Information recommendation method, device, equipment, storage medium and program product
By identifying application scenarios and intent scenarios in the information editing interface, screening candidate recommendation information and using machine learning models to optimize the recommendation order, the problem of inaccurate information recommendation in existing technologies is solved, and more efficient information recommendation is achieved.
Patent Information
- Application Number
- CN202211080945.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-05
- Publication Date
- 2025-09-12
- Estimated Expiration
- 2042-09-05
AI Technical Summary
Existing technologies fail to effectively consider users' actual application scenarios and intentions during the information input process, resulting in poor accuracy and pertinence of information recommendations.
By displaying editing prompt information in the information editing interface to determine the target application scenario, and identifying the intent scenario based on the content input by the user, the corresponding candidate recommendation information is screened out, the application icon or pop-up prompt is dynamically displayed, and the recommendation priority is predicted by combining the machine learning model to achieve accurate information recommendation.
The accuracy and pertinence of information recommendations are improved, the amount of recommended information selected by users is reduced, and selection efficiency is improved.
Smart Images

Figure CN117009494B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to computer technology, and in particular to an information recommendation method, apparatus, device, storage medium, and program product. Background Art
[0002] With the development of computer technology, electronic devices such as mobile phones and tablet computers are becoming more and more popular, bringing great convenience to people's life, study and work. These electronic devices are usually installed with input method applications (abbreviated as input methods), allowing users to use the input methods to input information.
[0003] In order to improve the efficiency of information input, relevant technologies provide corresponding related information based on the user's input content during the information input process. However, this recommendation method only mechanically provides related words based on the input content, without considering the application scenarios and intentions actually required by the user, resulting in poor accuracy and pertinence of information recommendations. Summary of the Invention
[0004] The embodiments of the present application provide an information recommendation method, apparatus, device, computer-readable storage medium, and computer program product, which can improve the accuracy and pertinence of information recommendations.
[0005] The technical solution of the embodiment of the present application is implemented as follows:
[0006] This embodiment of the present application provides an information recommendation method, including:
[0007] Displaying an information editing interface including editing prompt information, wherein the editing prompt information is used to determine an application scenario of the information editing interface;
[0008] In response to determining that the application scenario of the information editing interface is a target application scenario based on the editing prompt information, displaying recommendation prompt information corresponding to the target application scenario, wherein the recommendation prompt information is used to indicate that there is recommended information corresponding to the target application scenario;
[0009] In response to a triggering operation on the recommendation prompt information, displaying at least one first candidate recommendation information corresponding to the target application scenario;
[0010] In response to the target intent scenario corresponding to the target content input based on the information editing interface being a target intent scenario, displaying at least one second candidate recommendation information corresponding to the target intent scenario, where the second candidate recommendation information is obtained by screening from the first candidate recommendation information;
[0011] In response to a selection operation on target recommended information in the at least one second candidate recommended information, the target recommended information is displayed in the information editing interface.
[0012] The present invention provides an information recommendation device, including:
[0013] A first display module is configured to display an information editing interface including editing prompt information, wherein the editing prompt information is used to determine an application scenario of the information editing interface;
[0014] a second display module, configured to, in response to determining that the application scenario of the information editing interface is a target application scenario based on the editing prompt information, display recommendation prompt information corresponding to the target application scenario, wherein the recommendation prompt information is used to indicate that there is recommended information corresponding to the target application scenario;
[0015] a third display module, configured to display at least one first candidate recommendation information corresponding to the target application scenario in response to a triggering operation on the recommendation prompt information;
[0016] a fourth display module, configured to, in response to the target intent scenario corresponding to the target content input based on the information editing interface being a target intent scenario, display at least one second candidate recommendation information corresponding to the target intent scenario, where the second candidate recommendation information is obtained by screening from the first candidate recommendation information;
[0017] The fifth display module is configured to display the target recommended information in the information editing interface in response to a selection operation on the target recommended information in the at least one second candidate recommended information.
[0018] In the above scheme, the second display module is also used to display a virtual keyboard in the information editing interface, dynamically display the application icon corresponding to the target application scenario in the toolbar of the virtual keyboard, and use the dynamically displayed application icon as the recommended prompt information; or, in the information editing interface, display the recommended prompt information corresponding to the target application scenario through a pop-up window.
[0019] In the above scheme, the third display module is also used to display an application scenario category selection interface through a sub-interface independent of the information editing interface, and highlight the target application scenario in the application scenario category selection interface; in response to a trigger operation for the target application scenario, at least one first candidate recommendation information corresponding to the target application scenario is displayed.
[0020] In the above scheme, the device also includes: a sixth display module, which is used to display a switching control in the associated display area of the target application scene during the process of highlighting the target application scene; wherein, the switching control is used to switch the target application scene to other application scenes to recommend information in the other application scenes.
[0021] In the above scheme, the third display module is further used to determine the recommendation priority of each first candidate recommendation information when the number of the first candidate recommendation information is at least two; and display the corresponding first candidate recommendation information using a display method that is compatible with the recommendation priority.
[0022] In the above scheme, the third display module is also used to obtain recommendation reference parameters, and the recommendation reference parameters include at least one of the following: the matching degree between the current object and each of the first candidate recommendation information, and the historical interaction rate corresponding to each of the first candidate recommendation information; based on the recommendation reference parameters, the machine learning model is called to perform recommendation priority prediction to obtain the recommendation priority of each of the first candidate recommendation information.
[0023] In the above scheme, the third display module is also used to display each first candidate recommendation information in a manner such that the higher the recommendation priority, the earlier the corresponding first candidate recommendation information; or, according to the recommendation priority, each first candidate recommendation information is displayed in a different display style.
