Speech interaction method, apparatus and device, and storage medium
By acquiring and matching voiceprint features through voice interaction devices, and automatically playing messages after verification, the problem of smart home appliances being unable to play messages seamlessly is solved, thus improving the success rate of message reception and the level of intelligence.
Patent Information
- Application Number
- PCT/CN2026/095138
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-09
- Filing Date
- 2026-05-07
- Publication Date
- 2026-11-12
AI Technical Summary
Existing smart home appliances cannot effectively play messages for users in a seamless and non-intrusive manner, which may cause users to miss reading messages and affect the message interaction effect.
The system responds to voice interaction requests through a voice interaction device, obtains voice interaction data and status information of the target interaction object, and automatically plays the target message data associated with the target interaction object when the preset message triggering conditions are met, including steps such as voiceprint feature matching and voiceprint confirmation password verification.
It enables the effective playback of messages without the user's awareness, improves the success rate of receiving messages, reduces the user's operational burden in listening to messages, and expands the intelligence level of smart home appliances.
Smart Images

Figure CN2026095138_12112026_PF_FP_ABST
Abstract
Description
Voice interaction methods, devices, equipment and storage media This application claims priority to Chinese Patent Application No. 202510599782.3, filed on May 9, 2025, entitled "Voice Interaction Method, Apparatus, Device and Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field This application relates to the field of computer technology, specifically to a voice interaction method, apparatus, device, and storage medium. Background Technology Currently, with the continuous advancement of technology, home appliances are gradually developing towards intelligence. More and more smart home appliances are beginning to integrate voice recognition and voice control functions. However, although existing smart home appliances have integrated voice recognition and voice control functions, they still rely on paper records, text messages, or emails for leaving messages. However, these message leaving methods cannot ensure that users can effectively read messages in a seamless and non-intrusive manner, which may cause users to miss reading messages and affect the message interaction effect. Technical solutions This application provides a voice interaction method, apparatus, device, and storage medium, aiming to solve the technical problem in the prior art that smart home appliances cannot effectively play messages for users without their awareness. On one hand, embodiments of this application provide a voice interaction method, which includes the following steps: Responding to a voice interaction request, the system obtains the voice interaction data for that request. Obtain the object state information of the target interaction object corresponding to the voice interaction request; When the voice interaction data and the object status information meet the preset message triggering conditions, the target message data associated with the target interaction object is played. In one possible implementation of this application, the step of playing target message data associated with the target interactive object when the voice interaction data and the object state information meet the preset message triggering conditions includes: Based on the target wake-up word in the voice interaction data, the voiceprint features are extracted to obtain the target voiceprint features; The target voiceprint feature is matched with the preset voiceprint feature to obtain the target identity identifier corresponding to the target voiceprint feature; If the object status information and the target identity identifier meet the preset message triggering conditions, the target message data associated with the target identity identifier will be played. In one possible implementation of this application, the step of playing target message data associated with the target identity when the object state information and the target identity meet the preset message triggering conditions includes: If the object status information is the first object status information, and there is a first candidate message associated with the target identity, then obtain the voiceprint confirmation password associated with the preset message triggering condition. Obtain updated voice data associated with the voiceprint confirmation password, and updated voiceprint features in the updated voice data; If the updated voiceprint feature is the same as the target voiceprint feature, then the first candidate message is determined as the target message data, and the target message data is played. In one possible implementation of this application, the step of playing target message data associated with the target identity when the object state information and the target identity meet the preset message triggering conditions includes: If the object status information is the first object status information and the target identity meets the preset message triggering conditions, then a message retrieval request is generated based on the device identification information and the target identity. Based on the message retrieval request, read the target message data associated with the target identity in the message database, and play the target message data. In one possible implementation of this application, before playing the target message data associated with the voice interaction data, the method further includes: In response to a message generation request, obtain the message input data associated with the message generation request; Candidate message data is generated based on the message pointer and message content data in the message input data. In one possible implementation of this application, the message input data includes voice input data; The step of generating candidate message data based on the message pointer and message content data in the message input data includes: If the message input data is voice input data, then perform audio recognition on the voice input data to obtain the message pointing identifier corresponding to the voice input data; Activity detection is performed on the voice input data to obtain the message content data of the voice input data; Candidate message data is generated based on the message pointer and the message content data. In one possible implementation of this application, the step of performing activity detection on the voice input data to obtain the message content data of the voice input data includes: The voice input data is subjected to feature extraction to obtain voice input features; Calculate the window feature value of each sliding analysis window based on the voice input features; The target analysis window corresponding to the voice input data is determined based on the window feature value and the preset window detection threshold. The message content data in the voice input data is extracted using the target analysis window. In one possible implementation of this application, the message pointer includes a first message identifier and a second message identifier, and the candidate message data includes a first candidate message and a second candidate message; The step of generating candidate message data based on the message pointing identifier and the message content data includes: If the message pointer is a first message identifier, then a first candidate message is generated based on the preset voiceprint features corresponding to the first message identifier and the message content data; If the message pointer is a second message identifier, then a second candidate message is generated based on the first message identifier and the message content data. In one possible implementation of this application, the message input data includes text input data; The step of generating candidate message data based on the message pointing identifier and the message content data includes: If the message input data is text input data, then obtain the text content data in the text input data; Generate synthetic message data based on the text content data and the target message timbre; Candidate message data is generated based on the synthesized message data and the message pointing identifier. On the other hand, this application provides a voice interaction device, the voice interaction device comprising: The data acquisition module is configured to respond to a voice interaction request and acquire the voice interaction data of the voice interaction request. The status acquisition module is configured to acquire the object status information of the target interaction object corresponding to the voice interaction request; The message playback module is configured to play target message data associated with the voice interaction data when the voice interaction data meets the preset message triggering conditions. On the other hand, this application also provides a voice interaction device, the voice interaction device comprising: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the