Artificial intelligence-based guidance system and method for electronic product unpacking and setup, and terminal
Through the unboxing and setting guidance system for electronic products based on artificial intelligence, using intelligent mobile terminals and generative artificial intelligence large language model, dynamically guide users to complete unboxing settings, solving the problem that users in the existing technology are difficult to effectively complete unboxing settings. Improves setting efficiency and product stickiness.
Patent Information
- Application Number
- PCT/CN2024/105372
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-08-10
- Filing Date
- 2024-07-13
- Publication Date
- 2025-02-13
AI Technical Summary
During the unboxing and setting up existing electronic products, it is difficult for users to obtain effective help through paper instructions, resulting in low setup efficiency and reduced product stickiness.
The unboxing and setting guidance system for electronic products based on artificial intelligence is adopted, and through intelligent mobile terminals and model servers, the user interaction information is analyzed using a generative artificial intelligence large language model, and the target demonstration page is played dynamically to guide users to complete unboxing settings.
It effectively improves the efficiency of unboxing and use of electronic products, increases product stickiness, and helps users complete unboxing and setting operations smoothly.
Smart Images

Figure CN2024105372_13022025_PF_FP_ABST
Abstract
Description
Artificial intelligence-based electronic product unpacking and setting guidance system, method, and terminal
[0001] This application claims priority to the Chinese patent application filed with the Patent Office of the State Intellectual Property Office of China on August 10, 2023, with application number CN 2023110104824 and entitled “AI-based electronic product unpacking and setting guidance system, method and terminal”, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The embodiments of the present application relate to the field of smart glasses technology, and more particularly to an artificial intelligence-based electronic product unpacking and setting guidance system, method, and smart mobile terminal. Background Art
[0003] Unboxing refers to the process of unpacking the box after purchasing the product, taking out the electronic product packaged inside, and then assembling and setting up the electronic product. With the development of computer technology, smart electronic products are becoming more and more popular, and the structure and functions of smart electronic products are becoming more and more complex. However, existing paper manuals usually only have a few words, and it is difficult for users to get effective help from paper manuals during the unboxing process of electronic products. In particular, when the manual description is unclear, the electronic product setup process is difficult, or technical failures are encountered, users are often unable to correctly set up and use the electronic product, which affects the efficiency of unboxing, setting up and using the electronic product, causing users to have some unpleasant feelings and experiences with the electronic product, thereby reducing product stickiness. Technical issues
[0004] The embodiments of the present application provide an artificial intelligence-based electronic product unpacking and setup guidance system, method, and smart mobile terminal, which are used to improve the efficiency of electronic product unpacking, setup, and use, and increase product stickiness. Technical Solutions
[0005] In one aspect, an embodiment of the present application provides an artificial intelligence-based electronic product unpacking and setup guidance system, the system comprising: an intelligent mobile terminal and a model server, wherein the model server is configured with a generative artificial intelligence large language model, and the intelligent mobile terminal is installed with a client program having multiple demonstration pages;
[0006] The smart mobile terminal is configured to play the demonstration page through the client program to guide the user to perform unpacking and setting operations on the electronic product, obtain interaction information between the user and the client program during the unpacking and setting process, and send text generated based on the interaction information to the model server;
[0007] The model server is configured to parse the text using the generative artificial intelligence language model and return the parsing result to the smart mobile terminal;
[0008] The smart mobile terminal is further configured to determine a target demonstration page according to the analysis result and play the target demonstration page.
[0009] In one aspect, an embodiment of the present application further provides an artificial intelligence-based electronic product unpacking and setting guidance method, which is applied to a smart mobile terminal. The method includes:
[0010] Playing a preset demonstration page by a client program installed on the smart mobile terminal to guide the user to perform unpacking and setting operations on the electronic product, wherein the client program has a plurality of the demonstration pages;
[0011] Obtaining interaction information between the user and the client program during the unboxing and setup process, and sending text generated based on the interaction information to the model server, so that the model server parses the text through a generative artificial intelligence language model and returns the parsing result to the smart mobile terminal;
[0012] A target demonstration page is determined according to the analysis result, and the target demonstration page is played.
