Input guiding method and computing device

Abstract

The embodiment of the invention provides an input guiding method and computing equipment. In the input guiding method, in response to user operation, a computing device displays first guiding information for guiding a user to input a service request text in an input area of an interactive interface, and determines second guiding information for guiding the user to perform supplementary input under the condition that it is detected that text content of a target type appears in the input area, and displaying the second guide information in the input area.

Description

Technical Field

[0001] This specification relates to the field of Internet technology, and in particular to an input guidance method and a computing device. Background Technology

[0002] In the field of human-computer interaction, relevant platforms (such as content creation platforms, AI assistants, ticket submission platforms, and development platforms) can provide corresponding services to users based on their input at the interface. In this process, the accuracy and completeness of the user's input determines the efficiency and quality of the platform's services.

[0003] The information in the background section is merely information known only to the inventor and does not imply that such information had entered the public domain before the date of this application, nor does it imply that it can be considered prior art in this disclosure. Summary of the Invention

[0004] This manual provides an input guidance method and computing device that can provide continuous guidance to users, assisting them in inputting more accurate, complete, and platform-predictable descriptive text, thereby improving user experience and enhancing the platform's service efficiency and quality.

[0005] In a first aspect, this specification provides an input guidance method, which includes: in response to a user operation, displaying first guidance information in an input area of ​​an interactive interface to guide the user to input service request text; when text content of a target type is detected in the input area, determining second guidance information to guide the user to supplement the input; and then displaying the second guidance information in the input area.

[0006] In some embodiments, displaying the second guidance information in the input area when the current cursor is adjacent to the last character of the text content includes: determining the current display position of the current cursor in the input area; determining the target display position of the second guidance information in the input area based on the current display position, wherein the target display position and the current display position are adjacent and do not overlap; and displaying the second guidance information at the target display position.

[0007] In some embodiments, determining the current display position of the current cursor within the input area includes: determining first position information of the current cursor within the interactive interface, and determining second position information of the input area within the interactive interface; and determining the current display position based on the first position information and the second position information.

[0008] In some embodiments, the interactive interface is a browser interface, which includes a rich text editor built on the Slate.js framework. Determining any one of the first location information or the second location information includes: obtaining the Slate range corresponding to the target object and converting it into a DOM range, wherein the target object is the current cursor or the input area; and determining the location information corresponding to the target object based on the DOM range.

[0009] In some embodiments, the second boot information is configured to disable pointer events.

[0010] In some embodiments, the interactive interface supports multiple display levels, and displaying the second guidance information in the input area includes: determining a pre-configured level of the second guidance information, wherein the pre-configured level is an intermediate level among the multiple display levels; and displaying the second guidance information at the input area position of the pre-configured level.

[0011] In some embodiments, the input area includes an add control, the target type is an automatically generated type, and the text content is obtained based on the following: in response to detecting that the user triggers the add control, displaying multiple sub-service tags to the user; and automatically generating text content corresponding to the target sub-service tag in the input area based on the user's selection operation of the target sub-service tag.

[0012] In some embodiments, different sub-service tags correspond to different preset guidance information, and the second guidance information is determined based on the preset guidance information corresponding to the target sub-service tag.

[0013] In some embodiments, the method further includes updating the second guidance information if the text content corresponding to the target sub-service label changes within the input area.

[0014] In some embodiments, the first guidance information and the second guidance information are different. The second guidance information is displayed when preset display conditions are met. The preset display conditions include at least one of the following: the input guidance function is enabled; no text is currently selected; the target type is an automatically generated type; or the second guidance information is not empty.

[0015] In some embodiments, the target type is a non-automatically generated type, the first guidance information and the second guidance information are the same, and displaying the second guidance information in the input area includes: during user input, continuously and dynamically displaying the second guidance information at a position adjacent to the cursor in the input area.

[0016] Secondly, this specification also provides a computing device, comprising: at least one storage medium storing at least one instruction set; and at least one processor communicatively connected to the at least one storage medium, wherein the at least one processor reads the at least one instruction set during operation and executes the method as described in the first aspect according to the instructions of the at least one instruction set.

[0017] Thirdly, this specification provides a computer-readable non-transitory storage medium, wherein the computer-readable non-transitory storage medium stores at least one instruction set, which, when executed by at least one processor, implements the method as described in the first aspect.

[0018] Other functions of the input boot methods, computing devices, and storage media provided in this specification will be partially listed in the following description. The inventive aspects of the input boot methods, computing devices, and storage media provided in this specification can be fully understood through practice or by using the methods, devices, and combinations described in the detailed examples below. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A schematic diagram illustrating an application scenario for input guidance provided according to embodiments of this specification is shown; Figure 2 A hardware structure diagram of a computing device provided according to an embodiment of this specification is shown; Figure 3 A flowchart of an input guidance method provided according to an embodiment of this specification is shown; Figure 4 A schematic diagram showing the display of first guidance information in an input area according to an embodiment of this specification is shown; Figure 5 A schematic diagram illustrating the display of second guidance information in an input area according to an embodiment of this specification is shown; Figure 6 A schematic diagram of user input based on second guidance information provided according to an embodiment of this specification is shown; Figure 7 Another schematic diagram illustrating user input based on second guidance information, provided according to an embodiment of this specification, is shown; and Figure 8A schematic diagram of an input completion interface provided according to an embodiment of this specification is shown. Detailed Implementation

[0021] The following description provides specific application scenarios and requirements for this specification, intended to enable those skilled in the art to make and use the contents of this specification. Various partial modifications to the disclosed embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments and applications without departing from the spirit and scope of this specification. Therefore, this specification is not limited to the embodiments shown, but rather to the widest scope consistent with the claims.

