User interface generation method and device and storage medium

Abstract

The invention discloses a user interface generation method and device and a storage medium, and relates to the technical field of smart home, the method comprises the following steps: sending a first interaction instruction input by a target object to a cloud server, so that the cloud server analyzes the first interaction instruction to obtain a first analysis result; generating a user interface corresponding to the response data according to a preset editing rule; displaying a user interface in a visual interface area of the terminal equipment, generating a second interaction instruction according to the operation of the target object on the visual interface object and the link address of the jump link, and sending the second interaction instruction to the cloud server, so that the cloud server analyzes the second interaction instruction to obtain a second analysis result; and updating the user interface according to the second analysis result. By adopting the technical scheme, the technical problems that the generation efficiency of the user interface of the terminal equipment is low and the display mode is too complicated are solved.

Description

Technical Field

[0001] This application relates to the technical field of smart homes. Specifically, it relates to a method, device, and storage medium for generating a user interface. Background Art

[0002] Currently, as the intelligence level of smart home devices gets higher and higher, people's demand for the convenience of devices is also increasing. In response to this demand, terminal devices with displays are used more and more widely. However, the interface designs of these terminal devices often overemphasize function integration, and the display methods are very complex, which not only occupies more operating resources but also reduces the device operation speed. Moreover, different system platforms of terminal devices require different development languages, which will cause developers to spend a lot of time on language conversion and platform adaptation, increasing the time cost and labor cost, reducing the development efficiency, and thus leading to low efficiency in generating user interfaces.

[0003] In the related art, there are technical problems such as low efficiency in generating the user interface of terminal devices and overly complex display methods.

[0004] In view of the technical problems in the related art, such as low efficiency in generating the user interface of terminal devices and overly complex display methods, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of this application provide a method, device, and storage medium for generating a user interface to at least solve the technical problems in the related art, such as low efficiency in generating the user interface of terminal devices and overly complex display methods.

[0006] According to an embodiment of the embodiments of this application, a method for generating a user interface is provided, which is applied to a terminal device and includes: sending a first interaction instruction input by a target object to a cloud server, and receiving a first parsing result sent by the cloud server based on the first interaction instruction, where the first parsing result at least includes response data of the first interaction instruction; generating a user interface corresponding to the response data according to a preset editing rule, where the user interface integrates a device interaction entry, and a jump link has been set for a visual interface object corresponding to the response data on the user interface; displaying the user interface in a visual interface area of the terminal device, generating a second interaction instruction according to an operation of the target object on the visual interface object and a link address of the jump link, and sending the second interaction instruction to the cloud server, and receiving a second parsing result sent by the cloud server based on the second interaction instruction; updating the user interface according to the second parsing result.

[0007] In an exemplary embodiment, generating a user interface corresponding to the response data according to a preset editing rule includes: obtaining multiple groups of data after classifying the response data, where the data types of each group of data are the same; using the document code corresponding to each group of data to generate user interface elements corresponding to each group of data, and arranging the user interface elements according to the preset editing rule to obtain the user interface.

[0008] In an exemplary embodiment, using the document code corresponding to each group of data to generate user interface elements corresponding to each group of data includes at least one of the following: for the first group of data with a data type of text, using the document code corresponding to the first group of data to generate a text box corresponding to the first group of data; for the second group of data with a data type of picture, using the document code corresponding to the second group of data to generate a picture box corresponding to the second group of data; for the third group of data with a data type of video, using the document code corresponding to the third group of data to generate a video player corresponding to the third group of data; for the fourth group of data with a data type of audio, using the document code corresponding to the fourth group of data to generate an audio player corresponding to the fourth group of data.

[0009] In an exemplary embodiment, generating a second interaction instruction according to the operation of the target object on the visual interface object and the link address of the jump link includes: in the case of determining that the target object performs a selection operation on the visual interface object, if it is determined that the link address of the jump link belongs to an internal database address supported by the cloud server, generating a second interaction instruction according to the selection operation and the link address of the jump link; and / or, in the case of determining that the target object performs a modification operation on the visual interface object, if it is determined that the link address of the jump link belongs to an external search address supported by the cloud server, generating a second interaction instruction according to the modification operation and the link address of the jump link.

[0010] According to another aspect of the embodiments of the present application, there is also provided a method for generating a user interface, which is applied to a cloud server. An artificial intelligence large model is configured on the cloud server, and the method includes: parsing a first interaction instruction from a terminal device using the artificial intelligence large model to obtain an instruction field; determining response data of the first interaction data based on the instruction field, and sending a first parsing result generated based on the response data to the terminal device so that the terminal device generates a user interface according to the first parsing result; and in the case of receiving a second interaction instruction sent by the terminal device based on the first parsing result, sending a second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device so that the terminal device updates the user interface according to the second parsing result.