[0013] In one aspect, an embodiment of the present application further provides an intelligent mobile terminal, characterized in that it includes: a processor and a non-transitory storage electrically connected to the processor, a wireless communication device, an input device, and an output device;
[0014] One or more computer programs executable by the processor are stored on the non-transitory memory, wherein the computer programs include a plurality of instructions for:
[0015] Playing a demonstration page in the client program through the output device to guide the user to perform unpacking and setting operations on the smart mobile terminal, wherein the client program has a plurality of the demonstration pages;
[0016] Acquiring interaction information between the user and the client program during the unpacking and setup process through the input device, and sending text generated based on the interaction information to the model server through the wireless communication device, so that the model server parses the text through the generative artificial intelligence large language model and obtains a parsing result;
[0017] The analysis result returned by the model server is received through the wireless communication device, a target demonstration page is determined according to the analysis result, and the target demonstration page is played through the output device. Beneficial effects
[0018] In each embodiment of the present application, since the smart mobile terminal can play a demonstration page through the client program to guide the user to perform unboxing and setup operations on the electronic product, and in the process of interaction with the user, the user's intention is analyzed through the generative artificial intelligence large language model, and the target demonstration page is played according to the intention to answer the user's questions, it can effectively help the user complete the unboxing and setup operations, thereby improving the efficiency of unboxing, setup and use of electronic products and increasing product stickiness. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0020] FIG1 is a schematic diagram of the structure of an artificial intelligence-based electronic product unpacking and setting guidance system provided in one embodiment of the present application;
[0021] FIG2 is a flowchart of an artificial intelligence-based electronic product unpacking and setting guidance method provided in one embodiment of the present application;
[0022] FIG3 is a schematic diagram of an application scenario of the method shown in FIG2 ;
[0023] FIG4 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0024] FIG5 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0025] FIG6 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0026] FIG7 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0027] FIG8 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0028] FIG9 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0029] FIG10 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0030] FIG11 is a schematic diagram of a demonstration page in the method shown in FIG2 ;
[0031] FIG12 is a schematic structural diagram of a smart mobile terminal provided in one embodiment of the present application. Modes for Carrying Out the Invention
[0032] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0033] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.
[0034] Furthermore, the terms “first,” “second,” “third,” etc., are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.
[0035] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.
[0036] 1 , which is a schematic diagram of an artificial intelligence-based electronic product unpacking and setup guidance system according to an embodiment of the present invention. As shown in FIG1 , the guidance system 100 includes a smart mobile terminal 110 and a model server 120 .
[0037] Smart mobile terminal 110 may include, but is not limited to, a cellular phone, a smartphone, other wireless communication devices, a personal digital assistant (PDA), an audio player, other media players, a music recorder, a video recorder, a camera, other media recorders, a smart radio, a laptop computer, a personal digital assistant (PDA), a portable multimedia player (PMP), a Moving Picture Experts Group (MPEG-1 or MPEG-2) Audio Layer 3 (MP3) player, a digital camera, and a smart wearable device (such as a smart watch, a smart bracelet, etc.). The smart mobile terminal 112 may also be installed with an Android, iOS, or other operating system.
[0038] Model server 120 can be a single server or a distributed server cluster consisting of multiple servers, equipped with a Generative Artificial Intelligence Large Language Model (GAILLM). For ease of understanding, these models are collectively referred to as GAILLM servers. A Generative Artificial Intelligence Large Language Model (GAILLM) is a pre-trained language model with billions of parameters (B+) (e.g., GPT-3, Bloom, LLaMA) derived from artificial intelligence technologies that can generate content, solutions, or new concepts. These models are typically trained on large amounts of data using advanced algorithms such as deep learning and neural networks.
[0039] The GAILLM can be, for example but not limited to: Open AI's ChatGPT, Google's Bard, and other models with similar functions. The GAILLM is trained by taking a large number of characters or character groups and their corresponding meanings as samples. The characters may include: characters or character groups converted from user voices, and the meanings corresponding to the characters or character groups may include incomplete semantics and complete semantics corresponding to the characters or character groups. Alternatively, the characters may also include: characters or character groups input by the user, and the meanings corresponding to the characters or character groups may include complete semantics corresponding to the characters or character groups. Alternatively, the characters or character groups may also include: characters or character groups used to describe user operations, and the meanings corresponding to the characters or character groups may include the intentions corresponding to the user operations.
[0040] Specifically, a client program with multiple preset demonstration pages is installed on the smart mobile terminal 110. The demonstration page contains preset guidance information, which includes: information for introducing the electronic product 130 and / or at least one of text, demonstration animation and voice for guiding the user to perform one or more operations related to unpacking. The one or more operations related to unpacking may include, but are not limited to: assembling the electronic product 130, configuring parameters for the electronic product 130, using the electronic product 130 and troubleshooting and repairing the electronic product 130, introducing the functions of the electronic product 130 to the user, guiding the user on how to use the electronic product 130, etc. The smart mobile terminal 110 generally refers to a smart phone, a smart watch, a smart bracelet, etc. In some specific cases, the smart mobile terminal 110 may be an electronic product 130.
[0041] The smart mobile terminal 110 is configured to play the demonstration page through the client program to guide the user through the unboxing and setup operations of the electronic product, obtain interaction information between the user and the client program during the unboxing and setup process, and send text generated based on the interaction information to the model server 120. The electronic product 130 may include, but is not limited to, smart wearable devices (such as smart glasses, smart watches, smart earrings, smart bracelets, smart clothing, and smart shoes and hats), as well as other smart non-wearable devices (such as smart cameras, smart appliances, smartphones, tablets, laptops, and desktop computers). The text can be generated by the smart mobile terminal 110 based on the interaction information. Alternatively, the smart mobile terminal 110 can also send the interaction information to other external devices, such as a cloud server or the electronic product 130, and the other external device can generate the text based on the interaction information.