[0022] The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not restrictive. For example, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” used herein may also include the plural forms. Unless otherwise stated, the term “a plurality” means two or more, and “at least one” means one or more. Terms such as “first,” “second,” etc., may be used in this specification to describe various information, but such information should not be limited to these terms. These terms are used to distinguish information of the same type from one another and do not necessarily imply a specific order or sequence. For example, “first” may also be referred to as “second” without departing from the scope of embodiments described herein, and similarly, “second” may also be referred to as “first.”

[0023] The term "at least one of A, B, or C" includes seven cases: A only, B only, C only, both A and B, both A and C, both B and C, and both A, B, and C. Similarly, the statement "at least one of multiple items" refers to all possible combinations based on these items. The term "and / or" refers to any or all possible combinations of one or more related listed items. For example, "A and / or B" includes three cases: A only, B only, and both A and B. "A, B, and / or C" is equivalent to "at least one of A, B, or C". The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0024] The term "comprising" is an open-ended description and should be understood as "including but not limited to," potentially including other content beyond what has been described. When used in this specification, the terms "comprising," "including," and / or "containing" mean the presence of the associated integers, steps, operations, elements, and / or components, but do not exclude the presence of one or more other features, integers, steps, operations, elements, components, and / or groups, or the possibility of adding other features, integers, steps, operations, elements, components, and / or groups to the system / method.

[0025] Considering the following description, these and other features of this specification, as well as the operation and function of the related components of the structure, and the economy of assembly and manufacture of the parts, can be significantly improved. All of these form part of this specification with reference to the accompanying drawings. However, it should be clearly understood that the drawings are for illustrative and descriptive purposes only and are not intended to limit the scope of this specification. It should also be understood that the drawings are not drawn to scale.

[0026] The flowcharts used in this specification illustrate operations implemented according to some embodiments of this specification. It should be clearly understood that the operations in the flowcharts may not be implemented in a sequential order. Instead, the operations may be implemented in reverse order or simultaneously. Furthermore, one or more additional operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

[0027] Figure 1 A schematic diagram illustrating an application scenario for input guidance provided according to embodiments of this specification is shown. For example... Figure 1 As shown, scenario 100 includes user 10 and service platform 20.

[0028] In some embodiments, the service platform 20 provides services to the user 10 through a client installed in the terminal device 21.

[0029] In some embodiments, the service platform 20 provides services to the user 10 through a client and a server 23 installed in the terminal device 21. The server 23 provides background services to the client.

[0030] For example, the client installed on terminal device 21 can be an application (APP) of the service platform, or a browsing APP (such as a browser) that can access the service platform website. The client can display the interactive interface provided by the service platform to user 10, and the user can operate on the interactive interface to request the service platform to provide corresponding services.

[0031] Terminal device 21 may include mobile devices, tablets, laptops, built-in devices in motor vehicles, or similar content, or any combination thereof. In some embodiments, the mobile device may include smart home devices, smart mobile devices, virtual reality devices, augmented reality devices, or similar devices, or any combination thereof. In some embodiments, the smart home device may include a smart TV, desktop computer, etc., or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, personal digital assistant, gaming device, navigation device, etc., or any combination thereof. In some embodiments, the virtual reality device or augmented reality device may include a virtual reality headset, virtual reality glasses, virtual reality patch, augmented reality headset, augmented reality glasses, augmented reality patch, or similar content, or any combination thereof. For example, the virtual reality device or the augmented reality device may include AR glasses, head-mounted displays, VR, etc. In some embodiments, the built-in device in the motor vehicle may include an in-vehicle computer, in-vehicle TV, etc.

[0032] In some embodiments, the interactive interface displayed by the service platform 20 to the user 10 through the terminal device 21 includes an input area, where the user can input their needs or necessary information for the services provided by the service platform. The client in the terminal device 21 responds to the user 10's input, executing the task corresponding to the need or related service either independently or in collaboration with the server 23. After execution, the client can display the execution result to the user 10 through the interactive interface.

[0033] Taking content creation as an example, the service platform provides content creation services or content generation services. The interactive interface displayed by the service platform to user 10 through terminal device 21 includes an input area. Users can input their content creation needs in the input area, and then the service platform can generate the creation content specified by user 10 (such as images, videos, audio, PPTs, resumes, etc.) and display it to user 10.

[0034] Taking a dialogue scenario as an example, the service platform can be an intelligent robot that provides dialogue services. The interactive interface for dialogue displayed to user 10 through terminal device 21 includes an input area. Users can input their intentions, questions, or needs in the input area, and then the service platform generates an answer to display to user 10.

[0035] Generally, service platforms can only guarantee service efficiency and quality when users input relatively accurate and complete descriptive text. For some complex service scenarios, users need to input a larger number of characters or more detailed content to ensure the accuracy and completeness of their needs, which presents a higher barrier to entry. To lower the input barrier for users and improve input standardization, service platforms can adopt input guidance mechanisms (or input prompt mechanisms) to guide users in inputting relevant content.

[0036] In some embodiments, the service platform can employ placeholder technology, which displays static guiding text when the input box of the interactive interface is empty, directing the user's input direction. However, placeholder is a native attribute of the input element in Hyper Text Markup Language (HTML). This static guiding text disappears immediately after the user enters characters, which is sufficient for inputs with a limited number of characters. In some complex service scenarios, when the static guiding text is lengthy, its disappearance may cause users to forget the content midway through input, leading to omissions or incorrect input. Users would then need to delete the input to review the static guiding text, resulting in low input efficiency and a poor user experience.

[0037] In some embodiments, the service platform can implement input guidance using Cascading Style Sheets (CSS) pseudo-elements. For example, the service platform uses `::before` to add an icon to the left of the input area, wraps the input area in a container with relative positioning, uses the container's `::after` pseudo-element to create input guidance information, and places the input guidance information in an appropriate position within the input area. In this embodiment, the service platform has difficulty accurately positioning the cursor (i.e., the user's current position indicator in the text input area), and the input guidance information is not easily dynamically changed.

