Human-computer interaction method, device, equipment, medium and program product

Abstract

The application provides an interaction method, device, equipment, medium and program product, wherein the method comprises: determining text information corresponding to interaction data input by a user through a physical device according to the interaction data; obtaining response information corresponding to the text information; and outputting the response information. The application can increase the diversity and flexibility of interaction operations, meet the personalized interaction needs of users, and improve the user experience.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction technology, and in particular to a human-computer interaction method, apparatus, device, medium, and program product. Background Technology

[0002] With the continuous development of smart home devices such as smart speakers and various physical devices such as smart toys, physical devices can provide people with a variety of functions, bringing many conveniences to people's lives and work. For example, physical devices can provide human-computer interaction functions to interact with users, thereby enhancing the interaction between users and devices and improving the convenience of interaction.

[0003] However, when users interact with physical devices, the physical devices offer limited interactive operations, resulting in limitations that fail to meet users' personalized interaction needs. Summary of the Invention

[0004] This application provides a human-computer interaction method, apparatus, device, medium, and program product, which can increase the diversity and flexibility of interactive operations, meet users' personalized interaction needs, and improve users' user experience.

[0005] In a first aspect, embodiments of this application provide an interaction method, including:

[0006] Based on the interaction data input by the user through a physical device, determine the text information corresponding to the interaction data;

[0007] Obtain the response information corresponding to the text information;

[0008] Output the response information.

[0009] Secondly, embodiments of this application provide an interactive device, including:

[0010] The text determination module is used to determine the text information corresponding to the interaction data input by the user through a physical device.

[0011] The information acquisition module is used to acquire the response information corresponding to the text information;

[0012] An interactive response module is used to output the response information.

[0013] Thirdly, embodiments of this application provide an electronic device, including:

[0014] A processor and a memory, the memory being used to store a computer program, and the processor being used to invoke and run the computer program stored in the memory to perform the interactive method as described in the foregoing first aspect embodiment and various implementations.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium for storing a computer program that causes a computer to perform the interaction method as described in the foregoing first aspect embodiments and various implementations.

[0016] Fifthly, embodiments of this application provide a computer program product containing program instructions that, when executed on an electronic device, cause the electronic device to perform the interaction method as described in the first aspect embodiment and its various implementations.

[0017] The technical solution disclosed in this application determines the text information corresponding to the interaction data based on the interaction data input by the user through a physical device, obtains the response information corresponding to the text information, and then outputs the response information. In this way, the response information corresponding to the interaction data input by the user is output to the user, thereby increasing the diversity and flexibility of interactive operations, meeting the user's personalized interaction needs, and improving the user experience. Attached Figure Description

[0018] 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.

[0019] Figure 1 A flowchart illustrating an interaction method provided in an embodiment of this application;

[0020] Figure 2a A schematic diagram of a settings page for a ring provided in an embodiment of this application;

[0021] Figure 2b This is a schematic diagram of a custom gesture settings interface provided in an embodiment of this application;

[0022] Figure 2c This is a schematic diagram illustrating the setting of custom gestures and corresponding interaction commands for custom gestures, provided as an embodiment of this application.

[0023] Figure 2d This is a schematic diagram of an interactive command editing interface provided in an embodiment of this application;

[0024] Figure 2e A schematic diagram illustrating another way of setting custom gestures to correspond to interactive commands, provided in an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of a preset application provided in an embodiment of this application;

[0026] Figure 4 A flowchart for obtaining response information corresponding to text information is provided in an embodiment of this application;

[0027] Figure 5 This is a schematic diagram of another preset application provided in the embodiments of this application;

[0028] Figure 6 A schematic block diagram of an interactive device provided in an embodiment of this application;

[0029] Figure 7 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0030] 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. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0032] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or solution described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0033] In the description of the embodiments in this application, unless otherwise stated, "multiple" means two or more, that is, at least two. "At least one" means one or more. "Any" means any one or any several.

[0034] As mentioned earlier, with the continuous development of smart home devices such as smart speakers and smart toys, physical devices can provide people with various functions, bringing numerous conveniences to their lives and work. For example, physical devices can provide human-computer interaction functions to interact with users, enhancing the interaction between users and devices and improving the convenience of interaction. In related technologies, when users interact with physical devices, the physical devices perceive and recognize the interactive operation data input by the user based on their own human-computer interaction functions, execute corresponding operations based on the recognition results, and then generate corresponding response results based on the execution results. However, the above-mentioned human-computer interaction methods limit the interactive operations provided by physical devices, resulting in interaction limitations and failing to meet users' personalized interaction needs.

[0035] To address the aforementioned technical problems, this application provides an interactive method, apparatus, device, medium, and program product to solve the problem that current physical devices offer limited interactive operations to users, have interactive limitations, and cannot meet users' personalized interactive needs.

[0036] The technical solutions provided by the embodiments of this application will be described in detail below through some examples. The embodiments described below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0037] Figure 1 This is a flowchart illustrating an interaction method provided in an embodiment of this application. The interaction method of this embodiment can be executed by an interaction device, which can consist of hardware and / or software and can be integrated into an electronic device with a display screen. In this application, the electronic device can be, but is not limited to, smartphones, smart glasses, and tablet computers, etc., and no limitation is placed on the type of electronic device herein.

[0038] like Figure 1 As shown, the method may include the following steps:

[0039] S101, determine the text information corresponding to the interaction data based on the interaction data input by the user through the physical device.

[0040] In this application, the physical device can be a smart home device, such as a smart speaker, smart refrigerator, smart air purifier, smart humidifier, etc.; or, the physical device can be a smart toy, such as an early education robot, a robotic cat, a robotic dog, etc.; or, the physical device can be an electronic device including at least one physical button and a touch area, such as an in-vehicle device and a wearable device. It should be noted that the above descriptions of the types of physical devices are for illustrative purposes only and are not intended to limit the specific physical devices used in this application.

[0041] When the physical device is a wearable device, it can be a ring, earphones, necklace, or bracelet, etc.

[0042] It should be understood that when the wearable device in this application is a ring, earphone, necklace, or bracelet, the ring is a smart ring integrating health monitoring, mobile payment, and other functions; the earphone is a smart earphone integrating active noise cancellation, spatial audio, health monitoring, and posture correction; the necklace is a smart necklace integrating health monitoring, emotional companionship, and positioning and anti-loss functions; and the bracelet is a smart bracelet integrating health monitoring, motion tracking, and other functions.

[0043] In addition, the physical device in this application may include at least one of a button, a touch area, a microphone, a speaker, an inertial measurement sensor, and a camera.