[0011] In an exemplary embodiment, parsing a first interaction instruction from a terminal device using the artificial intelligence large model to obtain an instruction field includes: for a first interaction instruction in text form, performing semantic analysis on the first interaction instruction using the artificial intelligence large model to obtain keywords of the first interaction instruction in text form, and determining the instruction field based on the keywords; and / or, for a first interaction instruction in audio form, converting the first interaction instruction in audio form into the first interaction instruction in text form using the artificial intelligence large model, and performing semantic analysis on the first interaction instruction in text form to obtain keywords of the first interaction instruction in text form, and determining the instruction field based on the keywords.

[0012] In an exemplary embodiment, determining response data of the first interaction data based on the instruction field includes: in the case of querying the interaction data corresponding to the instruction field in the database, determining the response data of the first interaction data based on the interaction data; in the case of not querying the interaction data corresponding to the instruction field in the database, obtaining a network search result of the instruction field and determining the response data according to the network search result.

[0013] According to another aspect of the embodiments of the present application, there is also provided a user interface generation device, including: a first sending module, configured to send a first interaction instruction input by a target object to a cloud server, and receive a first parsing result sent by the cloud server based on the first interaction instruction, where the first parsing result at least includes response data of the first interaction instruction; a generation module, configured to generate a user interface corresponding to the response data according to a preset editing rule, where the user interface integrates a device interaction entry, and a visual object corresponding to the response data on the user interface has a jump link set; a second sending module, configured to display the user interface in a visualization interface area of a terminal device, generate a second interaction instruction according to an operation of the target object on the visual object and a link address of the jump link, and send the second interaction instruction to the cloud server, and receive a second parsing result sent by the cloud server based on the second interaction instruction; an update module, configured to update the user interface according to the second parsing result.

[0014] According to another aspect of the embodiments of the present application, there is also provided a user interface generation device, including: a parsing module, configured to parse a first interaction instruction from a terminal device using an artificial intelligence large model to obtain instruction fields; a third sending module, configured to determine response data of the first interaction data based on the instruction fields, and send a first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result; a fourth sending module, configured to, when receiving a second interaction instruction sent by the terminal device based on the first parsing result, send a second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device, so that the terminal device updates the user interface according to the second parsing result.

[0015] According to yet another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the above-mentioned user interface generation method when running.

[0016] According to yet another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the above-mentioned processor executes the above-mentioned user interface generation method through the computer program.

[0017] In an embodiment of the present application, on the side of the terminal device, on the one hand, the first interaction instruction input by the target object is sent to the cloud server, so that the cloud server parses the first interaction instruction to obtain a first parsing result including at least the response data of the first interaction instruction, and generates a user interface corresponding to the response data according to a preset editing rule. The user interface integrates a device interaction entry, and jump links are set for the visual interface objects corresponding to the response data on the user interface. By setting jump links for the visual interface objects of the user interface, the display content on the current interface can be simplified, and more content can be displayed using the new interface corresponding to the jump link, thus solving the technical problem that the display method of the user interface of the terminal device is too complex, simplifying the display method, and improving the display efficiency. On the other hand, the user interface is displayed in the visualization interface area of the terminal device, a second interaction instruction is generated according to the operation of the target object on the visual interface object and the link address of the jump link, and the second interaction instruction is sent to the cloud server, and the second parsing result sent by the cloud server based on the second interaction instruction is received; the user interface is updated according to the second parsing result; the instruction input by the user can be uploaded to the cloud through the terminal device, and then the parsing result of the cloud's parsing of the instruction can be obtained, and a user interface can be generated according to the preset logic function, the user interface can be displayed to the user, and a corresponding page update function can be provided to the user according to the user's operation on the user interface to display the latest user interface to the user. By adopting the above technical solution, the development process is simplified, the technical problem of low generation efficiency of the user interface of the terminal device is solved, and thus the generation efficiency of the user interface of the terminal device is improved, and the user experience is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and, together with the specification, are used to explain the principles of the present application.

[0019] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic diagram of the hardware environment of a method for generating a user interface according to an embodiment of the present application;

[0021] Figure 2 It is a flowchart of a method for generating a user interface according to an embodiment of the present application;

[0022] Figure 3It is a flowchart of another method for generating a user interface according to an embodiment of the present application;

[0023] Figure 4 It is an interactive schematic diagram (one) of a user interface according to an embodiment of the present application;

[0024] Figure 5 It is an interactive schematic diagram (two) of a user interface according to an embodiment of the present application;

[0025] Figure 6 It is a schematic diagram of the interactive result of a user interface according to an embodiment of the present application;

[0026] Figure 7 It is a layout design schematic diagram (one) of a user interface according to an embodiment of the present application;

[0027] Figure 8 It is a layout design schematic diagram (two) of a user interface according to an embodiment of the present application;