[0038] In some embodiments, the service platform can implement input guidance through dynamic insertion using JavaScript. For example, in response to events such as focus, input, and click within the input area, the service platform obtains the cursor's position information in the interactive interface in real time, dynamically creates elements carrying input guidance information based on this position information, and sets their styles to position the input guidance information near the cursor or around the input area. This embodiment's input guidance method is complex to implement, computationally expensive, and may suffer from inaccurate positioning in complex layouts.

[0039] In view of this, this specification provides an input guidance method P300 to overcome the above problems.

[0040] The input guidance method P300 provided in this manual can be completed independently by terminal device 21, or it can be completed collaboratively by terminal device 21 and server 23. This manual does not impose any restrictions on this. The following text mainly describes the method completed independently by terminal device 21 as an example.

[0041] In some embodiments, terminal device 21 is a device with certain data processing capabilities. Terminal device 21 can execute the input guidance method P300 described herein. For example, terminal device 21 can store data and instructions for implementing input guidance method P300, and can execute or be used to execute said data and instructions. In some embodiments, terminal device 21 may include hardware devices with data information processing functions and the necessary programs required to drive the hardware devices to work.

[0042] Figure 2 A hardware structure diagram of a computing device 200 provided according to an embodiment of this specification is shown. The computing device 200 may be... Figure 1 Terminal device 21 in the middle.

[0043] like Figure 2 As shown, the computing device 200 may include at least one storage medium 230 and at least one processor 220. In some embodiments, the computing device 200 may also include a communication port 250 and an internal communication bus 210. Furthermore, the computing device 200 may also include I / O components 260.

[0044] The internal communication bus 210 can connect to different system components. For example, the internal communication bus 210 can connect to storage medium 230, processor 220, communication port 250, and I / O component 260.

[0045] I / O component 260 supports input / output between computing device 200 and other components.

[0046] Communication port 250 is used for data communication between computing device 200 and the outside world. For example, communication port 250 can be used for data communication between computing device 200 and a network. Communication port 250 can be a wired communication port or a wireless communication port.

[0047] In some embodiments, the network can be any type of wired or wireless network, or a combination thereof. For example, the network may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network™, a ZigBee™ short-range wireless network, a near field communication (NFC) network, or a similar network.

[0048] In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations or internet switching points. Through these access points, one or more components of various devices corresponding to computing device 200 can connect to the network to exchange data or information.

[0049] Storage medium 230 may include a data storage device. The data storage device may be a non-transitory storage medium or a temporary storage medium. For example, the data storage device may include one or more of a disk 232, a read-only storage medium (ROM) 234, or a random access storage medium (RAM) 236. Storage medium 230 also includes at least one instruction set stored in the data storage device. The instruction set may include computer program code, which may include programs, routines, objects, components, data structures, procedures, modules, etc., that execute the input boot methods provided in this specification.

[0050] Processor 220 can be communicatively connected to storage medium 230. Processor 220 is used to execute at least one of the above-described instruction sets. When computing device 200 is running, processor 220 reads the at least one instruction set and executes the input boot method provided in this specification according to the instructions of the at least one instruction set.

[0051] Processor 220 may be in the form of one or more processors. In some embodiments, processor 220 may include one or more hardware processors, such as microcontrollers, microprocessors, reduced instruction set computers (RISC), application-specific integrated circuits (ASICs), application-specific instruction set processors (ASIPs), central processing units (CPUs), graphics processing units (GPUs), physical processing units (PPUs), microcontroller units, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), advanced RISC machines (ARMs), programmable logic devices (PLDs), any circuit or processor capable of performing one or more functions, or any combination thereof.

[0052] For the purpose of illustrating the point only, in the appendix Figure 2 Only one processor 220 is shown in the computing device 200. However, it should be noted that the computing device 200 may also include multiple processors. Therefore, the operation and / or method steps disclosed in this specification may be executed by one processor as described in this specification, or they may be executed jointly by multiple processors. For example, if the processor 220 of the computing device 200 in this specification executes steps A and B, it should be understood that steps A and B may also be executed jointly or separately by two different processors 220 (e.g., the first processor executes step A, the second processor executes step B, or the first and second processors jointly execute steps A and B).

[0053] Figure 3 A flowchart of an input guidance method P300 provided according to an embodiment of this specification is shown. The computing device 200 can execute the input guidance method P300.

[0054] The input guidance method P300 provided in this manual can be applied to any scenario requiring text input, such as content creation scenarios where users create or generate specified content, development scenarios where developers write code, and dialogue scenarios with large models or intelligent agents. The following descriptions primarily focus on content creation scenarios; this manual does not impose limitations on these scenarios.

[0055] like Figure 3 As shown, the input guidance method P300 includes the following steps.

[0056] S310: In response to user operation, display first guidance information in the input area of ​​the interactive interface to guide the user to enter the service request text.

[0057] User actions can be understood as requests made through the interactive interface. When a dedicated app developed by the service platform is installed on the computing system 200, the user action can be either opening the dedicated app on the terminal device or a triggered action performed on the target service within the initial interface provided by the dedicated app after the user has opened it on the terminal device. When a browsing app is installed on the computing system 200, the user action can be accessing the service platform website or a triggered action performed on the target service within the initial interface provided by the service platform website after the user has accessed the service platform website through the browsing app.

[0058] The target services include, but are not limited to, content creation or dialogue. For example, if the service platform provides content creation services, user actions could be requests made through the content creation interface. Similarly, if the service platform provides dialogue services, user actions could be requests made through the dialogue interface.

[0059] After detecting a user interaction, the computing device 200 can display an interactive interface to the user. This interactive interface can be an interface within a dedicated app or a browser-based app. Taking a dedicated app as an example, the interactive interface can be the initial screen (the first screen displayed after the app is opened) or the screen after the user interacts with the app and switches from the initial screen; this manual does not impose any restrictions on this.