[0024] In the above scheme, when the at least one first candidate recommendation information is located in the target recommendation package, before displaying the at least one first candidate recommendation information corresponding to the target application scenario, the device also includes: a recommendation package creation module, used to display a creation entry for creating a recommendation package; in response to the recommendation package creation operation triggered based on the creation entry, the recommendation package parameters of the created target recommendation package are displayed, and the recommendation package parameters include at least one of the following: the name, cover, directory, and at least one first candidate recommendation information of the recommendation package; in response to the determination operation of the recommendation package parameters, an association relationship is established between the target recommendation package and the recommendation package parameters, and at least one candidate application scenario option for selection is displayed; in response to the application scenario association operation, an association relationship is established between the target recommendation package and the selected target application scenario.
[0025] In the above scheme, when the recommendation package parameters include: the name of the target recommendation package and at least one associated first candidate recommendation information, the recommendation package creation module is also used to display a recommendation package creation interface in response to a trigger operation on the creation entry, and display a first creation area for creating a recommendation package name and a second creation area for creating candidate recommendation information in the recommendation package creation interface; in response to the recommendation package name creation operation, the name of the created target recommendation package is displayed in the first creation area, and in response to the candidate recommendation information creation operation, the at least one first candidate recommendation information created is displayed in the second creation area.
[0026] In the above scheme, the device also includes: a details display module, which is used to display the details viewing entrance of the recommended package corresponding to the target application scenario; in response to the triggering operation of the details viewing entrance of the recommended package, at least one recommended package corresponding to the target application scenario is displayed, and the at least one recommended package includes at least the target recommended package.
[0027] In the above scheme, the fourth display module is also used to display a search control for searching for recommended information in the information editing interface; in response to the intention scenario corresponding to the target content input based on the search control being the target intention scenario, at least one second candidate recommended information corresponding to the target intention scenario is displayed.
[0028] In the above scheme, after the information editing interface including editing prompt information is displayed, the device also includes: an application scenario determination module, which is used to extract keywords from the editing prompt information to obtain a first keyword corresponding to the editing prompt information; obtain a second keyword corresponding to at least one application scenario corresponding to the information editing interface, and match the first keyword with each of the second keywords; when the first keyword matches the second keyword corresponding to the target application scenario, determine that the application scenario of the information editing interface is the target application scenario.
[0029] In the above scheme, before displaying at least one second candidate recommendation information corresponding to the target intention scene, the device also includes: an intention scene determination module, which is used to identify the intention scene of the target content input based on the information editing interface, and obtain the identified intention scene corresponding to the target content; obtain at least one candidate intention scene under the target application scenario, and match the identified intention scene with each of the candidate intention scenes; when the identified intention scene matches the target intention scene in the at least one candidate intention scene, determine that the intention scene corresponding to the target content is the target intention scene.
[0030] An embodiment of the present application provides an electronic device, including:
[0031] a memory for storing computer-executable instructions;
[0032] The processor is configured to implement the information recommendation method provided in the embodiment of the present application when executing the computer-executable instructions stored in the memory.
[0033] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for causing a processor to execute instructions to implement the information recommendation method provided in the embodiment of the present application.
[0034] An embodiment of the present application provides a computer program product, including a computer program or computer-executable instructions. When the computer program or computer-executable instructions are executed by a processor, the information recommendation method provided in the embodiment of the present application is implemented.
[0035] The embodiments of the present application have the following beneficial effects:
[0036] When applying the embodiment of the present application, in the information recommendation process, the target application scenario corresponding to the information editing interface is first determined based on the editing prompt information in the information editing interface, and the first candidate recommended information under the target application scenario is displayed; secondly, based on the target content input in the information editing interface, the second candidate recommended information corresponding to the target intention scenario corresponding to the target content is filtered out from the first candidate recommended information for user selection. In this way, after two rounds of screening, the recommended information finally displayed is the recommended information corresponding to the information editing interface and the target content, which not only improves the pertinence and accuracy of the information recommendation, but also greatly reduces the number of recommended information available for selection, making it easier for users to select the most suitable recommended information at the moment, thereby improving selection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 A schematic diagram of the architecture of the information recommendation system 100 provided in an embodiment of the present application;
[0038] Figure 2 A schematic diagram of the structure of an electronic device 500 provided in an embodiment of the present application;
[0039] Figure 3 A flowchart of the information recommendation method provided in an embodiment of the present application;
[0040] Figures 4A-4B A schematic diagram of the display of the information editing interface provided in an embodiment of the present application;
[0041] Figures 5A-5B A schematic diagram showing the display of recommended prompt information provided in an embodiment of the present application;
[0042] Figure 6A A schematic diagram of creating a recommendation package provided in an embodiment of the present application;
[0043] Figures 6B-6C A schematic diagram of creating a recommendation package provided in an embodiment of the present application;
[0044] Figure 7 A schematic diagram showing details of the recommended package provided in the embodiment of this application;
[0045] Figure 8 A schematic diagram showing the display of the first candidate recommendation information provided in an embodiment of the present application;
[0046] Figure 9A schematic diagram of switching between application scenarios provided in an embodiment of the present application;
[0047] Figure 10 A schematic diagram of creating a recommendation package provided in an embodiment of the present application;
[0048] Figure 11 A schematic diagram of the search function provided in an embodiment of the present application;
[0049] Figure 12 A functional diagram of the discovery page provided in an embodiment of the present application;
[0050] Figure 13 A schematic diagram of the collection page function provided in an embodiment of the present application;
[0051] Figure 14 Schematic diagram of information recommendation processing provided in an embodiment of the present application. DETAILED DESCRIPTION
[0052] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0053] It is understandable that in the embodiments of the present application, when data related to user information (such as object characteristics of the current object, interactive characteristics for recommended information, etc.) is involved, when the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.
