Human-computer interaction method and related device suitable for young children
By collecting the needs information of young children and the environmental sounds, prompt words are automatically generated, which solves the problem of high threshold of human-computer interaction for young children in the existing technology and achieves a more friendly interactive experience.
Patent Information
- Application Number
- CN202411503430.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2044-10-25
AI Technical Summary
Existing human-computer interaction products based on large models have a high threshold for use by young children and require users to design prompt words, resulting in unfriendly interactions.
Collect user input demand information and environmental sounds as prompt elements, automatically generate prompt words corresponding to the target function, and then generate reply content to reduce dependence on users.
It lowers the threshold for human-computer interaction, improves convenience for young children, and achieves natural interaction through the combination of ambient sound and user input.
Smart Images
Figure CN119311242B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a human-computer interaction method, apparatus, device, storage medium, and program product suitable for young children. Background Art
[0002] With the development of artificial intelligence technology, interactive products based on large-scale models (LSMs) are becoming increasingly common. Current interactive products require users to design prompts during the human-computer interaction process. This makes these products difficult for users to use, making them particularly unfriendly for young children. Summary of the Invention
[0003] In view of the above problems, this application provides a human-computer interaction method, device, equipment, storage medium and program product suitable for young children to improve the convenience of human-computer interaction for young children. The specific solution is as follows:
[0004] In a first aspect, the present application provides a human-computer interaction method suitable for young children, the method comprising:
[0005] During the execution of the target function selected by the user, prompt elements are collected, wherein the prompt elements include at least one of the following: user input requirement information, environmental sound; the target function is any one of several functions provided by the human-computer interaction device;
[0006] generating a prompt word corresponding to the target function according to the prompt element;
[0007] Generate and output reply content corresponding to the target function based on the prompt word.
[0008] In a possible implementation, the target function is triggered to run in the following manner:
[0009] Display multiple first-class interaction interfaces, where different first-class interaction interfaces correspond to different interaction dimensions;
[0010] In response to a selection operation on any one of the first-type interaction interfaces, a plurality of second-type interaction interfaces are displayed, where different second-type interaction interfaces correspond to different functions;
[0011] In response to a selection operation on any second-type interactive interface, a target function is executed; the target function is a function corresponding to any second-type interactive interface.
[0012] In a possible implementation, when the prompt element includes an ambient sound, generating a prompt word corresponding to the target function according to the prompt element includes:
[0013] Generate a text based on the environmental sound, the text including at least one of the following: an onomatopeia representing the environmental sound, and an object corresponding to the environmental sound;
[0014] Obtaining a prompt word template corresponding to the target function;
[0015] If the prompt element only includes the ambient sound, the text is added to the prompt word template to obtain the prompt word corresponding to the target function;
[0016] If the prompt element includes demand information input by the user, the demand information and the text are added to the prompt word template to obtain the prompt word corresponding to the target function.
[0017] In a possible implementation, the collection prompt elements include:
[0018] Collecting prompt elements corresponding to the interaction dimension to which the target function belongs;
[0019] Among them, the functions under different interaction dimensions are different; the components of the prompt elements corresponding to different interaction dimensions are the same or different.
[0020] In a possible implementation, the target function is a function of performing multiple rounds of interaction with the user, and the method further includes:
[0021] Recording rounds of interaction with the user;
[0022] After the number of rounds of interaction with the user reaches a preset number, the interaction ends.
[0023] In a possible implementation, the method further includes:
[0024] Prompt information is displayed, where the prompt information at least represents the remaining interaction rounds.
[0025] In a possible implementation, the target function is a knowledge question-answering function; after generating the reply content, the method further includes:
[0026] Perform keyword extraction on the reply content to obtain a number of keywords;
[0027] screening out at least one target keyword that does not match the user's knowledge scope from the plurality of keywords;
[0028] A question containing the target keyword is generated and output based on the target keyword.
[0029] A second aspect of the present application provides a human-computer interaction device suitable for young children, the device comprising:
[0030] a collection module, configured to collect prompt elements during the process of executing a target function selected by the user, wherein the prompt elements include at least one of the following: user input requirement information and environmental sounds; the target function is any one of several functions provided by the human-computer interaction device;
[0031] A generating module, configured to generate a prompt word corresponding to the target function according to the prompt element;
[0032] The reply module is used to generate and output reply content corresponding to the target function based on the prompt word.