[0044] The aforementioned buttons can include physical buttons and pressure-sensitive buttons. Physical buttons enable input through pressing, while pressure-sensitive buttons collect input data via pressure sensors. In this application, pressure-sensitive buttons can be configured on a physical device in the same way as physical buttons, or any sub-area within the touch area can be designated as a pressure-sensitive area, using this area as the pressure-sensitive button to achieve its function.

[0045] The aforementioned inertial measurement sensor can be called an inertial measurement unit (IMU).

[0046] Therefore, when users interact with the physical device, they can do so by pressing or clicking buttons; alternatively, by swiping on the touch area; by using gestures; or by capturing user-inputted voice through a microphone for voice-based interaction. These buttons can be physical buttons or pressure-sensitive buttons located on the physical device.

[0047] Furthermore, when the physical device detects user-input interaction data, it can transmit this data to the electronic device via a communication connection. This allows the electronic device to determine the corresponding text information based on the user-input interaction data. The text information corresponding to each piece of interaction data describes the interaction instruction, enabling the electronic device to understand and use the instruction based on the text information.

[0048] In this application, when interacting with the physical device by pressing or clicking a button, the physical device can acquire button data or pressure-sensitive data from the user's button press or click; when interacting with the physical device by swiping on the touch area, the physical device can acquire touch data from the user on the touch area; when interacting with the physical device by gestures, the physical device can acquire at least one of inertial measurement data and hand image data, wherein the hand image data is acquired by a camera; when interacting with the physical device by voice, the physical device can acquire interactive voice data input by the user through a microphone.

[0049] Furthermore, the aforementioned button data or pressure sensitivity data may include, but is not limited to: single click, double click, triple click, and long press.

[0050] The aforementioned touch data may include swipe-up, swipe-down, swipe-left, and swipe-right operations.

[0051] The gesture data corresponding to the aforementioned inertial measurement data and / or hand image data may include, but is not limited to: gesture data of pinching two fingers together once, gesture data of flipping the palm, and gesture data of drawing circles in the air with the fingers.

[0052] That is, the interactive data input by the user through the physical device in this application includes at least one of the following: touch data, button data, pressure-sensitive data, inertial measurement data, hand image data, and voice data.

[0053] It should be understood that the interactive data input by the user through the physical device includes at least one of the following: touch data, button data, pressure-sensitive data, inertial measurement data, hand image data, and voice data. This means that the interactive data input by the user through the physical device is at least one of touch data, button data, pressure-sensitive data, inertial measurement data, hand image data, and voice data.

[0054] Furthermore, when receiving interactive data input by a user through a physical device, the electronic device of this application can search for the text information corresponding to the interactive data in a preset mapping relationship between interactive data and text information.

[0055] For example, the mapping relationship between the above-mentioned preset interactive data and text information can be shown in Table 1 below:

[0056] Table 1

[0057] Interactive data Text information Click the button Answer the phone or hang up the phone Double-click button Report current heart rate Triple-click the button Play audio content or pause audio content Long press the button Photograph Swipe up Increase audio volume Swipe down Lower the audio volume Turn your palm over What time is it now? ...... ...... Pinch two fingers together twice How's the weather today?

[0058] In some optional embodiments, the buttons in the physical device of this application can correspond to different triggering methods, including but not limited to: single click, double click, triple click, and long press. Furthermore, different interactive commands can correspond to different triggering methods of the buttons, specifically as follows:

[0059] Scenario 1: When the button triggering method in the physical device is a single click, the corresponding interactive command for this single click triggering method can be to answer the phone or hang up the phone.

[0060] Scenario 2: When the button triggering method in the physical device is double-click, the corresponding interactive command for this double-click triggering method can be to announce the current heart rate;

[0061] Scenario 3: When the button triggering method in the physical device is a triple click, the corresponding interactive command for the triple click triggering method can be to play audio content or pause audio content playback;

[0062] Scenario 4: When the button triggering method in the physical device is a long press, the corresponding interaction command for this long press triggering method can be taking a picture.

[0063] The audio content can be music or novels, and there are no restrictions on it.

[0064] It should be noted that the interactive commands corresponding to different button triggering methods described above can be flexibly adjusted according to user needs to meet personalized usage requirements. In other words, when using the physical device, different users can customize the interactive commands corresponding to different button triggering methods in the device's settings page according to their own usage needs.

[0065] In some embodiments, a user's swipe operation on the touch area of ​​a physical device can be, but is not limited to, swiping up, swiping down, swiping left, and swiping right. Furthermore, each of these swipe operations corresponds to different interaction commands, as detailed below:

[0066] In the first scenario, when a user swipes up on the touch area, the corresponding interaction command for that swipe could be to increase the audio volume.

[0067] In the second scenario, when a user swipes down on the touch area, the corresponding interaction command for that swipe could be to lower the audio volume.

[0068] In the third scenario, when a user swipes left on the touch area, the corresponding interaction command for that swipe can be to switch to the previous audio content.

[0069] In the third scenario, when a user swipes right on the touch area, the corresponding interaction command for that swipe can be to switch to the next audio content.

[0070] It should be noted that the interaction commands corresponding to different swipe operations on the touch area can be flexibly adjusted according to user needs to meet personalized usage requirements. That is, when using the physical device, different users can set different interaction commands for each swipe operation on the touch area in the device's settings page, thus achieving the goal of customizing the interaction commands for each swipe operation on the touch area.

[0071] Furthermore, the interaction commands corresponding to different swiping operations performed by the user on the touch area are different from the interaction commands corresponding to different triggering methods of the button. This can avoid misoperation caused by the same interaction command corresponding to different triggering methods and simplify the human-computer interaction process.

[0072] In some embodiments, when a user interacts with a physical device through gestures, this application can collect the user's gesture data through at least one of an inertial measurement sensor and a camera on the physical device. The gesture data can be expressed as inertial measurement data and / or hand image data. That is, when a user interacts with a physical device through gestures, the gesture data obtained by the physical device is inertial measurement data and / or hand image data.

[0073] It should be noted that the user can input various gestures in this application, and each gesture can correspond to different interaction commands. For example, the interaction command corresponding to two fingers pressing twice could be to ask about the weather.

[0074] Furthermore, the interactive instructions corresponding to each gesture can be flexibly adjusted according to user needs.

[0075] In addition, users can customize gestures and set corresponding interaction commands and text information for the custom gestures. This can meet users' personalized needs, thereby improving the convenience and efficiency of interaction between users and physical devices.