[0028] Figure 9 It is an interactive timing diagram of a method for generating a user interface according to an embodiment of the present application;

[0029] Figure 10 It is a structural block diagram of a device for generating a user interface according to an embodiment of the present application;

[0030] Figure 11 It is a structural block diagram of another device for generating a user interface according to an embodiment of the present application. Detailed implementation manners

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0032] It should be noted that 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 sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] According to one aspect of an embodiment of the present application, a method for generating a user interface is provided. The method for generating a user interface is widely used in smart home, smart home, smart home device ecology, smart house ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above-mentioned method for generating a user interface can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0034] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0035] In this embodiment, a method for generating a user interface is provided, which is applied to the above terminal device. Figure 2 It is a flowchart of a method for generating a user interface according to an embodiment of the present application. The process includes the following steps:

[0036] Step S202: Send the first interaction instruction input by the target object to the cloud server, and receive the first parsing result sent by the cloud server based on the first interaction instruction, where the first parsing result at least includes the response data of the first interaction instruction.

[0037] Optionally, the above first interaction instruction is, for example, input by the target object through the device interaction entry. The device interaction entry can receive instructions in different forms such as text and audio.

[0038] The cloud server parses the received first interaction instruction to obtain the first parsing result.

[0039] Step S204: Generate a user interface corresponding to the response data according to a preset editing rule, where the user interface integrates a device interaction entry, and a jump link has been set for the visual object corresponding to the response data on the user interface.

[0040] It should be noted that the above user interface refers to User Interface, UI. UI design refers to the overall design of the human-computer interaction, operation logic, and interface aesthetics of software, including the interaction relationship between the user and the interface.

[0041] Optionally, the preset editing rule can, for example, represent rules for text size, font color, bold, italic, underline, paragraph spacing, title level, insertion position of pictures and videos, jump logic of links, etc., which can improve the clarity of information expression, thereby improving the interaction effect with the user.

[0042] Among them, the terminal device needs to have a relatively high computing power to generate a user interface corresponding to the response data according to the preset editing rule. When the computing power of the terminal device is insufficient, the user interface can also be directly generated by the cloud and then sent to the terminal device.

[0043] In this step, by embedding relevant hyperlinks (i.e., jump links) in the user interface, the user can click on the hyperlink for secondary query or obtain more detailed information, enhancing the interactivity and information depth.

[0044] Step S206: Display the user interface in the visualization interface area of the terminal device, generate a second interaction instruction according to the operation of the target object on the visual interface object and the link address of the jump link, and send the second interaction instruction to the cloud server, and receive a second parsing result sent by the cloud server based on the second interaction instruction;

[0045] Among them, the cloud server parses the received second interaction instruction to obtain a second parsing result.

[0046] Step S208: Update the user interface according to the second parsing result.

[0047] Optionally, updating the user interface according to the second parsing result, for example, means updating the time or weather in the user interface.

[0048] Through the above steps, on the terminal device side, on the one hand, by sending the first interaction instruction input by the target object to the cloud server, so that the cloud server parses the first interaction instruction to obtain a first parsing result including at least the response data of the first interaction instruction, and generates a user interface corresponding to the response data according to a preset editing rule. Among them, the user interface integrates a device interaction entry, and a jump link has been set for the visual interface object corresponding to the response data on the user interface. By setting a jump link for the visual interface object of the user interface, the display content on the current interface can be simplified, and more content can be displayed using the new interface corresponding to the jump link, thus solving the technical problem that the display method of the user interface of the terminal device is too complex, simplifying the display method, and improving the display efficiency. On the other hand, display the user interface in the visualization interface area of the terminal device, generate a second interaction instruction according to the operation of the target object on the visual interface object and the link address of the jump link, and send the second interaction instruction to the cloud server, receive a second parsing result sent by the cloud server based on the second interaction instruction; update the user interface according to the second parsing result; the instruction input by the user can be uploaded to the cloud through the terminal device, and then the parsing result of the cloud's parsing of the instruction can be obtained, and a user interface can be generated according to the preset logic function, the user interface can be displayed to the user, and a corresponding page update function can be provided to the user according to the user's operation on the user interface to display the latest user interface to the user. By adopting the above technical solution, the development process is simplified, the technical problem of low generation efficiency of the user interface of the terminal device is solved, and further, the generation efficiency of the user interface of the terminal device is improved, and the user experience is also improved.

[0049] In an exemplary embodiment, generating a user interface corresponding to the response data according to a preset editing rule includes: obtaining multiple sets of data after classifying the response data, where the data type of each set of data is the same; using the document code corresponding to each set of data to generate a user interface element corresponding to each set of data, and arranging the user interface elements according to the preset editing rule to obtain the user interface.

[0050] Among them, the sorted user interface elements are the visual object of the user interface.

