Methods and devices for responding to voice commands, storage media and electronic devices

Abstract

This application discloses a voice command response method, apparatus, storage medium, and electronic device, relating to the field of smart home technology. The voice command response method includes: after responding to a first voice command from a first object, if a second voice command from the first object is received, then acquiring dialogue interaction information pre-configured for a voice interaction device; wherein the first voice command is used to indicate a first intention of the first object, and the second voice command is used to indicate a second intention of the first object; if it is determined from the dialogue interaction information that continuous response to the first and second voice commands is permitted, then acquiring a first reception time of the first voice command and a second reception time of the second voice command; if the time difference between the first and second reception times is less than a preset threshold, then responding to the second voice command.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a voice command response method and apparatus, storage medium and electronic device. Background Technology

[0002] A voice dialogue system is a voice input and voice output system, which, according to the system flow, includes the following sub-modules: ASR (Automatic Speech Recognition), NLU (Natural Language Understanding), DM (Dialogue Management), NLG (Natural Language Generation), and TTS (Text to Speech). The specific interaction flow of a voice dialogue system is as follows: Figure 3 As shown, where:

[0003] The role of the ASR module is to convert speech into text, which is then processed by subsequent modules.

[0004] The role of the NLU module is to understand the intent (what the user's purpose is) and slots (parameter information attached to complete the user's purpose) of the user interaction. For example, the intent of "I want to know what the weather will be like in Beijing tomorrow" is "check the weather", and there are two slots: "location = Beijing" and "time = tomorrow".

[0005] The DM module's role is to manage the context of the session and determine which strategy to use for the response.

[0006] The NLG module is used to generate text content to answer the user.

[0007] TTS (Text-to-Speech) converts text into speech, allowing devices to play it back.

[0008] Existing voice dialogue systems all involve waking up the user before interacting, and this process is repeated every time.

[0009] The following problems will occur if the device is woken up before interaction: (1) Each interaction requires waking up, resulting in a poor interaction experience; (2) If interaction is delayed after waking up, the interaction will miss the opportunity to receive sound from the device, leading to interaction failure; (3) If interaction is premature after waking up, the sound may not be fully received, resulting in ASR errors and interaction errors; (4) Multiple wake-ups result in a large number of interactions.

[0010] There is no effective solution to the problem that existing voice dialogue systems require waking up before interaction and that each interaction requires waking up.

[0011] Therefore, it is necessary to improve the relevant technology to overcome the aforementioned defects. Summary of the Invention

[0012] This application provides a voice command response method and apparatus, storage medium and electronic device to at least solve the problem that the interaction process of existing voice dialogue systems in the related art is to wake up first and then interact, and that wake-up is required for each interaction.

[0013] According to one aspect of the embodiments of this application, a voice command response method is provided, comprising: after responding to a first voice command of a first object, if a second voice command of the first object is received, then acquiring dialogue interaction information pre-configured for a voice interaction device; wherein the first voice command is used to indicate a first intention of the first object, the second voice command is used to indicate a second intention of the first object, and the dialogue interaction information is used to indicate whether to continuously respond to the first voice command and the second voice command when there is no wake-up voice of the first object between the first voice command and the second voice command; if it is determined according to the dialogue interaction information that continuous response to the first voice command and the second voice command is allowed, acquiring a first reception time of the first voice command and a second reception time of the second voice command; and responding to the second voice command when the time difference between the first reception time and the second reception time is less than a preset threshold.

[0014] In an exemplary embodiment, before obtaining pre-configured dialogue interaction information for a voice interaction device, the method further includes: receiving a configuration operation from a first object or a second object; generating the dialogue interaction information in response to the configuration operation; wherein the dialogue interaction information includes: multiple keywords.

[0015] In an exemplary embodiment, after obtaining pre-configured dialogue interaction information for the voice interaction device, the method further includes: parsing the first voice command to obtain the first intent corresponding to the first voice command; obtaining the target keyword included in the first intent; and, if the target keyword is matched among multiple keywords included in the dialogue interaction information, determining that the dialogue interaction information allows for continuous response to the first voice command and the second voice command.

[0016] In an exemplary embodiment, after obtaining pre-configured dialogue interaction information for the voice interaction device, the method further includes: parsing the first voice command and the second voice command to obtain the first intent corresponding to the first voice command and the second intent corresponding to the second voice command; obtaining the target keyword included in the first intent and the device function required to execute the second intent; and determining that the dialogue interaction information allows continuous response to the first voice command and the second voice command when the target keyword is matched among the multiple keywords included in the dialogue interaction information and the voice interaction device has the device function.