[0076] When an electronic device receives interactive data input by a user through a physical device, the electronic device can identify the interactive data and then, based on the identification result, search for the interactive instruction corresponding to the identification result and the text information corresponding to the interactive instruction in the preset mapping relationship between interactive data, instructions, and text information.

[0077] In some alternative embodiments, when recognizing gesture data collected by inertial measurement sensors and / or cameras, the electronic device can obtain a gesture recognition result for the user's input gesture by recognizing the gesture data. Then, based on the gesture recognition result, an interaction command corresponding to the gesture recognition result is determined.

[0078] In this process, determining the interaction command corresponding to the gesture recognition result can be done by determining a preset interaction command associated with the gesture recognition result and then determining the preset interaction command as the interaction command corresponding to the gesture recognition result.

[0079] In this application, when recognizing gesture action data, the similarity between the gesture action data and each preset gesture in a pre-built gesture set can be calculated, and the preset gesture with the highest similarity can be selected as the gesture recognition result; alternatively, the gesture action data can be processed and the gesture recognition result can be output by using a gesture recognition model. The gesture recognition model can be any machine learning model that supports gesture recognition based on gesture action data, and this application does not impose any restrictions on the model.

[0080] Considering the noise and other interference present in gesture data collected by inertial measurement sensors and / or cameras, electronic devices, upon receiving user gesture data from these physical devices, can first perform preprocessing operations such as noise reduction, filtering, and feature extraction to obtain more reliable and effective gesture data. Then, recognition operations are performed based on the preprocessed gesture data. This preprocessing removes noise and useless data, making the gesture data more realistic and reliable, thereby improving the quality of the gesture data and providing conditions for accurate gesture recognition.

[0081] In some embodiments, the mapping relationship between preset interactive data, instructions, and text information in this application can be shown in Table 2 below:

[0082] Table 2

[0083]

[0084] For example, assuming a user interacts with a physical device by inputting a palm flip gesture, after the electronic device receives the interaction data sent by the physical device, it can first identify the palm flip gesture action data input by the user to obtain the palm flip gesture recognition result. Then, based on the palm flip gesture recognition result, it can search for the interaction command "ask for time" corresponding to the palm flip gesture recognition result and the text information "what time is it now" corresponding to the interaction command "ask for time" in the mapping relationship between preset interaction data, commands and text information in Table 2 above.

[0085] S102, obtain the response information corresponding to the text information.

[0086] In this application, response information refers to information that provides feedback or replies to text information corresponding to interactive data input by a user through a physical device. For example, assuming the text information corresponding to the interactive data input by the user is "How's the weather today?", then the response information would be the specific weather information provided in response to "How's the weather today?".

[0087] In some optional embodiments, the electronic device of this application can determine whether a preset application is in a working state. If it is determined that the preset application is in a working state, the text information corresponding to the interactive data can be input into the preset application in the working state to obtain the response information corresponding to the text information through the preset application. If it is determined that the preset application is in a sleep state, the preset application is woken up to wake it up from the sleep state to the working state, and then the text information corresponding to the interactive data is input into the preset application in the working state to obtain the response information corresponding to the text information through the preset application.

[0088] In some embodiments, obtaining response information corresponding to text information through a preset application may involve performing semantic analysis on the text information using a preset application to generate response information corresponding to the text information.

[0089] Optionally, this application performs semantic analysis on the text information using a pre-defined application to determine semantic information such as entities, relationships between entities, and sentiment within the text information, enabling the pre-defined application to understand the deeper meaning corresponding to the text information. Furthermore, the pre-defined application generates corresponding response information based on the deeper meaning corresponding to the text information. Here, entities in the text information refer to information such as location and time. Sentiment in the text information refers to the user's emotions, such as positive, negative, or neutral.

[0090] In some embodiments, response information corresponding to text information can be obtained through a preset application, or semantic analysis of text information can be performed through a preset application to determine the user's interaction intent, and then response information corresponding to text information can be generated by the preset application based on the user's interaction intent.

[0091] Optionally, semantic analysis of the text information can be performed through a preset application to determine the user's interaction intent. This can be achieved by understanding the meaning of words, phrases, and sentences in the text information through a preset application, and then determining the user's intent to input the text information based on the meaning expressed in the text information, i.e., determining the user's interaction intent.

[0092] In some embodiments, generating response information corresponding to text information by a preset application according to a user interaction intention may include: determining, by the preset application according to the user interaction intention, a response template for generating the response information, and acquiring target information corresponding to the user interaction intention; then, adjusting the target information according to the response template to obtain the response information corresponding to the text information.

[0093] The step of acquiring, by the preset application according to the user interaction intention, the target information corresponding to the user interaction intention may be implemented by at least one of networking and local data.

[0094] For example, assuming that the text information is "What is the weather like today", the preset application may determine that the user interaction intention is to acquire today's weather information according to the text information "What is the weather like today", then the preset application may acquire the current day's weather information at the user's location through networking, which is "It is sunny today, the temperature is -3 to 6 degrees, with gentle breeze, and it is relatively cold in the morning and evening", and acquire a weather information response template. Then, according to the weather information response template, the current weather information "It is sunny today, the temperature is -3 to 6 degrees, with gentle breeze, and it is relatively cold in the morning and evening" is adjusted, to obtain the response information as "It is sunny today, the temperature is between -3 and 6 degrees, and the wind is light. However, it is cold in the morning and evening, so it is best to wear a thick cotton-padded coat and put on a scarf and gloves when going out to keep warm."

[0095] In this application, before performing semantic analysis on the text information, the preset application may further perform text cleaning on the text information to remove irrelevant characters or punctuation marks in the text information, as well as stop words that are not helpful for understanding the text information, such as words like "is", "of", etc. In this way, the processing difficulty of the preset application on the text information can be reduced, the consumption of computing resources can be lowered, and the accuracy of processing results can be improved.

[0096] In this application, the preset application may be an Artificial Intelligence (AI) application.

[0097] It should be understood that the AI application refers to an application developed using artificial intelligence technology.

[0098] Moreover, the AI application may optionally be an entrance of a Large Language Model (LLM) that processes language-related tasks, such as question answering, text generation, etc. This application does not impose specific limitations on the AI application.

[0099] The large language model described above refers to a computer model with a large number of parameters and powerful language generation and understanding capabilities.

[0100] S103: Output the response information.

[0101] In some alternative embodiments, response information may be displayed on the screen of an electronic device.

[0102] Considering that physical devices communicating with electronic devices can include speakers, when outputting response information, preset application-generated response information can be output through the speaker of the physical device to enable personalized interaction with the user.