[0054] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
[0055] In the following description, the terms "first\second..." are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first\second..." can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.
[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.
[0057] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.
[0058] 1) Client: An application running in the terminal to provide various services, such as a short video client, a video playback client, an instant messaging client, a learning client, etc.
[0059] 2) In response, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed can be real-time or have a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.
[0060] See also Figure 1 , Figure 1 This is an architectural diagram of the information recommendation system 100 provided in an embodiment of the present application. To support an exemplary application, terminals (terminal 400-1 and terminal 400-2 are shown as examples) are connected to the server 200 via a network 300. The network 300 can be a wide area network or a local area network, or a combination of the two, and wireless links are used to achieve data transmission.
[0061] In actual applications, the terminal 400 can be various types of user terminals such as smart phones, tablet computers, laptops, etc., or a desktop computer, a television, or a combination of any two or more of these data processing devices; the server 200 can be a separately configured server that supports various services, or it can be configured as a server cluster, or it can be a cloud server, etc.
[0062] In actual applications, the terminal is provided with clients, such as short video clients, video playback clients, instant messaging clients, learning clients, etc. When the user opens the client on the terminal to edit information, the terminal displays an information editing interface including editing prompt information, wherein the editing prompt information is used to determine the application scenario of the information editing interface; in response to the application scenario of the information editing interface determined based on the editing prompt information as the target application scenario, the recommendation prompt information corresponding to the target application scenario is displayed, wherein the recommendation prompt information is used to prompt that there is recommended information corresponding to the target application scenario; in response to the trigger operation for the recommendation prompt information, a recommendation request is sent to the server 200; the server determines at least one first candidate recommendation information corresponding to the target application scenario in response to the recommendation request, and returns the at least one first candidate recommendation information corresponding to the determined target application scenario to the terminal for display; in response to the intention scenario corresponding to the target content input based on the information editing interface as the target intention scenario, the terminal sends a recommendation request to the server 200; in response to the recommendation request, the server filters out at least one second candidate recommendation information corresponding to the target intention scenario from the first candidate recommendation information, and returns the at least one second candidate recommendation information corresponding to the determined target intention scenario to the terminal for display; the terminal displays the target recommendation information in the information editing interface in response to the selection operation of the target recommendation information in the at least one second candidate recommendation information.
[0063] See also Figure 2 , Figure 2 This is a structural diagram of an electronic device 500 provided in an embodiment of the present application. In practical applications, the electronic device 500 may be Figure 1 The terminal or server 200 in the embodiment of the present invention is an electronic device. Figure 1 Taking the terminal shown as an example, an electronic device that implements the information recommendation method of the embodiment of the present application is described. Figure 2 The electronic device 500 shown includes: at least one processor 510, a memory 550, at least one network interface 520 and a user interface 530. The various components in the electronic device 500 are coupled together via a bus system 540. It is understood that the bus system 540 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 540 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 540 is not shown in FIG. Figure 3 Various buses are labeled as bus system 540 .
[0064] The processor 510 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.
[0065] The user interface 530 includes one or more output devices 531 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 530 also includes one or more input devices 532, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.
[0066] The memory 550 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical drives, etc. The memory 550 may optionally include one or more storage devices that are physically remote from the processor 510.
[0067] The memory 550 includes volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 550 described in the embodiments of the present application is intended to include any suitable type of memory.
[0068] In some embodiments, the memory 550 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplified below.
[0069] Operating system 551, including system programs for processing various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;
[0070] A network communication module 552 for reaching other computing devices via one or more (wired or wireless) network interfaces 520 , exemplary network interfaces 520 including Bluetooth, WiFi, and USB;
[0071] a presentation module 553 for enabling presentation of information via one or more output devices 531 (e.g., a display screen, a speaker, etc.) associated with the user interface 530 (e.g., a user interface for operating peripheral devices and displaying content and information);
[0072] The input processing module 554 is configured to detect one or more user inputs or interactions from one of the one or more input devices 532 and to translate the detected inputs or interactions.
[0073] In some embodiments, the information recommendation device provided in the embodiments of the present application can be implemented in software. Figure 2 An information recommendation device 555 stored in a memory 550 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: a first display module 5551, a second display module 5552, a third display module 5553, a fourth display module 5554 and a fifth display module 5555. These modules are logical, and therefore can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.
[0074] In other embodiments, the information recommendation device provided in the embodiments of the present application can be implemented in hardware. As an example, the information recommendation device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the information recommendation method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.
[0075] In some embodiments, the terminal or server can implement the information recommendation method provided in the embodiments of the present application by running a computer program. For example, the computer program can be a native program or software module in the operating system; it can be a native application (APP, Application), that is, a program that needs to be installed in the operating system to run, such as a live broadcast APP or an instant messaging APP; it can also be a small program, that is, a program that can be run only by downloading it into a browser environment; it can also be a small program that can be embedded in any APP. In short, the above-mentioned computer program can be any form of application, module or plug-in.
[0076] Based on the above description of the information recommendation system provided by the embodiment of the present application, the information recommendation method provided by the embodiment of the present application is described below. In actual implementation, the method can be Figure 1 The terminal or server 200 shown is implemented separately, and can also be implemented by Figure 1 The terminal and server 200 shown are implemented in conjunction with each other. Figure 1 and Figure 3 , Figure 3 This is a flow chart of the information recommendation method provided in the embodiment of the present application. Figure 1 The terminal shown is used as an example to illustrate the information recommendation method provided in the embodiment of the present application.