[0017] In an exemplary embodiment, after obtaining pre-configured dialogue interaction information for the voice interaction device, the method further includes: parsing the first voice command and the second voice command to obtain the first intent corresponding to the first voice command and the second intent corresponding to the second voice command; obtaining the target keyword included in the first intent and the device function required to execute the second intent; and determining that the dialogue interaction information allows continuous response to the first voice command and the second voice command when the target keyword is matched among multiple keywords included in the dialogue interaction information and the execution priority of the device function is higher than the priority of the current execution function of the voice interaction device.

[0018] In an exemplary embodiment, after obtaining dialogue interaction information pre-configured for the voice interaction device, the method further includes: if it is determined based on the dialogue interaction information that continuous response to the first voice command and the second voice command is prohibited, determining whether a wake-up voice of the first object is received between the first reception time and the second reception time; and if the wake-up voice is received, responding to the second voice command.

[0019] In an exemplary embodiment, after obtaining the first reception time of the first voice command and the second reception time of the second voice command, the method further includes: if the time difference between the first reception time and the second reception time is greater than or equal to a preset threshold, performing at least one of the following: sending a rejection response message to the target terminal of the first object to instruct the first object to re-wake up the voice interaction device; displaying the rejection response message on the display page of the voice interaction device to instruct the first object to re-wake up the voice interaction device; and playing the rejection response message through the voice interaction device to instruct the first object to re-wake up the voice interaction device.

[0020] According to another aspect of the embodiments of this application, a voice command response device is also provided, comprising: a first acquisition module, configured to, after responding to a first voice command of a first object, acquire dialogue interaction information pre-configured for a voice interaction device if a second voice command of the first object is received; wherein the first voice command is used to indicate a first intention of the first object, the second voice command is used to indicate a second intention of the first object, and the dialogue interaction information is used to indicate whether to continuously respond to the first voice command and the second voice command when there is no wake-up voice of the first object between the first voice command and the second voice command; a second acquisition module, configured to, when it is determined according to the dialogue interaction information that continuous response to the first voice command and the second voice command is permitted, acquire a first reception time of the first voice command and a second reception time of the second voice command; and a response module, configured to respond to the second voice command when the time difference between the first reception time and the second reception time is less than a preset threshold.

[0021] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the response method of the above-mentioned voice command when it is run.

[0022] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the response method of the voice command through the computer program.

[0023] This application addresses the issue that, upon responding to a first voice command from a first object, if a second voice command from the first object is received, pre-configured dialogue interaction information for the voice interaction device is acquired. The first voice command indicates a first intention of the first object, the second voice command indicates a second intention of the first object, and the dialogue interaction information indicates whether to continuously respond to the first and second voice commands if there is no wake-up voice from the first object between the first and second voice commands. If, based on the dialogue interaction information, it is determined that continuous response to the first and second voice commands is permitted, a first reception time of the first voice command and a second reception time of the second voice command are acquired. If the time difference between the first and second reception times is less than a preset threshold, the second voice command is responded to. In other words, the dialogue interaction information determines whether continuous response to the first and second voice commands is permitted, and if permitted, further determines the magnitude of the time difference between the first and second voice commands and a preset threshold to determine whether to respond to the second voice command. This technical solution solves the problem in existing voice dialogue systems where the interaction process requires wake-up before interaction, and each interaction requires wake-up. It achieves the technical effect of continuous interaction with a single wake-up, thereby reducing wake-up actions and improving interaction efficiency. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the hardware environment for an optional voice command response method according to an embodiment of this application;

[0027] Figure 2 This is a flowchart of an optional voice command response method according to an embodiment of this application;

[0028] Figure 3 This is a schematic diagram of a voice dialogue system interaction according to an embodiment of this application;

[0029] Figure 4This is a schematic diagram showing the location of an optional voice command response method according to an embodiment of this application;

[0030] Figure 5 This is a flowchart illustrating an optional voice command response method according to an embodiment of this application;

[0031] Figure 6 This is a structural block diagram of an optional voice command response device according to an embodiment of this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] According to one aspect of the embodiments of this application, a voice command response method is provided. This voice command response method is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligencehouse ecosystems. Optionally, in this embodiment, the above-mentioned voice command response method can be applied to, for example... Figure 1 The hardware environment shown consists of multiple terminal devices 102 and a server 104. Figure 1As shown, server 104 is connected to multiple terminal devices 102 via a network and can be used to provide services (such as application services) to terminals or clients installed on terminals. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0035] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0036] This embodiment provides a voice command response method, including but not limited to those applied to voice interaction devices. Figure 2 This is a flowchart of a voice command response method according to an embodiment of this application, the process including the following steps:

[0037] Step S202: After responding to the first voice command of the first object, if a second voice command of the first object is received, then the dialogue interaction information pre-configured for the voice interaction device is obtained; wherein, the first voice command is used to indicate the first intention of the first object, the second voice command is used to indicate the second intention of the first object, and the dialogue interaction information is used to indicate whether to respond to the first voice command and the second voice command continuously when there is no wake-up voice of the first object between the first voice command and the second voice command.