[0051] For the above document code, for example, it can be implemented using basic C++ language or Json development language to be universal on different system platforms. Through this embodiment, according to user input and device characteristics, a user interface that conforms to reading habits and visual aesthetics can be automatically and quickly generated based on the editing rule, while simplifying the complexity of cross-platform UI development and improving development efficiency.

[0052] In an exemplary embodiment, using the document code corresponding to each set of data to generate a user interface element corresponding to each set of data includes at least one of the following: for the first set of data with a data type of text, using the document code corresponding to the first set of data to generate a text box corresponding to the first set of data; for the second set of data with a data type of picture, using the document code corresponding to the second set of data to generate a picture box corresponding to the second set of data; for the third set of data with a data type of video, using the document code corresponding to the third set of data to generate a video player corresponding to the third set of data; for the fourth set of data with a data type of audio, using the document code corresponding to the fourth set of data to generate an audio player corresponding to the fourth set of data.

[0053] Optionally, the document code corresponding to the first set of data is used to set rules such as the size, color, and format of the text box. The document code corresponding to the second set of data is used to set the position and size of the picture box. The document code corresponding to the third set of data is used to set the position of the video player on the screen. The document code corresponding to the fourth set of data is used to set the position of the audio player on the screen.

[0054] For the above document code, for example, it is Markdown document code. By performing data processing steps of data parsing, data conversion, and data formatting on multiple sets of data in sequence, and finally combining the formatted text into a Markdown document code including metadata such as adding a document title, description, author information, etc., this embodiment can dynamically generate UI elements using Markdown document code according to different input contents and rules and layout them on the user interface.

[0055] In an exemplary embodiment, generating a second interaction instruction according to the operation of the visual interface object by the target object and the link address of the jump link includes: when it is determined that the target object performs a selection operation on the visual interface object, if it is determined that the link address of the jump link belongs to the internal database address supported by the cloud server, generating a second interaction instruction according to the selection operation and the link address of the jump link; and / or, when it is determined that the target object performs a modification operation on the visual interface object, if it is determined that the link address of the jump link belongs to the external search address supported by the cloud server, generating a second interaction instruction according to the modification operation and the link address of the jump link.

[0056] In one embodiment, the terminal device generates a user interface corresponding to the response data according to a preset editing rule. While meeting the screen display requirements, it uses the link jump function of the user interface to cooperate with the user's interaction operation to provide the user with a function of an interaction closed-loop. For example, if the user clicks on text or a picture with a link on the user interface, the cloud parses the user's requirements again and then sends them to the terminal device, and the terminal device displays the retrieval results of the requirements.

[0057] According to another aspect of the embodiments of the present application, there is also provided a method for generating a user interface, which is applied to a cloud server, wherein an artificial intelligence large model is configured on the cloud server. Figure 3 FIG. is a flowchart of a method for generating a user interface according to an embodiment of the present application. The process includes the following steps:

[0058] Step S302, using the artificial intelligence large model to parse the first interaction instruction from the terminal device to obtain an instruction field;

[0059] Among them, the artificial intelligence large model may include, but is not limited to, a natural language processing model for speech parsing, an image recognition model for picture parsing, and a video understanding model for video parsing. Instruction fields such as querying the weather, playing music, displaying product information, etc.

[0060] Step S304, determining the response data of the first interaction data based on the instruction field, and sending the first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result;

[0061] Step S306, when receiving the second interaction instruction sent by the terminal device based on the first parsing result, sending the second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device, so that the terminal device updates the user interface according to the second parsing result.

[0062] Through the above steps, on the cloud server side, the first interaction instruction from the terminal device is parsed using the artificial intelligence large model to obtain instruction fields; based on the instruction fields, the response data of the first interaction data is determined, and the first parsing result generated based on the response data is sent to the terminal device, so that the terminal device generates a user interface according to the first parsing result; in the case of receiving the second interaction instruction sent by the terminal device based on the first parsing result, the second parsing result obtained by parsing the second interaction data using the artificial intelligence large model is sent to the terminal device, so that the terminal device updates the user interface according to the second parsing result. After the terminal device uploads the instruction input by the user to the cloud, the artificial intelligence large model can be used on the cloud to parse instructions in the form of voice / text / pictures, etc., and then the parsing result is transmitted to the terminal device, which is convenient for the device side to generate a user interface according to the parsing result and update the already generated user interface.