[0033] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the human-computer interaction method suitable for young children according to the above-mentioned first aspect or any implementation method of the first aspect.
[0034] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:
[0035] The memory is used to store computer programs;
[0036] The processor is used to execute the computer program so that the electronic device can implement the human-computer interaction method suitable for young children according to the above-mentioned first aspect or any implementation method of the first aspect.
[0037] In a fifth aspect, the present application provides a computer storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the human-computer interaction method suitable for young children according to the first aspect or any implementation of the first aspect.
[0038] By means of the above technical solution, the human-computer interaction method, apparatus, device, storage medium and program product provided by the present application are suitable for young children. In the process of running the target function selected by the user, prompt elements are collected. The prompt elements include at least one of the following: user-input demand information and environmental sounds. Prompt words corresponding to the target function are generated according to the prompt elements, and reply content corresponding to the target function is generated and output based on the prompt words. In the process of running the target function, the present application does not require the user to design prompt words. Instead, prompt elements (user demand information and / or environmental sounds) are collected, prompt words corresponding to the target function are automatically generated based on the collected prompt elements, and reply content corresponding to the target function is generated and output based on the prompt words. In this human-computer interaction solution, input information is not limited to natural language input by the user, but can also include environmental sounds. Moreover, prompt words are not required to be designed by the user, but are automatically generated, thereby lowering the threshold for human-computer interaction and improving the convenience of human-computer interaction for young children. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.
[0040] Figure 1 A flowchart of an implementation of the human-computer interaction method for young children provided in this application;
[0041] Figure 2 An example of the interactive interface provided for this application;
[0042] Figure 3 A flowchart for generating prompt words corresponding to a target function according to prompt elements provided by the present application when the prompt elements include ambient sounds;
[0043] Figure 4 Examples of four human-computer interaction interfaces after a young child user selects the anime-style function under the AI painting dimension provided in this application;
[0044] Figure 5 A schematic diagram of the structure of a human-computer interaction device suitable for young children provided in this application;
[0045] Figure 6 A schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION
[0046] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.
[0047] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0048] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0049] The human-computer interaction method and device for young children provided in this application can be applied to an electronic device, which is configured with an application based on a large model. The electronic device may be deployed with a large model or may not be deployed with a large model, but can communicate with a cloud device configured with a large model through the application.
[0050] Large models are machine learning models with numerous parameters and complex structures, capable of processing large amounts of data. By processing massive amounts of data, large models can accurately represent data distribution and learn complex features, thereby improving their accuracy, generalization, and ability to handle complex problems.
[0051] Currently, applications based on large models require users to design prompts based on their needs. The application then inputs the prompts into the large model, which then generates responses based on the received prompts. The quality of these responses depends on the user's ability to design the prompts. Clearly, current human-computer interaction methods have a certain user barrier to entry. Even adults cannot easily master large models, and the challenge is even greater for young children. Even large models trained for children have a high barrier to entry to automatically generate the content desired by the user, making them particularly unfriendly to children.
[0052] This application is proposed to improve the convenience of human-computer interaction for young children.
[0053] like Figure 1 As shown in FIG. 1 , a flowchart of an implementation of a human-computer interaction method for young children provided in an embodiment of the present application may include:
[0054] Step S101: During the process of running the target function selected by the user, prompt elements are collected, which include at least one of the following: user input requirement information and environmental sound.
[0055] The target function is any one of several functions provided by the human-computer interaction device.
[0056] In this application, the human-computer interaction device provides several functions for the user to select. After the user selects one of the functions (referred to as the target function for ease of description and distinction), the human-computer interaction device begins to execute the target function. During the execution of the target function, the human-computer interaction device collects prompt elements.
[0057] There are multiple ways for users to input their needs. These include using a data input device (e.g., a keyboard, either physical or virtual) (in which case, the needs are collected in text form), or using voice input (in which case, voice recognition is performed on the collected voice to obtain text). When users input their needs, there's no need to design prompts; they simply need to express their needs according to their daily habits.