[0038] Step S204: If it is determined that continuous response to the first voice command and the second voice command is allowed based on the dialogue interaction information, obtain the first reception time of the first voice command and the second reception time of the second voice command;

[0039] Step S206: If the time difference between the first reception time and the second reception time is less than a preset threshold, respond to the second voice command.

[0040] It should be noted that the first object may include a first target object and / or a second target object. Furthermore, the first voice command and the second voice command may be issued by the same target object or by different target objects. Specifically, there are two scenarios: 1) Both the first and second voice commands are issued by the first target object, or both are issued by the second target object; 2) The first voice command is issued by the first target object and the second voice command is issued by the second target object, or the first voice command is issued by the second target object and the second voice command is issued by the first target object.

[0041] Through the above steps, after responding to the first voice command from the first object, if a second voice command from the first object is received, pre-configured dialogue interaction information for the voice interaction device is obtained. The first voice command indicates the first intention of the first object, the second voice command indicates the second intention of the first object, and the dialogue interaction information indicates whether to continuously respond to the first and second voice commands when there is no wake-up voice from the first object between the first and second voice commands. If, based on the dialogue interaction information, it is determined that continuous response to the first and second voice commands is permitted, the first reception time of the first voice command and the second reception time of the second voice command are obtained. If the time difference between the first and second reception times is less than a preset threshold, the second voice command is responded to. In other words, the dialogue interaction information determines whether continuous response to the first and second voice commands is permitted, and if permitted, further determines the magnitude of the time difference between the first and second voice commands and a preset threshold to determine whether to respond to the second voice command. This technical solution solves the problem in existing voice dialogue systems where the interaction process requires wake-up before interaction, and each interaction requires wake-up; it achieves the technical effect of continuous interaction with a single wake-up, thereby reducing wake-up actions and improving interaction efficiency.

[0042] In an exemplary embodiment, before obtaining pre-configured dialogue interaction information for a voice interaction device, the method further includes: receiving a configuration operation from a first object or a second object; generating the dialogue interaction information in response to the configuration operation; wherein the dialogue interaction information includes: multiple keywords.

[0043] Optionally, the dialogue interaction information can be pre-configured, meaning the second target could be a product engineer, or the user can add configurations based on their own habits and preferences, making the user the first target. Furthermore, the dialogue interaction information includes multiple keywords, and corresponding principles are configured based on different keywords. For example, "Principle: If you wake up the speaker to check the weather, the radio will be turned on by default and the conversation will continue without rejection," the corresponding keyword would be "weather." Alternatively, "Principle: If you adjust the temperature by speaking into the air conditioner, the radio will be turned on by default and the conversation will continue without rejection," the corresponding keyword would be... The above content is merely illustrative and this embodiment does not limit its scope.

[0044] In an exemplary embodiment, after obtaining pre-configured dialogue interaction information for the voice interaction device, the method further includes: parsing the first voice command to obtain the first intent corresponding to the first voice command; obtaining the target keyword included in the first intent; and, if the target keyword is matched among multiple keywords included in the dialogue interaction information, determining that the dialogue interaction information allows for continuous response to the first voice command and the second voice command.

[0045] Optionally, the NLU module of the voice interaction system parses the first voice command and outputs the first intent corresponding to the first voice command. Further, it obtains the target keyword from the first intent. The target keyword can be a word related to the function the first voice command wants the voice interaction device to perform. For example, if the first voice command is "How's the weather in Beijing?", the intent output by the NLU after parsing the first voice command is: "Check the weather," and the target keyword is: "weather." If the target keyword is matched among the keywords included in any of the principles configured in the dialogue interaction information, it is determined that the dialogue interaction information allows for continuous response to the first and second voice commands.

[0046] In an exemplary embodiment, after obtaining pre-configured dialogue interaction information for the voice interaction device, the method further includes: parsing the first voice command and the second voice command to obtain the first intent corresponding to the first voice command and the second intent corresponding to the second voice command; obtaining the target keyword included in the first intent and the device function required to execute the second intent; and determining that the dialogue interaction information allows continuous response to the first voice command and the second voice command when the target keyword is matched among the multiple keywords included in the dialogue interaction information and the voice interaction device has the device function.

[0047] Optionally, if the target keyword of the first intent is obtained and the target keyword is matched among multiple keywords included in the dialogue interaction information, it is further determined that the voice interaction device can perform the device function required by the second intent, including: determining the first device information of the target execution device indicated by the second intent according to the second intent, and obtaining the second device information of the voice interaction device; if the first device information and the second device information are the same, it is determined that the voice interaction device can perform the device function required by the second intent.

