Speech interaction method, interaction device, electronic device and storage medium

Abstract

The embodiments of the present disclosure relate to a speech interaction method, an interaction device, an electronic device and a storage medium. The method provided herein comprises: when a speech assistant application does not play speech content, in response to a first operation for an interaction device, triggering the speech assistant application on a terminal device to actively play first speech content; and during the playing of the first speech content, in response to a second operation for the interaction device, triggering the speech assistant application on the terminal device to actively play second speech content, wherein the second speech content is different from the first speech content.

Description

Method for voice interaction, interactive device, electronic device and storage medium

[0001] The present application claims priority to the Chinese patent application No. 202411253462.4, filed on September 6, 2024, entitled "Method for voice interaction, interactive device, electronic device and storage medium", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The example embodiments of the present disclosure generally relate to the field of computer, and in particular, to a method for voice interaction, an interactive device, an electronic device and a storage medium. BACKGROUND

[0003] With the development of computer technology, voice interaction technology has become one of the important ways of human-computer interaction. For example, a user can interact with a voice assistant application on a terminal device.

[0004] The traditional voice interaction scenario is usually that the voice assistant application passively responds to the voice request of the user. For example, the user can initiate a voice request for weather query, and the voice assistant application accordingly broadcasts the weather condition. SUMMARY

[0005] In a first aspect of the present disclosure, a method for voice interaction is provided. The method comprises: in response to a first operation on an interactive device when a voice assistant application does not play voice content, triggering the voice assistant application on a terminal device to actively play first voice content; and in response to a second operation on the interactive device during playing of the first voice content, triggering the voice assistant application on the terminal device to actively play second voice content; wherein the second voice content is different from the first voice content.

[0006] In a second aspect of the present disclosure, an interactive device adapted to be worn on a finger of a user is provided. The interactive device comprises: a first triggering module configured to, in response to a first operation on the interactive device when a voice assistant application does not play voice content, trigger the voice assistant application on a terminal device to actively play first voice content; and a second triggering module configured to, in response to a second operation on the interactive device during playing of the first voice content, trigger the voice assistant application on the terminal device to actively play second voice content; wherein the second voice content is different from the first voice content.

[0007] In a third aspect of the present disclosure, an electronic device is provided. The device comprises at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. The instructions, when executed by the at least one processor, cause the device to perform the method of the first aspect.

[0008] In a fourth aspect of the disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has stored thereon computer-executable instructions that are executable by a processor to implement the method of the first aspect.

[0009] In a fifth aspect of the disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer- executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0010] It should be understood that nothing in the Summary is to be construed as a limitation on the scope of the embodiments of the disclosure or the present disclosure. Various embodiments of the disclosure will be described in conjunction with the drawings, which are intended to be exemplary only and not limiting of the disclosure. Described are example systems, methods, and computer program products according to embodiments of the disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0011] The above and other features, aspects, and advantages of various embodiments of the present disclosure will become more apparent from the following detailed description, taken in conjunction with the accompanying drawings, in which like reference numbers represent like elements throughout. In the drawings:

[0012] FIG. 1 shows a schematic diagram of an example environment in which embodiments according to the present disclosure can be implemented;

[0013] FIG. 2 shows a flowchart of a voice interaction process according to some embodiments of the present disclosure;

[0014] FIG. 3 shows a flowchart of an example interaction process according to some embodiments of the present disclosure;

[0015] FIG. 4 shows a schematic block diagram of an example interaction device according to some embodiments of the present disclosure; and

[0016] FIG. 5 shows a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described below in detail with reference to accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather, the embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are merely for illustrative purposes and should not be construed as limiting the scope of protection of the present disclosure.

[0018] It should be noted that the headings provided in any section / subsection herein are not limitations. Various embodiments are described throughout this document and any type of embodiment can be included under any section / subsection. Furthermore, embodiments described in any section / subsection can be combined with any other embodiments described in the same section / subsection and / or different section / subsection in any manner.

[0019] In the description of embodiments of the disclosure, the term "includes" and its derivatives, should be understood to be open terms, i.e., "including, but not limited to." The term "based on" should be understood as "based, at least in part, on." The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment." The term "some embodiments" should be understood as "at least some embodiments." Other explicit or implicit definitions can also be included below. The terms "first", "second", etc. can refer to different or the same objects. Other explicit and implicit definitions can also be included below.