voice interaction method. On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the steps in the voice interaction method. This application obtains voice interaction data for a voice interaction request in response to the request; obtains object state information of the target interaction object corresponding to the voice interaction request; and plays target message data associated with the target interaction object when the voice interaction data and the object state information meet preset message triggering conditions. This enables the acquisition of voice interaction data of the target interaction object and the detection of object state information when the target interaction object interacts with a smart home appliance. When the voice interaction data and object state information meet preset message triggering conditions indicating the ability to effectively listen to the corresponding target message data, the target message data associated with the target interaction object is automatically played. This allows for message interaction using smart home appliances, improving the success rate of message reception for users and effectively reducing the user's operational burden when listening to messages, thus expanding the intelligence level of smart home appliances. Attached Figure Description To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 is a schematic diagram of a scenario of the voice interaction method according to an embodiment of this application; Figure 2 is a flowchart illustrating one embodiment of the voice interaction method in this application. Figure 3 is a flowchart illustrating an embodiment of the voice interaction method for generating message data provided in this application. Figure 4 is a flowchart illustrating an embodiment of the voice interaction method provided in this application for generating candidate message data based on text input data. Figure 5 is a structural schematic diagram of an embodiment of the voice interaction device provided in this application; Figure 6 is a structural schematic diagram of an embodiment of the voice interaction device provided in this application. Implementation methods of this application The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified. In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application. Currently, with the continuous advancement of technology, home appliances are gradually developing towards intelligence. More and more smart home appliances are beginning to integrate voice recognition and voice control functions. However, although existing smart home appliances have integrated voice recognition and voice control functions, they still rely on paper records, text messages, or emails for leaving messages. However, these message leaving methods cannot ensure that users can effectively read messages in a seamless and non-intrusive manner, which may cause users to miss reading messages and affect the message interaction effect. Based on this, this application proposes a voice interaction method, apparatus, device, and computer-readable storage medium to solve the technical problem in the prior art that smart home appliances cannot effectively play messages for users without their awareness. The voice interaction method in this embodiment is applied to a voice interaction device, which is provided in a voice interaction equipment. The voice interaction equipment includes one or more processors, a memory, and one or more applications. The one or more applications are stored in the memory and configured to be executed by the processor to implement the voice interaction method. The voice interaction equipment can be a smart terminal, such as a mobile phone, tablet computer, network device, and smart computer. Optionally, the voice interaction equipment can also be a server or a service cluster composed of multiple servers. As shown in Figure 1, which is a schematic diagram of a voice interaction method according to an embodiment of this application, the voice interaction scenario in this embodiment includes a voice interaction device 100 (which integrates a voice interaction mechanism), a cloud server 200, and a mobile message terminal 300. The voice interaction device 100 runs a computer-readable storage medium corresponding to the voice interaction method to execute the steps of the voice interaction method. The cloud server 200 is a cloud server used to store message data and transmit messages during the voice interaction process. The mobile message terminal 300 can be a mobile terminal for inputting messages to any voice interaction device 100. Optionally, the mobile message terminal 300 can be a smart terminal such as a mobile phone, tablet computer, network device, server, or smart computer. Optionally, in other scenarios, the voice interaction scenario may also include only the voice interaction device 100. It is understood that the voice interaction device in the voice interaction method scenario shown in Figure 1, or the device included in the voice interaction device, does not constitute a limitation on the embodiments of this application. That is, the number or type of the voice interaction device included in the voice interaction method scenario, or the number or type of the device included in each device, does not affect the overall implementation of the technical solution in the embodiments of this application, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of this application. In this embodiment of the application, the voice interaction device 100 is mainly used for: responding to a voice interaction request and obtaining the voice interaction data of the voice interaction request; Obtain the object state information of the target interaction object corresponding to the voice interaction request; When the voice interaction data and the object status information meet the preset message triggering conditions, the target message data associated with the target interaction object is played. The voice interaction device 100 in this application embodiment can be an independent smart home appliance, such as home appliances like air conditioners, televisions, and refrigerators, or other smart home devices such as cars, door locks, and smart speakers. This application provides a voice interaction method, apparatus, device, and computer-readable storage medium, which will be described in detail below. Those skilled in the art will understand that the application environment shown in Figure 1 is only one application scenario related to the solution of this application, and does not constitute a limitation on the application scenario of the solution of this application. Other application environments may include more or fewer voice interaction devices or voice interaction network connections than those shown in Figure 1. For example, only one voice interaction device is shown in Figure 1. It is understood that the scenario of this voice interaction method may also include one or more voice interaction devices, which is not specifically limited here. The voice interaction device 100 may also include a memory for storing voice interaction data and other data. It should be noted that the scenario diagram of the voice interaction method shown in Figure 1 is merely an example. The scenario of the voice interaction method described in the embodiments of this application is for the purpose of more clearly illustrating the technical solution of the embodiments of this application, and does not constitute a limitation on the technical solution provided in the embodiments of this application. Based on the scenarios described above for voice interaction methods, various embodiments of the voice interaction methods disclosed in this application are proposed. As shown in Figure 2, Figure 2 is a flowchart of an embodiment of the voice interaction method in this application. The voice interaction method includes the following steps 201 to 203: 201. Respond to the voice interaction request and obtain the voice interaction data of the voice interaction request; The voice interaction method in this embodiment is applied to a voice interaction device. The type and number of voice interaction devices are not specifically limited. That is, the voice interaction device can be one or more smart home appliance terminals. In a specific embodiment, the voice interaction device is a smart home appliance or other smart device. For example, the voice interaction device can be a smart home appliance such as an air conditioner, television and refrigerator, smart door lock and smart speaker with voice interaction function. The voice interaction device can seamlessly play target message data that meets preset message triggering conditions to the target interaction object when message data exists and a scheduled interaction request is made. This ensures that the user can effectively receive the target message data and effectively reduces the user's operational burden of listening to messages. The target interaction object is the user who interacts with the voice interaction device via voice. The target message data is the voice message data associated with the target interaction object that the voice interaction device stores or receives from a cloud server or mobile messaging terminal. That is, after receiving voice message data