[0042] The GAILLM server 120 is configured to parse the text through GAILLM and return the parsing result to the smart mobile terminal 110. Specifically, GAILLM may perform semantic parsing on the text and use the semantics contained in the parsed text as the parsing result.
[0043] The smart mobile terminal 110 is further configured to determine a target presentation page based on the parsing result and play the target presentation page, for example, by displaying the text and / or image information in the target presentation page on a display screen, playing the sound in the target presentation page through a speaker, and so on. Optionally, the smart mobile terminal 110 further stores a file recording the associations between multiple preset presentation pages in the client program APP and different parsing results (e.g., different semantics). The target presentation page can be determined by querying the file recording the associations between the multiple preset presentation pages and different parsing results. Specifically, the file recording the associations between the multiple preset presentation pages and different parsing results can be part of the APP, and the APP determines the target presentation page by querying the file. Alternatively, the file recording the associations between the multiple preset presentation pages and different parsing results can be third-party data stored in the smart mobile terminal 110 that is independent of the APP. Other software modules in the smart mobile terminal 110 determine the target presentation page by querying the file and send relevant data of the target presentation page to the APP, so that the APP plays the target presentation page.
[0044] Optionally, in other embodiments of the present application, the smart mobile terminal 110 is further configured to obtain a download link for the client program, download an installation program for the client program according to the download link, and run the installation program to install the client program on the smart mobile terminal 110, wherein the client program matches the device information of the smart mobile terminal 110. For example, the server may store multiple versions of the client program, each suitable for smartphones with different operating systems.
[0045] Specifically, the smart mobile terminal 110 can obtain the client program download link by scanning a graphic code (e.g., a QR code or barcode) on the electronic product. Alternatively, the smart mobile terminal 110 can obtain the client program download link input by the user via an input device (e.g., a keyboard, touch screen, etc.). Alternatively, the smart mobile terminal 110 can obtain the client program download link based on a user's search operation in an application store.
[0046] When the smart mobile terminal 110 sends a download request to the software storage server according to the download link, it sends the device information of the smart mobile terminal 110 to the software storage server, so that the software storage server sends the installation program of the client program that matches the device information to the smart mobile terminal 110 according to the device information.
[0047] The device information of the smart mobile terminal 110 may include, but is not limited to, at least one of the hardware information, operating system type, operating system version number, and device model of the smart mobile terminal 110 .
[0048] Optionally, in other embodiments of the present application, at least one presentation interface of the multiple presentation pages is a user interaction interface, and the interaction information includes text information input by the user on the user interaction interface.
[0049] Optionally, in other embodiments of the present application, the interaction information includes user voice. The smart mobile terminal 110 is further configured to receive the user voice sent by the electronic product 130, or to obtain the user voice through a built-in microphone and convert the user voice into the text.
[0050] Specifically, the smart mobile terminal 110 can convert the user's voice into corresponding text through a built-in voice-to-text engine. Alternatively, the smart mobile terminal 110 can also send the user's voice to a conversion server to convert the user's voice into corresponding text through a voice-to-text engine configured in the conversion server.
[0051] The smart mobile terminal 110 first determines whether a speech-to-text engine is installed locally based on the installation log. If the speech-to-text engine is installed locally, the smart mobile terminal 110 calls the speech-to-text engine to convert the user's speech into corresponding text. If the speech-to-text engine is not installed locally, the smart mobile terminal 110 sends the user's speech to the conversion server.
[0052] Optionally, in other embodiments of the present application, the interactive information includes personal information input by the user.
[0053] The smart mobile terminal 110 is further configured to generate a virtual character that matches the user's personal information and configure the virtual character into the demonstration page.
[0054] The smart mobile terminal 110 is further configured to synchronously control the virtual character when playing the target demonstration page, so as to interact with the user through the virtual character.
[0055] The virtual character includes a two-dimensional or three-dimensional animated dynamic virtual character image. In addition to the virtual character, the target demonstration page also includes preset guidance information, such as at least one of a text explanation, a demonstration animation, and an explanation voice for the function and usage of the electronic product in question.
[0056] While playing the guidance information in the target demonstration page, the smart mobile terminal 110 can control the virtual character to synchronously make corresponding expressions and / or actions to assist or guide the user to complete the product assembly and / or configuration process, or introduce the product functions to the user and guide the user on how to use the product.
[0057] Optionally, in other embodiments of the present application, the multiple demonstration pages include a first demonstration page for guiding pairing. The smart mobile terminal 110 is further configured to respond to a user operation on the first demonstration page and, through the client program, pair with the electronic product 130 using a short-range wireless communication network. The short-range wireless communication network may include, but is not limited to, a Bluetooth network, a Wi-Fi (Wireless Fidelity) network, an infrared point-to-point communication network (IrDA), a near-field communication (NFC) network, and a ZigBee network.
[0058] Optionally, in other embodiments of the present application, the multiple demonstration pages further include a second demonstration page for guiding new users to register. The smart mobile terminal 110 is further configured to obtain registration information entered by the user on the second demonstration page and perform a user registration operation based on the registration information.