[0077] Step 101: The terminal displays an information editing interface including editing prompt information, wherein the editing prompt information is used to determine an application scenario of the information editing interface.
[0078] In actual applications, a terminal is provided with a client, such as a short video client, a video playback client, an instant messaging client, a learning client, etc. When a user opens a client on the terminal to edit information, the terminal displays an information editing interface including editing prompt information. The information editing interface includes, but is not limited to, the following interfaces: an information editing interface in a video playback application, an information editing interface in a web browsing application, an information editing interface in an information sharing application, etc., which is not limited in the embodiment of the present invention.
[0079] The editing prompt information can be the default copy displayed in the edit box or input box in the information editing interface. The default copy can be used to determine the application scenario of the information editing interface. It can also be template information for information editing. The template information can be used to determine the application scenario of the information editing interface. The application scenarios include but are not limited to posting barrages, comments, chatting, posting to Moments, product introductions or short video releases.
[0080] See also Figures 4A-4B , Figures 4A-4B This is a schematic diagram of the information editing interface provided in the embodiment of the present application. Figure 4A In the information editing interface 401A of the video playback application, an editing prompt message 402A such as "Send a friendly comment to witness the moment" (i.e., a default copy) is displayed. Through the editing prompt message 402A, it can be determined that the application scenario of the current information editing interface is the application scenario of sending a comment; Figure 4BIn the information editing interface 401B of the information sharing application, template information 402B for information editing is displayed, such as the editing area, location, who to remind to see, who can see, etc. Since the template information is consistent with the template information in the application scenario of posting to Moments, the template information can be used to determine that the application scenario of the current information editing interface is the application scenario of posting to Moments.
[0081] Step 102: In response to the application scenario of the information editing interface being determined as the target application scenario based on the editing prompt information, displaying recommendation prompt information corresponding to the target application scenario, wherein the recommendation prompt information is used to prompt that there is recommended information corresponding to the target application scenario.
[0082] Here, the target application scenario is an application scenario for which the system is pre-configured with corresponding recommended information. In some embodiments, after the terminal displays the information editing interface including editing prompt information, it can determine that the application scenario of the information editing interface is the target application scenario in the following manner: perform keyword extraction on the editing prompt information to obtain the first keyword corresponding to the editing prompt information; obtain the second keyword corresponding to at least one application scenario of the information editing interface, and match the first keyword with each second keyword; when the first keyword matches the second keyword corresponding to the target application scenario, determine that the application scenario of the information editing interface is the target application scenario.
[0083] Here, in actual applications, before the terminal identifies the application scenario, it can pre-establish an association relationship between each application scenario and the corresponding keyword (i.e., the second keyword). When the information editing interface is displayed in the terminal, the editing prompt information in the information editing interface is collected, and the editing prompt information is subjected to keyword extraction. The extracted first keyword is matched with the corresponding second keyword of each application scenario (such as calculating the cosine similarity value between the first keyword and each second keyword). When the first keyword matches the second keyword corresponding to the target application scenario (such as the cosine similarity value between the two exceeds the similarity threshold), the application scenario of the information editing interface is determined to be the target application scenario.
[0084] It should be noted that the terminal can also determine the application scenario of the information editing interface through the triggering display method of the information editing interface. For example, when the information editing interface is displayed by the user clicking the barrage control in the target application (such as a video playback application), it can be determined that the application scenario of the information editing interface is the barrage sending scenario corresponding to the barrage control; for example, when the information editing interface is displayed by the user clicking the chat control in the target application (such as an instant messaging application), it can be determined that the application scenario of the information editing interface is the chat scenario corresponding to the chat control.
[0085] When the terminal determines that the application scenario corresponding to the current information editing interface is the target application scenario, the terminal displays recommendation prompt information corresponding to the target application scenario in the information editing interface. In some embodiments, the terminal can display the recommendation prompt information corresponding to the target application scenario in the following ways: displaying a virtual keyboard in the information editing interface, dynamically displaying an application icon corresponding to the target application scenario in the toolbar of the virtual keyboard, and using the dynamically displayed application icon as the recommendation prompt information; or displaying the recommendation prompt information corresponding to the target application scenario in a pop-up window in the information editing interface to prompt the user that there is recommended information corresponding to the target application scenario for selection and use.
[0086] See also Figures 5A-5B , Figures 5A-5B This is a schematic diagram showing the display of recommended prompt information provided in an embodiment of the present application. Figure 5A In the example, assuming that the target application scenario is a Moments posting application scenario, an application icon 501A in the shape of a circle is displayed in the toolbar of the virtual keyboard in the information editing interface, and the application icon is displayed in a special effect form (such as a flipping effect). The application icon displayed in this way is used as a recommended prompt information for the Moments posting application scenario; Figure 5B In the application scenario of posting to Moments, a pop-up window may be displayed in the information editing interface to display a recommendation prompt message 501B such as "Click me to view more Moments content". The pop-up window may have a certain degree of transparency and may be controlled to move synchronously with the user's sliding operation in the information editing interface.
[0087] It can be understood that in actual applications, the recommendation prompt information varies according to different application scenarios. For example, when the application icon of the target application scenario is used as the recommendation prompt information, different target application scenarios correspond to different application icons. For example, when the target application scenario is application scenario A, the corresponding recommendation prompt information is represented by application icon a, and when the target application scenario is application scenario B, the corresponding recommendation prompt information is represented by application icon b.
[0088] Step 103: In response to a triggering operation on the recommendation prompt information, display at least one first candidate recommendation information corresponding to the target application scenario.