[0048] In an exemplary embodiment, after obtaining pre-configured dialogue interaction information for the voice interaction device, the method further includes: parsing the first voice command and the second voice command to obtain the first intent corresponding to the first voice command and the second intent corresponding to the second voice command; obtaining the target keyword included in the first intent and the device function required to execute the second intent; and determining that the dialogue interaction information allows continuous response to the first voice command and the second voice command when the target keyword is matched among multiple keywords included in the dialogue interaction information and the execution priority of the device function is higher than the priority of the current execution function of the voice interaction device.

[0049] It is understandable that the functions of a voice interaction device may be configured with priorities, meaning that a certain function must be executed first. For example, if the voice interaction device is an air conditioner, then turning on the air conditioner could be set as the first priority, and cooling as the second priority, etc. Users can also set the priorities of device functions according to their own needs. Therefore, if the priority of the device function required by the second intention is higher than the currently executed function of the voice interaction device, it is determined that the dialogue interaction information allows for continuous response to the first and second voice commands; if the priority of the device function required by the second intention is lower than the currently executed function of the voice interaction device, it is determined that the dialogue interaction information indicates that the second voice command should not be responded to.

[0050] Furthermore, when the first voice command and the second voice command are issued to different objects, for example: 1) determine the device functions required for the second intent and the priorities set for the currently executed functions of the voice interaction device, i.e., first priority and second priority; 2) set weights for the first target object issuing the first voice command and the second target object issuing the second voice command in the system of the voice interaction device, i.e., first weight and second weight. Compare the product of the first priority and the first weight and the product of the second priority and the second weight. If the product of the second priority and the second weight is larger, it is determined that the dialogue interaction information allows for continuous response to the first voice command and the second voice command. It should be noted that the weight settings can be pre-designed by product engineers or subsequently modified or reconfigured by the user.

[0051] In an exemplary embodiment, after obtaining dialogue interaction information pre-configured for the voice interaction device, the method further includes: if it is determined based on the dialogue interaction information that continuous response to the first voice command and the second voice command is prohibited, determining whether a wake-up voice of the first object is received between the first reception time and the second reception time; and if the wake-up voice is received, responding to the second voice command.

[0052] Optionally, the dialogue interaction information may also include principles related to control commands. For example, if a user issues a first voice command, "Don't speak," and the DM module determines that it is acting on a voice interaction device, it further analyzes the intent and matches keywords in the dialogue interaction information. Based on the keywords, it determines the relevant principles of control commands corresponding to the keywords. Furthermore, it determines whether a wake-up voice from the first object is received between the first reception time of the first voice command and the second reception time of the second voice command; if the wake-up voice is received, it responds to the second voice command.

[0053] In an exemplary embodiment, after obtaining the first reception time of the first voice command and the second reception time of the second voice command, the method further includes: if the time difference between the first reception time and the second reception time is greater than or equal to a preset threshold, performing at least one of the following: sending a rejection response message to the target terminal of the first object to instruct the first object to re-wake up the voice interaction device; displaying the rejection response message on the display page of the voice interaction device to instruct the first object to re-wake up the voice interaction device; and playing the rejection response message through the voice interaction device to instruct the first object to re-wake up the voice interaction device.

[0054] Optionally, if the time difference between the first receiving time and the second receiving time is greater than or equal to a preset threshold, the rejection response information can be sent to the target terminal of the first object. If the rejection response information is sent to the target terminal a preset number of times, the rejection response information can be played directly through a voice interaction device.

[0055] Obviously, the embodiments described above are only some embodiments of this application, and not all embodiments. To better understand the above voice command response method, the process is described below in conjunction with embodiments, but this is not intended to limit the technical solutions of the embodiments of this application. Specifically:

[0056] based on Figure 3 As can be seen, the voice dialogue system first converts the user's audio interaction into text, which is then passed to the semantic understanding module to parse out the intent and slots. The dialogue management module makes decisions based on the intent and slots, the response generation module generates the corresponding text answer based on the template, and finally the TTS module converts the text into audio output.

[0057] The continuous dialogue method proposed in the optional embodiments of this application relies on the parsing results of the NLU (Semantic Understanding) module, namely intent and slot information. During the startup process of the voice dialogue system, the prepared continuous dialogue combination configuration information (equivalent to the dialogue interaction information in the above embodiments) is loaded. Figure 4 As shown, in the Dialogue Management (DM) step, the voice dialogue system processes the intent information based on the continuous dialogue combination configuration information. Specifically, it matches the target keywords in the first intent corresponding to the first voice command with the keywords in the dialogue interaction information, further compares the time difference between the first reception time of the first voice command and the second reception time of the second voice command with the size of the preset threshold, and after comprehensive judgment by the control logic, outputs continuous dialogue control parameters to the device to decide whether to reject the second intent corresponding to the second voice command or to allow the device to continue receiving audio.