[0020] Data of users, acquisition and / or use of data, etc. can be involved in embodiments of the disclosure. These aspects all comply with corresponding laws and regulations and relevant provisions. In embodiments of the disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms. Accordingly, when implementing various embodiments of the disclosure, the type of data or information that can be involved, the use range, the use scenario, etc. should be notified to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations. The specific notification and / or authorization mode can vary according to the actual situation and application scenario, and the scope of the disclosure is not limited in this respect.

[0021] In the specification and embodiments of the present disclosure, if personal information processing is involved, it will be processed on the premise of legality (for example, obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and only within the prescribed or agreed range. Users refuse to process personal information other than the necessary information required for basic functions, which will not affect the user's use of basic functions.

[0022] As mentioned above, voice interaction is an important interaction capability. The traditional voice interaction scenario is usually that the voice assistant application passively responds to the user's voice request. Then, such voice interaction relies on the user to actively start the corresponding topic, which requires higher interaction cost of the user.

[0023] Embodiments of the present disclosure propose a voice interaction scheme. According to the scheme, when a voice assistant application does not play voice content, an interaction device can trigger the voice assistant application on a terminal device to actively play first voice content in response to a first operation for the interaction device. Further, during playing of the first voice content, the interaction device can also trigger the voice assistant application on the terminal device to actively play second voice content in response to a second operation for the interaction device; wherein the second voice content is different from the first voice content.

[0024] In this way, embodiments of the present disclosure can trigger the voice assistant application to actively provide voice content based on operations of the interaction device, and can trigger the voice assistant application to actively provide different voice content based on operations of the interaction device during playing of the voice content. Thus, embodiments of the present disclosure can reduce the cost of voice interaction of the user, and improve the quality of voice content provided by the voice assistant application.

[0025] Various example implementations of the scheme are described in further detail below in conjunction with the accompanying drawings.

[0026] Example Environment

[0027] FIG. 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG. 1, the example environment 100 can include a terminal device 110.

[0028] In the example environment 100, the terminal device 110 can run a voice assistant application 120 that supports voice interaction. A user 140 can interact with the voice assistant application 120 via the terminal device 110 and / or its attached devices.

[0029] As shown in FIG. 1, the terminal device 110 can also be connected with an interaction device 160. As an example, the interaction device 160 can be connected with the terminal device 110 in a wired or wireless manner.

[0030] As will be described in detail below, the interaction device 160 can detect operations of the user 140 for the interaction device 160, and can trigger the voice assistant application 120 to actively play voice content.

[0031] In some embodiments, the interaction device 160 can include an audio acquisition unit, e.g., a microphone or a microphone array. The interaction device 160 can receive a voice signal of the user by using the audio acquisition device, to trigger the voice assistant application 120 to passively play voice content corresponding to the voice signal based on the voice signal.

[0032] In some embodiments, the interaction device 160 can be implemented as a suitable peripheral device, such as a headset, a speaker, etc. In some embodiments, the interaction device 160 can also be worn on a finger of the user 140. As an example, the interaction device 160 can be in the form of a ring or a bracelet, etc.

[0033] In the environment 100 of FIG. 1, the terminal device 110 can also render an interface 150 for supporting interface interaction through the voice assistant application 120 if the voice assistant application 120 is active. As an example, the interface 150 can be an interaction interface with the voice assistant application 120 to, for example, demonstrate the interaction process between the user and the voice assistant application. The present disclosure is not intended to limit the specific form of the interface 150.

[0034] In some embodiments, the terminal device 110 communicates with the server 130 to implement the provisioning of services for the application 120. The terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a palmtop computer, a portable gaming terminal, a VR / AR device, a Personal Communication System (PCS) device, a personal navigation device, a Personal Digital Assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including accessories and peripherals of these devices, or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface to the user (such as “wearable” circuitry, etc.).

[0035] The server 130 can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and basic cloud computing services such as big data and artificial intelligence platforms, etc. The server 130 may, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, etc. The server 130 can provide background services for the application 120 in the terminal device 110 that supports a virtual scene.

[0036] A communication connection can be established between the server 130 and the terminal device 110. The communication connection can be established through a wired manner or a wireless manner. The communication connection can include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, and the like, and embodiments of the present disclosure are not limited in this regard. In embodiments of the present disclosure, the server 130 and the terminal device 110 can implement signaling interaction through the communication connection therebetween.