[0063] Optionally, the user interface corresponding to the response data can also be generated by the cloud according to preset editing rules, and then the user interface is sent to the terminal device, and the terminal device only needs to display the user interface. For example, the artificial intelligence large model designs the layout and style of the response interface using a lightweight markup language such as markdown and preset rules based on user needs and the obtained information, combined with programming languages such as C++ / Json, and then automatically generates a response interface containing text, pictures, videos and links, which can not only reduce the device operation pressure of the terminal device and improve the device operation efficiency, but also improve the matching degree between the display result and the reading habits and aesthetic preferences of users. In this embodiment, the artificial intelligence large model can realize requirement recognition and logic matching. Specifically, the artificial intelligence large model identifies the requirements of the user, such as querying the weather, playing music, displaying product information, etc., according to the parsed text information. Then, the identified requirements are matched with the preset logic functions to judge whether the user request can be directly processed by the preset functions or needs to perform a network search to obtain more detailed information. If the user's requirements can be directly met by the device's preset functions, the corresponding functions or services are directly called to generate response data. Otherwise, external network resources are queried, and API or crawler technology is used to obtain the required information.

[0064] Optionally, the guiding word logic for intelligent preprocessing of the instruction input by the user can also be performed to improve the accuracy and efficiency of the artificial intelligence large model in parsing instructions.

[0065] Similarly, the parsing process of the second interaction instruction can refer to the first interaction instruction and will not be elaborated here.

[0066] In an exemplary embodiment, the artificial intelligence large model is used to parse the first interaction instruction from the terminal device to obtain instruction fields, including: for the first interaction instruction in text form, the artificial intelligence large model is used to perform semantic analysis on the first interaction instruction to obtain keywords of the first interaction instruction in text form, and the instruction fields are determined based on the keywords; and / or, for the first interaction instruction in audio form, the artificial intelligence large model is used to convert the first interaction instruction in audio form into the first interaction instruction in text form, and perform semantic analysis on the first interaction instruction in text form to obtain keywords of the first interaction instruction in text form, and the instruction fields are determined based on the keywords.

[0067] Among them, using the artificial intelligence large model to perform semantic analysis on the first interaction instruction can be understood as using a natural language processing model to parse the text and understand the user's intentions and needs. This includes semantic analysis, keyword extraction, and sentiment analysis, etc., to determine the specific operations that the user wants to query or execute.

[0068] Using the artificial intelligence large model to convert the first interaction instruction in audio form into the first interaction instruction in text form, and performing semantic analysis on the first interaction instruction in text form can be understood as using a speech recognition model to convert the speech signal into text, and then parsing it through a natural language processing model.

[0069] Optionally, for the first interaction instruction input as a picture, an image recognition model is used to analyze the picture content, extract key information, and convert it into text form for further processing.

[0070] In an exemplary embodiment, determining the response data of the first interaction data based on the instruction fields includes: when the interaction data corresponding to the instruction fields is queried in the database, determining the response data of the first interaction data based on the interaction data; when the interaction data corresponding to the instruction fields is not queried in the database, obtaining the network search results of the instruction fields, and determining the response data according to the network search results. Through this series of steps, this embodiment can effectively understand and respond to the user's needs, determine the response data in multiple ways, improve the richness of the user interface, and thus enhance the user experience.

[0071] To better understand the process of the above method for generating a user interface, the following further describes the implementation method flow of the above generation of the user interface in combination with optional embodiments, but it is not used to limit the technical solutions of the embodiments of the present application.

[0072] Optionally, in this embodiment, for the process of using an artificial intelligence large model to parse user instructions, identify user needs, and generate response data including text, pictures, videos, and links, as Figure 4 shown, the following steps may further be included:

[0073] Step 1, the user inputs an instruction.

[0074] Step 2, the terminal device forwards the instruction to the cloud.

[0075] Step 3, the cloud parses the instruction to obtain a parsing result.

[0076] The user sends an instruction of a device interaction entry (such as text input, voice input, picture upload, etc.) to the cloud, and the cloud preprocesses the data, for example, converts voice into text and converts pictures into text information.

[0077] Step 4, send the parsing result to the terminal device.

[0078] Step 5, the terminal device generates a user interface according to the parsing result and displays the generated user interface to the user according to preset UI rules.

[0079] As Figure 5 shown, an interaction process of "speaking", "loading", and "execution completed" can be completed according to the above steps. Among them, the UI interface also includes a user feedback mechanism, such as the air conditioner opening state corresponding to "turn on the air conditioner" being successful, to intuitively inform the user of the operation result and enhance the user's operation perception.

[0080] Next, the user's secondary interaction is realized through the following steps.

[0081] Step 6, the user clicks on a hyperlink on the screen or inputs a new voice instruction.

[0082] Step 7, the terminal device converts the voice instruction into audio information and sends it to the cloud.

[0083] Step 8, the cloud parses the instruction to obtain a parsing result.

[0084] Step 9, send the parsing result to the terminal device.

[0085] Step 10, update the user interface.

[0086] As Figure 6 shown, the user can perform secondary queries or operations by clicking on the hyperlink content on the UI interface (such as selecting 27° on the temperature interface) or inputting a new instruction, so as to achieve a richer interaction experience. Among them, the new user interface is as Figure 7 shown.