[0059] Optionally, in other embodiments of the present application, the guidance system 100 further includes an application server. A generative artificial intelligence language model for acquiring target operation instructions is configured on the application server. The generative artificial intelligence language model for acquiring target operation instructions is trained using a large number of parsing results and corresponding operation instructions as samples.
[0060] The smart mobile terminal 110 is further configured to send the analysis result to the application server.
[0061] The application server is used to obtain the target operation instruction according to the analysis result through the generative artificial intelligence language model used to obtain the target operation instruction, and send the target operation instruction to the smart mobile terminal 110.
[0062] The smart mobile terminal 110 is further configured to execute the operation indicated by the target operation instruction through the client program, wherein the operation includes at least one of the following: playing the page indicated by the target operation instruction, playing the animation indicated by the target operation instruction, playing the voice indicated by the target operation instruction, displaying the text indicated by the target operation instruction, modifying the configuration parameters of the virtual character, and running the application indicated by the target operation instruction. Modifying the configuration parameters of the virtual character may specifically include, but is not limited to, modifying the image, expression, action, or voice (or voice) of the virtual character to a specified image, expression, action, or voice. Specifically, the user can select a preferred image, expression, action, or voice from multiple alternative images, expressions, actions, or voices of the virtual character pre-installed in the app by clicking in the menu bar provided by the app or using voice commands, thereby personalizing the configuration parameters of the virtual character.
[0063] Alternatively, in other embodiments of the present application, the model server 120 may also send the analysis result and the identity information of the smart mobile terminal 110 to the application server after obtaining the analysis result, so that the application server obtains the target operation instruction according to the analysis result through the generative artificial intelligence large language model for obtaining the target operation instruction, and sends the target operation instruction to the smart mobile terminal 110 according to the identity information of the smart mobile terminal 110.
[0064] Optionally, in other embodiments of the present application, the guidance system 100 further includes a page server, in which a plurality of demonstration pages are stored.
[0065] The smart mobile terminal 110 is further configured to determine, based on the parsing result, whether the target presentation page is included in the multiple presentation pages; if the target presentation page is included in the multiple presentation pages, play the target presentation page; and if the target presentation page is not included in the multiple presentation pages, send description information of the target presentation page to the page server so that the target presentation page is downloaded from the page server. The description information of the target presentation page may include, but is not limited to, a number or a description of the purpose of the target presentation page.
[0066] Optionally, in other embodiments of the present application, the analysis result includes questions raised by the user.
[0067] The smart mobile terminal 110 is also used to determine whether the question is included in the currently played demonstration page, wherein the currently played demonstration page includes multiple alternative questions and hyperlinks to demonstration pages associated with each alternative question; if the currently played demonstration page includes the question, the target demonstration page is played according to the hyperlink; if the currently played demonstration page does not include the question, the question is sent to the application server to determine the target demonstration page through the application server, and the application server determines the target demonstration page based on the question, and sends the identity information of the target demonstration page, or the download link of the target demonstration page, or the data of the target demonstration page to the smart mobile terminal 110.
[0068] The smart mobile terminal 110 is further configured to play the target demonstration page according to the identity information, the download link, or the data of the target demonstration page sent by the application server. The target demonstration page includes: at least one of text, a demonstration animation, and a voice for answering the user's question, a virtual character, and a navigation menu.
[0069] In the system provided in this embodiment, the smart mobile terminal can play a demonstration page through the client program to guide the user to perform unboxing and setting operations on the electronic product. In the process of interaction with the user, the user's intention is analyzed through the generative artificial intelligence large language model, and the target demonstration page is played according to the intention to answer the user's questions, thereby effectively helping the user to complete the unboxing and setting operations, thereby improving the efficiency of unboxing, setting and use of electronic products and increasing product stickiness.
[0070] See Figure 2, which is a flow chart of an artificial intelligence-based electronic product unpacking and setup guidance method provided in one embodiment of the present application. This method can be applied to the smart mobile terminal 110 in the embodiment shown in Figure 1. As shown in Figure 2, the method includes the following steps:
[0071] S301, playing a preset demonstration page through a client program installed on the smart mobile terminal to guide the user to perform unpacking and setting operations on the electronic product;
[0072] The client program has multiple preset demonstration pages. The smart terminal plays the preset demonstration screens through the built-in client program according to the playback instructions, guiding the user to unpack and set up the electronic product.
[0073] The demonstration page includes preset guidance information, including at least one of text, demonstration animation, and voice information for introducing the electronic product and / or guiding the user to perform one or more operations related to unboxing. The one or more operations related to unboxing may include, but are not limited to, assembling the electronic product, configuring parameters of the electronic product, using the electronic product, and troubleshooting and repairing the electronic product.
[0074] Furthermore, in other embodiments of the present application, the method also includes: obtaining a download link of the client program, and downloading the installation program of the client program according to the download link; running the installation program to install the client program on the smart mobile terminal, wherein the client program matches the device information of the smart mobile terminal.