[0103] In other words, in addition to being displayed on the screen of an electronic device, the response information of this application can also be output through the speaker of a wearable device.

[0104] This application outputs response information corresponding to text information through the above-mentioned output method, which can realize the output of response information corresponding to interactive data to users through different output channels, thereby improving user interaction satisfaction.

[0105] In some alternative embodiments, considering that this application can determine the interaction instruction based on the user's input interaction data, the interaction operation corresponding to the interaction instruction can also be executed before outputting the response information. This can support complex interaction scenarios, allowing users to clearly understand the execution status and response information of the interaction instruction, and helping users to better interact with physical devices.

[0106] For example, assuming the user inputs an interactive command that corresponds to "switch to the next audio", the electronic device can respond to the interactive command "switch to the next audio", perform an audio switching operation, and output a response message "switched to the next audio" through the speaker of the physical device.

[0107] That is, this application may also include: responding to an interactive instruction, performing an interactive operation corresponding to the interactive instruction, and outputting response information.

[0108] In some optional embodiments, after obtaining response information based on text information, this application may optionally generate a dialogue record based on the text information and response information, and store the dialogue record in the dialogue record of a preset application, thereby enhancing the transparency of the interaction between the user and the physical device, and enabling information tracing based on the dialogue record when information tracing is required.

[0109] In some optional embodiments, the dialogue record generated in this application based on text information and response information is a partial dialogue fragment in a multi-turn dialogue record. This can provide context for the multi-turn dialogue, making the multi-turn dialogue more coherent, and can also improve the efficiency and quality of the dialogue.

[0110] The technical solution disclosed in this application determines the text information corresponding to the interaction data input by the user through a physical device, obtains the response information corresponding to the text information, and then outputs the response information. This achieves the output of response information corresponding to the user's input interaction data, thereby increasing the diversity and flexibility of interactive operations, meeting users' personalized interaction needs, and improving the user experience. Furthermore, by inputting the text information corresponding to the interaction data into a preset application, the preset application intelligently obtains the response information corresponding to the text information, thereby improving the intelligence level of human-computer interaction and enhancing the human-computer interaction effect.

[0111] In some alternative embodiments, considering that the physical device can be a wearable device, when the wearable device is a ring, the ring may include buttons, a touch area, and an inertial measurement sensor. Therefore, this application determines the text information corresponding to the interaction data based on the interaction data input by the user through the physical device, specifically including: determining the text information corresponding to the interaction data based on the interaction data input by the user through the wearable device. The wearable device is specifically a ring.

[0112] Optionally, when a user interacts with the ring and inputs interactive data through the ring, they can interact with the ring by pressing or clicking a button; alternatively, they can interact with the ring by swiping on the touch area; or they can interact with the ring through gestures. These buttons can be physical buttons or pressure-sensitive buttons located on the ring.

[0113] Furthermore, when the ring detects user-input interaction data, it can send the user-input interaction data to the electronic device through its communication connection with the electronic device, so that the electronic device can determine the corresponding text information based on the user-input interaction data.

[0114] In this application, when interacting with the ring by pressing or clicking a button, the ring can acquire button data or pressure data of the user pressing or clicking the button; when interacting with the ring by sliding on the touch area, the ring can acquire touch data of the user on the touch area; when interacting with the ring by gestures, the ring can acquire inertial measurement data that collects the user's gesture data.

[0115] Furthermore, the aforementioned button data or pressure sensitivity data may include, but is not limited to: single click, double click, triple click, and long press.

[0116] The aforementioned touch data may include swipe-up, swipe-down, swipe-left, and swipe-right operations.

[0117] The hand gesture data corresponding to the aforementioned inertial measurement data may include, but is not limited to: hand gesture data of pinching two fingers together once, hand gesture data of flipping the palm, and hand gesture data of drawing circles in the air with the fingers.

[0118] That is, the interactive data input by the user through the wearable device in this application includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data.

[0119] It should be understood that the interactive data input by the user through the wearable device includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data. This means that the interactive data input by the user through the wearable device is at least one of touch data, button data, pressure-sensitive data, and inertial measurement data.

[0120] Furthermore, the interactive data input by the user through the wearable device in this application does not include voice data. That is, when the user interacts with the ring, it does not include the interaction method of interacting with the ring via voice.

[0121] Furthermore, when receiving interactive data input by the user via the ring, the electronic device can search for the corresponding text information in the preset mapping relationship between interactive data and text information.

[0122] In some optional embodiments, the buttons in the ring of this application can correspond to different triggering methods, including but not limited to: single click, double click, triple click, and long press. Furthermore, different interactive commands can correspond to different triggering methods of the buttons, as specifically in the following situations:

[0123] Scenario 1: When the button trigger method in the ring is a single click, the corresponding interaction command for this single click trigger method can be to answer a call or hang up a call.

[0124] Scenario 2: When the button trigger method on the ring is double-click, the corresponding interaction command for this double-click trigger method can be to announce the current heart rate;

[0125] Scenario 3: When the button trigger method in the ring is a triple click, the corresponding interactive command for the triple click trigger method can be to play audio content or pause audio content playback;

[0126] Scenario 4: When the button on the ring is triggered by a long press, the corresponding interaction command can be taking a photo.

[0127] The audio content can be music or novels, and there are no restrictions on it.

[0128] It should be noted that the interactive commands corresponding to different button triggering methods described above can be flexibly adjusted according to user needs to meet personalized usage requirements. In other words, when using the ring, different users can customize the interactive commands corresponding to different button triggering methods in the ring's settings page according to their own usage needs.

[0129] In some embodiments, the user's swipe operation on the touch area can be, but is not limited to, swiping up, swiping down, swiping left, and swiping right. Furthermore, each of these swipe operations corresponds to different interaction commands, as detailed below:

[0130] In the first scenario, when a user swipes up on the touch area, the corresponding interaction command for that swipe could be to increase the audio volume.

[0131] In the second scenario, when a user swipes down on the touch area, the corresponding interaction command for that swipe could be to lower the audio volume.

[0132] In the third scenario, when a user swipes left on the touch area, the corresponding interaction command for that swipe can be to switch to the previous audio content.

[0133] In the third scenario, when a user swipes right on the touch area, the corresponding interaction command for that swipe can be to switch to the next audio content.

[0134] It should be noted that the interaction commands corresponding to different swipe operations on the touch area can be flexibly adjusted according to user needs to meet personalized usage requirements. In other words, when using the ring, different users can set different interaction commands for each swipe operation on the touch area in the ring's settings page, thus achieving the goal of customizing the interaction commands for each swipe operation on the touch area.