[0089] In actual applications, at least one first candidate recommendation information corresponding to the target application scenario can exist in the form of a recommendation package, that is, the terminal displays the recommendation package corresponding to the target application scenario in response to the trigger operation for the recommendation prompt information, wherein at least one first candidate recommendation information is displayed in the recommendation package. When the number of first candidate recommendation information is at least two, these at least two first candidate recommendation information can be stored in the same recommendation package or in different recommendation packages. Next, taking the example of at least one first candidate recommendation information corresponding to the target application scenario being stored in the same recommendation package (i.e., the target recommendation package), the creation of the target recommendation package corresponding to the target application scenario is explained.
[0090] In some embodiments, when at least one first candidate recommendation information is located in a target recommendation package, before displaying at least one first candidate recommendation information corresponding to the target application scenario, an association relationship between the target application scenario and the target recommendation package can be created in the following manner: displaying a creation entry for creating a recommendation package; in response to a recommendation package creation operation triggered based on the creation entry, displaying recommendation package parameters of the created target recommendation package, wherein the recommendation package parameters include at least one of the following: the name, cover, directory, and at least one first candidate recommendation information of the recommendation package; in response to a determination operation on the recommendation package parameters, displaying at least one candidate application scenario option for selection and association; in response to the application scenario association operation, establishing an association relationship between the target recommendation package and the selected target application scenario.
[0091] In some embodiments, when the recommendation package parameters include: the name of the target recommendation package and at least one associated first candidate recommendation information, the terminal can display the recommendation package parameters of the created target recommendation package in response to the recommendation package creation operation triggered based on the creation entry in the following manner: in response to the trigger operation for the creation entry, the recommendation package creation interface is displayed, and a first creation area for creating the recommendation package name and a second creation area for creating candidate recommendation information are displayed in the recommendation package creation interface; in response to the recommendation package name creation operation, the name of the created target recommendation package is displayed in the first creation area, and in response to the candidate recommendation information creation operation, the at least one first candidate recommendation information created is displayed in the second creation area.
[0092] See also Figure 6A , Figure 6AA schematic diagram of creating a recommendation package provided in an embodiment of the present application, wherein the terminal displays a creation entry (such as creation) 601 in the information editing interface, and in response to a trigger operation on the creation entry 601, displays a recommendation package creation interface 602 for creating a recommendation package (such as creating a quotation package), and displays creation areas for creating recommendation table parameters in the recommendation package creation interface 602, such as a first creation area 603 for creating a recommendation package name, a second creation area 604 for creating candidate recommendation information, a third creation area 605 for creating a recommendation package cover, and a fourth creation area 606 for creating a recommendation package directory. In response to the recommendation package creation operation, the recommendation package parameters of the created target recommendation package are displayed, such as the name of the target recommendation package can be created through the first creation area 603, the cover of the target recommendation package can be created through the third creation area 605 (such as taking a photo, obtaining an image from a local album or from the Internet as the cover of the target recommendation package), the directory of the target recommendation package can be created through the fourth creation area 606, and at least one first candidate recommendation can be edited and created through the second creation area 604. Information, after determining the recommendation package parameters of the target recommendation package, the user clicks the "Next" button, and the terminal establishes an association relationship between the target recommendation package and the recommendation package parameters in response to the determination operation for the recommendation package parameters triggered by the click operation, such as when the recommendation package parameters include at least one first candidate recommendation information, establishes an association relationship between the target recommendation package and the at least one first candidate recommendation information, so as to store the at least one first candidate recommendation information in the target recommendation package, and displays at least one candidate application scenario option for selection and association, such as displaying multiple candidate application scenario options through a sub-interface 607 suspended above the information editing interface, responding to the application scenario selection operation, the selected candidate application scenario is used as the target application scenario, and responding to the application scenario association operation for the target application scenario (also called a save operation, such as triggered by clicking the save button or clicking the share button (such as the submit button)), establishes an association relationship between the target recommendation package and the selected target application scenario, and saves or publishes the target recommendation package (including at least one first candidate recommendation information) at the same time.
[0093] Specifically, see Figures 6B-6C , Figures 6B-6C A schematic diagram of creating a recommendation package provided in an embodiment of this application is provided. Figure 6BIn the example, when creating the recommendation package parameters such as the name, directory and candidate recommendation information of the recommendation package, in response to the trigger operation for the first creation area (i.e., adding the quotation package name) 603, the creation interface of the recommendation package name (i.e., the quotation package name) is displayed, and the name of the target recommendation package can be created through the creation interface; in response to the trigger operation for the fourth creation area (i.e., the directory) 606, the creation interface of the recommendation package directory is displayed, and the directory of the target recommendation package can be created through the creation interface. In actual applications, the association relationship between the directory and the candidate recommendation information can be bound, that is, when the directory has been created, in response to the trigger operation for the second creation area (i.e., adding sentences) 604, the creation interface for creating candidate recommendation information is displayed, and at least one first candidate recommendation information can be edited and created through the creation interface. Figure 6C In response to the trigger operation for the third creation area (i.e., cover) 605, a creation interface for adding a cover is displayed, and through this creation interface, an image can be obtained from a photo, a local album, or the Internet as the cover of the target recommendation package.
[0094] In some embodiments, the terminal may also display a recommended package detail viewing entry corresponding to the target application scenario; in response to a trigger operation on the recommended package detail viewing entry, at least one recommended package corresponding to the target application scenario is displayed, wherein the at least one recommended package includes at least the target recommended package.
[0095] Here, after the user saves or publishes the created target recommendation package, the user can view the recommendation package corresponding to the target application scenario through the recommendation package details viewing entrance corresponding to the target application scenario.