[0058] Ambient sounds include, but are not limited to, sounds made by animals or objects, such as a dog barking, music played by a toy, or the sounds of a toy barking; and the sounds of objects colliding, such as slapping a table, the rubbing of a chair against the floor, or the bouncing of a ball. Ambient sounds can be user-initiated (e.g., a user operating an electronic device to play music), or they can be non-user-initiated, such as sounds made by animals, other devices, or objects near the electronic device due to non-human factors.
[0059] Optionally, the human-computer interaction device can collect both user demand information and environmental sounds during the process of running the target function. In this case, if the user does not input demand information, only environmental sounds may be collected, that is, the user demand information in the collected prompt element is empty; if there is no environmental sound, only the demand information input by the user is collected, that is, the environmental sound in the collected prompt element is empty. Of course, if the user neither inputs demand information nor environmental sounds, and there is no other environmental sounds around the electronic device, the collected prompt element is empty, and the user can be prompted to input demand information or environmental sounds. In this implementation, the human-computer interaction device collects user demand information and environmental sounds regardless of what function it runs, but the specific type of information collected is determined according to actual conditions.
[0060] Optionally, during the execution of a target function, the human-computer interaction device may determine the components of a prompt element based on preset rules, and then determine the information to be collected based on the determined components of the prompt element. For example, if the user pre-sets the components of the prompt element, the components of the prompt element may be determined based on the user's settings. Alternatively, the components of the prompt element may be determined based on the target function. For example, each target function corresponds to a specific component of the prompt element, and the components of the prompt element corresponding to different target functions may be the same or different. The components of the prompt element represent which of the following information the prompt element includes: user-input demand information, ambient sound. In this example, if the components of the prompt element only include the demand information input by the user, and the user inputs the demand information via voice, noise reduction processing is required on the collected audio to filter out the collected ambient sound and retain only the user's voice. Similarly, if the components of the prompt element only include ambient sound, and the user inputs the demand information via voice, noise reduction processing is required on the collected audio to filter out the collected user's voice and retain only the ambient sound. If the components of the prompt element include both the user-input demand information and ambient sound, noise reduction processing is not required.
[0061] Step S102: Generate prompt words corresponding to the target function according to the prompt elements.
[0062] In this application, prompt words are automatically generated according to prompt elements and target functions, and users no longer need to design prompt words.
[0063] Step S103: Generate and output reply content corresponding to the target function based on the prompt word.
[0064] The prompt words can be input into the big model, and the big model generates reply content corresponding to the target function based on the prompt words, and the reply content generated by the big model is output to the user.
[0065] The human-computer interaction method suitable for young children provided in the embodiment of the present application does not require the user to design prompt words during the operation of the target function. Instead, prompt elements (user demand information and / or environmental sounds) are collected, and prompt words corresponding to the target function are automatically generated based on the collected prompt elements. Then, response content corresponding to the target function is generated and output based on the prompt words. In this human-computer interaction solution, input information is not limited to natural language input by the user, but can also include environmental sounds. Moreover, the user does not need to design prompt words, but prompt words are automatically generated, thereby lowering the threshold for human-computer interaction and improving the convenience of human-computer interaction for young children.
[0066] In an optional embodiment, the target function can be triggered to run in the following manner:
[0067] Multiple first-class interaction interfaces are displayed, and different first-class interaction interfaces correspond to different interaction dimensions.
[0068] This application divides the functions provided by the human-computer interaction device into multiple interaction dimensions. For each interaction dimension, an interaction interface (referred to as a first-class interaction interface for ease of description and distinction) is provided. Different interaction dimensions correspond to different first-class interaction interfaces, allowing users to select the interaction dimension.
[0069] like Figure 2 The above is an example of an interactive interface provided in an embodiment of the present application. In this example, the interactive interface includes multiple first-class interactive interfaces, and the multiple interactive dimensions may include but are not limited to: AI learning assistant, AI painting, challenge simulator, AI storytelling, etc.
[0070] In response to a selection operation on any first-type interaction interface, a plurality of second-type interaction interfaces are displayed, and different second-type interaction interfaces correspond to different functions.