[0135] Furthermore, the interaction commands corresponding to different swiping operations performed by the user on the touch area are different from the interaction commands corresponding to different triggering methods of the button. This can avoid misoperation caused by the same interaction command corresponding to different triggering methods and simplify the human-computer interaction process.

[0136] In some embodiments, when a user interacts with the ring through gestures, this application can collect the user's gesture data through an inertial measurement sensor on the ring. This gesture data can be represented by inertial measurement data, that is, when a user interacts with the ring through gestures, the gesture data obtained by the ring is inertial measurement data.

[0137] It should be noted that the user input gestures mentioned above can be of various types, each corresponding to different interaction commands. Furthermore, the interaction commands corresponding to each gesture can be flexibly adjusted according to user needs.

[0138] In addition, users can customize gestures and set corresponding interaction commands and text information for the custom gestures. This can meet users' personalized needs, thereby improving the convenience and efficiency of interaction between users and the ring.

[0139] In this application, the aforementioned custom gestures may include, but are not limited to: a two-finger pinch gesture, a fist gesture, a palm flip gesture, a two-finger pinch gesture, and a finger circling gesture in the air.

[0140] For two-finger pinch gestures, since each user has different habits regarding wearing rings—for example, user A usually wears the ring on their index finger, while user B usually wears it on their middle finger—the pinch gesture can be performed by the finger on which the ring is worn, combined with any of the remaining fingers on the user's hand. For instance, assuming a user wears the ring on the index finger of either hand, the two-finger pinch gesture can be performed by using the index finger and thumb of the user's hand to pinch together.

[0141] The following example illustrates how to define user-defined gestures and set corresponding interaction commands for them. For instance, suppose a user wants to define custom gestures and set corresponding interaction commands. The user can establish a communication connection between the ring and the electronic device, and the electronic device will display a settings page for the ring, such as... Figure 2a As shown. The ring's settings page includes custom gesture options and general settings options.

[0142] Furthermore, users can select the "Custom Gestures" option in the ring's settings page to open the custom gesture settings interface, such as... Figure 2b As shown. The custom gesture settings interface includes a placeholder area for a custom gesture illustration and a setting area for the corresponding interaction command. Users can then execute custom gestures using their real hands, such as a two-finger pinch gesture. After the inertial measurement sensor on the ring collects the two-finger pinch gesture, the ring can send the gesture data to the electronic device via a communication connection. The electronic device then reproduces the gesture in the custom gesture illustration area of ​​the custom gesture settings interface based on the gesture data sent by the ring. Furthermore, the custom gesture's identifier "two-finger pinch twice" is displayed in the corresponding interaction command setting area, and the interaction command for the two-finger pinch gesture is displayed as "none." (See also...) Figure 2c As shown.

[0143] Next, the user can select the interaction command settings area in the custom gesture settings interface to switch the interaction command settings area from a non-editable state to an editable state, and enter the interaction command editing interface, such as... Figure 2d As shown. Furthermore, in the interactive command editing interface, users can set the corresponding interactive command "Ask the Weather" for the user-inputted custom gesture "Pinch twice with two fingers" displayed in the editable interactive command settings area, and set the corresponding text information "How's the weather today?" for the interactive command "Ask the Weather". Afterwards, users can select to create a command control to implement user-defined gestures and set corresponding interactive commands and text information for those custom gestures, see [link to documentation]. Figure 2e .

[0144] Furthermore, when the electronic device receives interactive data input by the user through the ring, the electronic device can identify the interactive data and then, based on the identification result, search for the interactive instruction corresponding to the identification result and the text information corresponding to the interactive instruction in the preset mapping relationship between interactive data, instructions and text information.

[0145] The electronic device identifies the interactive data and then searches for the interactive instruction corresponding to the identification result in the mapping relationship between preset interactive data, instructions and text information based on the identification result. The specific implementation process of the interactive instruction and the text information corresponding to the interactive instruction can be found in the aforementioned embodiments, and will not be elaborated on here.

[0146] After determining the text information corresponding to the interactive data, the electronic device of this application can obtain the response information corresponding to the text information and output the response information.

[0147] The implementation principle of obtaining the response information corresponding to the text information is the same as or similar to the implementation principle of step S102 in the aforementioned embodiment. For the specific implementation process, please refer to step S102 in the aforementioned embodiment. It will not be elaborated on here.

[0148] In some embodiments, considering that the ring may include a vibration motor in addition to a speaker, when outputting response information, in addition to displaying the response information on the screen of the electronic device and outputting the response information through the speaker of the ring, a vibration signal corresponding to the response information can be obtained according to the response information generated by the preset application, and then the vibration signal corresponding to the response information can be output through the vibration motor of the ring, thus improving the diversity of response information output.

[0149] Optionally, this application obtains a vibration signal corresponding to the response information generated by a preset application, and can select a target vibration mode from multiple vibration modes based on the response information generated by the preset application. These multiple vibration modes may include continuous vibration, single vibration, indirect vibration, and combinations of vibrations at different frequencies. For example, if the response information is to start playing an audio clip, the target vibration mode can be selected as continuous vibration; if the response information is to increase the audio volume, the target vibration mode can be selected as single vibration, etc.

[0150] Simultaneously, the parameters of the vibration signal corresponding to the response information can be determined, such as amplitude, frequency, and duration. Then, a vibration signal is generated based on the vibration pattern and the vibration signal's parameters using a vibration signal generation tool. For example, when the response information is a simple notification, such as a change in audio content, lower parameters can be selected for the vibration signal's amplitude, frequency, and duration. When the response information is an important notification, such as answering a phone call, higher parameters can be selected for the vibration signal's amplitude, frequency, and duration.

[0151] In some embodiments, when this application outputs a response signal, it can also output a response information generated by a preset application through the ring's speaker, while simultaneously outputting a vibration signal corresponding to the response information through the ring's vibration motor. This can speed up the user's reception of the response information and reduce the response delay caused by waiting for the voice response information to play.

[0152] In other words, in addition to displaying the response information through the screen of an electronic device, the response information may also be output through the speaker of a wearable device; and / or, a vibration signal corresponding to the response information may be output through the vibration motor of a wearable device.

[0153] In some optional embodiments, considering that this application can determine the interaction command based on the user's input interaction data, the interaction operation corresponding to the interaction command can also be executed before outputting the response information. This can support complex interaction scenarios, allowing users to clearly understand the execution status and response information of the interaction command, and helping users to better interact with the smart ring.