sent by the cloud server and / or mobile voice message terminal, the voice interaction device can trigger the message playback detection process when it receives a voice interaction request triggered by the target interaction object, and then identify whether to play the specified message data in subsequent steps. Specifically, during the operation process, the voice interaction device can respond to a voice interaction request to perform voice interaction with the user, acquire the voice interaction data of the voice interaction request in the voice interaction process, and further determine whether to play specified message data according to the voice interaction data in subsequent steps, so as to play the associated message data to the target interaction object imperceptibly. The voice interaction request is an operation in which the target interaction object wakes up the voice interaction device in a voice interaction manner and drives the voice interaction device to execute a specific interaction operation. For example, in a specific embodiment, the target interaction object wakes up the voice interaction device by speaking a wake word corresponding to the voice interaction device, and speaks a relevant operation instruction when the voice interaction device is in a woken state to trigger the voice interaction request. For another example, in another specific embodiment, the wake word of the voice interaction device is "Xiao T Xiao T", and the target interaction object can speak "Xiao T Xiao T + operation instruction" to trigger the voice interaction request for the voice interaction device. Specifically, a microphone assembly is pre-configured in the voice interaction device, configured to receive a voice interaction request and acquire the voice interaction data corresponding to the voice interaction request. The voice interaction data is voice data carrying a voice interaction instruction that represents the to-be-executed voice interaction instruction by which the target interaction object drives the voice interaction device. Optionally, the voice interaction instruction may be a conventional interaction instruction or a message acquisition instruction. The conventional interaction instruction may be other voice interaction instructions apart from performing message interaction. For example, the conventional interaction instruction may be a voice interaction instruction by which the target interaction object drives the voice interaction device to perform function switching, parameter adjustment, mode adjustment, device start / stop and the like in a voice interaction manner. The message acquisition instruction is a voice interaction instruction that represents that the target interaction object drives the voice interaction device to broadcast a relevant message in a voice interaction manner. That is, the voice interaction device can trigger a message playing process when the target interaction object performs conventional voice interaction. In addition, the voice interaction device can also trigger the message playing process when the target interaction object actively acquires message data, so as to play the associated target message data to the target interaction object in an imperceptible and non-intrusive manner. 202. Acquire object state information of a target interaction object corresponding to the voice interaction request; Specifically, after the voice interaction device acquires the voice interaction request and executes the voice interaction instruction corresponding to the voice interaction request, to ensure that the target message data can be completely received by the target interaction object, the voice interaction device further acquires the object state information of the target interaction object corresponding to the voice interaction request. The object state information is state information representing that the target interaction object can effectively listen to the message data currently. Optionally, the object state information includes first object state information in which message information can be completely acquired and second object state information in which message information cannot be completely acquired. Specifically, the voice interaction device can use an image acquisition component or a posture detection component to perform state recognition on the target interactive object, thereby determining the object's state information. For example, the voice interaction device can acquire the object posture data of the target interactive object through the image acquisition component or the posture detection component, and use this object posture data to perform object state recognition, thereby determining the object's state information. The image acquisition component and / or posture detection component can be set by the voice interaction device itself, or set by other terminals. The voice interaction device communicates and interacts with other terminals to obtain the object posture data acquired by the image acquisition component and / or posture detection component set by the other terminals. Optionally, the voice interaction device can use an image acquisition component to acquire regional image information in a preset area, and use a preset image segmentation model to segment object image information in the regional image information, perform pose recognition on the object image information to obtain object pose data of the target interactive object, and match the object pose data with reference pose information corresponding to each object state information, determine the reference pose information with a similarity greater than a preset similarity threshold as the target pose information, and determine the object state information corresponding to the target pose state information as the object state information of the target interactive object. Optionally, in one specific embodiment, the reference posture information associated with the first object state information can be posture information such as standing posture information and sitting posture information, which represent the user's focused interaction with the voice interaction device. The reference posture information associated with the second object state information can be posture information such as sleeping posture information, walking posture information, and undetected posture information, which represent the user's unfocused interaction with the voice interaction device. 203. When the voice interaction data and the object status information meet the preset message triggering conditions, play the target message data associated with the target interaction object. Specifically, after obtaining the voice interaction data and object status information of the target interactive object, the voice interaction device further determines whether the voice interaction data and object status information meet the preset message triggering conditions. When the voice interaction data and object status information meet the preset message triggering conditions, the device obtains the target message data associated with the target interactive object and plays the target message data. Optionally, after obtaining the object state information of the target interactive object, if the voice interaction device determines that the object state information is the second object state information, it determines that the target interactive object is currently unable to focus on listening to the message data. If there is no clear message playback instruction in the voice interaction data of the target interactive object, the message data will not be played to the target interactive object. Optionally, after the voice interaction device acquires the object state information of the target interaction object, if it is determined that the object state information is first object state information, it is determined that the target interaction object can effectively listen to message data currently, then the voice interaction device further judges whether the voice interaction data meets a preset message trigger condition, and when the voice interaction data meets the preset message trigger condition, acquires and plays the target message data associated with the target interaction object, so as to realize imperceptible, non-intrusive and effective playing of the message data to the user. The preset message trigger condition is a trigger condition strategy representing that the voice interaction data is driven to play the message data. Optionally, in a specific embodiment, the preset message trigger condition is that the object state information is the first object state information and there exists message data associated with the target identity identifier corresponding to the voice interaction data. The target message data is voice message data generated by a message object through voice input or text input via a voice interaction device or a mobile message terminal. Optionally, in a specific embodiment, the target message data includes first target message data and second target message data. The first target message data is directed message data received by a specified interaction object. The second target message data is general message data received for any interaction object. Specifically, the candidate message data to be played in the voice interaction