[0087] Of course, in this application, there can also be a function to automatically adjust the UI layout and element sizes according to the device screen size and resolution, so as to optimize the visual effect and reading experience. Or use the basic style changes of the text size, thickness, and color to express different levels. For example, through the combined layout of images and text as shown in Figure 8 or the combined layout rules of text and video as shown in Figure 9 to enrich the visual effect.

[0088] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of this application, in essence or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of this application.

[0089] Figure 10 is a structural block diagram of a user interface generation device according to an embodiment of this application; as shown in Figure 10 it includes:

[0090] A first sending module 1002, configured to send a first interaction instruction input by a target object to a cloud server, and receive a first parsing result sent by the cloud server based on the first interaction instruction, where the first parsing result at least includes response data of the first interaction instruction;

[0091] A generating module 1004, configured to generate a user interface corresponding to the response data according to a preset editing rule, where the user interface integrates a device interaction entry, and a jump link has been set for a visual interface object corresponding to the response data on the user interface;

[0092] A second sending module 1006, configured to display the user interface in a visual interface area of a terminal device, generate a second interaction instruction according to an operation of the target object on the visual interface object and a link address of the jump link, and send the second interaction instruction to the cloud server, and receive a second parsing result sent by the cloud server based on the second interaction instruction;

[0093] An updating module 1008, configured to update the user interface according to the second parsing result.

[0094] Through the above device, on the terminal device side, on the one hand, the first interaction instruction input by the target object is sent to the cloud server, so that the cloud server parses the first interaction instruction to obtain a first parsing result including at least the response data of the first interaction instruction, and generates a user interface corresponding to the response data according to a preset editing rule. The user interface integrates a device interaction entry, and jump links have been set for the visual interface objects corresponding to the response data on the user interface. By setting jump links for the visual interface objects of the user interface, the display content on the current interface can be simplified, and more content can be displayed using the new interface corresponding to the jump link, thus solving the technical problem that the display method of the user interface of the terminal device is too complex, simplifying the display method, and improving the display efficiency. On the other hand, the user interface is displayed in the visualization interface area of the terminal device, a second interaction instruction is generated according to the operation of the target object on the visual interface object and the link address of the jump link, and the second interaction instruction is sent to the cloud server, and the second parsing result sent by the cloud server based on the second interaction instruction is received; the user interface is updated according to the second parsing result; the instruction input by the user can be uploaded to the cloud through the terminal device, then the parsing result of the cloud's parsing of the instruction can be obtained, and the user interface can be generated according to the preset logic function, the user interface is displayed to the user, and the corresponding page update function is provided to the user according to the user's operation on the user interface to display the latest user interface to the user. By adopting the above technical solution, the development process is simplified, the technical problem of low generation efficiency of the user interface of the terminal device is solved, and thus the generation efficiency of the user interface of the terminal device is improved, and the user experience is also improved.

[0095] In an exemplary embodiment, the generating module is further configured to: obtain multiple groups of data after data classification of the response data, where the data types of each group of data are the same; use the document code corresponding to each group of data to generate user interface elements corresponding to each group of data, and arrange the user interface elements according to the preset editing rule to obtain the user interface.

[0096] In an exemplary embodiment, the generating module is further configured to: for the first group of data with a data type of text, use the document code corresponding to the first group of data to generate a text box corresponding to the first group of data; for the second group of data with a data type of picture, use the document code corresponding to the second group of data to generate a picture box corresponding to the second group of data; for the third group of data with a data type of video, use the document code corresponding to the third group of data to generate a video player corresponding to the third group of data; for the fourth group of data with a data type of audio, use the document code corresponding to the fourth group of data to generate an audio player corresponding to the fourth group of data.

[0097] In an exemplary embodiment, the second sending module is further configured to: when it is determined that the target object performs a selection operation on the visual object, if it is determined that the link address of the jump link belongs to an internal database address supported by the cloud server, generate a second interaction instruction according to the selection operation and the link address of the jump link; and / or, when it is determined that the target object performs a modification operation on the visual object, if it is determined that the link address of the jump link belongs to an external search address supported by the cloud server, generate a second interaction instruction according to the modification operation and the link address of the jump link.

[0098] According to another aspect of the embodiments of the present application, there is also provided a device for generating a user interface, as Figure 11 shown, including:

[0099] A parsing module 1102, configured to parse a first interaction instruction from a terminal device using an artificial intelligence large model to obtain instruction fields;

[0100] A third sending module 1104, configured to determine response data of the first interaction data based on the instruction fields, and send a first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result;

[0101] A fourth sending module 1106, configured to, when receiving a second interaction instruction sent by the terminal device based on the first parsing result, send a second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device, so that the terminal device updates the user interface according to the second parsing result.