[0037] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only, without implying any limitation on the scope of the present disclosure.

[0038] Some example embodiments of the present disclosure will be described below with continued reference to the drawings.

[0039] Example voice interaction process

[0040] A voice interaction process according to embodiments of the present disclosure will be described below with reference to the drawings. FIG. 2 shows a flowchart 200 of a voice interaction process according to some embodiments of the present disclosure.

[0041] As shown in FIG. 2, at 205, the interaction device 160 can detect a first operation for the interaction device 160 during the voice assistant application 120 not playing voice content on the terminal device 110.

[0042] In some embodiments, the interaction device 160 can be provided with a button. The button can include a physical button or a pressure-sensitive button. The interaction device 160 may, for example, detect an interaction operation for the button to detect the first operation for the interaction device 160.

[0043] For example, the interaction device 160 can detect a press of the physical button by the user 140. Alternatively, the interaction device 160 can also detect a press of the pressure-sensitive button through a pressure-sensitive sensor.

[0044] In some embodiments, such a press may, for example, include a single click, a double click, or a long press, and the like appropriate press operation. As an example, during the voice assistant application 120 not playing voice content, the user 140 can press the button on the interaction device 160 (e.g., a ring) to trigger the voice assistant application 120 to actively play voice content based on the process described below.

[0045] In some embodiments, the first operation can also be other types of interactive operations, for example, body sense actions. Taking the ring as an example of the interactive device 160, such preset body sense actions can include, for example, wrist actions, gesture actions, etc. It should be understood that the interactive device 160 can detect such body sense actions by using appropriate sensors, and the present disclosure is not intended to be limited thereto.

[0046] In some embodiments, the specific operation type corresponding to the first operation can be determined based on the configuration of the user 140. As an example, the user can configure the specific key operation type, for example, via the interface 150 provided by the voice assistant application 120.

[0047] Further, as shown in FIG. 2, at 210, the interactive device 160 can send a control signal corresponding to the first operation to the terminal device 110. Accordingly, after receiving the control signal, the terminal device 110 can trigger the voice assistant application 120 to play the first voice content.

[0048] In some embodiments, the first voice content can be played by the terminal device 110 or an audio device 202 connected to the terminal device 110. In some embodiments, the audio device 202 can include an external audio device, for example, earphones, a sound system, etc., which is connected to the terminal device 110 and has an audio playing unit.

[0049] In some embodiments, although the interactive device 160 and the audio device 202 are shown as two independent blocks in FIG. 2, the audio device 202 can also be the interactive device 160 which is deployed with an audio playing unit, for example, a speaker or a speaker array.

[0050] Specifically, as shown in FIG. 2, at 215, the terminal device 110 can send the first voice content to the audio device 202. At 220, the audio device 202 can play the received first voice content.

[0051] In some embodiments, when the terminal device 110 is connected to multiple devices with audio playing capabilities, the terminal device 110 can select a specific device for playing according to a preset strategy. The present disclosure is not intended to be limited to the specific selection strategy.

[0052] With reference to FIG. 2, during the playing of the first voice content, the interactive device 160 can also detect whether the user 140 initiates a preset operation. As shown in FIG. 2, at 225, the interactive device 160 can detect a second operation during the playing of the first voice content.

[0053] In some embodiments, the second operation can be the same or different operation as the first operation described above. As an example, the first operation can be a short press operation on a button on the interactive device 160, and the second operation can be a double click operation on the button on the interactive device 160.

[0054] As another example, both the first operation and the second operation can be a short press operation on a button on the interactive device 160. In the case that the voice assistant application 120 does not play the voice content, the short press operation can trigger the voice assistant application 120 to play a first voice content; during the playing of the first voice content, the short press operation can trigger the voice assistant application 120 to play a second voice content different from the first voice content.

[0055] In some embodiments, the specific operation type corresponding to the second operation can be determined based on the configuration of the user 140. As an example, the user can configure the specific button operation type, e.g., via the interface 150 provided by the voice assistant application 120.

[0056] Further, as shown in FIG. 2, at 230, the interactive device 160 can send a control signal corresponding to the second operation to the terminal device 110. Accordingly, upon receiving the control signal, the terminal device 110 can trigger the voice assistant application 120 to play a second voice content different from the first voice content.