[0075] Specifically, the smart mobile terminal 110 can obtain the client program download link by scanning a graphic code (e.g., a QR code or barcode) on the electronic product. Alternatively, the smart mobile terminal 110 can obtain the client program download link input by the user through an input device (e.g., a keyboard, touch screen, etc.) of the smart mobile terminal 110. Alternatively, the smart mobile terminal 110 can obtain the client program download link based on a user's search operation in an application store.
[0076] S302: Obtain interaction information between the user and the client program during the unpacking and setup process, and send a text generated based on the interaction information to the model server;
[0077] The smart mobile terminal uses the generative artificial intelligence large language model in the model server to analyze the interaction information between the user and the client program during the unboxing and setup process to determine the user's intention.
[0078] The interactive information may include text information input by the user on the demonstration page.
[0079] Alternatively, the interaction information may also include user voice sent by the electronic product or user voice captured by a built-in microphone of the smart mobile terminal. The smart mobile terminal may convert the user voice into text using a built-in voice-to-text engine, or may convert the user voice into text using a voice-to-text engine in an external device (such as a conversion server in the cloud).
[0080] Alternatively, the interaction information may also include associated data of various preset operations of the user on the demonstration page, such as: associated information of options and buttons in the menu bar of the demonstration page clicked by the user, associated information of sliding gestures made by the user on the demonstration page, etc.
[0081] S303: Determine the target demonstration page according to the parsing result returned by the model server, and play the target demonstration page.
[0082] Optionally, in other embodiments of the present application, the method also includes: generating a virtual character that matches the user's personal information, and configuring the virtual character into the demonstration page; and, when playing the target demonstration page, synchronously controlling the virtual character to interact with the user through the virtual character.
[0083] Optionally, in other embodiments of the present application, the multiple demonstration pages include a first demonstration page for guiding pairing, and the method further includes: in response to the user's operation on the first demonstration page, pairing with the electronic product via the client program using a short-range wireless communication network.
[0084] Optionally, in other embodiments of the present application, the multiple demonstration pages include a second demonstration page for guiding new users to register, and the method also includes: obtaining registration information entered by the user on the second demonstration page, and performing user registration operations based on the registration information.
[0085] To facilitate understanding, the guidance method provided by this application is illustrated below with reference to Figures 3 to 11. In one application example, as shown in Figure 3, the guidance method can be used to guide the unpacking and setup operations of smart glasses 200 via a smartphone 110 and a model server 120. It is understood that in addition to unpacking and setup, users can also obtain guidance on the setup operations of smart glasses 200 through this guidance method at any other time or in any scenario.
[0086] Specifically, after removing the smart glasses 200 from the packaging, the user scans the QR code on the smart glasses 200 using the camera on the smartphone 110 to obtain a download link for the client application APP. The smartphone 110 downloads the APP installation program according to the download link and runs it to install the APP on the smartphone 110. The APP is pre-installed with multiple demonstration pages to guide the user through the assembly, configuration, use, troubleshooting and repair of the smart glasses, and reporting repairs.
[0087] It is understandable that different models of smart glasses may have different functions. The smartphone 110 runs the app and automatically plays the start page of the multiple demonstration pages shown in Figure 4 to guide the user to select the model of smart glasses 200. The smartphone 110 determines the corresponding demonstration page based on the model selected by the user, so that in subsequent operations, the target demonstration page can be determined from the corresponding demonstration pages based on the parsing results returned by the model server. Furthermore, if the target demonstration page is determined by other devices (such as the application server mentioned above), the smartphone 110 can send the information about the model of smart glasses 200 selected by the user to the other devices, so that the other devices can determine the target demonstration page based on the model and the parsing results.
[0088] Furthermore, in response to the user clicking the "Next Page" button on the demonstration page shown in FIG. 4 , smartphone 110 plays the demonstration page shown in FIG. 5 to guide the user through new user registration. Smartphone 110 obtains the registration information entered by the user on the demonstration page shown in FIG. 5 and performs the user registration operation based on that registration information. Alternatively, the user can instruct smartphone 110 to jump to the next demonstration page by issuing a voice command "Next Page." The process by which the smartphone uses GAILLM to parse the voice command and determine the corresponding operation can be found in the above-mentioned related content and will not be further described here.
[0089] Furthermore, in response to the user clicking the "Log in later" button in the demonstration page shown in Figure 5, the smartphone 110 plays a navigation page as shown in Figure 6, which includes a virtual character 501, a selection menu 502 (such as, "Yes, please guide me", "No, thank you"), prompt text (such as, "Do you need me to guide you to perform the setup operation?"), a control button 503 and a prompt voice, such as, "Do you need me to guide you to perform the setup operation? Please state your choice, or you can also make a choice by clicking "Yes, please guide me" or "No, thank you" (not shown in Figure 6).
[0090] Furthermore, the smartphone 110 obtains the interaction information between the user and the APP, such as the voice uttered by the user while pressing the control button 503, converts the voice into text, and then sends the text to the model server, and displays the text in the current demonstration page, such as "Yes, this is a good idea" in Figure 6.