[0058] Furthermore, the dialogue interaction information includes multiple keywords, which are combined with "input parameters," "output parameters," and some "control logic" for comprehensive judgment. The set of input parameters includes the device category (i.e., Figure 5 The input parameters include the device type, device model, and NLU intent information. Output parameters include parameters indicating whether to reject the second voice command and parameters indicating whether to continue receiving audio. Control logic includes whether a wake-up action exists between the first and second reception times, the maximum timeout (equivalent to whether the time difference in the above embodiment is less than a preset threshold), and whether to ignore the wake-up action. The intent information output by the NLU module, along with related device information, is first matched with the input parameters, then neutralized and judged by the control logic, and finally the output parameters for continuous dialogue are output.

[0059] Specifically, Figure 5 This is a flowchart illustrating an optional voice command response method according to an embodiment of this application, as shown below. Figure 5 As shown, the specific steps are as follows:

[0060] Step 1: Verify the "input parameters" based on the device category, device model, NLU intent information, page information, etc.

[0061] Step 2: Control logic judgment.

[0062] Based on whether a wake-up action is performed, the maximum timeout, whether the wake-up action is ignored, and other factors, combined with the configuration information of the continuous dialogue, and combined with the device category, device model, NLU intent information, page information, etc. verified in step 1, the control logic is judged.

[0063] Step 3: Determine whether to reject the message or continue the dialogue based on the control logic results.

[0064] For example, if you wake up a speaker by saying "How's the weather in Beijing?", the NLU will output the intent as "Check the weather," the slot location as "Beijing," the device type as "speaker," no page information, and a wake-up event. If the continuous dialogue configuration information includes a principle of "Wake up the speaker to check the weather, then the radio will be turned on by default to continue the dialogue without rejection," then after calculation based on the input parameters and control parameters, the final output parameter will be "Start continuous dialogue."

[0065] Furthermore, through the optional embodiments of this application, continuous dialogue functionality across different devices can be achieved simply by modifying the configuration information. Specifically, the optional embodiments of this application rely on the NLU module results of the dialogue system. Therefore, continuous dialogue can be achieved from the initial implementation of the dialogue system, solving the cold start problem. At the same time, this method controls continuous dialogue based on the combination configuration of intent and slot, requiring no training data or annotation, greatly reducing the workload. If the system functionality is expanded, only the combination configuration needs to be updated, allowing for flexible configuration and rapid iteration.

[0066] The optional embodiments of this application solve the problem of waking up before interacting, and that each interaction requires waking up, thereby also solving the derived problems and achieving the following effects: (1) After waking up once, continuous interaction can be achieved without waking up again, just like smooth communication between people; (2) During continuous interaction, the problem of interaction failure caused by interaction being premature or delayed is avoided, which greatly improves the probability of successful interaction; (3) Reduce waking up actions and improve interaction efficiency.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0068] This embodiment also provides a voice command response device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0069] Figure 6 This is a structural block diagram of an optional voice command response device according to an embodiment of this application. The device includes:

[0070] The first acquisition module 62 is used to acquire dialogue interaction information pre-configured for the voice interaction device if a second voice command of the first object is received after responding to the first voice command of the first object; wherein the first voice command is used to indicate the first intention of the first object, the second voice command is used to indicate the second intention of the first object, and the dialogue interaction information is used to indicate whether to respond to the first voice command and the second voice command continuously if there is no wake-up voice of the first object between the first voice command and the second voice command.

[0071] The second acquisition module 64 is used to acquire the first reception time of the first voice command and the second reception time of the second voice command when it is determined from the dialogue interaction information that continuous response to the first voice command and the second voice command is allowed.

[0072] The response module 66 is used to respond to the second voice command when the time difference between the first reception time and the second reception time is less than a preset threshold.

[0073] With the above-described device, after responding to the first voice command from the first object, if a second voice command from the first object is received, pre-configured dialogue interaction information for the voice interaction device is obtained. The first voice command indicates the first intention of the first object, the second voice command indicates the second intention of the first object, and the dialogue interaction information indicates whether to continuously respond to the first and second voice commands when there is no wake-up voice from the first object between the first and second voice commands. If, based on the dialogue interaction information, it is determined that continuous response to the first and second voice commands is permitted, the first reception time of the first voice command and the second reception time of the second voice command are obtained. If the time difference between the first and second reception times is less than a preset threshold, the second voice command is responded to. In other words, the dialogue interaction information determines whether continuous response to the first and second voice commands is permitted. If permitted, the time difference between the first and second voice commands is further determined relative to a preset threshold to determine whether to respond to the second voice command. This technical solution solves the problem in existing voice dialogue systems where the interaction process requires wake-up before interaction, and wake-up is needed for each interaction. It achieves the technical effect of continuous interaction with a single wake-up, thereby reducing wake-up actions and improving interaction efficiency.