[0060] The input area in the interactive interface is a module of the computing device 200 that collects user input (such as service request text). It has intuitive visual identifiers (such as text boxes, hidden menus, buttons, etc.) and clearly indicates the user's input position through clear boundaries. It supports diverse input methods, including but not limited to: user input via keyboard, voice, or handwriting, or input automatically generated by the user performing specific operations. The input area can be a continuous input box, meaning the space for user input is a continuous, undivided area; this specification does not impose any restrictions on this.

[0061] The first guidance information is used to guide users to enter service request text. Service request text can be understood as: description information of user needs, or necessary information that users need to fill in during the process of the service platform providing services to users (such as content creation, answering questions).

[0062] When a service platform offers a diverse range of services, the initial guidance information can be more general, applicable to service request texts for multiple service types. Conversely, when a service platform offers a relatively singular range of services, the initial guidance information can be more specialized, applicable to service request texts for a specific service type.

[0063] The initial guidance information may be input content suggestions provided by the computing device 200 to the user through natural language. This information guides the user to understand one or more of the following: the purpose of the input area, the required dimensions of the input content, examples of the input content, or the format requirements of the input content, ensuring that the user inputs valid, comprehensive, and service-platform-compliant content within the input area. The initial guidance information includes, but is not limited to: the format of the input content, the dimensions, scope, and direction of the input content. Based on the prompts provided by the initial guidance information, the user can input their specific needs or necessary or key information required by the platform within the input area.

[0064] For example, the service platform provides content creation services, and the interactive interface is as follows: Figure 4 As shown, the gray characters are the first guiding information, guiding users to input the information dimensions required by the service platform to complete content creation (such as user needs, ideas, content usage scenarios, functions, style, etc.).

[0065] S320: If text content of the target type is detected in the input area, determine the second guidance information to guide the user to complete the input.

[0066] The computing device 200 can monitor changes in the content of the input area. When characters appear in the input area, the computing device determines that text content has appeared in the input area. The target type can be automatically generated or non-automatically generated; this specification does not limit this. Non-automatically generated text content can be understood as: the characters in the text content in the input area are manually typed or voice-inputted by the user. Automatically generated text content can be understood as: the characters in the text content in the input area are automatically generated by the computing device 200 based on specific user operations; that is, the characters in the text content are not typed or voice-inputted by the user in sequence. When the text content includes multiple characters, these multiple characters are generated and appear simultaneously.

[0067] In some embodiments, the input area includes an add control, and the target type is automatically generated. The text content appearing in the input area is obtained as follows: in response to detecting that a user has triggered the add control, multiple sub-service labels are displayed to the user, and based on the user's selection of the target sub-service label, the text content corresponding to the target sub-service label is automatically generated in the input area.

[0068] Multiple sub-service tags can be identifiers for multiple sub-services after the service platform has finely divided the services it supports. After the user selects a sub-service tag, the computing device 200 can automatically generate the aforementioned text content.

[0069] For example, in a content creation scenario, multiple sub-service tags correspond to different creation types. For instance... Figure 5As shown, after the computing device 200 detects that the user clicks to add a control, it can display a pop-up window (or hide the menu) on the interactive interface. The pop-up window can display the following sub-service tags: Resume Creation, PPT Creation, and Product Creation Factory. When the computing device 200 detects that the user selects the Resume Creation tag, it generates the text content corresponding to the Resume Creation tag. The text content corresponding to the Resume Creation tag can be the resume creation itself, or it can be the preset extended content corresponding to the Resume Creation tag; this manual does not impose any restrictions on this. The computing device 200 can pre-set the extended content related to each sub-service tag, thereby saving the user's input time and improving input efficiency.

[0070] See also Figure 5 When a user selects the "Resume Creation" tab and clicks the "OK" button in the pop-up window, the input area automatically generates text containing "Resume Creation," and the current cursor is immediately next to the last character of "Resume Creation."

[0071] In this embodiment, users can automatically generate text content through simple operations such as clicking and checking, without having to type it word by word, thus improving input efficiency, reducing human input error rate, and improving input accuracy.

[0072] If the text content appearing in the input area is of the automatically generated type and the user has not finished entering the service request text, the computing device 200 also needs to determine the second guidance information to guide the user to complete the input.

[0073] In some embodiments, different sub-service tags correspond to different preset guidance information, which can be stored locally on the computing device 200. The computing device 200 can determine the second guidance information based on the preset guidance information corresponding to the target sub-service tag. In this case, the first guidance information and the second guidance information are different. The first guidance information can be understood as general guidance content provided by the service platform, and the second guidance information can be understood as specific guidance content corresponding to the target sub-service tag.

[0074] For example, the preset guidance information corresponding to each sub-service tag can be predetermined and stored locally by the computing device 200, or it can be determined in real time by the computing device 200 during user input. This specification does not impose any restrictions on this. For instance, after the computing device 200 determines that the user has selected a target sub-service tag, it assembles the target sub-service tag and the preset prompt and inputs them into the large language model. The large language model then outputs the second guidance information corresponding to the target sub-service tag.

[0075] The second guiding information corresponding to the target sub-service tag guides the user to input the service request text for the target sub-service, enabling the user to understand one or more of the following: the coverage dimensions of the input content, examples of the input content, or the format requirements of the input content. The service request text for the target sub-service can be understood as: a description of the user's needs for the target sub-service, or necessary information that the user needs to fill in during the process of the service platform providing the target sub-service (such as PPT creation or resume creation). The second guiding information is similar in form to the first guiding information, such as being expressed in natural language, and will not be elaborated further.

[0076] In some embodiments, when the text content appearing in the input area is of a non-automatically generated type and the user's service request text has not been fully entered, the second guidance information determined by the computing device 200 is the same as the first guidance information.

[0077] S330: Display the second guidance information in the input area.