device may be first candidate message data and second candidate message data. When there is the first candidate message that is only played to a specified user, after the voice interaction device determines that the object state information of the target interaction object is the first object state information, the voice interaction device further judges whether the voice interaction data meets the preset message trigger condition. That is, the voice interaction device performs voiceprint extraction according to the target wake-up word in the voice interaction data to determine the target voiceprint feature of the target interaction object. The target wake-up word is pre-set voice data corresponding to the specified wake-up word for triggering the voice interaction device to perform voice interaction. For example, in a specific embodiment, the target wake-up word is set as "Xiao T Xiao T", in addition, the target wake-up word can also be customized and modified by the user. Specifically, after being woken up by the target interaction object, the voice interaction device acquires the voice interaction data corresponding to the voice interaction request, performs wake-up word extraction on the voice interaction data, determines the target wake-up word in the voice interaction data, and performs audio feature extraction on the target wake-up word to acquire the target voiceprint feature of the target interaction object. Specifically, after acquiring the target voiceprint feature of the target interaction object, the voice interaction device matches the target voiceprint feature with a preset voiceprint feature, so as to determine the target identity identifier corresponding to the target voiceprint feature. That is, the voice interaction device compares the target voiceprint feature with the preset voiceprint feature, so as to determine the identity identifier associated with the preset voiceprint feature that is the same as the target voiceprint feature as the target identity identifier of the target interaction object. The preset voiceprint features are voiceprint features stored in the preset voiceprint database of the voice interaction device and associated with a specific identity identifier. Each preset voiceprint feature corresponds to an object identity identifier. The target identity identifier is the unique identifier information that represents a specific speaker. Optionally, this identity identifier information can be any one or more of the identity tag, user nickname, and user name configured by the user or the voice interaction device. For example, in one specific embodiment, the identity identifier information can be an identity tag, such as father / mother / grandfather / grandmother, etc. In another specific embodiment, the identity identifier information can be a user name, such as Zhang San / Li Si / Wang Wu, etc. Furthermore, in another specific embodiment, the identity identifier information can also be a user nickname set by the user. Specifically, after obtaining the target identity identifier of the target interaction object, the voice interaction device determines whether the preset message triggering conditions are met based on the target identity identifier, and then determines whether to play the corresponding voice message data. That is, after determining the target identity identifier, the voice interaction device accesses the preset message database to confirm whether there is a first candidate message associated with the target identity identifier in the message database. If there is a first candidate message associated with the target identity identifier, then the first candidate message is determined as the target message data. Optionally, when the voice interaction device determines that the object status information of the target interaction object is the first object status information, and there is a first candidate message associated with the target identity in the candidate message data, the voice interaction device also guides the target interaction object to perform voiceprint confirmation according to the pre-set voiceprint confirmation password. The voiceprint confirmation password is a preset password used to guide the target interactive object to output updated voice data. In one specific embodiment, the voiceprint confirmation password includes a random confirmation password and a custom confirmation password. The random confirmation password is generated by a cloud server or voice interaction device to remind the target interactive object to repeat it. For example, in one specific embodiment, the random confirmation password is a random password consisting of a preset password template and a randomly generated verification code: "You have unread messages, say..."
[5634] "You will be playing it next."
[5634] refers to randomly generated verification codes. Furthermore, in another specific embodiment, the custom confirmation password is a pre-defined follow-up password information set by the target interaction object or the target message object. For example, in one specific embodiment, the custom confirmation password could be "You have unread messages. Say the password to play them for you." Specifically, after obtaining the voiceprint confirmation command, the voice interaction device plays the voiceprint confirmation command to the target interaction object, obtains the updated voice data read by the target interaction object based on the voiceprint confirmation command, and extracts the voiceprint from the updated voice data to obtain the updated voiceprint features in the updated voice data. Optionally, if the voice interaction device determines that the updated voiceprint feature is the same as the target voiceprint feature, then the first candidate message is determined as the target message data, and the target message data is played. Optionally, in other embodiments, if the voice interaction device determines that the object status information is the first object status information and the target identity meets the preset message triggering conditions, then a message retrieval request is generated based on the device identification information and the target identity. This drives the voice interaction device or the cloud server to read the target message data associated with the target identity in the message database according to the message retrieval request, and the target message data is played using the audio output module of the voice interaction device. Optionally, the message database can be set as a cloud database on a cloud server, or it can be set locally on the voice interaction device when the voice interaction device hardware meets the corresponding storage requirements. Optionally, in other embodiments, after the voice interaction device determines that there is a second candidate message that can be listened to by any interactive object, when the object state information of the target interactive object is the first object state information and the target interactive object sends voice interaction data, the voice interaction device determines that the target interactive object meets the preset message conditions, generates a message acquisition request corresponding to the second candidate message, obtains the second candidate message from the message database based on the message acquisition request, and uses the second candidate message as the target message data for playback processing. Optionally, in another specific embodiment, the voice interaction device further receives a message replay request from the target interactive object, determines the target voiceprint features of the target interactive object based on the message replay request, and plays the historical message data associated with the target interactive object based on the target voiceprint features. The historical message data may be first target message data and / or second target message data. In this embodiment, the voice interaction device responds to a voice interaction request, acquires the voice interaction data of the request, acquires the object status information of the target interaction object corresponding to the request, and plays the target message data associated with the target interaction object when the voice interaction data and the object status information meet a preset message triggering condition. This enables the acquisition of the target interaction object's voice interaction data and detection of its object status information during voice interaction with the smart home appliance. When the voice interaction data and object status information meet a preset message triggering condition indicating the ability to effectively listen to the corresponding target message data, the device automatically plays the target message data associated with the target interaction object. This allows for message interaction using the smart home appliance, improving the success rate of message reception and effectively reducing the user's workload in listening to messages, thus expanding the intelligence level of the smart home appliance. As shown in Figure 3, Figure 3 is a flowchart illustrating an embodiment of the voice interaction method for generating message data provided in this application. Specifically, in this embodiment, the voice interaction method further includes steps 301 