[0091] The model server performs semantic analysis on the text through a generative artificial intelligence language model to obtain the user's intention, that is, to perform a navigation operation, and sends the analysis result to the smartphone 110.
[0092] Based on the analysis result, the smartphone 110 confirms and plays a demonstration page, as shown in FIG7 , for guiding the user to pair with the smart glasses 200. The demonstration page shown in FIG7 includes an avatar 701, a demonstration animation 702, prompt text 703, control buttons or a navigation menu 704, and prompt voice, such as the voice corresponding to prompt text 703 (not shown in FIG7 ).
[0093] Afterwards, in response to the user clicking the control button or navigation menu 704 in FIG. 7 , the smartphone 110 plays a demonstration page as shown in FIG. 8 to guide the user through the pairing operation on the smartphone 110 and prompt the pairing progress through voice, text, and animation. After detecting that pairing with the smart glasses 200 is complete, the smartphone 110 plays a demonstration page as shown in FIG. 9 to prompt the user to complete the pairing.
[0094] Furthermore, smartphone 110 captures user interaction information with the demonstration page shown in FIG9 , such as information input by the user clicking the "OK" button or user voice captured via a microphone. It then sends a text containing this interaction information to the model server. The model server parses this text, confirming that the user may wish to ask a question, and then sends the parsing result, including instructions for guiding the user to ask questions, to smartphone 110. Based on this parsing result, smartphone 110 plays the demonstration page shown in FIG10 to guide the user in asking questions.
[0095] As shown in FIG10 , the demonstration page includes multiple navigation menus to help users select questions they need answered, such as "Can you tell me how to turn the phone on and off?" and "How do I adjust the volume?" Furthermore, the demonstration page may include voice prompts, such as, "You can choose from the following questions, or you can press and hold the virtual button on the smart glasses and ask a question related to AirGo." If the user chooses to press and hold the virtual button on the smart glasses and ask a question related to AirGo, the smart glasses 200 capture the user's voice and send it to the smartphone 110. The smartphone 110, using its built-in speech-to-text engine or conversion server, converts the user's voice into text and displays the text on the current demonstration page, such as the question "Can you tell me how to chat on 'Solos Chat'?" shown in FIG10 . Simultaneously, the smartphone 110 sends the text to the model server for semantic analysis. Based on the analysis results returned by the model server, the smart phone 110 determines whether the user's question is a question in the navigation menu. If it is a question in the navigation menu, the smart phone 110 obtains the data of the corresponding demonstration page for playback based on the hyperlink associated with the navigation menu. If it is not a question in the navigation menu, the smart phone 110 determines the target demonstration page as shown in Figure 11 and plays it based on the preset association relationship between different analysis results and demonstration pages.
[0096] It should be noted that FIG. 3 to FIG. 11 are merely examples and are not limited thereto in practical applications.
[0097] For details not covered in the above embodiments of the guidance method, please refer to the relevant descriptions in the above-mentioned guidance system and the following embodiments of the smart mobile terminal, which will not be repeated here.
[0098] The method provided in this embodiment uses a built-in client program on a smart mobile terminal to play a demonstration page to guide the user to perform unboxing and setup operations on an electronic product. In the process of interaction with the user, the generative artificial intelligence large language model is used to analyze the user's intention, and the target demonstration page is played according to the intention to answer the user's questions, thereby effectively helping the user complete the unboxing and setup operations, thereby improving the efficiency of unboxing, setup and use of electronic products and increasing product stickiness.
[0099] Referring to Figure 12 , Figure 12 is a schematic diagram of the structure of a smart mobile terminal provided in one embodiment of the present application. The smart mobile terminal includes: one or more processors 501, one or more memories 502, one or more wireless communication devices 503, one or more input devices 504, and one or more output devices 504 (for ease of understanding, Figure 12 shows only one of each device; in actual applications, this is not limited to the examples).
[0100] One or more processors 501 are electrically connected to one or more memories 502, one or more wireless communication devices 503, one or more input devices 504, and one or more output devices 504, and perform data communication among them via a communication bus.
[0101] The one or more memories 502 may be non-transitory storage. The one or more input devices 504 may be at least one of a camera, a microphone, a touch panel, a physical button, a mouse, or various sensors. The one or more output devices 804 may be at least one of a display screen and a speaker.
[0102] The one or more wireless communication devices 503 include: a wireless signal transceiver and surrounding circuits. The wireless signal transceiver can use, but is not limited to, at least one of the WiFi (Wireless Fidelity) protocol, NFC (Near Field Communication) protocol, ZigBee, UWB (Ultra Wideband, carrier-free communication), RFID (Radio Frequency Identification) protocol, and cellular mobile communication (Cellular Mobile Communication) protocol (such as 3G / 4G / 5G, etc.) for data transmission.