[0071] Each dimension corresponds to one or more functions. Different dimensions correspond to different functions. For each function, an interactive interface (referred to as a second-type interactive interface for ease of description and distinction) is set up. Different functions correspond to different second-type interactive interfaces, allowing users to select the function they want to use.
[0072] For example, if the user selects the "AI Painting" interaction dimension, the displayed second-category interaction interfaces may include interfaces for different painting styles, such as comic style, traditional Chinese style, clay style, and anime style. In other words, different second-category interaction interfaces correspond to different painting functions, and different painting functions are used to achieve different painting styles.
[0073] In response to a selection operation on any second-type interactive interface, a target function is executed; the target function is a function corresponding to any of the above-mentioned second-type interactive interfaces.
[0074] After the user selects any second-type interactive interface, the function corresponding to the second-type interactive interface becomes the target function.
[0075] By dividing several functions into different interaction dimensions, it is easier for users to quickly find the functions they want to use, further improving the convenience of human-computer interaction for young children.
[0076] In an optional embodiment, when the prompt element only includes the requirement information input by the user, one implementation method of generating the prompt word corresponding to the target function based on the prompt element may be:
[0077] Get the prompt word template corresponding to the target function.
[0078] In this embodiment, different prompt word templates are pre-set for different functions. The prompt word template corresponding to each function records the factors that the macro model needs to consider in implementing the function based on the prompt elements. Of course, in the prompt word template, the "prompt element" is a slot that needs to be filled, which is used to fill the prompt element collected during the process of running the target function selected by the user.
[0079] For example, if the target function is to generate comic-style drawings, the factors that need to be considered by the large model in the prompt word template may include but are not limited to the following aspects: style, lens focal length, viewing angle, etc.
[0080] For example, if the target function is storytelling, the factors that need to be considered by the large model in the prompt word template may include but are not limited to the following aspects: characters, time, place, scene, story length, etc.
[0081] The user input requirement information is added to the prompt word template to obtain the prompt word corresponding to the target function.
[0082] In an optional embodiment, when the prompt element includes environmental sound, a flowchart for realizing the generation of prompt words corresponding to the target function according to the prompt element is as follows: Figure 3 As shown, this may include:
[0083] Step S301: Generate text based on the environmental sound, where the text includes at least one of the following: an onomatopeia representing the environmental sound, and an object corresponding to the environmental sound.
[0084] Alternatively, the ambient sound can be input into a speech recognition model to obtain a speech recognition result, which is an onomatopeia representing the ambient sound. The onomatopeia can be input into an object recognition model to obtain the object corresponding to the ambient sound. Alternatively, the ambient sound and the onomatopeia can be input into an object recognition model to obtain the object corresponding to the ambient sound.
[0085] The object corresponding to the environmental sound may be a sound source of the environmental sound (an animal or an object, etc.).
[0086] For example, if the environmental sound is a dog barking, the onomatopeia can be "woof woof", and the object corresponding to the environmental sound can be: dog, puppy or big dog, etc.
[0087] For example, if the environmental sound is the sound of basketball bouncing, the onomatopeia can be "dong dong dong", and the object corresponding to the environmental sound can be: ball, leather ball or basketball, etc.
[0088] Step S302: Obtain a prompt word template corresponding to the target function.
[0089] This application pre-sets different prompt word templates for different functions. The prompt word template corresponding to each function records the factors that the large model needs to consider to implement any function based on the prompt elements. Of course, in the prompt word template, "prompt element" is a slot that needs to be filled, which is used to fill the prompt elements collected during the process of running the target function selected by the user.
[0090] Step S303: If the prompt element only includes environmental sounds, the text generated based on the environmental sounds is added to the prompt word template to obtain the prompt word corresponding to the target function; if the prompt element includes user-entered demand information, the demand information and the text generated based on the environmental sounds are added to the prompt word template to obtain the prompt word corresponding to the target function.
[0091] In an optional embodiment, one implementation of the above-mentioned collection prompt element may be:
[0092] Collect prompt elements corresponding to the interaction dimension to which the target function belongs.
[0093] Among them, the functions under different interaction dimensions are different; the components of the prompt elements corresponding to different interaction dimensions are the same or different.