[0096] See also Figure 7 , Figure 7 A schematic diagram of viewing the details of the recommended package provided in an embodiment of the present application. When the target application scenario is the application scenario of posting to Moments, when the user clicks on the application scenario of posting to Moments (which can be regarded as the entry for viewing the details of the recommended package), the terminal responds to the click operation and displays the recommended package under the application scenario of posting to Moments, and responds to the detail viewing operation for the recommended package and displays the detailed information of the recommended package.
[0097] In addition, when the user clicks on the "My" control, the terminal responds to the click operation and displays the recommended packages that the user has created or collected. In response to the click operation on the recommended package, the detailed information of the created or collected recommended package can be displayed. Moreover, when there are multiple recommended information in the recommended package, in response to the sending operation on the recommended package (such as triggered by clicking the sequential send button), multiple recommended information in the recommended package can be sent in sequence with one click.
[0098] In some embodiments, the terminal may display at least one first candidate recommendation information corresponding to the target application scenario in the following manner: displaying an application scenario category selection interface through a sub-interface independent of the information editing interface, and highlighting the target application scenario in the application scenario category selection interface; and displaying at least one first candidate recommendation information corresponding to the target application scenario in response to a trigger operation for the target application scenario.
[0099] Here, application scenarios can be divided from multiple dimensions. For example, application scenarios can be divided into multiple application scenarios such as posting barrages, comments, chatting or posting on Moments according to usage scenarios; when there are multiple categories of application scenarios, the terminal responds to the trigger operation for the recommendation prompt information, and can directly display at least one first candidate recommendation information corresponding to the target application scenario, or it can first display the application scenario category selection interface, and display multiple application scenario options for selection in the application scenario category selection interface, and highlight the target application scenario to distinguish it from other application scenarios, and respond to the trigger operation for the target application scenario, display at least one first candidate recommendation information under the target application scenario.
[0100] See also Figure 8 , Figure 8 A display diagram of the first candidate recommended information provided in an embodiment of the present application. Here, it is assumed that the application scenario corresponding to the current information editing interface is the application scenario of "posting to Moments". The terminal divides the application scenarios into application scenarios corresponding to the current information editing interface (such as posting to Moments) and application scenarios corresponding to non-current information editing interfaces, such as Discover (new application scenarios) and Mine (added or favorited application scenarios), according to whether they belong to the application scenarios corresponding to the information editing interface. The application scenarios are displayed in the application scenario category selection interface, especially highlighting the target application scenario corresponding to the current information editing interface, that is, the application scenario of "posting to Moments". When the user triggers the application scenario of "posting to Moments", multiple first candidate recommended information under the application scenario of "posting to Moments" are displayed.
[0101] It should be noted that, due to the size limitation of the display interface, the multiple first candidate recommendation information displayed in the current display interface may only be part of the first candidate recommendation information under the target application scenario. The user can refresh the current display interface by sliding the display interface, such as pulling up or down, to display more first candidate recommendation information for the user to choose.
[0102] In some embodiments, while highlighting the target application scenario, the terminal may also display a switching control in the associated display area of the target application scenario; wherein the switching control is used to switch the target application scenario to other application scenarios to recommend information in other application scenarios.
[0103] Here, when the user does not want to select information for editing from the candidate recommendation information corresponding to the target application scenario, the target application scenario can be switched to other application scenarios through the switching control associated with the target application scenario, so as to recommend information in the other application scenarios after switching, such as displaying multiple candidate recommendation information corresponding to other application scenarios, and selecting the target recommendation information from the multiple candidate recommendation information for sharing, so as to share the selected target recommendation information.
[0104] See also Figure 9 , Figure 9 A schematic diagram of switching application scenarios provided in an embodiment of the present application is provided. Taking the target application scenario as the Moments application scenario as an example, the terminal displays a change control 901 at the associated display area of the Moments application scenario. In response to a trigger operation on the switch control 901, at least two candidate application scenarios are displayed for selection, such as support, comment, release, control, and other application scenarios. In response to the application scenario selection operation, the Moments application scenario is switched to the selected other application scenario. For example, when the selected other application scenario is the comment application scenario, the Moments application scenario is switched to the comment application scenario to perform information recommendation under the comment application scenario, such as displaying multiple candidate recommendation information corresponding to the comment application scenario for users to share the target recommendation information. In this way, users can change the application scenario at will, which improves the convenience of operation and is conducive to improving the efficiency of human-computer interaction.
[0105] In some embodiments, the terminal may display at least one first candidate recommendation information corresponding to the target application scenario in the following manner: when the number of first candidate recommendation information is at least two, determine the recommendation priority of each first candidate recommendation information; and use a display method that is compatible with the recommendation priority to display the corresponding first candidate recommendation information.
[0106] Here, when the number of first candidate recommendation information is at least two, the corresponding first candidate recommendation information can be displayed in a display manner adapted to the recommendation priority according to the different recommendation priorities of each first candidate recommendation information, such as displaying each first candidate recommendation information in a manner where the higher the recommendation priority, the earlier the corresponding first candidate recommendation information is displayed; or, according to the recommendation priority, each first candidate recommendation information can be displayed in a different display style, such as displaying each first candidate recommendation information with different recommendation priorities in a different display style (such as different colors, different brightness, different indication information, etc.), especially highlighting the first candidate recommendation information with a higher recommendation priority to give a significant prompt, so as to facilitate the user to select the most appropriate first candidate recommendation information as the recommendation information required by the current information editing interface, thereby improving the convenience of operation and helping to improve the efficiency of human-computer interaction.
[0107] In some embodiments, the terminal can determine the recommendation priority of each first candidate recommendation information in the following manner: obtaining recommendation reference parameters, wherein the recommendation reference parameters include at least one of the following: the matching degree between the current object and each first candidate recommendation information, and the historical interaction rate corresponding to each first candidate recommendation information; based on the recommendation reference parameters, calling the machine learning model to perform recommendation priority prediction to obtain the recommendation priority of each first candidate recommendation information.