[0103] The non-transitory memory 502 stores one or more computer programs executable by the processor 501. The computer programs include a plurality of instructions for:
[0104] Playing a demonstration page in the client program through the output device 505 to guide the user to perform unpacking and setting operations on the smart mobile terminal, wherein the client program has multiple demonstration pages;
[0105] The user obtains the interaction information between the user and the client program during the unpacking and setting process through the input device 504, and sends the text generated based on the interaction information to the model server through the wireless communication device 503, so that the model server can parse the text and obtain the parsing result through the generative artificial intelligence language model;
[0106] The analysis result returned by the model server is received through the wireless communication device 503 , a target demonstration page is determined according to the analysis result, and the target demonstration page is played through the output device 505 .
[0107] Optionally, in other implementations of the present application, the multiple instructions are further used to:
[0108] Obtain a download link for the client program, and download an installation program for the client program according to the download link via the wireless communication device 503;
[0109] The installation program is run to install the client program on the smart mobile terminal, wherein the client program matches the device information of the smart mobile terminal.
[0110] Optionally, in other embodiments of the present application, at least one of the multiple demonstration pages includes a user interaction interface, and the interaction information includes text information input by the user on the user interaction interface.
[0111] Optionally, in other embodiments of the present application, the interaction information includes user voice, the input device 504 includes a microphone, and the multiple instructions are further used to obtain the user voice through the microphone and convert the user voice into the text.
[0112] Optionally, in other implementations of the present application, the multiple instructions are further used to:
[0113] Generate a virtual character that matches the user's personal information and configure the virtual character into the demonstration page; and
[0114] When the target demonstration page is played, the virtual character is synchronously controlled to interact with the user through the virtual character.
[0115] Optionally, in other implementations of the present application, the multiple instructions are further used to:
[0116] The registration information entered by the user on the demonstration page for guiding new user registration is obtained, and a user registration operation is performed according to the registration information.
[0117] For details not covered in the above embodiments of the smart mobile terminal, please refer to the relevant descriptions in the embodiments of the above guidance system and guidance method, which will not be repeated here.
[0118] The smart mobile terminal provided in this embodiment uses a built-in client program to play a demonstration page to guide the user to perform unboxing and setup operations on the electronic product. In the process of interaction with the user, the generative artificial intelligence large language model is used to analyze the user's intention, and the target demonstration page is played according to the intention to answer the user's questions, thereby effectively helping the user complete the unboxing and setup operations, thereby improving the efficiency of unboxing, setup and use of electronic products and increasing product stickiness.
[0119] The present application also provides a non-transitory computer-readable storage medium, which may be provided in the smart mobile terminal described in each of the above embodiments. The non-transitory computer-readable storage medium may be the memory 502 described in the embodiment shown in FIG12 . The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the artificial intelligence-based electronic product unpacking and setup guidance method described in each of the above embodiments. Furthermore, the computer-readable storage medium may be a USB flash drive, a mobile hard drive, a read-only memory (ROM), RAM, a magnetic disk, or an optical disk, among other media capable of storing program code.
[0120] In the several embodiments provided herein, it should be understood that the disclosed guidance systems, methods, and terminals can be implemented in other ways. For example, multiple modules or components can be combined or integrated into another system, or some features can be omitted or not implemented. Furthermore, the connections or direct or communicative connections shown or discussed can be indirect or communicative connections through interfaces, devices, or modules, and can be electrical, mechanical, or other forms.
[0121] It should be noted that for the aforementioned method embodiments, for ease of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.
[0122] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0123] The above is a description of the guidance system, method and terminal provided in this application. For those skilled in the art, based on the ideas of the embodiments of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. An electronic product unpacking and setting guidance system based on artificial intelligence, characterized in that: The system comprises: an intelligent mobile terminal and a model server, wherein the model server is configured with a generative artificial intelligence large language model, and the intelligent mobile terminal is installed with a client program having multiple demonstration pages; The smart mobile terminal is used to play the demonstration page through the client program to guide the user to perform unpacking and setting operations on the electronic product, obtain the interaction information between the user and the client program during the unpacking and setting process, and send the text generated based on the interaction information to the model server; The model server is used to parse the text through the generative artificial intelligence large language model and return the parsing result to the smart mobile terminal; The intelligent mobile terminal is further used to determine a target demonstration page according to the analysis result, and play the target demonstration page.
2. The system according to claim 1, wherein: The smart mobile terminal is also used to obtain a download link for the client program, download an installation program for the client program according to the download link, and run the installation program to install the client program on the smart mobile terminal, wherein the client program matches the device information of the smart mobile terminal.
3. The system according to claim 1, wherein: At least one of the demonstration pages is a user interaction interface, and the interaction information includes text information input by the user in the user interaction interface.
4. The system according to claim 1, wherein: The interaction information includes user voice; The intelligent mobile terminal is further used to receive the user voice sent by the electronic product, or to obtain the user voice through a built-in microphone, and to convert the user voice into the text.
5. The system according to claim 1, wherein: The intelligent mobile terminal is further used to generate a virtual character matching the personal information of the user, and configure the virtual character into the demonstration page; The intelligent mobile terminal is further used to synchronously control the virtual character when playing the target demonstration page, so as to interact with the user through the virtual character.