[0078] In some embodiments, the text content appearing in the input area is not automatically generated. In this case, the content of the first guidance information and the second guidance information is the same. The current cursor is immediately adjacent to the last character of the text content. During user input, the computing device 200 can continuously and dynamically display the second guidance information at a position adjacent to the cursor in the input area (to the right, below, or lower right, etc.). As the user continues to input characters, the display position of the second guidance information moves synchronously with the direction of cursor movement.

[0079] In this embodiment, the first and second guidance information have the same content, but their attributes can be different. For example, the first guidance information displayed before the user enters text content can be a placeholder that disappears as the user inputs. After the user enters text content, the second guidance information displayed is not a placeholder and does not disappear as the user inputs. This is suitable for complex input scenarios where the number of characters in the first guidance information exceeds a preset threshold. Continuously displaying guidance information in the input area can provide continuous guidance to the user, ensuring the accuracy and completeness of the user's input and improving the user's input experience.

[0080] In some embodiments, the text content appearing in the input area is automatically generated; in this case, the first and second guidance messages differ. See also... Figure 5, after the automatically generated text content appears in the input area, the first guiding information disappears, and the current cursor is adjacent to the last character of the text content (such as the character "zuo" in resume creation). After the computing device 200 determines the second guiding information corresponding to the target sub-service label, it can display the second guiding information (such as "Provide your work experience, including working time period, work unit, job responsibilities, etc.") at an adjacent position (right, below, or lower right, etc.) of the cursor in the input area.

[0081] In this embodiment, the time period between the disappearance of the first guiding information and the display of the second guiding information is at the millisecond level. Visually for the user, the second guiding information and the automatically generated text content can appear almost simultaneously, and the second guiding information can provide more professional and detailed guidance to the user, improving the user's input experience.

[0082] Before the computing device 200 displays the second guiding information in the input area, it also needs to determine the target display position of the second guiding information.

[0083] In some embodiments, the current cursor is adjacent to the last character of the text content (automatically generated type or non-automatically generated type) in the input area. The computing device 200 can determine the current display position of the current cursor in the input area, determine the target display position of the second guiding information in the input area based on the current display position, and display the second guiding information at the target display position. The target display position is adjacent to and does not overlap with the current display position.

[0084] The current display position is the current position to be input in the input area, and can be on the right adjacent side of the last character of the text content. In this embodiment, the current focus of the user's attention is near the cursor. Displaying the second guiding information near the cursor in the input area can prevent the display position of the second guiding information from being fixed or additionally occupying other layout spaces in the interactive interface other than the input area. In a compact interactive interface such as a mobile device, it can save space resources, improve the visual neatness of the interactive interface, and also reduce the range of the user's line of sight movement when referring to the second guiding information, improving the input efficiency and input experience.

[0085] The computing device 200 can determine the current display position of the current cursor in the input area in various ways. Here are several ways for example, and this specification does not limit this.

[0086] Method 1 The computing device 200 determines the first position information of the current cursor on the interactive interface and the second position information of the input area on the interactive interface, and then determines the current display position based on the first and second position information. The current display position is the relative position of the current cursor within the input area. Position information can be understood as the position coordinates of one or more pixels on the display screen of the terminal device, but this specification does not limit this.

[0087] For example, the interactive interface is a browser interface, which includes a rich text editor built on the Slate.js framework. The computing device 200 obtains the Slate range corresponding to the target object and converts it into a Document Object Model (DOM) range, determining the position information of the target object based on this DOM range. The target object is the current cursor or input area.

[0088] For example, computing device 200 can obtain the Slate range corresponding to the current cursor and convert it into the DOM range corresponding to the current cursor, and then determine the first position information based on the DOM range corresponding to the current cursor. Computing device 200 can also obtain the Slate range corresponding to the input area and convert it into the DOM range corresponding to the input area, and then determine the second position information based on the DOM range corresponding to the input area. In this example, the text editor of the input area uses the Slate.js framework (a customizable rich text editor framework), and the complexity of computing device 200 in determining each position information is low, with minimal computational overhead.

[0089] Specifically, the computing device 200 can call the `ReactEditor.toDOMRange` method of `Slate.js` to convert the Slate range corresponding to the current cursor into a DOM range, and then call the `getBoundingClientRect` method of the DOM range to return a `DOMRect` object containing at least some of the attributes such as top, left, right, bottom, width, and height. The first position information is then determined based on the `DOMRect` object. The computing device 200 determines the second position information in a similar way, and will not be described further.

[0090] After determining the first position information and the second position information, the computing device 200 can determine the relative position information of the current cursor in the input area based on the first position information and the second position information, and use it as the current display position.

[0091] Method 1 ensures that when the second guidance information is continuously displayed at a position adjacent to the cursor, the second guidance information can move with the cursor, avoiding being obscured by the user's input content. It also avoids the situation where the second guidance information and the cursor are separated due to the scrolling of the input area on the interactive interface, thus improving the user's input fluency.

[0092] Method 2 Each character within the input area has the same width. The computing device 200 can determine the initial position of the cursor within the input area (i.e., the cursor position before the user inputs characters when the input area has no text content) using the selectionStart attribute of the textarea element, and then determine the current display position based on the number of characters in the text content appearing within the input area and the width of each character. After determining the current display position of the cursor, the computing device 200 can offset the cursor to the right and / or down by a preset number of pixels (e.g., about 1-5 pixels) to obtain the target display position, so that the second guidance information is close to the cursor without obscuring it, thus avoiding obstacles to user input.

[0093] In some embodiments, after obtaining the current display position of the cursor, the computing device 200 can also create a div element (short for Division) and display second guidance information to the user at the target display position through the div element. The div element is a commonly used block-level container element in HTML, which has no semantic meaning and does not affect the content or layout of the interactive interface.