[0094] When the functions provided by the human-computer interaction device are divided into multiple interaction dimensions, the components of the prompt elements can be pre-set for each interaction dimension. In this way, the components of the prompt elements that need to be collected for different functions within the same interaction dimension are the same, and the components of the prompt elements that need to be collected for different interaction dimensions can be the same or different.
[0095] Compared with setting the components of the prompt elements corresponding to each function, setting the components of the prompt elements corresponding to the interaction dimensions reduces the amount of storage units occupied by configuration information while meeting user needs.
[0096] Optionally, if the target function's interaction dimension is story generation (i.e., storytelling), the prompt elements consist of user-inputted request information and ambient sounds. Specifically, if the target function's interaction dimension is story generation, both user-inputted request information and ambient sounds need to be collected. For other interaction dimensions (e.g., simulator challenge, article generation, or poem generation), the prompt elements may only include user-inputted request information.
[0097] In an optional embodiment, the target function is a function of performing multiple rounds of interactions with the user, such as simulating shopping bargaining, simulating asking for leave from a teacher, simulating borrowing things from classmates, etc.
[0098] In traditional multi-round interaction, there will be unlimited interactions with the user, which is not conducive to the ability development of young children. In order to encourage young children to actively think during the simulation challenge and improve their abilities, this application also records the number of rounds of interaction with the user when the target function is a function that interacts with the user in multiple rounds;
[0099] After the number of rounds of interaction with the user reaches the preset number, the interaction ends.
[0100] By controlling the number of rounds of interaction with users, young children can be encouraged to think about solutions to problems, which is conducive to improving their abilities.
[0101] Furthermore, a prompt message may be displayed, which at least indicates the remaining interaction rounds, so that the user can perceive the interaction progress more clearly.
[0102] As an example, the prompt information represents the completed interaction rounds and the remaining interaction rounds.
[0103] The prompt information may be a number, including: a first number representing a completed interaction round, and a second number representing a remaining interaction round.
[0104] As an example, the prompt information represents the target total interaction rounds (ie, the maximum number of interaction rounds), the completed interaction rounds, and the remaining interaction rounds.
[0105] The prompt information may be a progress bar, the total length of which represents the target total number of interactions, and the completed interaction rounds and the remaining interaction rounds are marked in different colors on the progress bar.
[0106] In an optional embodiment, when the target function is a question-and-answer function, after outputting the reply content, the human-computer interaction method of the present application may further include:
[0107] Perform keyword extraction on the reply content to obtain a number of keywords. The keywords can be extracted using existing keyword extraction methods, and this application does not specifically limit the keyword extraction method.
[0108] At least one target keyword that does not match the user's knowledge scope is screened out from the plurality of keywords.
[0109] The user's knowledge scope may be determined based on at least one of the following: the user's age (different ages correspond to different knowledge scopes), the user's grade (different grades correspond to different knowledge scopes), and the user's question and answer history.
[0110] Keywords that do not match the user's knowledge range refer to keywords that are not within the user's knowledge range.
[0111] Generate and output questions containing target keywords based on target keywords.
[0112] As an example, the question containing the target keyword may be a question asking about the meaning of the target keyword, or a question asking about the function of the thing represented by the target keyword, etc.
[0113] After outputting the reply content, this application generates and outputs questions based on keywords in the reply content that are beyond the user's knowledge range, guiding the user to have an in-depth understanding of the reply content.
[0114] Furthermore, the human-computer interaction method of the present application may further include:
[0115] In response to a selection operation for any question, the question is used as a prompt element and a prompt word corresponding to the target function is generated. Based on the prompt word, a reply content for the question corresponding to the target function is generated and output.
[0116] like Figure 4 As shown, there are four examples of human-computer interaction interfaces after a young child user selects the cartoon style function under the AI painting dimension provided in an embodiment of the present application.
[0117] In this example, a young child can press and hold the screen (anywhere, not specifically) to trigger the electronic device's voice collection device to capture their voice. After the user finishes inputting their voice and stops pressing the screen, the electronic device sends the collected user voice to a cloud device. The cloud device converts the user voice into text and sends the text to the electronic device for display. The cloud device also adds the text to the prompt word template corresponding to the anime-style function to obtain the target prompt word. This target prompt word is then input into a large model to generate an image generated by the large model. The cloud device then sends the image to the electronic device for display.