[0074] Before acquiring the pre-configured dialogue interaction information for the voice interaction device, the first acquisition module 62 is further configured to receive a configuration operation from a first object or a second object; in response to the configuration operation, generate the dialogue interaction information; wherein the dialogue interaction information includes: multiple keywords.

[0075] Optionally, the dialogue interaction information can be pre-configured, meaning the second target could be a product engineer, or the user can add configurations based on their own habits and preferences, making the user the first target. Furthermore, the dialogue interaction information includes multiple keywords, and corresponding principles are configured based on different keywords. For example, "Principle: If you wake up the speaker to check the weather, the radio will be turned on by default and the conversation will continue without rejection," the corresponding keyword would be "weather." Alternatively, "Principle: If you adjust the temperature by speaking into the air conditioner, the radio will be turned on by default and the conversation will continue without rejection," the corresponding keyword would be... The above content is merely illustrative and this embodiment does not limit its scope.

[0076] After acquiring the dialogue interaction information pre-configured for the voice interaction device, the first acquisition module 62 is further configured to parse the first voice command to obtain the first intent corresponding to the first voice command; acquire the target keyword included in the first intent; and, if the target keyword is matched among the multiple keywords included in the dialogue interaction information, determine that the dialogue interaction information allows for continuous response to the first voice command and the second voice command.

[0077] Optionally, the NLU module of the voice interaction system parses the first voice command and outputs the first intent corresponding to the first voice command. Further, it obtains the target keyword from the first intent. The target keyword can be a word related to the function the first voice command wants the voice interaction device to perform. For example, if the first voice command is "How's the weather in Beijing?", the intent output by the NLU after parsing the first voice command is: "Check the weather," and the target keyword is: "weather." If the target keyword is matched among the keywords included in any of the principles configured in the dialogue interaction information, it is determined that the dialogue interaction information allows for continuous response to the first and second voice commands.

[0078] After acquiring the pre-configured dialogue interaction information for the voice interaction device, the first acquisition module 62 is further configured to parse the first voice command and the second voice command to obtain the first intent corresponding to the first voice command and the second intent corresponding to the second voice command; acquire the target keywords included in the first intent, and the device functions required to execute the second intent; and if the target keywords are matched among the multiple keywords included in the dialogue interaction information, and the voice interaction device has the device functions, determine that the dialogue interaction information allows for continuous response to the first voice command and the second voice command.

[0079] Optionally, if the target keyword of the first intent is obtained and the target keyword is matched among multiple keywords included in the dialogue interaction information, it is further determined that the voice interaction device can perform the device function required by the second intent, including: determining the first device information of the target execution device indicated by the second intent according to the second intent, and obtaining the second device information of the voice interaction device; if the first device information and the second device information are the same, it is determined that the voice interaction device can perform the device function required by the second intent.

[0080] After acquiring the pre-configured dialogue interaction information for the voice interaction device, the first acquisition module 62 is further configured to parse the first voice command and the second voice command to obtain the first intent corresponding to the first voice command and the second intent corresponding to the second voice command; acquire the target keyword included in the first intent, and the device function required to execute the second intent; and if the target keyword is matched among the multiple keywords included in the dialogue interaction information, and the execution priority of the device function is higher than the priority of the current execution function of the voice interaction device, determine that the dialogue interaction information allows for continuous response to the first voice command and the second voice command.

[0081] It is understandable that the functions of a voice interaction device may be configured with priorities, meaning that a certain function must be executed first. For example, if the voice interaction device is an air conditioner, then turning on the air conditioner could be set as the first priority, and cooling as the second priority, etc. Users can also set the priorities of device functions according to their own needs. Therefore, if the priority of the device function required by the second intention is higher than the currently executed function of the voice interaction device, it is determined that the dialogue interaction information allows for continuous response to the first and second voice commands; if the priority of the device function required by the second intention is lower than the currently executed function of the voice interaction device, it is determined that the dialogue interaction information indicates that the second voice command should not be responded to.

[0082] Furthermore, when the first voice command and the second voice command are issued to different objects, for example: 1) determine the device functions required for the second intent and the priorities set for the currently executed functions of the voice interaction device, i.e., first priority and second priority; 2) set weights for the first target object issuing the first voice command and the second target object issuing the second voice command in the system of the voice interaction device, i.e., first weight and second weight. Compare the product of the first priority and the first weight and the product of the second priority and the second weight. If the product of the second priority and the second weight is larger, it is determined that the dialogue interaction information allows for continuous response to the first voice command and the second voice command. It should be noted that the weight settings can be pre-designed by product engineers or subsequently modified or reconfigured by the user.