[0057] In some embodiments, the voice assistant application 120 can continue to play the second voice content after finishing playing the first voice content. In other embodiments, the voice assistant application 120 can also stop playing the first voice content and start playing the second voice content in response to the control signal corresponding to the second operation.

[0058] Specifically, as shown in FIG. 2, at 235, the terminal device 110 can send the second voice content to the audio device 202. At 240, the audio device 202 can play the received second voice content. Taking FIG. 2 as an example, the audio device 202 can stop playing the first voice content and start playing the second voice content.

[0059] In this way, embodiments of the present disclosure can support the user to quickly obtain other voice content by operation on the interactive device when obtaining undesired voice content, thereby improving the efficiency of voice interaction.

[0060] The above describes the active voice interaction process 280 triggered in response to the interactive operation on the interactive device 160. The specific generation process of the first voice content and the second voice content played by the voice assistant application 120 in response to the operation on the interactive device will be further introduced below.

[0061] In some embodiments, the first voice content and the second voice content can be associated with different topics. For example, the first voice content can be associated with a first topic, and the second voice content can be associated with a different second topic.

[0062] In the present disclosure, a topic of voice content can be used to represent a type of topic involved in the voice content. Such topics can include, but are not limited to, a news topic, a local topic, a life topic, a skill topic, etc.

[0063] For example, the first voice content played by the voice assistant application 120 can be related to a news topic. After the user performs a preset operation through the interaction device 160, the voice assistant application 120 can switch the topic of the played content, and for example, can switch to play second voice content related to a life topic (e.g., weather).

[0064] In some embodiments, the first voice content and the second voice content can also be related to different content of the same topic. For example, the first voice content and the second voice content can both be related to news. The user can trigger the voice assistant application 120 to switch to play different news content through the interaction device 160.

[0065] In some embodiments, the topic corresponding to the first voice content and / or the second voice content can be determined from a plurality of preset topics. For example, the voice assistant application 120 can be associated with a plurality of preset topics, such as a news topic, a local topic, a life topic, a skill topic, etc.

[0066] The voice assistant application 120 may, for example, randomly or according to a predetermined logic, determine a first topic corresponding to the first voice content from the plurality of preset topics, and can accordingly obtain the first voice content.

[0067] For example, the voice assistant application 120 can determine that the first topic of the first voice content to be played is news. Accordingly, the voice assistant application 120 can obtain first voice content related to news.

[0068] In some embodiments, such first voice content can be preset content related to the first topic. For example, the first voice content can be “Do you want to know the latest news?”.

[0069] In other embodiments, such first voice content can also be generated by the voice assistant application 120 using a generative model. As an example, the voice assistant application 120 can trigger a generative model (e.g., a language model) to generate first voice content related to the current real-time news after determining that the first topic is news. For example, the first voice content can be “Latest news: XXXX, do you want to know more?”.

[0070] In yet some embodiments, the voice assistant application 120 may, for example, pre-generate preset contents associated with different topics to build the content list. As an example, such a content list can include a plurality of content items associated with a plurality of preset topics, where each content item can include text content or voice content.

[0071] Upon receiving a triggering operation of the user on the interactive device 160, the voice assistant application 120 may, for example, obtain the corresponding voice content from the content list for playing. As another example, the voice assistant application 120 may, for example, also obtain the corresponding text content from the content list and convert it into voice content for playing.

[0072] In some embodiments, such a content item list can be maintained at the terminal device 110 to improve the response speed of the voice assistant application 120.

[0073] In some embodiments, such a content list can be updated periodically to ensure the timeliness of the corresponding content. For example, the voice assistant application 120 can update such a content list at a fixed time every day to provide higher quality voice content.

[0074] In some embodiments, the voice assistant application 120 may, in response to the corresponding voice content being played, also remove the content item corresponding to the voice content from the content list. For example, the content list can include the content item “It’s a good day today, it’s recommended to go out for a walk”. After the user triggers the playing of the voice content corresponding to the content item, the voice assistant application 120 can delete the content item from the content item list. In this way, the voice assistant application 120 can avoid providing repetitive voice content.

[0075] Correspondingly, when the number of content items in the content list is less than a threshold value, the voice assistant application 120 can trigger the generation of a new plurality of content items to update the content list. As an example, when the content list is an empty list, the voice assistant application 120 can use the generative model to generate a plurality of new content items to add to the content list.