[0154] For example, assuming the user inputs an interactive command that corresponds to "pause playback of audio XXX", the electronic device can respond to the interactive command "pause playback of audio XXX", execute the audio XXX playback stop operation, and output "Audio XXX has stopped playing" through the ring's speaker. At the same time, the ring's vibration motor outputs a vibration signal corresponding to "Audio XXX has stopped playing".

[0155] The technical solution disclosed in this application determines the text information corresponding to the interaction data based on the interaction data input by the user through a wearable device, obtains the response information corresponding to the text information, and then outputs the response information. In this way, the user is given response information corresponding to the interaction data based on the user input, thereby increasing the diversity and flexibility of interactive operations, meeting the user's personalized interaction needs, and improving the user experience.

[0156] In some embodiments, such as Figure 3 As shown, the preset application in the aforementioned embodiments may include multiple sub-applications, each with different scenario information. For example, sub-application XX1 corresponds to a daily conversation scenario, sub-application XX2 corresponds to an article generation scenario, and sub-application XX3 corresponds to an audio recognition scenario, etc. It should be understood that each of the above sub-applications can be an entry point for a large language model. For example, any sub-application can be a specialized large language model corresponding to a daily conversation scenario, etc.

[0157] exist Figure 3 Based on the preset application structure shown, such as Figure 4 As shown, the above S102 includes the following steps S102-1 to S102-3:

[0158] S102-1, Determine the scene information corresponding to the text information.

[0159] S102-2, Based on the scene information corresponding to the text information, determine the target sub-application from multiple sub-applications.

[0160] S102-2, Input the text information into the target sub-application so that the target sub-application can obtain the response information corresponding to the text information.

[0161] In some embodiments, the scene information corresponding to the text information can be determined by a preset application, and the determination of the scene information corresponding to the text information may include the following implementation methods:

[0162] One approach involves extracting keywords from text information using a pre-defined application, and then determining the corresponding scene information based on the extracted keywords within a pre-established mapping relationship between keywords and scene information.

[0163] For example, if the keyword is "weather", then the corresponding scenario information for the keyword "weather" can be set to "daily conversation scenario".

[0164] The second implementation method involves determining the scene information corresponding to the text information by using a preset application to map the text information, preset short sentences, and scene information.

[0165] Optionally, this application may calculate the similarity between the text information and each preset phrase, and select the preset phrase with the highest similarity as the target phrase. Then, the scene information corresponding to the target phrase is determined as the scene information corresponding to the text information.

[0166] The third approach involves inputting text information into a pre-trained machine learning model through the first sub-application. This model then uses the machine learning model to understand the semantic content of the text information and determine the corresponding scene information based on the semantic content.

[0167] It should be noted that the above-described implementation methods are merely illustrative examples of the embodiments of this application and are not intended to limit the scope of this application.

[0168] After obtaining the scene information corresponding to the text information, this application can determine the target sub-application corresponding to the scene information from multiple sub-applications based on the scene information. Then, the text information is input into the target sub-application so that the target sub-application can perform semantic analysis on the text information and generate response information corresponding to the text information.

[0169] The implementation principle of generating response information corresponding to text information by performing semantic analysis on text information through target sub-application is the same as or similar to the implementation principle of obtaining response information corresponding to text information through preset application. For the specific implementation process, please refer to the aforementioned embodiment section, which will not be elaborated on here.

[0170] In some embodiments, such as Figure 5 As shown, the pre-defined application in this application includes multiple sub-applications, which can be divided into: a first sub-application and multiple second sub-applications. The first sub-application can be understood as the main sub-application, and the second sub-applications as auxiliary sub-applications. Furthermore, the scenario information corresponding to each second sub-application is different. For example, the scenario information corresponding to second sub-application YY1 is a daily dialogue scenario, the scenario information corresponding to second sub-application YY2 is an article generation scenario, and the scenario information corresponding to second sub-application YY3 is an audio recognition scenario, etc. It should be understood that the aforementioned first sub-application and each second sub-application can each serve as an entry point for a large language model. For example, the first sub-application can be the entry point for a general large language model, and any second sub-application can be a specialized large language model corresponding to a daily dialogue scenario, etc.

[0171] Therefore, this application obtains the response information corresponding to the text information through a preset application, which can be selected as follows: inputting the text information into a first sub-application to determine the scene information corresponding to the text information through the first sub-application; determining a target second sub-application from multiple second sub-applications based on the scene information corresponding to the text information; inputting the text information into the target second sub-application to obtain the response information corresponding to the text information through the target second sub-application.

[0172] In some embodiments, the above-mentioned determination of the scene information corresponding to the text information through the first sub-application may include the following implementation methods:

[0173] The first implementation method involves extracting keywords from the text information through a first sub-application, and then determining the scene information corresponding to the text information based on the extracted keywords and the pre-established mapping relationship between keywords and scene information.

[0174] The second implementation method involves determining the scene information corresponding to the text information by mapping the text information to preset short sentences and scene information through the first sub-application.

[0175] The third approach involves inputting text information into a pre-trained machine learning model through the first sub-application. This model then uses the machine learning model to understand the semantic content of the text information and determine the corresponding scene information based on the semantic content.

[0176] It should be noted that the above-described implementation methods are merely illustrative examples of the embodiments of this application and are not intended to limit the scope of this application.

[0177] After obtaining the scene information corresponding to the text information, this application can determine the target second sub-application corresponding to the scene information from multiple second sub-applications based on the scene information. Then, the text information is input into the target second sub-application to perform semantic analysis on the text information and generate response information corresponding to the text information.

[0178] The implementation principle of generating response information corresponding to text information by performing semantic analysis on text information through the second sub-application of the target is the same as or similar to the implementation principle of obtaining response information corresponding to text information by the preset application. For the specific implementation process, please refer to the aforementioned embodiment section, which will not be elaborated on here.

[0179] In other words, this application can determine the scene information corresponding to the text information, and then input the text information into a sub-application that processes the scene information in a targeted manner, enabling the sub-application to obtain the response information corresponding to the text information more accurately and efficiently; or, by determining the scene information corresponding to the text information through a first sub-application in a preset application, the application can input the text information into a second sub-application that processes the scene information in a targeted manner, enabling the second sub-application to obtain the response information corresponding to the text information more accurately and efficiently. In this way, a more accurate and personalized response can be provided to the user based on the scene information corresponding to the text information, further enhancing the user's interactive experience.