[0094] The computing device 200 can obtain (or set) the `position` property of the second guiding information or the `div` element containing the second guiding information. For example, the `position` property of the second guiding information or the `div` element containing the second guiding information is set to absolute positioning. Furthermore, the computing device 200 can also obtain (or set) the values ​​of the `top` style (`style.top`) and / or `left` style (`style.left`) of the second guiding information or the corresponding `div` element, thereby ensuring that the second guiding information is displayed to the right, below, or lower right of the current cursor, avoiding overlap with the cursor. The value of `style.top` represents the distance of the top edge of the second guiding information relative to the top edge of the positioning context (the current cursor). The value of `style.left` represents the distance of the left edge of the second guiding information relative to the left edge of the positioning context (the current cursor). Absolute positioning is one of the positioning methods, where the second guiding information (the element to be positioned) is positioned relative to the nearest positioned ancestor element (the current cursor).

[0095] In some embodiments, the second guidance information or the div element carrying the second guidance information is configured to disable pointer events. Disabling pointer events can be understood as: the second guidance information displayed in the input area will not respond to pointer operations such as mouse, touch, or stylus input.

[0096] For example, the computing device 200 can pre-set the pointerEvents field of the second guidance information or the div element carrying the second guidance information to 'none'. This way, when a user accidentally touches the second guidance information in the input area, the second guidance information will not become the target of mouse or other pointer operations. Mouse or other pointers can pass through the second guidance information and act on other content in the same spatial location on the interactive interface. In other words, the second guidance information only serves as a visual cue, without affecting or interfering with the user's normal input operations, thus improving the user's input experience.

[0097] In some embodiments, the interactive interface supports multiple display layers. The computing device 200 can determine (or set) the pre-configured layer of the second guidance information or the div element carrying the second guidance information, and then display the second guidance information at the input area position or target display position of the pre-configured layer. The pre-configured layer is the middle layer among multiple display layers. The display layer can be understood as a layer perpendicular to the display screen; the higher the priority of the display layer, the closer the display layer is to the user.

[0098] For example, the z-Index field indicates the display hierarchy of different content or div elements carrying different content, controlling the stacking order of related elements on the z-axis perpendicular to the display screen. After determining the second guidance information and its target display position, the computing device 200 can read the z-Index field value of the second guidance information or the div element carrying the second guidance information, and determine the pre-configured hierarchy of the second guidance information based on the field value.

[0099] In this embodiment, the computing device 200 can set an appropriate zIndex field value for the second guidance information or the div element carrying the second guidance information, so that during the display of the second guidance information in the interactive interface, other content (such as content with lower display priority) will not cover the second guidance information above it, causing the user to not see the second guidance information and causing input obstacles. In addition, it can also ensure that the second guidance information will not cover pop-ups, menus, tools or other content with higher display priority in the input area, so as to avoid affecting or interfering with the user's use of higher priority functions or tools.

[0100] In some embodiments, if the text content corresponding to the target sub-service label changes within the input area, the computing device 200 updates the second guidance information displayed within the input area.

[0101] For example, if a user deletes the text content corresponding to the target sub-service tag in the input area and selects another sub-service tag (such as PPT creation), the computing device 200 can display the third guidance information corresponding to the other sub-service tag in the input area, at which point the second guidance information disappears. If the number of characters in the text content corresponding to the other sub-service tag and the target sub-service tag is the same, the computing device 200 can update only the second guidance information to the third guidance information. If the number of characters in the text content corresponding to the other sub-service tag and the target sub-service tag is different, the computing device 200 needs to recalculate the display position of the third guidance information and then display the third guidance information in the corresponding position in the input area. In this case, the display position of the third guidance information is different from the display position of the second guidance information.

[0102] For example, when a user deletes the text content corresponding to the target sub-service label in the input area and does not select other sub-service labels, the computing device 200 can update the second guidance information in the input area to the first guidance information. At this time, the content and display position of the first guidance information are different from the second guidance information.

[0103] For example, after a user adds a new sub-service label based on the target sub-service label using the add control, the computing device 200 can update the second guidance information to the third guidance information corresponding to the newly added sub-service label, determine the display position of the third guidance information, and then display the third guidance information at the corresponding position in the input area.

[0104] In some embodiments, the first guidance information and the second guidance information are different. The computing device 200 determines and displays the second guidance information when preset display conditions are met. The preset display conditions include at least one of the following: ① the input guidance function is enabled; ② no text is currently selected; ③ the target type is automatically generated; or ④ the second guidance information is not empty.

[0105] For example, the preset display conditions include ①. The computing device 200 can read the indicator field (such as absolutePlaceholder) indicating the input guidance function's on / off state. If the indicator field is true, the computing device 200 determines that the input guidance function is on, and condition ① is met. If the indicator field is false, the computing device 200 determines that the input guidance function is off, and condition ① is not met. The on / off state of the input guidance function can be set by the computing device 200 by default, or it can be set by the user during user input; this specification does not impose any restrictions on this.

[0106] For example, the preset display condition includes ②. The computing device 200 can monitor changes in the selection area of ​​the input region (the selection area represents a segment of characters selected by the user using a mouse or keyboard) to determine whether text is currently selected in the input region. If the computing device 200 detects that the cursor in the input region is blinking, it determines that no text is currently selected, i.e., condition ② is met. If the computing device 200 detects that the user has selected at least one character in the input region, it determines that text is currently selected, i.e., condition ② is not met.

[0107] For example, the preset display condition includes ③. The computing device 200 can determine whether the text content appearing in the input area is automatically generated. If the text content appearing in the input area is automatically generated after the user adds a control, the computing device 200 determines that condition ③ is met. If the text content appearing in the input area is typed or voice-inputted by the user, the computing device 200 determines that condition ③ is not met.

[0108] For example, the preset display condition includes ④. The computing device 200 can read the guidance information indication field (such as displayPlaceholder) corresponding to the target sub-service tag. If the guidance information indication field indicates that the preset guidance information corresponding to the target sub-service tag is empty, then it is determined that the second guidance information is empty, and condition ④ is not satisfied. If the guidance information indication field indicates that the preset guidance information corresponding to the target sub-service tag is not empty, then it is determined that the second guidance information is not empty, and condition ④ is satisfied.