[0108] Here, when there are at least two first candidate recommendation information, when determining the recommendation priority of each first candidate recommendation information, an artificial intelligence algorithm can be used to predict the recommendation priority. For example, the terminal automatically obtains relevant recommendation reference parameters, such as the matching degree between the current object and each first candidate recommendation information (such as the matching degree between the object characteristics of the current object and the information characteristics of each first candidate recommendation information), the historical interaction rate corresponding to each first candidate recommendation information (such as the probability of each first candidate recommendation information being selected, commented or liked within the historical target time period), and other recommendation reference parameters. The recommendation priority is predicted by a machine learning model based on an artificial intelligence algorithm to obtain the recommendation priority of each first candidate recommendation information. Generally, the higher the matching degree or the higher the historical interaction rate, the higher the recommendation priority of the corresponding first candidate recommendation information. By screening out the target recommendation information that the current object most needs to select from multiple first candidate recommendation information to be selected based on the recommendation priority, the prediction results and screening results can be made more accurate.
[0109] It should be noted that the above-mentioned machine learning model can be a neural network model (such as a convolutional neural network, a deep convolutional neural network, or a fully connected neural network, etc.), a decision tree model, a gradient boosting tree, a multi-layer perceptron, and a support vector machine, etc. The embodiment of this application does not specifically limit the type of machine learning model.
[0110] Step 104: In response to the target intent scenario corresponding to the target content input based on the information editing interface being the target intent scenario, at least one second candidate recommendation information corresponding to the target intent scenario is displayed, wherein the second candidate recommendation information is obtained by screening from the first candidate recommendation information.
[0111] In some embodiments, before displaying at least one second candidate recommendation information corresponding to the target intention scene, the terminal performs intention scene recognition on the target content input based on the information editing interface to obtain the recognized intention scene corresponding to the target content; obtains at least one candidate intention scene under the target application scenario, and matches the recognized intention scene with each candidate intention scene; when the recognized intention scene matches the target intention scene in at least one candidate intention scene, the intention scene corresponding to the target content is determined to be the target intention scene.
[0112] Here, in actual applications, the terminal pre-creates multiple candidate intent scenarios under the target application scenario. For example, when the target application scenario is a circle of friends application scenario, the corresponding candidate intent scenarios may include but are not limited to: travel, food, sports, baby show, etc. When the user inputs the target content based on the information editing interface (there are various forms, such as edited text or uploaded pictures, etc.), the terminal can identify the intent scenario of the target content, such as using a pre-trained intent recognition model to identify the intent scenario of the target content, and obtain the recognized intent scenario corresponding to the target content, and match the recognized intent scenario with each candidate intent scenario corresponding to the target application scenario (such as calculating the cosine similarity value between the recognized intent scenario and each candidate intent scenario), and use the candidate intent scenario that matches the recognized intent scenario (such as the cosine similarity value between the two exceeds the similarity threshold) as the target intent scenario.
[0113] In some embodiments, the terminal may respond to the target intent scenario corresponding to the target content input based on the information editing interface as the target intent scenario by displaying at least one second candidate recommendation information corresponding to the target intent scenario in the following manner: displaying a search control for searching for recommended information in the information editing interface; and responding to the target intent scenario corresponding to the target content input based on the search control as the target intent scenario by displaying at least one second candidate recommendation information corresponding to the target intent scenario.
[0114] Here, when the target application scenario corresponds to multiple intent scenarios, the recommended information corresponding to different intent scenarios is different. When the intent scenario corresponding to the target content input by the user based on the information editing interface is the target intent scenario, the terminal filters out at least one second candidate recommended information corresponding to the target intent scenario from at least one first candidate recommended information corresponding to the target application scenario for the user to select. In this way, after two screenings, the recommended information finally displayed is the recommended information corresponding to the information editing interface and the target content, which improves the pertinence and accuracy of the information recommendation, and reduces the number of recommended information available for selection, making it easier for users to select the most suitable recommended information at the moment, which is conducive to improving selection efficiency.
[0115] Step 105: In response to a selection operation on target recommended information in at least one second candidate recommended information, the target recommended information is displayed in the information editing interface.
[0116] Here, when the user selects target recommended information from at least one second candidate recommended information, the selected target recommended information can be displayed in the information editing interface for the user to share (such as publish or forward, etc.).
[0117] The information recommendation method provided in the embodiments of the present application can also be applied to product introduction scenarios. For example, an editing prompt such as "Writing appropriate copy will allow more people to see the product you want to introduce" is displayed in the information editing interface of the product introduction scenario. In response to determining that the application scenario of the information editing interface is a product introduction scenario (i.e., a target application scenario) based on the editing prompt, recommendation prompt information corresponding to the product introduction scenario is displayed, such as a dynamic special effect in the style of "product introduction". In response to a triggering operation on the recommendation prompt, at least one first candidate recommendation information corresponding to the product introduction scenario is displayed. In response to the intent scenario corresponding to the target content input based on the information editing interface being the target intent scenario, such as the input target content being a picture of cosmetics A and the determined intent scenario being a cosmetics introduction scenario (i.e., the target intent scenario), at least one second candidate recommendation information corresponding to the cosmetics introduction scenario is displayed. In response to a selection operation on the target recommendation information in the at least one second candidate recommendation information, the target recommendation information is displayed in the information editing interface, so that the target recommendation information is used as the introduction copy of cosmetics A. After the introduction copy of cosmetics A is published, the introduction information of cosmetics A is recommended to other users.