[0180] The following is a reference to the appendix. Figure 6 This application describes an interactive device proposed in its embodiments. Figure 6 As shown, the interactive device 300 includes: a text determination module 310, an information acquisition module 320, and an interactive response module 330.

[0181] The text determination module 310 is used to determine the text information corresponding to the interaction data based on the interaction data input by the user through a physical device.

[0182] Information acquisition module 320 is used to acquire response information corresponding to the text information;

[0183] The interactive response module 330 is used to output the response information.

[0184] In one optional implementation of this application embodiment, the information acquisition module 320 is specifically used for:

[0185] The text information is input into a preset application to obtain the response information corresponding to the text information through the preset application.

[0186] In one optional implementation of this application embodiment, the information acquisition module 320 is further used for:

[0187] The preset application performs semantic analysis on the text information to generate response information corresponding to the text information.

[0188] In one optional implementation of this application embodiment, the preset application includes multiple sub-applications, and the information acquisition module 320 is further configured to:

[0189] Determine the scene information corresponding to the text information;

[0190] Based on the scene information corresponding to the text information, the target sub-application is determined from the plurality of sub-applications;

[0191] The text information is input into the target sub-application so that the response information corresponding to the text information can be obtained through the target sub-application.

[0192] In one optional implementation of this application, when the physical device is a wearable device, the text determination module 310 is specifically used to: determine the text information corresponding to the interaction data input by the user through the wearable device.

[0193] In one optional implementation of this application, the interactive data input by the user through the wearable device includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data.

[0194] In one optional implementation of this application, the interactive data input by the user through the wearable device does not include voice data.

[0195] In one optional implementation of this application, the wearable device is a ring.

[0196] In one optional implementation of this application embodiment, the wearable device includes a speaker and a vibration motor, and the interaction response module 330 is specifically used for:

[0197] The response information is output through the speaker of the wearable device; and / or,

[0198] The wearable device's vibration motor outputs a vibration signal corresponding to the response information.

[0199] In one optional implementation of this application embodiment, the interactive device 300 further includes: a recording module;

[0200] The recording module is used to generate a dialogue record based on the text information and the response information.

[0201] In one optional implementation of this application, the dialogue record is a partial dialogue segment from a multi-turn dialogue record.

[0202] It should be understood that the device embodiments and the foregoing method embodiments can correspond to each other, and similar descriptions can be found in the first aspect of the method embodiments. To avoid repetition, further details are omitted here. Specifically, Figure 6 The device 300 shown can perform Figure 1 The corresponding method embodiments, and the foregoing and other operations and / or functions of each module in device 300 are respectively implemented to achieve Figure 1 For the sake of brevity, the corresponding processes in each method are not described in detail here.

[0203] The apparatus 300 of this application embodiment has been described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that this functional module can be implemented in hardware, in software instructions, or in a combination of hardware and software modules. Specifically, the steps of the first aspect method embodiment in this application can be completed by integrated logic circuits in the processor's hardware and / or by software instructions. The steps of the first aspect method disclosed in this application embodiment can be directly embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the first aspect method embodiment described above.

[0204] Figure 7This is a schematic block diagram of an electronic device provided as an embodiment of this application. Figure 7 The electronic device shown may include a memory 410 and a processor 420. The memory 410 stores computer programs and transmits the program code to the processor 420. In other words, the processor 420 can call and run the computer program from the memory 410 to implement the interaction method described in the first aspect of the embodiments of this application.

[0205] For example, the processor 420 can be used to execute the interactive method described in the first aspect above according to instructions in the computer program.

[0206] In some embodiments, the interaction method includes:

[0207] Based on the interaction data input by the user through a physical device, determine the text information corresponding to the interaction data;

[0208] Obtain the response information corresponding to the text information;

[0209] Output the response information.

[0210] In some embodiments, obtaining the response information corresponding to the text information includes:

[0211] The text information is input into a preset application to obtain the response information corresponding to the text information through the preset application.

[0212] In some embodiments, obtaining the response information corresponding to the text information through the preset application includes:

[0213] The preset application performs semantic analysis on the text information to generate response information corresponding to the text information.

[0214] In some embodiments, the preset application includes multiple sub-applications, and the step of inputting the text information into the preset application to obtain response information corresponding to the text information through the preset application includes:

[0215] Determine the scene information corresponding to the text information;

[0216] Based on the scene information corresponding to the text information, the target sub-application is determined from the plurality of sub-applications;

[0217] The text information is input into the target sub-application so that the response information corresponding to the text information can be obtained through the target sub-application.

[0218] In some embodiments, when the physical device is a wearable device, determining the text information corresponding to the interaction data based on the interaction data input by the user through the physical device includes:

[0219] Based on the interaction data input by the user through the wearable device, determine the text information corresponding to the interaction data.

[0220] In some embodiments, the interactive data input by the user through the wearable device includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data.

[0221] In some embodiments, the interactive data input by the user through the wearable device does not include voice data.

[0222] In some embodiments, the wearable device is a ring.

[0223] In some embodiments, the wearable device includes a speaker and a vibration motor, and the output of the response information includes:

[0224] The response information is output through the speaker of the wearable device; and / or,

[0225] The wearable device's vibration motor outputs a vibration signal corresponding to the response information.

[0226] In some embodiments, the method further includes:

[0227] A dialogue record is generated based on the text information and the response information.

[0228] In some embodiments, the dialogue record is a portion of a dialogue segment from a multi-turn dialogue record.

[0229] In some embodiments of this application, the processor 420 may include, but is not limited to:

[0230] General-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0231] In some embodiments of this application, the memory 410 includes, but is not limited to:

[0232] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0233] In some embodiments of this application, the computer program may be divided into one or more modules, which are stored in the memory 410 and executed by the processor 420 to complete the interactive method provided in this application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device.

[0234] like Figure 7 As shown, the electronic device 400 may further include:

[0235] Transceiver 430, which can be connected to processor 420 or memory 410.

[0236] The processor 420 can control the transceiver 430 to communicate with other devices; specifically, it can send information or data to other devices or receive information or data sent by other devices. The transceiver 430 may include a transmitter and a receiver. The transceiver 430 may further include antennas, and the number of antennas may be one or more.

[0237] It should be understood that the various components in the electronic device are connected through a bus system, which includes a data bus, a power bus, a control bus, and a status signal bus.

[0238] This application also provides a computer storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to perform the interactive method described in the first aspect above.

[0239] In some embodiments, the interaction method includes:

[0240] Based on the interaction data input by the user through a physical device, determine the text information corresponding to the interaction data;

[0241] Obtain the response information corresponding to the text information;

[0242] Output the response information.