[0118] Corresponding to the method embodiment, the present application also provides a human-computer interaction device suitable for young children. A structural schematic diagram of the human-computer interaction device suitable for young children provided in the embodiment of the present application is as follows: Figure 5 As shown, this may include:
[0119] Collection module 501, generation module 502 and response module 503;
[0120] The collection module 501 is used to collect prompt elements during the process of running the target function selected by the user, and the prompt elements include at least one of the following: user input demand information and environmental sound; the target function is any function provided by the human-computer interaction device;
[0121] The generating module 502 is used to generate a prompt word corresponding to the target function according to the prompt element;
[0122] The reply module 503 is used to generate and output reply content corresponding to the target function based on the prompt word.
[0123] The human-computer interaction device suitable for young children provided in the embodiment of the present application does not require the user to edit prompt words during the operation of the target function. Instead, prompt elements (user demand information and / or environmental sounds) are collected, and prompt words corresponding to the target function are automatically generated based on the collected prompt elements. Then, reply content corresponding to the target function is generated and output based on the prompt words. In this human-computer interaction solution, input information is not limited to natural language, but can also include environmental sounds. Moreover, the user does not need to design prompt words, but prompt words are automatically generated, thereby lowering the threshold for human-computer interaction and improving the convenience of human-computer interaction for young children.
[0124] In an optional embodiment, the human-computer interaction device suitable for young children further includes an interaction module for:
[0125] Display multiple first-class interaction interfaces, where different first-class interaction interfaces correspond to different interaction dimensions;
[0126] In response to a selection operation on any one of the first-type interaction interfaces, a plurality of second-type interaction interfaces are displayed, where different second-type interaction interfaces correspond to different functions;
[0127] In response to a selection operation on any second-type interactive interface, a target function is executed; the target function is a function corresponding to any second-type interactive interface.
[0128] In an optional embodiment, when the prompt element includes an ambient sound, the generating module 502 generates the prompt word corresponding to the target function according to the prompt element, which is configured to:
[0129] Generate a text based on the environmental sound, the text including at least one of the following: an onomatopeia representing the environmental sound, and an object corresponding to the environmental sound;
[0130] Obtaining a prompt word template corresponding to the target function;
[0131] If the prompt element only includes the ambient sound, the text is added to the prompt word template to obtain the prompt word corresponding to the target function;
[0132] If the prompt element includes demand information input by the user, the demand information and the text are added to the prompt word template to obtain the prompt word corresponding to the target function.
[0133] In an optional embodiment, when collecting prompt elements, the collection module 501 is used to:
[0134] Collecting prompt elements corresponding to the interaction dimension to which the target function belongs;
[0135] Among them, the functions under different interaction dimensions are different; the components of the prompt elements corresponding to different interaction dimensions are the same or different.
[0136] In an optional embodiment, the human-computer interaction device suitable for young children further includes a recording module for:
[0137] When the target function is a function that performs multiple rounds of interaction with the user, recording the rounds of interaction with the user;
[0138] After the number of rounds of interaction with the user reaches a preset number, the interaction ends.
[0139] In an optional embodiment, the human-computer interaction device suitable for young children further includes an output module for:
[0140] Prompt information is displayed, where the prompt information at least represents the remaining interaction rounds.
[0141] In an optional embodiment, when the target function is a knowledge question and answer function, the reply module 503 is further configured to:
[0142] After generating the reply content, performing keyword extraction on the reply content to obtain a number of keywords;
[0143] screening out at least one target keyword that does not match the user's knowledge scope from the plurality of keywords;
[0144] A question containing the target keyword is generated and output based on the target keyword.
[0145] An electronic device is also provided in an embodiment of the present application. Figure 6 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application can be a pet robot or other electronic devices, such as a children's watch. Figure 6 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.
[0146] like Figure 6As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 602 or programs loaded from a storage device 608 into a random access memory (RAM) 603. When the electronic device is powered on, the RAM 603 also stores various programs and data required for the operation of the electronic device. The processing device 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0147] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Figure 6 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.