[0076] In some embodiments, the first voice content and / or the second voice content can also be generated based on user association information and / or device association information.

[0077] As an example, the voice assistant application may, with the user’s knowledge and permission, play voice content related to the user association information and / or the device association information. As an example, the user association information can include the user’s schedule, and as an example, the first voice content or the second voice content can be “There is traffic congestion to the airport today, it is recommended to leave early”.

[0078] As another example, the user-associated information can also include the user's historical interaction with the voice assistant application. For example, the second voice content or the second voice content can be related to a historical topic, e.g., "that movie I recommended last time is officially released."

[0079] As an example, the device-associated information can include location information of the device, and as an example, the first voice content or the second voice content can be "XX restaurant nearby is particularly good, try it out."

[0080] In this way, embodiments of the present disclosure can improve the quality of voice interaction, helping users to more efficiently obtain desired information.

[0081] In some embodiments, during the playing of the first voice content or the second voice content, the interaction device 160 can also detect a preset operation for the interaction device 160, and accordingly trigger the voice assistant application to stop playing the first voice content or the second voice content.

[0082] As an example, during the playing of the first voice content or the second voice content by the voice assistant application 120, the interaction device 160 can receive a double-click operation of the user 140 on the button, and trigger the voice assistant application 120 to stop playing the first voice content or the second voice content, and not switch to play the voice content of the signal.

[0083] In some embodiments, such an operation can be different from the first operation or the second operation discussed above. Additionally, such an operation can also be configured by the user 120 via the voice assistant application 120, for example.

[0084] In some embodiments, the voice assistant application 120 can be able to passively output corresponding voice content in response to a voice request of the user. In the present disclosure, active provision refers to the voice assistant application playing voice content actively without receiving a voice request of the user. Passive provision refers to the voice assistant application generating and playing voice content in response to a voice request of the user upon receiving the voice request.

[0085] FIG. 2 further shows a passive voice interaction process 290 triggered in response to a voice request of the user. Specifically, as shown in FIG. 2, at 245, the interaction device 160 can detect a third operation. In some embodiments, the third operation can also include any appropriate type such as a button operation, a body sense operation, a voice instruction, etc. For example, the user can trigger the acquisition of the voice request by long-pressing a button of the interaction device 160.

[0086] Further, the interaction device 160 can trigger the terminal device 110, an audio capturing unit connected with the terminal device, to receive the voice request of the user. Such an audio capturing unit can be deployed at the interaction device 160, other audio devices 202, or other appropriate external devices, for example.

[0087] As an example, at 250, the interaction device 160 can acquire the voice request of the user with the deployed audio capturing unit. At 255, the interaction device 160 can send the voice request to the terminal device 110.

[0088] At 260, the terminal device 110 can generate the third voice content based on the received voice request.

[0089] In some embodiments, the terminal device 110 can process the voice request, for example, with a locally deployed application or model, to generate the third voice content. For example, the terminal device 110 can be locally deployed with a voice processing model to generate the third voice content based on the voice request as a reply to the first voice signal.

[0090] In some embodiments, the terminal device 110 can also generate the third voice content, for example, based on the communication with the server 130. As an example, the server 130 can provide a voice interaction service associated with the voice assistant application 120, for example.

[0091] Specifically, upon receiving the first voice signal, the terminal device 110 can send the voice request to the server 130. The server 130 can generate the corresponding third voice content based on the voice request, for example.

[0092] As an example, the server 130 can convert the voice request to first text content and provide to a model associated with the voice assistant application 120 to generate second text content, for example. Further, the server 130 can generate the corresponding third voice content based on the second text content.

[0093] It should be appreciated that such a model can include any appropriate generative model, for example, a language model. Alternatively, the model can directly process the first voice signal to generate the third voice content, for example.

[0094] In some embodiments, the generation of the third voice content can not only be related to the received voice request, but also be related to the first voice content and / or the second voice content provided by the voice assistant application.

[0095] For example, the server 130 can provide the first speech content and / or the second speech content as context information to the model for generating the third speech content or corresponding text content. Further, such text content can be converted to the third speech content and sent to the terminal device 110 for playing.

[0096] In particular, as shown in FIG. 2, at 265, the terminal device 110 can send the third speech content to the audio device 202. At 270, the audio device 202 can play the received third speech content.