[0243] In some embodiments, obtaining the response information corresponding to the text information includes:

[0244] The text information is input into a preset application to obtain the response information corresponding to the text information through the preset application.

[0245] In some embodiments, obtaining the response information corresponding to the text information through the preset application includes:

[0246] The preset application performs semantic analysis on the text information to generate response information corresponding to the text information.

[0247] In some embodiments, the preset application includes multiple sub-applications, and the step of inputting the text information into the preset application to obtain response information corresponding to the text information through the preset application includes:

[0248] Determine the scene information corresponding to the text information;

[0249] Based on the scene information corresponding to the text information, the target sub-application is determined from the plurality of sub-applications;

[0250] The text information is input into the target sub-application so that the response information corresponding to the text information can be obtained through the target sub-application.

[0251] In some embodiments, when the physical device is a wearable device, determining the text information corresponding to the interaction data based on the interaction data input by the user through the physical device includes:

[0252] Based on the interaction data input by the user through the wearable device, determine the text information corresponding to the interaction data.

[0253] In some embodiments, the interactive data input by the user through the wearable device includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data.

[0254] In some embodiments, the interactive data input by the user through the wearable device does not include voice data.

[0255] In some embodiments, the wearable device is a ring.

[0256] In some embodiments, the wearable device includes a speaker and a vibration motor, and the output of the response information includes:

[0257] The response information is output through the speaker of the wearable device; and / or,

[0258] The wearable device's vibration motor outputs a vibration signal corresponding to the response information.

[0259] In some embodiments, the method further includes:

[0260] A dialogue record is generated based on the text information and the response information.

[0261] In some embodiments, the dialogue record is a portion of a dialogue segment from a multi-turn dialogue record.

[0262] This application also provides a computer program product containing program instructions that, when executed on an electronic device, cause the electronic device to perform the interaction method described in the first aspect above.

[0263] In some embodiments, the interaction method includes:

[0264] Based on the interaction data input by the user through a physical device, determine the text information corresponding to the interaction data;

[0265] Obtain the response information corresponding to the text information;

[0266] Output the response information.

[0267] In some embodiments, obtaining the response information corresponding to the text information includes:

[0268] The text information is input into a preset application to obtain the response information corresponding to the text information through the preset application.

[0269] In some embodiments, obtaining the response information corresponding to the text information through the preset application includes:

[0270] The preset application performs semantic analysis on the text information to generate response information corresponding to the text information.

[0271] In some embodiments, the preset application includes multiple sub-applications, and the step of inputting the text information into the preset application to obtain response information corresponding to the text information through the preset application includes:

[0272] Determine the scene information corresponding to the text information;

[0273] Based on the scene information corresponding to the text information, the target sub-application is determined from the plurality of sub-applications;

[0274] The text information is input into the target sub-application so that the response information corresponding to the text information can be obtained through the target sub-application.

[0275] In some embodiments, when the physical device is a wearable device, determining the text information corresponding to the interaction data based on the interaction data input by the user through the physical device includes:

[0276] Based on the interaction data input by the user through the wearable device, determine the text information corresponding to the interaction data.

[0277] In some embodiments, the interactive data input by the user through the wearable device includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data.

[0278] In some embodiments, the interactive data input by the user through the wearable device does not include voice data.

[0279] In some embodiments, the wearable device is a ring.

[0280] In some embodiments, the wearable device includes a speaker and a vibration motor, and the output of the response information includes:

[0281] The response information is output through the speaker of the wearable device; and / or,

[0282] The wearable device's vibration motor outputs a vibration signal corresponding to the response information.

[0283] In some embodiments, the method further includes:

[0284] A dialogue record is generated based on the text information and the response information.

[0285] In some embodiments, the dialogue record is a portion of a dialogue segment from a multi-turn dialogue record.

[0286] When implemented using software, it can be implemented entirely or partially as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0287] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0288] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0289] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. For example, the functional modules in the various embodiments of this application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0290] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0291] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An interaction method, characterized in that, include: Based on the interaction data input by the user through a physical device, determine the text information corresponding to the interaction data; Obtain the response information corresponding to the text information; Output the response information.

2. The method according to claim 1, characterized in that, The step of obtaining the response information corresponding to the text information includes: The text information is input into a preset application to obtain the response information corresponding to the text information through the preset application.

3. The method according to claim 2, characterized in that, The step of obtaining the response information corresponding to the text information through the preset application includes: The preset application performs semantic analysis on the text information to generate response information corresponding to the text information.

4. The method according to claim 2, characterized in that, The preset application includes multiple sub-applications. The step of inputting the text information into the preset application to obtain response information corresponding to the text information through the preset application includes: Determine the scene information corresponding to the text information; Based on the scene information corresponding to the text information, the target sub-application is determined from the plurality of sub-applications; The text information is input into the target sub-application so that the response information corresponding to the text information can be obtained through the target sub-application.

5. The method according to claim 1, characterized in that, When the physical device is a wearable device, determining the text information corresponding to the interaction data based on the interaction data input by the user through the physical device includes: Based on the interaction data input by the user through the wearable device, determine the text information corresponding to the interaction data.

6. The method according to claim 5, characterized in that, The interactive data input by the user through the wearable device includes at least one of the following: touch data, button data, pressure-sensitive data, and inertial measurement data.

7. The method according to claim 5, characterized in that, The interactive data input by the user through the wearable device does not include voice data.

8. The method according to claim 5, characterized in that, The wearable device is a ring.

9. The method according to claim 5, characterized in that, The wearable device includes a speaker and a vibration motor, and the output of the response information includes: The response information is output through the speaker of the wearable device; and / or, The wearable device's vibration motor outputs a vibration signal corresponding to the response information.

10. The method according to claim 1, characterized in that, The method further includes: A dialogue record is generated based on the text information and the response information.

11. The method according to claim 10, characterized in that, The dialogue record is a partial dialogue segment from a multi-turn dialogue record.

12. An interactive device, characterized in that, include: The text determination module is used to determine the text information corresponding to the interaction data input by the user through a physical device. The information acquisition module is used to acquire the response information corresponding to the text information; An interactive response module is used to output the response information.

13. An electronic device, characterized in that, include: A processor and a memory, the memory for storing a computer program, the processor for calling and running the computer program stored in the memory to perform the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, Used to store a computer program that causes a computer to perform the method as described in any one of claims 1 to 11.

15. A computer program product containing program instructions, characterized in that, When the program instructions are executed on the electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1 to 11.

Images