to 302: 301. Respond to the message generation request and obtain the message input data associated with the message generation request; 302. Generate candidate message data based on the message pointer and message content data in the message input data. Based on the above embodiments, in this embodiment, before responding to a voice interaction request and triggering the message playback process and playing the target message data when executing the voice interaction request, the voice interaction device can also generate candidate message data through the voice interaction device or mobile message terminal. Specifically, during operation, the terminal responds to a message generation request. This message generation request is an operation request that drives the terminal to generate candidate message data. The triggering method for this message generation request is not specifically limited here; that is, the message generation request can be triggered by the target message recipient waking up the terminal with voice and inputting the corresponding message input data. Alternatively, the message generation request can also be triggered by clicking the message button on a preset message interface. Specifically, after receiving a message generation request, the terminal also obtains the message input data associated with the message generation request. This message input data is the input data used by the target message recipient during the message generation interaction. In one specific embodiment, this message input data includes voice input data or text input data. Voice input data refers to the audio data input by the target message recipient using voice as the input method during the message generation process. Text input data refers to the text data input by the target message recipient using text as the input method during the message generation process. Optionally, in one specific embodiment, the message input data can be voice input data. That is, after waking up the voice interaction device or mobile message terminal, the target message recipient makes an appointment interaction with the terminal through voice input. The terminal uses a speech recognition model to recognize the input data of the target message recipient and obtain the voice input data. Optionally, the speech recognition model can be an ASR (Automatic Speech Recognition) recognition model. Specifically, after acquiring the message input data, the terminal generates candidate message data based on the message pointing identifier and message content data in the input data. The message pointing identifier represents the target object to be listened to in the candidate message data. That is, the target message object can enter the message pointing identifier during the message generation process to determine who will listen to the message. The message pointing identifier includes a first message identifier and a second message identifier. The first message identifier points to a specific listening user. For example, the first message identifier can be any one or more of a configured identity tag, user nickname, and user name. For example, in one specific embodiment, the first message identifier can be an identity tag, such as "father / mother / grandfather / grandmother," etc. In another specific embodiment, the first message identifier can be a user name, such as "Zhang San / Li Si / Wang Wu," etc. Furthermore, in another specific embodiment, the first message identifier can also be a user-defined nickname. Optionally, in one specific embodiment, after the target message object wakes up the terminal and enters the message process, it voice-inputs "Leave a message for user A," and the message pointing identifier recognized by the terminal is "user A." In addition, the message pointer also includes a second message pointer for leaving messages to all household users. Specifically, after determining the message pointing identifier, the terminal also maps and binds the message pointing identifier and the voiceprint information of the target pointing object corresponding to the message pointing identifier to obtain preset voiceprint features. When the target pointing object triggers message playback, the terminal uses the preset voiceprint features corresponding to the message pointing identifier and the target voiceprint features of the target interactive object to match, thereby determining whether to play the candidate message data associated with the target pointing object as the target message data. Among them, the message content data is the portion of the message input data that represents the actual message content. Specifically, after the terminal obtains the voice input data, it creates an initial message file in the message database and performs audio recognition on the voice input data. It then matches the voice input data with each preset directional identifier, and uses the preset directional identifier with a similarity exceeding that of the directional identifier as the message directional identifier corresponding to the voice input data to determine the listener corresponding to the voice input data. Finally, it maps and binds the message directional identifier to the voiceprint information of the listener. Specifically, the terminal also performs audio activity detection on the voice input data to extract the message content data from the voice input data. That is, the terminal performs feature extraction on the voice input data to obtain the voice input features corresponding to the voice input data. Among them, the voice input features can be any one or more of the audio short-time energy, audio zero-crossing rate, and Mel-frequency cepstral coefficients associated with the voice input data. Specifically, the terminal also calculates the window feature value of each sliding analysis window based on the voice input feature. That is, the terminal pre-sets each sliding analysis window for the voice input data and calculates the voice feature value in each sliding analysis window as the window feature value of the sliding analysis window. Specifically, the terminal also pre-sets a window detection threshold to distinguish between voice activity and non-voice activity, and determines the target analysis window corresponding to the voice input data based on the window feature value and the preset window detection threshold. That is, the terminal determines the sliding analysis window whose window feature value is greater than or equal to the preset window detection threshold as the target analysis window, wherein the target analysis window is a sliding analysis window that represents the presence of voice activity. Specifically, after determining the target analysis window, the terminal uses that window to extract the message content data from the voice input data. That is, after determining the target analysis window, the terminal extracts the window audio data from each target analysis window, performs voice content recognition on the window audio data, and obtains the message content data. Optionally, in one specific embodiment, the terminal can also input the acquired voice input data to a cloud server. The cloud server performs audio activity detection and natural language recognition on the voice input data to obtain the message content data in the voice input data. Based on the message content data and the message pointing identifier, it generates candidate message data and sends the corresponding candidate message data to any voice interaction device as the target message data for playback when any voice interaction device triggers a message playback request. This reduces the terminal's computing power requirements and improves the smoothness of terminal operation. Specifically, when generating candidate message data, the terminal also generates different candidate message data based on different message pointing identifiers. Optionally, if the terminal determines that the message pointer is the first message pointer, then it generates a first candidate message that can only be listened to by the interactive object pointed to by the first message pointer based on the preset voiceprint feature corresponding to the first message pointer and the message content data. That is, the terminal associates and maps the preset voiceprint feature and the message content data as the first candidate message, and determines whether to play the first candidate message as the target message data by using the preset voiceprint feature and the target voiceprint feature of the target interactive object during the subsequent message playback process. Optionally, if the terminal determines that the message pointer is a second message pointer, then a second candidate message that any user can answer is generated based on the second message pointer and the message content data. Specifically, after obtaining the message pointer and message content data, the terminal or cloud server generates candidate message data based on the message pointer and message content data. That is, the terminal obtains the candidate message file corresponding to the message pointer, stores the message content data into the candidate message file, obtains the candidate message data, and stores the candidate message data in the message database of the cloud server. In this embodiment, the terminal