[0148] Optionally, the electronic device in the embodiment of the present application may also be an embedded device.
[0149] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the human-computer interaction methods suitable for young children provided in the embodiments of the present application.
[0150] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any one of the human-computer interaction methods suitable for young children provided in the embodiment of the present application.
[0151] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.
[0152] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general-purpose hardware, and of course can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.
[0153] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. Professionals and technicians may use different methods to implement the described functions for each specific solution, but such implementation should not be considered beyond the scope of this application.
[0154] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, training device or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center that includes one or more available media integrations. The available medium can be a magnetic medium, (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive (SSD)).
[0155] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0156] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A human-computer interaction method suitable for young children, characterized in that: The method comprises: During the execution of the target function selected by the user, prompt elements are collected, wherein the prompt elements include at least one of the following: user input requirement information, environmental sound; the target function is any one of several functions provided by the human-computer interaction device; In the case where the prompt element includes an environmental sound, a text is generated according to the environmental sound, the text including at least one of the following: an onomatopeia representing the environmental sound, and an object corresponding to the environmental sound; Obtaining a prompt word template corresponding to the target function; If the prompt element only includes the ambient sound, the text is added to the prompt word template to obtain the prompt word corresponding to the target function; if the prompt element includes the user input demand information, the demand information and the text are added to the prompt word template to obtain the prompt word corresponding to the target function; Input the prompt word into the big model, and the big model generates the reply content corresponding to the target function according to the prompt word; Output the reply content.
2. The method according to claim 1, characterized in that The target function is triggered to run in the following ways: Display multiple first-class interaction interfaces, where different first-class interaction interfaces correspond to different interaction dimensions; In response to a selection operation on any one of the first-type interaction interfaces, a plurality of second-type interaction interfaces are displayed, where different second-type interaction interfaces correspond to different functions; In response to a selection operation on any second-type interactive interface, a target function is executed; the target function is a function corresponding to any second-type interactive interface.
3. The method according to claim 1, characterized in that The collection prompt elements include: Collecting prompt elements corresponding to the interaction dimension to which the target function belongs; Among them, the functions under different interaction dimensions are different; the components of the prompt elements corresponding to different interaction dimensions are the same or different.
4. The method according to claim 3, characterized in that The target function is a function of performing multiple rounds of interaction with the user, and the method further includes: Recording rounds of interaction with the user; After the number of rounds of interaction with the user reaches a preset number, the interaction ends.
5. The method according to claim 4, characterized in that Also includes: Prompt information is displayed, where the prompt information at least represents the remaining interaction rounds.
6. The method according to claim 1, characterized in that The target function is a knowledge question and answer function; after generating the reply content, the method further includes: Perform keyword extraction on the reply content to obtain a number of keywords; screening out at least one target keyword that does not match the user's knowledge scope from the plurality of keywords; A question containing the target keyword is generated and output based on the target keyword.
7. A human-computer interaction device suitable for young children, characterized in that: The device comprises: a collection module, configured to collect prompt elements during the process of executing a target function selected by the user, wherein the prompt elements include at least one of the following: user input requirement information and environmental sounds; the target function is any one of several functions provided by the human-computer interaction device; a generation module configured to, if the prompt element includes an ambient sound, generate text based on the ambient sound, the text including at least one of the following: an onomatopeia representing the ambient sound and an object corresponding to the ambient sound; obtain a prompt word template corresponding to the target function; if the prompt element includes only the ambient sound, add the text to the prompt word template to obtain a prompt word corresponding to the target function; if the prompt element includes user-entered requirement information, add the requirement information and the text to the prompt word template to obtain a prompt word corresponding to the target function; The reply module is used to input the prompt word into the large model, and the large model generates the reply content corresponding to the target function according to the prompt word; and output the reply content.
8. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the human-computer interaction method suitable for young children as claimed in any one of claims 1 to 6.
9. An electronic device, characterized in that: The electronic device comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the human-computer interaction method suitable for young children as described in any one of claims 1 to 6.
10. A computer storage medium, characterized in that The storage medium carries one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the human-computer interaction method suitable for young children as described in any one of claims 1 to 6.