[0109] When the preset display conditions include multiple conditions, the computing device 200 determines whether each condition is met in a manner described above. Furthermore, when all conditions included in the preset display conditions are met, the computing device 200 determines that the preset display conditions are met. If the preset display conditions include multiple conditions, and only some conditions are met, the computing device 200 determines that the preset display conditions are not met.

[0110] The guidance information can be displayed in several ways, including but not limited to: Type 1: The guidance information disappears when content appears in the input area; Type 2: The guidance information is continuously displayed when content appears in the input area. The above preset display conditions can also be the display conditions corresponding to Type 2.

[0111] In this embodiment, the second guidance information is a condition-triggered prompt, which appears only when the preset display conditions are met, i.e. when there is a need for guidance. This ensures that the guidance information is strongly related to the user's current operation, provides more accurate guidance, and enhances the efficiency and accuracy of the interaction.

[0112] In some embodiments, after automatically generated text content appears in the input area, as the user inputs characters in the input area, the computing device 200 can continuously and dynamically display second guidance information at the position adjacent to the cursor in the input area until the user finishes inputting in the input area.

[0113] For example Figure 6 As shown, the computing device 200 can distinguish between user-inputted characters, automatically generated text content, and second guidance information by font color. As the number of characters entered by the user increases, the second guidance information moves with the cursor position. The computing device 200 can display at least a portion of the second guidance information on a new line, that is, switch characters that may exceed the input area boundary to the next line, ensuring that the second guidance information does not occupy interactive interface space outside the input area and avoids affecting the overall layout of the interactive interface.

[0114] In some embodiments, see Figure 7 After automatically generated text appears in the input area, the second guidance information can disappear as the user inputs more characters. This embodiment is applicable to input scenarios where the second guidance information is relatively simple, i.e., the number of characters in the second guidance information is less than or equal to a preset threshold. The disappearance of the second guidance information simplifies the input area, avoids unnecessary distraction of the user, and improves user input efficiency and visual experience.

[0115] In some embodiments, after the user finishes inputting in the input area, the computing device 200 obtains the automatically generated text content in the input area and / or the text content manually entered by the user (inputting by typing or voice, etc.), and provides the user with a target service (e.g., creating a resume) based on the obtained text content.

[0116] For example, Figure 8 As shown, after the user clicks the input completion button ("↑") in the input area, the computing device 200 can obtain the automatically generated text content (such as resume creation) in the input area and the text content manually entered by the user (such as the first job description: the employer is xx, the working period is xx, and the job responsibilities in the employer are xxxx...). Based on the above text content, the device can create a resume. After the resume is created, the device can display the detailed content of the resume or the link to view the resume on the interactive interface.

[0117] In this specification, the computing device 200 can also implement animated display effects of guidance information (such as first guidance information or second guidance information) through CSS transition or JavaScript animation library to enhance the user's visual experience.

[0118] It should be noted that the above description of method P300 uses a content creation scenario as an example. Therefore, the specific description uses terminology that would be involved in that scenario, such as sub-service tags and examples of sub-services. If method P300 is applied to other scenarios mentioned above, the terminology involved can be adjusted accordingly, and will not be listed here.

[0119] In summary, the input guidance method and computing device provided in this manual can continuously display guidance information during user input, guiding users to understand input requirements and specifications, and assisting users in inputting more accurate, complete, and descriptions that conform to the service platform's expectations or relevant specifications. This avoids problems such as user input omissions or non-standard input caused by the disappearance of guidance information after text content appears in the input area in complex input scenarios, thereby improving user input efficiency and also enhancing the service efficiency and quality of the service platform.

[0120] In this specification, the Large Language Model (LLM) may also be referred to simply as the Large Model. A Large Language Model is a natural language processing model based on deep learning techniques, typically with billions to hundreds of billions or even more parameters, possessing powerful language understanding and generation capabilities. Large Language Models can employ the Transformer architecture or its variants (such as GPT, BERT, etc.), which utilizes an attention mechanism to globally model sequential data, efficiently handling long-distance dependencies and thus performing exceptionally well in natural language tasks. Large Language Models learn the statistical features and semantic relationships of language through pre-training on large-scale corpora, giving them good generalization capabilities. The core capabilities of Large Language Models include, but are not limited to: understanding contextual semantics, generating coherent and grammatically correct text, performing logical reasoning, and handling multi-task scenarios. Its usage typically includes two modes: direct inference and fine-tuning. In direct inference mode, the user guides the Large Language Model to generate specific outputs by designing prompts. Cue words can be task descriptions or instructions in text form, used to stimulate the semantic understanding and generation capabilities of large language models. In fine-tuning mode, large language models are further trained on small-scale datasets in specific domains to optimize their performance on specific tasks. The powerful generalization ability and flexibility of large language models make them an important tool in the field of artificial intelligence, providing efficient and accurate solutions for automated text generation and understanding.

[0121] In some embodiments, large language models can also understand and generate data from other modalities (such as visual and audio data). In this case, large language models can also be called multimodal large language models (MLLMs). MLLMs provide a richer and more natural interactive experience by integrating multiple types of input and output, such as text, images, and sound. The core advantage of MLLMs lies in their ability to process and understand information from different modalities and fuse this information to complete complex tasks. For example, MLLMs can analyze an image and generate descriptive text, or generate a corresponding image based on a text description. This cross-modal understanding and generation capability makes MLLMs widely applicable across multiple fields.

[0122] It should be noted that the key technologies of large language models can be found in the detailed description in the paper "A Survey of Large Language Models" (paper number: arXiv:2303.18223v16, published on March 11, 2025, public link: https: / / doi.org / 10.48550 / arXiv.2303.18223), and will not be repeated here.