[0097] Based on the above-described speech interaction procedure, embodiments of the present disclosure can trigger the speech assistant application to actively provide speech content based on the operation of the interaction device, and can trigger the speech assistant application to actively provide different speech content based on the operation of the interaction device during the speech content playing. Thus, embodiments of the present disclosure can reduce the speech interaction cost of the user and improve the quality of the speech content provided by the speech assistant application.

[0098] Example procedure

[0099] FIG. 3 shows a flowchart of an example interaction procedure 300 according to some embodiments of the present disclosure. The procedure 300 can be implemented at the interaction device 160. The procedure 300 is described below with reference to FIG. 1.

[0100] As shown, at block 310, the interaction device 160, in response to a first operation for the interaction device, triggers the speech assistant application on the terminal device to actively play first speech content when the speech assistant application does not play speech content.

[0101] At block 320, the interaction device 160, in response to a second operation for the interaction device, triggers the speech assistant application on the terminal device to actively play second speech content during the playing of the first speech content; wherein the second speech content is different from the first speech content.

[0102] In some embodiments, the first speech content and / or the second speech content is content generated by the speech assistant application using a generative model.

[0103] In some embodiments, the procedure 300 further includes, in response to a third operation for the interaction device, triggering the terminal device or an audio acquisition unit connected with the terminal device to receive a speech request of the user, to trigger the speech assistant application to passively output third speech content based on the speech request.

[0104] In some embodiments, the third speech content is related to the first speech content and / or the second speech content and the speech request.

[0105] In some embodiments, the third voice content is generated by: obtaining text content generated by the model based on the first voice content and / or the second voice content and the voice request content; and converting the text content into the third voice content.

[0106] In some embodiments, the interaction device comprises an audio collection unit, and the interaction device is further configured to: receive the voice request by using the audio collection unit, and send the voice request to the terminal device to cause the voice assistant application to passively output corresponding voice content based on the voice request.

[0107] In some embodiments, the interaction device further comprises an audio playing unit, and the interaction device is further configured to: receive the first voice content and / or the second voice content from the terminal device, and play the first voice content and / or the second voice content by using the audio playing unit.

[0108] In some embodiments, the process 300 further comprises, during playing of the first voice content or the second voice content, triggering the voice assistant application to stop playing the first voice content or the second voice content in response to a fourth operation for the interaction device.

[0109] In some embodiments, the first voice content is related to a first topic, and the second voice content is related to a second topic, the first topic being different from the second topic.

[0110] In some embodiments, the first voice content and the second voice content are different contents related to the same topic.

[0111] In some embodiments, the first topic and / or the second topic is determined from a plurality of preset topics.

[0112] In some embodiments, the first voice content and the second voice content are determined based on a preset content list, the content list comprising a plurality of content items associated with different topics, the content item comprising voice content or text content.

[0113] In some embodiments, the content list is maintained at the terminal device.

[0114] In some embodiments, in response to the first voice content being played, a content item corresponding to the first voice content is removed from the content list.

[0115] In some embodiments, in response to the content list being an empty list or the content list not being updated within a predetermined period, a plurality of content items are triggered to be generated to update the content list.

[0116] In some embodiments, the interaction device is adapted to be worn on a finger of a user.

[0117] Example apparatus and devices

[0118] Embodiments of the present disclosure also provide a corresponding device for implementing the above method or process. FIG. 4 shows a schematic structural block diagram of an example interactive device 160 according to certain embodiments of the present disclosure. The interactive device 160 can be implemented as or included in the interactive device 160. Various modules / components in the interactive device 160 can be implemented by hardware, software, firmware, or any combination thereof.

[0119] As shown in FIG. 4, the interactive device 160 includes a collection module 410 configured to collect a first operation for the interactive device when a voice content is not played by a voice assistant application on a terminal device; a triggering module 420 configured to trigger the voice assistant application on the terminal device to actively play first voice content in response to the first operation; the collection module 410 is further configured to collect a second operation for the interactive device during the playing of the first voice content; the triggering module 420 is further configured to trigger the voice assistant application on the terminal device to actively play second voice content in response to the second operation; and the second voice content is different from the first voice content.

[0120] In some embodiments, the first voice content and / or the second voice content is content generated by the voice assistant application using a generative model.