[0102] Through the above steps, on the cloud server side, by using the artificial intelligence large model to parse the first interaction instruction from the terminal device to obtain instruction fields; determining the response data of the first interaction data based on the instruction fields, and sending a first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result; when receiving a second interaction instruction sent by the terminal device based on the first parsing result, sending a second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device, so that the terminal device updates the user interface according to the second parsing result. After the terminal device uploads the instruction input by the user to the cloud, the cloud can use the artificial intelligence large model to parse instructions in the form of voice / text / picture, etc., and then transfer the parsing result to the terminal device, which is convenient for the device side to generate a user interface according to the parsing result and update the already generated user interface.

[0103] In an exemplary embodiment, the parsing module is further configured to: for a first interaction instruction in text form, perform semantic analysis on the first interaction instruction using the artificial intelligence large model to obtain keywords of the first interaction instruction in text form, and determine the instruction field based on the keywords; and / or, for a first interaction instruction in audio form, use the artificial intelligence large model to convert the first interaction instruction in audio form into the first interaction instruction in text form, and perform semantic analysis on the first interaction instruction in text form to obtain keywords of the first interaction instruction in text form, and determine the instruction field based on the keywords.

[0104] In an exemplary embodiment, the third sending module is further configured to: when the interaction data corresponding to the instruction field is queried in the database, determine the response data of the first interaction data based on the interaction data; when the interaction data corresponding to the instruction field is not queried in the database, obtain the network search result of the instruction field, and determine the response data according to the network search result.

[0105] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the above program executes the method of any one of the above when running.

[0106] Optionally, in this embodiment, the above storage medium may be set to store program codes for executing the following steps:

[0107] S1. Send the first interaction instruction input by the target object to the cloud server, and receive the first parsing result sent by the cloud server based on the first interaction instruction, where the first parsing result at least includes the response data of the first interaction instruction;

[0108] S2. Generate a user interface corresponding to the response data according to a preset editing rule, where the user interface integrates a device interaction entry, and a jump link has been set for the visual object corresponding to the response data on the user interface;

[0109] S3. Display the user interface in the visualization interface area of the terminal device, generate a second interaction instruction according to the operation of the target object on the visual object and the link address of the jump link, and send the second interaction instruction to the cloud server, and receive the second parsing result sent by the cloud server based on the second interaction instruction;

[0110] S4. Update the user interface according to the second parsing result.

[0111] Alternatively, in this embodiment, the above storage medium may also be configured to store program code for performing the following steps:

[0112] Step S1: Parse the first interaction instruction from the terminal device using the artificial intelligence large model to obtain an instruction field;

[0113] Step S2: Determine the response data of the first interaction data based on the instruction field, and send the first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result;

[0114] Step S3: When receiving the second interaction instruction sent by the terminal device based on the first parsing result, send the second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device, so that the terminal device updates the user interface according to the second parsing result.

[0115] An embodiment of the present application also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0116] Optionally, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0117] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0118] S1: Send the first interaction instruction input by the target object to the cloud server, and receive the first parsing result sent by the cloud server based on the first interaction instruction, where the first parsing result at least includes the response data of the first interaction instruction;

[0119] S2: Generate a user interface corresponding to the response data according to a preset editing rule, where the user interface integrates a device interaction entry, and a jump link has been set for the visual object corresponding to the response data on the user interface;

[0120] S3: Display the user interface in the visualization interface area of the terminal device, generate a second interaction instruction according to the operation of the target object on the visual object and the link address of the jump link, and send the second interaction instruction to the cloud server, and receive the second parsing result sent by the cloud server based on the second interaction instruction;

[0121] S4. Update the user interface according to the second parsing result.

[0122] Alternatively, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0123] Step S1. Parse the first interaction instruction from the terminal device using the artificial intelligence large model to obtain an instruction field;

[0124] Step S2. Determine the response data of the first interaction data based on the instruction field, and send the first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result;

[0125] Step S3. In the case of receiving the second interaction instruction sent by the terminal device based on the first parsing result, send the second parsing result obtained by parsing the second interaction data using the artificial intelligence large model to the terminal device, so that the terminal device updates the user interface according to the second parsing result.

[0126] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media such as USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0127] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated herein.

[0128] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the present application is not limited to any specific combination of hardware and software.

[0129] The above is only the preferred embodiment of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A method for generating a user interface, characterized in that: Applied to terminal equipment, including: Sending a first interaction instruction input by the target object to a cloud server, and receiving a first parsing result sent by the cloud server based on the first interaction instruction, wherein the first parsing result at least includes response data of the first interaction instruction; Generate a user interface corresponding to the response data according to a preset editing rule, wherein the user interface is integrated with a device interaction entrance, and a jump link is set on a visual interface object corresponding to the response data on the user interface; Displaying the user interface in the visual interface area of ​​the terminal device, generating a second interaction instruction according to the target object's operation on the visual interface object and the link address of the jump link, sending the second interaction instruction to the cloud server, and receiving a second parsing result sent by the cloud server based on the second interaction instruction; The user interface is updated according to the second parsing result.