responds to a message generation request and obtains the message input data associated with the message generation request; it then generates candidate message data based on the message pointer and message content data in the message input data. This enables the generation of different types of message data through a voice interaction device, a mobile message terminal, and a cloud server, based on the message pointer and message content data, thereby optimizing the message generation effect. As shown in Figure 4, Figure 4 is a flowchart illustrating an embodiment of the voice interaction method provided in this application for generating candidate message data based on text input data. Specifically, in this embodiment, the voice interaction method includes steps 401 to 403: 401. If the message input data is text input data, then obtain the text content data in the text input data; 402. Generate synthesized message data based on the text content data and the target message timbre; 403. Generate candidate message data based on the synthesized message data and the message pointing identifier. Based on the above embodiments, in this embodiment, the target message recipient can also use a voice interaction device or mobile message terminal to input text input data as message input data, and drive the voice interaction device or mobile message terminal to generate candidate message data that can be played by voice based on the text input data. Specifically, during operation, the terminal responds to a message generation request. This message generation request is an operation request that drives the terminal to generate candidate message data. The triggering method for this message generation request is not specifically limited here; it can be triggered by the target message recipient clicking the message button on a preset message interface. Specifically, after triggering a message generation request, the terminal parses the request and determines the text message type corresponding to it. This text message type is the type used to determine the recipient of the message in a text input message scenario. In one specific embodiment, the text message type includes a first message type specifying the recipient and a second message type that can be received by any object. Specifically, after determining the type of text message, the terminal also receives the text data input by the target message recipient and obtains the text content data in the text input data, wherein the text content data is the message content data representing the target message recipient. Specifically, after acquiring the text content data of the candidate message data to be generated, the terminal also generates synthesized message data based on the text content data and the target message timbre. The synthesized message data is audio data representing the message audio data converted from the text content data into a speech style using the target message timbre. The target message timbre is the timbre data used when synthesizing the text content data into speech. This target message timbre can be a preset timbre selected by the target message object or a cloned timbre of the target message object, etc. Specifically, after generating the synthesized message data, the terminal generates candidate message data based on the synthesized message data and the message targeting identifier. That is, the terminal determines the target audience of the message to be listened to based on the message targeting identifier, generates a candidate message folder corresponding to the message targeting identifier on the cloud server or local storage area, uploads the synthesized message data to the candidate message folder and stores it, thus obtaining the candidate message data. Optionally, in one specific embodiment, the terminal can also input the acquired text input data to a cloud server, whereby the cloud server performs audio synthesis on the text input data to obtain synthesized message data corresponding to the text input data. Based on the synthesized message data and a message pointing identifier, candidate message data is generated, and when any voice interaction device triggers a message playback request, the corresponding candidate message data is sent to that voice interaction device as the target message data for playback. This reduces the terminal's computing power requirements and improves the smoothness of terminal operation. In this embodiment, the terminal determines that if the message input data is text input data, it acquires the text content data from the text input data; it generates synthesized message data based on the text content data and the target message timbre; and it generates candidate message data based on the synthesized message data and the message pointing identifier. This enables the generation of voice message data using multiple input methods, enriching the message generation scenarios and enhancing the fun of message interaction. To better implement the voice interaction method in the embodiments of this application, based on the voice interaction method, the embodiments of this application also provide a voice interaction device, as shown in FIG5. FIG5 is a structural schematic diagram of an embodiment of the voice interaction device provided in the embodiments of this application. Specifically, the voice interaction device 500 includes: The data acquisition module 501 is configured to respond to a voice interaction request and acquire the voice interaction data of the voice interaction request. The status acquisition module 502 is configured to acquire the object status information of the target interaction object corresponding to the voice interaction request; The message playback module 503 is configured to play target message data associated with the voice interaction data when the voice interaction data meets the preset message triggering conditions. In one possible implementation of this embodiment, when the voice interaction data and the object state information meet the preset message triggering conditions, the voice interaction device plays target message data associated with the target interaction object, including: Based on the target wake-up word in the voice interaction data, the voiceprint features are extracted to obtain the target voiceprint features; The target voiceprint feature is matched with the preset voiceprint feature to obtain the target identity identifier corresponding to the target voiceprint feature; If the object status information and the target identity identifier meet the preset message triggering conditions, the target message data associated with the target identity identifier will be played. In one possible implementation of this embodiment, if the object status information and the target identity identifier meet the preset message triggering conditions, the voice interaction device plays target message data associated with the target identity identifier, including: If the object status information is the first object status information, and there is a first candidate message associated with the target identity, then obtain the voiceprint confirmation password associated with the preset message triggering condition. Obtain updated voice data associated with the voiceprint confirmation password, and updated voiceprint features in the updated voice data; If the updated voiceprint feature is the same as the target voiceprint feature, then the first candidate message is determined as the target message data, and the target message data is played. In one possible implementation of this embodiment, if the object status information and the target identity identifier meet the preset message triggering conditions, the voice interaction device plays target message data associated with the target identity identifier, including: If the object status information is the first object status information and the target identity meets the preset message triggering conditions, then a message retrieval request is generated based on the device identification information and the target identity. Based on the message retrieval request, read the target message data associated with the target identity in the message database, and play the target message data. In one possible implementation of this embodiment, before the voice interaction device plays the target message data associated with the voice interaction data, it further includes: In response to a message generation request, obtain the message input data associated with the message generation request; Candidate message data is generated based on the message pointer and message content data in the message input data. In one possible implementation of this embodiment, the message input data in the voice interaction device includes voice input data; The step of generating candidate message data based on the message pointer and message content data in the message input data includes: If the message input data is voice input data, then perform audio recognition on the voice input data to obtain the message pointing identifier corresponding to the voice input data; Activity detection is performed on the voice input data to obtain the message content data of the voice input data; Candidate message data is generated based on the message pointer and the message content data. In one