[0121] In some embodiments, the interactive device 160 further includes a voice request triggering module configured to trigger the terminal device or an audio collection unit connected to the terminal device to receive a voice request of a user in response to a third operation for the interactive device, so as to trigger the voice assistant application to passively output third voice content based on the voice request.

[0122] In some embodiments, the third voice content is related to the first voice content and / or the second voice content and the voice request.

[0123] In some embodiments, the third voice content is generated by: obtaining text content generated by a model based on the first voice content and / or the second voice content and the voice request content; and converting the text content into the third voice content.

[0124] In some embodiments, the interactive device includes an audio collection unit, and the interactive device is further configured to receive the voice request using the audio collection unit and send the voice request to the terminal device so that the voice assistant application passively outputs corresponding voice content based on the voice request.

[0125] In some embodiments, the interactive device further includes an audio playback unit, and the interactive device is further configured to receive the first voice content and / or the second voice content from the terminal device and play the first voice content and / or the second voice content using the audio playback unit.

[0126] In some embodiments, the interaction device 160 further comprises a stop triggering module configured to, during playing of the first voice content or the second voice content, trigger the voice assistant application to stop playing the first voice content or the second voice content in response to a fourth operation on the interaction device.

[0127] In some embodiments, the first voice content is related to a first topic and the second voice content is related to a second topic, the first topic being different from the second topic.

[0128] In some embodiments, the first voice content and the second voice content are different contents related to a same topic.

[0129] In some embodiments, the first topic and / or the second topic is determined from a plurality of preset topics.

[0130] In some embodiments, the first voice content and the second voice content are determined based on a preset content list, the content list comprising a plurality of content items associated with different topics, the content item comprising voice content or text content.

[0131] In some embodiments, the content list is maintained at the terminal device.

[0132] In some embodiments, in response to the first voice content being played, the content item corresponding to the first voice content is removed from the content list.

[0133] In some embodiments, in response to the content list being an empty list or the content list not being updated within a predetermined period, a plurality of content items are triggered to be generated to update the content list.

[0134] In some embodiments, the interaction device is adapted to be worn on a finger of a user.

[0135] FIG. 5 illustrates a block diagram of an electronic device 500 in which one or more embodiments of the disclosure can be implemented. It should be understood that the electronic device 500 illustrated in FIG. 5 is merely exemplary and should not be construed as limiting on the functionality and scope of the embodiments described herein. The electronic device 500 can be used for at least part of the steps of the voice interaction process described above.

[0136] As shown in FIG. 5, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 can include, but are not limited to, one or more processing units or processors 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processor 510 can be a real or virtual processor and is capable of performing various processing according to programs stored in the memory 520. In a multi-processor system, multiple processors perform computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0137] Electronic device 500 typically includes a plurality of computer storage media. Such media can be any available media that is accessed by electronic device 500 via one or more interfaces, including, without limitation, volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile (such as register, cache, RAM), non-volatile (such as ROM, EEPROM, flash memory), or some combination of the two. Storage 530 can be removable or non-removable and can include machine-readable media, such as flash drives, magnetic disks, or any other medium that can be used to store information and / or data and that can be accessed by electronic device 500.

[0138] Electronic device 500 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5, a disk drive and a disk controller to access a removable, non-removable, volatile, or non-volatile memory medium (e.g., a floppy disk, a magnetic disk, or an optical disk) can be provided. In these cases, each drive can be connected to the bus (not shown) by one or more data media interfaces. Memory 520 can include computer program product 525 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0139] Communication unit 540 enables communications with other electronic devices over a communication medium. Additionally, the functionality of the components of electronic device 500 can be implemented in a single computing cluster or a plurality of computer machines that are capable of communicating with one another over a communication connection. As such, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes.

[0140] Input device 550 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. Output device 560 can be one or more output devices, such as a display, a speaker, a printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through communication unit 540, as needed, one or more devices that enable a user to interact with electronic device 500, or any devices (e.g., a network card, a modem, etc.) that enable electronic device 500 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0141] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0142] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0143] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0144] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0145] The computer program product of the present disclosure can have a signal including said computer program. This signal can be electronic, electromagnetic, optical, or any other suitable type of signal. Such a signal can be provided through a communication connection, such as electrical wiring, optical fiber, wireless interface, etc. Examples of computer program products include computer program implemented on a personal computer, server, or other networked device. A non-transitory computer readable medium, such as a floppy disk, CD-ROM, DVD-ROM, Blu-ray Disc, hard disk drive, or any other suitable non-transitory computer readable medium can store the computer program product.