2. The method for generating a user interface according to claim 1, characterized in that: Generating a user interface corresponding to the response data according to a preset editing rule includes: Acquire multiple groups of data after classifying the response data, wherein the data type of each group of data is the same; The document code corresponding to each group of data is used to generate the user interface element corresponding to each group of data, and the user interface elements are arranged according to the preset editing rule to obtain the user interface.

3. The method for generating a user interface according to claim 2, characterized in that: Generating a user interface element corresponding to each set of data using the document code corresponding to each set of data includes at least one of the following: For a first group of data whose data type is text, a text box corresponding to the first group of data is generated using a document code corresponding to the first group of data; For a second set of data whose data type is a picture, a picture frame corresponding to the second set of data is generated using a document code corresponding to the second set of data; For a third group of data whose data type is video, using a document code corresponding to the third group of data to generate a video player corresponding to the third group of data; For the fourth group of data whose data type is audio, the document code corresponding to the fourth group of data is used to generate an audio player corresponding to the fourth group of data.

4. The method for generating a user interface according to claim 2, characterized in that: Generating a second interaction instruction according to the target object's operation on the visual interface object and the link address of the jump link includes: In the case where it is determined that the target object performs a selection operation on the visual interface object, if it is determined that the link address of the jump link belongs to an internal database address supported by the cloud server, a second interaction instruction is generated according to the selection operation and the link address of the jump link; And / or, when it is determined that the target object performs a modification operation on the visual interface object, if it is determined that the link address of the jump link belongs to an external search address supported by the cloud server, a second interaction instruction is generated based on the modification operation and the link address of the jump link.

5. A method for generating a user interface, characterized in that: Applied to a cloud server, wherein the cloud server is configured with a large artificial intelligence model, including: Parsing the first interaction instruction from the terminal device using the artificial intelligence big model to obtain an instruction field; Determine response data of the first interaction data based on the instruction field, and send a first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result; Upon receiving a second interaction instruction sent by the terminal device based on the first analysis result, a second analysis result obtained by parsing the second interaction data using the artificial intelligence big model is sent to the terminal device, so that the terminal device updates the user interface according to the second analysis result.

6. The method for generating a user interface according to claim 5, characterized in that: The first interaction instruction from the terminal device is parsed using the artificial intelligence big model to obtain an instruction field, including: For a first interactive instruction in text form, use the artificial intelligence big model to perform semantic analysis on the first interactive instruction to obtain keywords of the first interactive instruction in text form, and determine the instruction field based on the keywords; And / or, for the first interaction instruction in audio form, use the artificial intelligence big model to convert the first interaction instruction in audio form into the first interaction instruction in text form, and perform semantic analysis on the first interaction instruction in text form to obtain keywords of the first interaction instruction in text form, and determine the instruction field based on the keywords.

7. The method for generating a user interface according to claim 5, characterized in that: Determining response data of the first interaction data based on the instruction field includes: In the case where the interaction data corresponding to the instruction field is queried in the database, determining the response data of the first interaction data based on the interaction data; When no interaction data corresponding to the instruction field is found in the database, a network search result of the instruction field is obtained, and the response data is determined according to the network search result.

8. A user interface generation device, characterized in that: include: A first sending module, configured to send a first interaction instruction input by a target object to a cloud server, and receive a first parsing result sent by the cloud server based on the first interaction instruction, wherein the first parsing result at least includes response data of the first interaction instruction; A generating module, used for generating a user interface corresponding to the response data according to a preset editing rule, wherein the user interface is integrated with a device interaction entrance, and a visual interface object corresponding to the response data on the user interface is provided with a jump link; A second sending module is used to display the user interface in the visual interface area of ​​the terminal device, generate a second interaction instruction according to the operation of the target object on the visual interface object and the link address of the jump link, and send the second interaction instruction to the cloud server, and receive a second parsing result sent by the cloud server based on the second interaction instruction; An updating module is used to update the user interface according to the second parsing result.

9. A user interface generation device, characterized in that: include: A parsing module, used to parse the first interaction instruction from the terminal device using the artificial intelligence big model to obtain an instruction field; A third sending module, configured to determine response data of the first interaction data based on the instruction field, and send a first parsing result generated based on the response data to the terminal device, so that the terminal device generates a user interface according to the first parsing result; The fourth sending module is used to send a second analysis result obtained by parsing the second interaction data using the artificial intelligence big model to the terminal device upon receiving a second interaction instruction sent by the terminal device based on the first analysis result, so that the terminal device updates the user interface according to the second analysis result.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.

Images