possible implementation of this embodiment, the voice interaction device performs activity detection on the voice input data to obtain the message content data of the voice input data, including: The voice input data is subjected to feature extraction to obtain voice input features; Calculate the window feature value of each sliding analysis window based on the voice input features; The target analysis window corresponding to the voice input data is determined based on the window feature value and the preset window detection threshold. The message content data in the voice input data is extracted using the target analysis window. In one possible implementation of this embodiment, the message pointing identifier in the voice interaction device includes a first message identifier and a second message identifier, and the candidate message data includes a first candidate message and a second candidate message; The step of generating candidate message data based on the message pointing identifier and the message content data includes: If the message pointer is a first message identifier, then a first candidate message is generated based on the preset voiceprint features corresponding to the first message identifier and the message content data; If the message pointer is a second message identifier, then a second candidate message is generated based on the first message identifier and the message content data. In one possible implementation of this embodiment, the message input data in the voice interaction device includes text input data; The step of generating candidate message data based on the message pointing identifier and the message content data includes: If the message input data is text input data, then obtain the text content data in the text input data; Generate synthetic message data based on the text content data and the target message timbre; Candidate message data is generated based on the synthesized message data and the message pointing identifier. In this embodiment, the voice interaction device responds to a voice interaction request, acquires the voice interaction data of the request, acquires the object status information of the target interaction object corresponding to the request, and plays the target message data associated with the target interaction object when the voice interaction data and the object status information meet a preset message triggering condition. This enables the acquisition of the target interaction object's voice interaction data and detection of its object status information during voice interaction with the smart home appliance. When the voice interaction data and object status information meet a preset message triggering condition indicating the ability to effectively listen to the corresponding target message data, the device automatically plays the target message data associated with the target interaction object. This allows for message interaction using the smart home appliance, increasing the success rate of message reception and effectively reducing the user's workload in listening to messages, thus expanding the intelligence level of the smart home appliance. This application also provides a voice interaction device, as shown in FIG6. FIG6 is a schematic diagram of an embodiment of the voice interaction device provided in this application. The voice interaction device integrates any of the voice interaction apparatuses provided in the embodiments of this application, and the voice interaction device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to execute the steps of the voice interaction method in any of the embodiments described above. Specifically, a voice interaction device may include components such as a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will understand that the voice interaction device structure shown in Figure 6 does not constitute a limitation on the voice interaction device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. The processor 601 is the control center of the voice interaction device. It connects various parts of the device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, thereby providing overall monitoring of the voice interaction device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601. The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the voice interaction device, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602. The voice interaction device also includes a power supply 603 that supplies power to the various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The voice interaction device may also include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. Although not shown, the voice interaction device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 601 in the voice interaction device loads the executable files corresponding to the processes of one or more applications into the memory 602 according to the following instructions, and the processor 601 runs the applications stored in the memory 602 to realize various functions, as follows: Responding to a voice interaction request, the system obtains the voice interaction data for that request. Obtain the object state information of the target interaction object corresponding to the voice interaction request; When the voice interaction data and the object status information meet the preset message triggering conditions, the target message data associated with the target interaction object is played. Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a disk, or an optical disk, etc. A computer program is stored thereon, which is loaded by a processor to execute the steps in any of the voice interaction methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps: Responding to a voice interaction request, the system obtains the voice interaction data for that request. Obtain the object state information of the target interaction object corresponding to the voice interaction request; When the voice interaction data and the object status information meet the preset message triggering conditions, the target message data associated with the target interaction object is played. In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here. In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here. For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here. The above provides a detailed description of a voice interaction method provided by the embodiments of this application. Specific embodiments have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and its core ideas. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A voice interaction method, wherein, The voice interaction method includes: Responding to a voice interaction request, the system obtains the voice interaction data for that request. Obtain the object state information of the target interaction object corresponding to the voice interaction request; When the voice interaction data and the object status information meet the preset message triggering conditions, the target message data associated with the target interaction object is played.
2. The voice interaction method according to claim 1, wherein, When the voice interaction data and the object state information meet the preset message triggering conditions, playing the target message data associated with the target interaction object includes: Based on the target wake-up word in the voice interaction data, the voiceprint features are extracted to obtain the target voiceprint features; The target voiceprint feature is matched with the preset voiceprint feature to obtain the target identity identifier corresponding to the target voiceprint feature; If the object status information and the target identity identifier meet the preset message triggering conditions, the target message data associated with the target identity identifier will be played.
3. The voice interaction method according to claim 2, wherein, The step of playing target message data associated with the target identity when the object status information and the target identity meet the preset message triggering conditions includes: If the object status information is the first object status information, and there is a first candidate message associated with the target identity, then obtain the voiceprint confirmation password associated with the preset message triggering condition. Obtain updated voice data associated with the voiceprint confirmation password, and updated voiceprint features in the updated voice data; If the updated voiceprint feature is the same as the target voiceprint feature, then the first candidate message is determined as the target message data, and the target message data is played.
4. The voice interaction method according to claim 2, wherein, The step of playing target message data associated with the target identity when the object status information and the target identity meet the preset message triggering conditions includes: If the object status information is the first object status information and the target identity meets the preset message triggering conditions, then a message retrieval request is generated based on the device identification information and the target identity. Based on the message retrieval request, read the target message data associated with the target identity in the message database, and play the target message data.