[0123] This specification, in another aspect, provides a computer-readable non-transitory storage medium storing at least one set of executable instructions for input boot. When the executable instructions are executed by a processor, they instruct the processor to perform the steps of method P300 described herein. In some possible embodiments, various aspects of this specification may also be implemented as a program product comprising program code. When the program product is run on computing device 200, the program code causes computing device 200 to perform the steps of method P300 described herein. The program product for implementing the above method may employ a portable compact disc read-only memory (CD-ROM) containing program code and may run on computing device 200. However, the program product of this specification is not limited thereto. In this specification, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. Program code for performing the operations described herein can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on computing device 200, partially on computing device 200, as a standalone software package, partially on computing device 200 and partially on a remote computing device, or entirely on a remote computing device.

[0124] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0125] In summary, after reading this detailed disclosure, those skilled in the art will understand that the foregoing detailed disclosure is presented by way of example only and is not restrictive. Although not explicitly stated herein, those skilled in the art will understand that this specification requires various reasonable changes, improvements, and modifications to the embodiments. These changes, improvements, and modifications are intended to be made by this specification and are within the spirit and scope of the exemplary embodiments described herein.

[0126] Furthermore, certain terms in this specification have been used to describe embodiments of this specification. For example, "an embodiment," "an embodiment," and / or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with that embodiment may be included in at least one embodiment of this specification. Therefore, it is to be emphasized and understood that two or more references to "an embodiment" or "an embodiment" or "alternative embodiment" in various parts of this specification do not necessarily refer to the same embodiment. Moreover, specific features, structures, or characteristics may be suitably combined in one or more embodiments of this specification.

[0127] It should be understood that in the foregoing description of the embodiments in this specification, various features are combined in a single embodiment, drawing, or description for the purpose of simplifying the description and aiding in the understanding of a feature. However, this does not mean that the combination of these features is necessary, and those skilled in the art will readily identify some of them as separate embodiments when reading this specification. That is, the embodiments in this specification can also be understood as an integration of multiple secondary embodiments. It is also valid when each secondary embodiment contains fewer than all the features of a single foregoing disclosed embodiment.

[0128] Every patent, patent application, publication of a patent application, and other material cited herein, such as articles, books, specifications, publications, documents, and literature (excluding any related historical examination documents), is referenced for all purposes relevant to this document, including in the specification and claims herein. However, in the event of any inconsistency or conflict between the descriptions, definitions, and / or terms used in the foregoing and those used herein, the descriptions, definitions, and / or terms used herein shall prevail.

[0129] Finally, it should be understood that the embodiments disclosed herein are illustrative of the principles of the embodiments described in this specification. Other modified embodiments are also within the scope of this specification. Therefore, the embodiments disclosed in this specification are merely examples and not limitations. Those skilled in the art can implement the applications described in this specification using alternative configurations based on the embodiments in this specification. Therefore, the embodiments in this specification are not limited to the embodiments precisely described in the applications.

Claims

1. An input guidance method, comprising: In response to user actions, the system displays initial guidance information in the input area of ​​the interactive interface, prompting the user to enter the text of the service request. If text content of the target type is detected in the input area, second guidance information is determined to guide the user to complete the input. as well as The second guidance information is displayed in the input area.

2. The method according to claim 1, wherein, The cursor is currently adjacent to the last character of the text content, and the second guiding information is displayed in the input area, including: Determine the current display position of the cursor within the input area; Based on the current display position, the target display position of the second guidance information within the input area is determined, wherein the target display position and the current display position are adjacent but do not overlap; and The second guidance information is displayed at the target display location.

3. The method according to claim 2, wherein, Determining the current display position of the current cursor within the input area includes: Determine the first position information of the current cursor on the interactive interface, and determine the second position information of the input area on the interactive interface; and The current display position is determined based on the first location information and the second location information.

4. The method according to claim 3, wherein, The interactive interface is a browser interface, which includes a rich text editor built on the Slate.js framework, and determines either the first location information or the second location information, including: Obtain the Slate range corresponding to the target object and convert it to a DOM range, wherein the target object is the current cursor or the input region; and The location information corresponding to the target object is determined based on the DOM range.

5. The method according to claim 1, wherein, The second boot information is configured to disable pointer events.

6. The method according to claim 1 or 5, wherein, The interactive interface supports multiple display levels, and displays the second guidance information in the input area, including: Determine the pre-configuration level of the second guidance information, wherein the pre-configuration level is an intermediate level among the plurality of display levels; and The second guidance information is displayed at the input area location of the pre-configured level.

7. The method according to claim 1, wherein, The input area includes an add control, the target type is an automatically generated type, and the text content is obtained based on the following method: In response to detecting that the user has triggered the add control, multiple sub-service tabs are displayed to the user; and Based on the user's selection of the target sub-service tag, the text content corresponding to the target sub-service tag is automatically generated in the input area.

8. The method according to claim 7, wherein, Different sub-service tags correspond to different preset guidance information, and the second guidance information is determined based on the preset guidance information corresponding to the target sub-service tag.

9. The method according to claim 7, wherein, The method further includes: If the text content corresponding to the target sub-service label changes within the input area, the second guidance information is updated.

10. The method according to claim 1, wherein, The first guidance information and the second guidance information are different. The second guidance information is displayed when preset display conditions are met, and the preset display conditions include at least one of the following: Input guidance is now enabled; No text is currently selected; The target type is an automatically generated type; or The second guidance information is not empty.

11. The method according to claim 1, wherein, The target type is a non-automatically generated type. The first guidance information and the second guidance information are the same. The second guidance information is displayed in the input area, including: During user input, the second guidance information is continuously and dynamically displayed at positions adjacent to the cursor within the input area.

12. A computing device, comprising: At least one storage medium storing at least one instruction set; as well as At least one processor is communicatively connected to the at least one storage medium, wherein the at least one processor reads the at least one instruction set during operation and performs the method as described in any one of claims 1-11 according to the instructions of the at least one instruction set.

Images