[0083] After acquiring the dialogue interaction information pre-configured for the voice interaction device, the first acquisition module 62 is further configured to determine whether the wake-up voice of the first object is received between the first reception time and the second reception time if it is determined that continuous response to the first voice command and the second voice command is prohibited based on the dialogue interaction information; and if the wake-up voice is received, respond to the second voice command.

[0084] Optionally, the dialogue interaction information may also include principles related to control commands. For example, if a user issues a first voice command, "Don't speak," and the DM module determines that it is acting on a voice interaction device, it further analyzes the intent and matches keywords in the dialogue interaction information. Based on the keywords, it determines the relevant principles of control commands corresponding to the keywords. Furthermore, it determines whether a wake-up voice from the first object is received between the first reception time of the first voice command and the second reception time of the second voice command; if the wake-up voice is received, it responds to the second voice command.

[0085] After acquiring the first reception time of the first voice command and the second reception time of the second voice command, the second acquisition module 64 is further configured to perform at least one of the following if the time difference between the first reception time and the second reception time is greater than or equal to a preset threshold: sending a rejection response message to the target terminal of the first object to instruct the first object to re-wake up the voice interaction device; displaying the rejection response message on the display page of the voice interaction device to instruct the first object to re-wake up the voice interaction device; or playing the rejection response message through the voice interaction device to instruct the first object to re-wake up the voice interaction device.

[0086] Optionally, if the time difference between the first receiving time and the second receiving time is greater than or equal to a preset threshold, the rejection response information can be sent to the target terminal of the first object. If the rejection response information is sent to the target terminal a preset number of times, the rejection response information can be played directly through a voice interaction device.

[0087] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0088] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0089] S1, after responding to the first voice command of the first object, if a second voice command of the first object is received, then the dialogue interaction information pre-configured for the voice interaction device is obtained; wherein, the first voice command is used to indicate the first intention of the first object, the second voice command is used to indicate the second intention of the first object, and the dialogue interaction information is used to indicate whether to respond to the first voice command and the second voice command continuously when there is no wake-up voice of the first object between the first voice command and the second voice command.

[0090] S2, if it is determined from the dialogue interaction information that continuous response to the first voice command and the second voice command is allowed, the first reception time of the first voice command and the second reception time of the second voice command are obtained;

[0091] S3, if the time difference between the first reception time and the second reception time is less than a preset threshold, respond to the second voice command.

[0092] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0093] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0094] Embodiments of this application also provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0095] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0096] S1, after responding to the first voice command of the first object, if a second voice command of the first object is received, then the dialogue interaction information pre-configured for the voice interaction device is obtained; wherein, the first voice command is used to indicate the first intention of the first object, the second voice command is used to indicate the second intention of the first object, and the dialogue interaction information is used to indicate whether to respond to the first voice command and the second voice command continuously when there is no wake-up voice of the first object between the first voice command and the second voice command.

[0097] S2, if it is determined from the dialogue interaction information that continuous response to the first voice command and the second voice command is allowed, the first reception time of the first voice command and the second reception time of the second voice command are obtained;

[0098] S3, if the time difference between the first reception time and the second reception time is less than a preset threshold, respond to the second voice command.

[0099] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0100] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0101] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0102] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of responding to a voice command, characterized by, The method comprises the following steps: In response to the first voice instruction of the first object, if the second voice instruction of the first object is received, the dialogue interaction information preconfigured for the voice interaction device is obtained; wherein the first voice instruction is used to indicate the first intention of the first object, the second voice instruction is used to indicate the second intention of the first object, and the dialogue interaction information is used to indicate whether the first voice instruction and the second voice instruction are continuously responded in the case that there is no wake-up voice of the first object between the first voice instruction and the second voice instruction, wherein the dialogue interaction information comprises a plurality of keywords and the principle corresponding to each keyword; The target keyword included in the first intention and the device function required for executing the second intention are obtained; in the case that the target keyword is matched in the plurality of keywords included in the dialogue interaction information, and the voice interaction device has the device function, and the execution priority of the device function is higher than the priority of the current execution function of the voice interaction device, it is determined that the dialogue interaction information allows the first voice instruction and the second voice instruction to be continuously responded; In the case that the first voice instruction and the second voice instruction are determined to be continuously responded according to the dialogue interaction information, the first receiving time of the first voice instruction and the second receiving time of the second voice instruction are obtained; In the case that the time difference value of the first receiving time and the second receiving time is less than a preset threshold, the second voice instruction is responded, wherein the first device information of the target execution device indicated by the second intention is determined according to the second intention, and the second device information of the voice interaction device is obtained; in the case that the first device information and the second device information are the same, it is determined that the voice interaction device can execute the device function required for executing the second intention.