5. The voice interaction method according to claim 1, wherein, Before playing the target message data associated with the voice interaction data, the method further includes: In response to a message generation request, obtain the message input data associated with the message generation request; Candidate message data is generated based on the message pointer and message content data in the message input data.
6. The voice interaction method according to claim 5, wherein, The message input data includes voice input data; The step of generating candidate message data based on the message pointer and message content data in the message input data includes: If the message input data is voice input data, then perform audio recognition on the voice input data to obtain the message pointing identifier corresponding to the voice input data; Activity detection is performed on the voice input data to obtain the message content data of the voice input data; Candidate message data is generated based on the message pointer and the message content data.
7. The voice interaction method according to claim 6, wherein, The process of performing activity detection on the voice input data to obtain the message content data of the voice input data includes: The voice input data is subjected to feature extraction to obtain voice input features; Calculate the window feature value of each sliding analysis window based on the voice input features; The target analysis window corresponding to the voice input data is determined based on the window feature value and the preset window detection threshold. The message content data in the voice input data is extracted using the target analysis window.
8. The voice interaction method according to claim 6, wherein, The message pointer includes a first message identifier and a second message identifier, and the candidate message data includes a first candidate message and a second candidate message; The step of generating candidate message data based on the message pointing identifier and the message content data includes: If the message pointer is a first message identifier, then a first candidate message is generated based on the preset voiceprint features corresponding to the first message identifier and the message content data; If the message pointer is a second message identifier, then a second candidate message is generated based on the first message identifier and the message content data.
9. The voice interaction method according to claim 5, wherein, The message input data includes text input data; The step of generating candidate message data based on the message pointing identifier and the message content data includes: If the message input data is text input data, then obtain the text content data in the text input data; Generate synthetic message data based on the text content data and the target message timbre; Candidate message data is generated based on the synthesized message data and the message pointing identifier.
10. A voice interaction device, wherein, The voice interaction device includes: The data acquisition module is configured to respond to a voice interaction request and acquire the voice interaction data of the voice interaction request. The status acquisition module is configured to acquire the object status information of the target interaction object corresponding to the voice interaction request; The message playback module is configured to play target message data associated with the voice interaction data when the voice interaction data meets the preset message triggering conditions.
11. The voice interaction device according to claim 10, wherein, The message playback module is used to play target message data associated with the target interaction object when the voice interaction data and the object status information meet the preset message triggering conditions, including: Based on the target wake-up word in the voice interaction data, the voiceprint features are extracted to obtain the target voiceprint features; The target voiceprint feature is matched with the preset voiceprint feature to obtain the target identity identifier corresponding to the target voiceprint feature; If the object status information and the target identity identifier meet the preset message triggering conditions, the target message data associated with the target identity identifier will be played.
12. The voice interaction device according to claim 11, wherein, The message playback module is used to play target message data associated with the target identity when the object status information and the target identity meet preset message triggering conditions, including: If the object status information is the first object status information, and there is a first candidate message associated with the target identity, then obtain the voiceprint confirmation password associated with the preset message triggering condition. Obtain updated voice data associated with the voiceprint confirmation password, and updated voiceprint features in the updated voice data; If the updated voiceprint feature is the same as the target voiceprint feature, then the first candidate message is determined as the target message data, and the target message data is played.
13. The voice interaction device according to claim 11, wherein, The message playback module is used to play target message data associated with the target identity when the object status information and the target identity meet preset message triggering conditions, including: If the object status information is the first object status information and the target identity meets the preset message triggering conditions, then a message retrieval request is generated based on the device identification information and the target identity. Based on the message retrieval request, read the target message data associated with the target identity in the message database, and play the target message data.
14. The voice interaction device according to claim 10, wherein, Before the message playback module plays the target message data associated with the voice interaction data, it also includes: In response to a message generation request, obtain the message input data associated with the message generation request; Candidate message data is generated based on the message pointer and message content data in the message input data.
15. The voice interaction device according to claim 14, wherein, The message input data of the message playback module includes voice input data; The message playback module is used to generate candidate message data based on the message pointer and message content data in the message input data, including: If the message input data is voice input data, then perform audio recognition on the voice input data to obtain the message pointing identifier corresponding to the voice input data; Activity detection is performed on the voice input data to obtain the message content data of the voice input data; Candidate message data is generated based on the message pointer and the message content data.
16. The voice interaction device according to claim 15, wherein, The message playback module is used to perform activity detection on the voice input data to obtain the message content data of the voice input data, including: The voice input data is subjected to feature extraction to obtain voice input features; Calculate the window feature value of each sliding analysis window based on the voice input features; The target analysis window corresponding to the voice input data is determined based on the window feature value and the preset window detection threshold. The message content data in the voice input data is extracted using the target analysis window.
17. The voice interaction device according to claim 15, wherein, The message pointing identifier in the message playback module includes a first message identifier and a second message identifier, and the candidate message data includes a first candidate message and a second candidate message; The message playback module generates candidate message data based on the message pointing identifier and the message content data, including: If the message pointer is a first message identifier, then a first candidate message is generated based on the preset voiceprint features corresponding to the first message identifier and the message content data; If the message pointer is a second message identifier, then a second candidate message is generated based on the first message identifier and the message content data.
18. The voice interaction device according to claim 14, wherein, The message input data in the message playback module includes text input data; The message playback module generates candidate message data based on the message pointing identifier and the message content data, including: If the message input data is text input data, then obtain the text content data in the text input data; Generate synthetic message data based on the text content data and the target message timbre; Candidate message data is generated based on the synthesized message data and the message pointing identifier.
19. A voice interaction device, wherein, The voice interaction device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the voice interaction method according to any one of claims 1 to 9.
20. A computer-readable storage medium, wherein, It stores a computer program, which is loaded by a processor to execute the steps of the voice interaction method according to any one of claims 1 to 9.