6. The system according to claim 1, wherein: The plurality of demonstration pages include a first demonstration page for guiding pairing; The intelligent mobile terminal is also used to respond to the user's operation on the first demonstration page and pair with the electronic product through the client program using a short-range wireless communication network.
7. The system according to claim 6, wherein: The short-range wireless communication network includes: a Bluetooth network, a Wireless Fidelity network and a Near Field Communication network.
8. The system according to claim 1, wherein: The plurality of demonstration pages include a second demonstration page for guiding new users to register; The smart mobile terminal is further used to obtain registration information input by the user on the second demonstration page, and perform a user registration operation according to the registration information.
9. An artificial intelligence-based electronic product unpacking and setting guidance method, applied to a smart mobile terminal, characterized in that: The method comprises: Playing a preset demonstration page through a client program installed on the smart mobile terminal to guide the user to perform unpacking and setting operations on the electronic product, wherein the client program has a plurality of the demonstration pages; Acquire the interaction information between the user and the client program during the unboxing and setting process, and send the text generated based on the interaction information to the model server, so that the model server parses the text through the generative artificial intelligence large language model, and returns the parsing result to the smart mobile terminal; A target demonstration page is determined according to the analysis result, and the target demonstration page is played.
10. The method according to claim 9, characterized in that The method further comprises: Obtain a download link for the client program, and download an installation program for the client program according to the download link; The installation program is run to install the client program in the smart mobile terminal, wherein the client program matches the device information of the smart mobile terminal.
11. The method according to claim 9, wherein At least one of the demonstration pages is a user interaction interface, and the interaction information includes text information input by the user in the user interaction interface.
12. The method according to claim 9, wherein: The interaction information includes user voice, and the method further includes: Receiving the user voice sent by the electronic product, or acquiring the user voice through the microphone of the smart mobile terminal; The user speech is converted into the text.
13. The method according to claim 9, wherein: The method further comprises: Generating a virtual character that matches the personal information of the user, and configuring the virtual character into the demonstration page; When the target demonstration page is played, the virtual character is synchronously controlled so as to interact with the user through the virtual character.
14. The method according to claim 9, wherein: The plurality of demonstration pages include a first demonstration page for guiding pairing, and the method further includes: In response to the user's operation on the first demonstration page, the client program is used to pair with the electronic product using a short-range wireless communication network.
15. The method according to claim 9, wherein: The plurality of demonstration pages include a second demonstration page for guiding a new user to register, and the method further includes: The registration information input by the user on the second demonstration page is obtained, and a user registration operation is performed according to the registration information.
16. A smart mobile terminal, characterized in that: include: A processor and a non-transitory storage, a wireless communication device, an input device, and an output device electrically connected to the processor; The non-transitory storage stores one or more computer programs executable by the processor, wherein the computer programs include a plurality of instructions for: Playing a demonstration page in the client program through the output device to guide the user to perform unpacking and setting operations on the smart mobile terminal, wherein the client program has a plurality of the demonstration pages; Acquire the interaction information between the user and the client program during the unboxing and setting process through the input device, and send the text generated based on the interaction information to the model server through the wireless communication device, so that the model server parses the text through the generative artificial intelligence large language model and obtains the parsing result; The analysis result returned by the model server is received through the wireless communication device, a target demonstration page is determined according to the analysis result, and the target demonstration page is played through the output device.
17. The intelligent mobile terminal according to claim 16, characterized in that: The plurality of instructions are also used to: Obtaining a download link of the client program, and downloading an installation program of the client program according to the download link through the wireless communication device; The installation program is run to install the client program in the smart mobile terminal, wherein the client program matches the device information of the smart mobile terminal.
18. The intelligent mobile terminal according to claim 16, characterized in that: At least one of the multiple demonstration pages includes a user interaction interface, and the interaction information includes text information input by the user in the user interaction interface.
19. The intelligent mobile terminal according to claim 16, characterized in that: The interaction information includes user voice, the input device includes a microphone, and the multiple instructions are further used to obtain the user voice through the microphone and convert the user voice into the text.
20. The intelligent mobile terminal according to claim 16, characterized in that: The plurality of instructions are also used to: Generating a virtual character that matches the user's personal information, and configuring the virtual character into the demonstration page; and When the target demonstration page is played, the virtual character is synchronously controlled so as to interact with the user through the virtual character.
21. The intelligent mobile terminal according to claim 16, characterized in that: The demonstration page includes a demonstration page for guiding new users to register, and the plurality of instructions are further used to: The registration information input by the user on the demonstration page for guiding new user registration is obtained, and a user registration operation is performed according to the registration information.
Citation Information
Patent Citations
Equipment and method for generating and using guide interface in terminal
CN104142787A
Interaction method and system based on intelligent voice, intelligent terminal and storage medium
CN111383346A
Operation demonstration method and device, electronic equipment and storage medium
CN114489416A
Operation guiding method and device of mobile terminal and electronic equipment
CN116107680A
Configuration of Voice Controlled Assistant
US20160372113A1