2. The method of responding to voice commands according to claim 1, wherein, Before obtaining the dialogue interaction information preconfigured for the voice interaction device, the method further comprises: Receiving a configuration operation of the first object or the second object; In response to the configuration operation, the dialogue interaction information is generated; wherein the dialogue interaction information comprises a plurality of keywords.

3. The method of responding to voice commands according to claim 2, wherein, After obtaining the dialogue interaction information preconfigured for the voice interaction device, the method further comprises: The first voice instruction is parsed to obtain the first intention corresponding to the first voice instruction; The target keyword included in the first intention is obtained; In the case that the target keyword is matched in the plurality of keywords included in the dialogue interaction information, it is determined that the dialogue interaction information allows the first voice instruction and the second voice instruction to be continuously responded.

4. The method of responding to voice commands according to claim 2, wherein, After obtaining the dialogue interaction information preconfigured for the voice interaction device, the method further comprises: The first voice instruction and the second voice instruction are parsed to obtain the first intention corresponding to the first voice instruction and the second intention corresponding to the second voice instruction; The target keyword included in the first intention and the device function required for executing the second intention are obtained; In a case where the target keyword is matched in the plurality of keywords included in the dialogue interaction information, and the voice interaction device has the device function, it is determined that the dialogue interaction information allows the first voice instruction and the second voice instruction to be continuously responded.

5. The method of responding to voice commands according to claim 2, wherein, After obtaining the dialogue interaction information pre-configured for the voice interaction device, the method further includes: parsing the first voice instruction and the second voice instruction to obtain the first intent corresponding to the first voice instruction and the second intent corresponding to the second voice instruction; obtaining a target keyword included in the first intent and a device function required for executing the second intent; In a case where the target keyword is matched in the plurality of keywords included in the dialogue interaction information, and the execution priority of the device function is higher than the priority of the current execution function of the voice interaction device, it is determined that the dialogue interaction information allows the first voice instruction and the second voice instruction to be continuously responded.

6. The method of responding to voice commands according to claim 1, wherein, After obtaining the dialogue interaction information pre-configured for the voice interaction device, the method further includes: In a case where it is determined according to the dialogue interaction information that the first voice instruction and the second voice instruction are not allowed to be continuously responded, it is determined whether a wake-up voice of the first object is received between the first receiving time and the second receiving time; In a case where the wake-up voice is received, the second voice instruction is responded.

7. The method of responding to voice commands according to claim 1, wherein, After obtaining the first receiving time of the first voice instruction and the second receiving time of the second voice instruction, the method further includes: In a case where the time difference between the first receiving time and the second receiving time is greater than or equal to a preset threshold, at least one of the following is performed: sending a rejection response information to a target terminal of the first object to instruct the first object to wake up the voice interaction device again; displaying the rejection response information on a display page of the voice interaction device to instruct the first object to wake up the voice interaction device again; playing the rejection response information through the voice interaction device to instruct the first object to wake up the voice interaction device again.

8. A device responsive to voice commands, characterized in that includes: The first obtaining module is configured to, in a case where a first voice instruction of a first object is responded, if a second voice instruction of the first object is received, obtain dialogue interaction information pre-configured for a voice interaction device; wherein the first voice instruction is used to indicate a first intent of the first object, the second voice instruction is used to indicate a second intent of the first object, and the dialogue interaction information is used to indicate whether the first voice instruction and the second voice instruction are continuously responded in a case where there is no wake-up voice of the first object between the first voice instruction and the second voice instruction, wherein the dialogue interaction information includes a plurality of keywords and a principle corresponding to each keyword. obtaining a target keyword included in the first intention and a device function required by the second intention; and determining that the dialogue interaction information allows the first voice instruction and the second voice instruction to be continuously responded to, in a case where the target keyword is matched from a plurality of keywords included in the dialogue interaction information, the voice interaction device has the device function, and an execution priority of the device function is higher than a current execution function priority of the voice interaction device; the second obtaining module is configured to, in a case where it is determined according to the dialogue interaction information that the first voice instruction and the second voice instruction are allowed to be continuously responded to, obtain a first receiving time of the first voice instruction and a second receiving time of the second voice instruction; the response module is configured to, in a case where a time difference between the first receiving time and the second receiving time is less than a preset threshold, respond to the second voice instruction, wherein first device information of a target execution device indicated by the second intention is determined according to the second intention, and second device information of the voice interaction device is obtained; and in a case where the first device information and the second device information are the same, it is determined that the voice interaction device is capable of executing the device function required by the second intention.

9. A computer readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7. 10.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 by using the computer program. The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 by using the computer program.

Images