word is set, and the volume control parameter is used to control the playback volume.

5. The method according to claim 4, characterized in that The executing the received voice instruction based on the voice word table matching the wake-up word includes: In response to first volume adjustment information input by voice, updating the volume control parameter based on the first volume adjustment information to adjust the playback volume; And / or, the method further comprises: A volume adjustment instruction sent by the main control chip is received, and the volume control parameter is updated based on the second volume adjustment information carried in the volume adjustment instruction.

6. The method according to claim 1, characterized in that The method further comprises: In response to the pause operation, within a first time period, refusing to respond to the received voice command or controlling to shut down the voice collection module; The suspend operation includes at least one of the following: In the second time period, at least two operation objects send voice messages; Voice input is used to trigger a keyword for pausing the voice control mode; On the device interaction interface configured with the voice module chip, a control for pausing acquisition of voice input information is triggered.

7. The method according to claim 1 or 6, characterized in that: The method further comprises: In the case of entering the voice control mode, if no information inputted by voice is received for a preset exit time, then exiting the voice control mode; The preset exit duration includes a first duration associated with the wake-up word, or a second duration set by the operation object; the second duration has a higher priority than the first duration; The second duration includes the duration set by the operation object through voice control in the voice control mode and / or the duration set by the exit duration setting page provided by the display of the device configured with the voice module chip.

8. A voice control method, characterized in that: Applied to the main control chip, the method includes: Receive the query command sent by the voice module chip when it is powered on; Feedback the first information to the voice module chip, so that the voice module chip determines the wake-up word based on the first information, and enters the voice control mode in response to the wake-up operation carrying the wake-up word, so as to execute the received voice command based on the voice word table matching the wake-up word; The first information at least includes information for indicating a target topic, and different topics have their own corresponding wake-up words.

9. The method according to claim 8, characterized in that The first information also includes volume control information, which is used for the voice module chip to set a volume control parameter associated with the wake-up word, and the volume control parameter is used to control the playback volume; The method further comprises: In response to a volume adjustment operation triggered by a volume adjustment button, a volume adjustment instruction is sent to the voice module chip, wherein the volume adjustment instruction carries second volume adjustment information, so that the voice module chip updates the volume control parameter based on the second volume adjustment information.

10. A chip system, characterized in that: The chip system is applied to an electronic device, and the chip system includes one or more processors, and the one or more processors are used to call computer instructions so that the electronic device executes the steps of the method described in any one of claims 1 to 7 or 8 to 9.

Images