[0146] Various implementations of the disclosure have been described in detail above. The foregoing description is exemplary and explanatory only, and is not intended to be exhaustive or to limit various implementations of the disclosure to the precise forms disclosed. Many modifications and variations are possible in light of the above teachings without departing from the scope and spirit of the disclosure. It is intended that the scope of the disclosure be limited only by the claims and the equivalents thereof. The use of the terms "including," "containing," "comprising," "having," "in involving," "portions," "elements," "components," "steps," "phases," "processes," "operations," "steps," "stages," "procedures," "methods," "mechanisms," "devices," "systems," "apparatuses," "units," "means," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "

Claims

1. A voice interaction method applied to an interaction device, the method comprising: in response to a first operation on the interaction device, triggering a voice assistant application on a terminal device to proactively play first voice content when the voice assistant application is not playing voice content; and in response to a second operation on the interaction device, triggering the voice assistant application on the terminal device to proactively play second voice content during playing of the first voice content, wherein the second voice content is different from the first voice content.

2. The method of claim 1, wherein the first voice content and / or the second voice content is content generated by the voice assistant application using a generative model.

3. The interaction method of claim 1, the method further comprising: in response to a third operation on the interaction device, triggering the terminal device or an audio acquisition unit connected to the terminal device to receive a voice request of a user to trigger the voice assistant application to passively output third voice content based on the voice request.

4. The method of claim 3, wherein the third voice content is related to the first voice content and / or the second voice content and the voice request.

5. The method of claim 4, wherein the third voice content is generated by: obtaining text content generated by a model based on the first voice content and / or the second voice content and the voice request content; and converting the text content into the third voice content.

6. The method of claim 1, wherein the interaction device comprises an audio acquisition unit, the interaction device is further configured to receive a voice request using the audio acquisition unit and send the voice request to the terminal device to cause the voice assistant application to passively output corresponding voice content based on the voice request.

7. The method of claim 1, wherein the interaction device further comprises an audio playback unit, the interaction device is further configured to receive the first voice content and / or the second voice content from the terminal device and play the first voice content and / or the second voice content using the audio playback unit.

8. The method of claim 1, further comprising: in response to a fourth operation on the interaction device, triggering the voice assistant application to stop playing the first voice content or the second voice content during playing of the first voice content or the second voice content.

9. The method of claim 1, wherein the first voice content is related to a first topic and the second voice content is related to a second topic, the first topic being different from the second topic.

10. The method of claim 1, wherein the first voice content and the second voice content are different content related to a same topic.

11. The method of claim 9, wherein the first topic and / or the second topic is determined from a plurality of preset topics. ​ 12.The method of claim 11, wherein the first voice content and the second voice content are determined based on a preset content list, the content list comprising a plurality of content items associated with different topics, the content items comprising voice content or text content. 13.The method of claim 11, wherein the content list is maintained at the terminal device. 14.The method of claim 11, wherein: in response to the first voice content being played, a content item corresponding to the first voice content is removed from the content list. 15.The method of claim 12, wherein: in response to the content list being an empty list or the content list being not updated within a predetermined time period, a plurality of content items are triggered to be generated to update the content list. 16.The method of claim 1, wherein the interaction device is adapted to be worn on a finger of a user. 17.An interaction device, comprising: a collecting module configured to collect a first operation for the interaction device when a voice content is not played by a voice assistant application on a terminal device; and a triggering module configured to trigger the voice assistant application on the terminal device to actively play a first voice content in response to the first operation; wherein the collecting module is further configured to collect a second operation for the interaction device during the playing of the first voice content; and the triggering module is further configured to trigger the voice assistant application on the terminal device to actively play a second voice content in response to the second operation, wherein the second voice content is different from the first voice content. 18.An electronic device, comprising: at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, cause the electronic device to perform the method of any one of claims 1-16. 19.A computer-readable storage medium having computer-executable instructions stored thereon that are executable by a processor to implement the method of any one of claims 1-16. 20.A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method of any one of claims 1-16. ​ ​ ​ ​ ​ ​ ​ ​ ​

Images