[0118] The information recommendation method provided by the embodiment of the present application can also be applied to short video publishing scenarios. For example, when a recorded short video is added to the information editing interface of the short video publishing scenario, an editing prompt message such as "Writing a title and using a suitable topic will allow more people to see the short video you are about to publish" is displayed, or the added recorded short video is used as editing prompt information. In response to the application scenario of the information editing interface determined based on the editing prompt information to be a short video publishing scenario (i.e., a target application scenario), recommendation prompt information corresponding to the short video publishing scenario is displayed, such as a dynamic special effect of the "short video publishing" style. In response to a trigger operation for the recommendation prompt information, the short video is displayed. At least one first candidate recommendation information corresponding to the release scenario, in response to the intention scenario corresponding to the target content input based on the information editing interface being the target intention scenario, such as the input target content is "My Pastoral Life Diary", and the determined intention scenario is a pastoral life recording scenario (i.e., the target intention scenario), then at least one second candidate recommendation information corresponding to the pastoral life recording scenario is displayed. In response to the selection operation of the target recommendation information in the at least one second candidate recommendation information, the target recommendation information is displayed in the information editing interface, so as to use the target recommendation information as the release copy of the short video "My Pastoral Life Diary", and recommend the released short video to other users.
[0119] Through the above method, in the information recommendation process, first, the target application scenario corresponding to the information editing interface is determined according to the editing prompt information in the information editing interface, and the first candidate recommended information under the target application scenario is displayed; secondly, based on the target content input in the information editing interface, the second candidate recommended information corresponding to the target intention scenario corresponding to the target content is screened out from the first candidate recommended information for user selection. In this way, after two screenings, not only the pertinence and accuracy of the information recommendation are improved, but also the number of recommended information available for selection is greatly reduced, which makes it easier for users to choose the most suitable recommended information at the moment and improves the selection efficiency.
[0120] The following will illustrate an exemplary application of the embodiment of the present application in an actual application scenario. In actual application, before using the information recommendation method provided by the embodiment of the present application to recommend information, it is necessary to first create a recommendation package in the input method, that is, to create an association between the application scenario and the recommendation package (there is at least one first candidate recommendation information in the recommendation package) in the input method, and save or publish the created recommendation package, see Figure 10 , Figure 10 A schematic diagram of creating a recommendation package provided in an embodiment of this application is provided. Figure 10 The detailed logic of creating, editing, saving and publishing recommendation packages is explained. This application is created in the structure of "package", which supports user saving (local use) and user publishing (uploading to the server for all users to use).
[0121] Next, combine Figures 6A-6C To illustrate, when creating the recommendation package parameters such as the name, directory, and candidate recommendation information of the recommendation package, in response to the trigger operation for the first creation area (i.e., adding the quotation package name) 603, a creation interface for the recommendation package name (i.e., the quotation package name) is displayed, and the name of the target recommendation package can be created through this creation interface; in response to the trigger operation for the fourth creation area (i.e., directory) 606, a creation interface for the recommendation package directory is displayed, and the directory of the target recommendation package can be created through this creation interface. In actual application, the association relationship between the directory and the candidate recommendation information can be bound, that is, when the directory has been created, in response to the trigger operation for the second creation area (i.e., adding sentences) 604, a creation interface for creating candidate recommendation information is displayed, and at least one first candidate recommendation information can be edited and created through this creation interface; Figure 6C In response to a trigger operation on the third creation area (i.e., cover) 605, a creation interface for adding a cover is displayed. Through this creation interface, an image can be taken from a photo, a local album, or obtained from the Internet as the cover of the target recommendation package. After creating the recommended package parameters, the recommended package can be saved or published.
[0122] Next, the additional functions of the input method provided in the embodiment of the present application are described.
[0123] See also Figure 11 , Figure 11 A schematic diagram of the search function provided in the embodiment of the present application, such as Figure 11 As shown, the search function provided by the embodiment of the present application supports search history, popular recommendations, and supports users to enter keywords and obtain search results. Among them, the search keywords in the history records or popular recommendations can be slid left and right. There is a delete button on the far right of the history records. The history records can be deleted by clicking on any search keyword to display the relevant search results corresponding to the search keyword; when the user manually enters the keyword, during the process of entering the keyword, the terminal displays the associated words related to the entered keyword, and the user can click on the associated words to obtain the corresponding search results. In this way, the user can quickly obtain the required search results without entering the complete search content, which can improve the search efficiency.
[0124] See also Figure 12 , Figure 12 This is a functional diagram of the discovery page provided in an embodiment of the present application. The user enters the discovery page by default, and the page recommends the hottest, latest, and most used golden sentences and phrase packs (i.e., popular quotations) in the input method to the user. The page supports single sentence collection and adding phrase packs. At the same time, it also provides users with creative content (i.e., xx says) by celebrity writers who cooperate with the input method. Users can view the corresponding content. For example, when clicking "xx says", the corresponding recommendation details are displayed.
[0125] See also Figure 13 , Figure 13 This is a schematic diagram of the collection page function provided in the embodiment of the present application, such as Figure 13 As shown, on the My Favorites page, users can view the recommended packages (or quotation packages) that have been added or collected by the user. Users can click on the recommended package to enter the recommended package details to manage the recommended package, such as changing the added or collected quotations. The recommended package can also be sent by selecting the corresponding recommended package. When a recommendation package includes multiple recommended information (i.e., sentences), when sending, it supports sending all the recommended information of the recommendation package in succession with one click (such as sending each recommended information in succession in the order in which each recommended information appears in the recommendation package), and supports manual selection of sending part of the recommended information, that is, sending the recommended information that the user chooses to send in the recommendation package.
[0126] Based on the above description, after the association between the application scenario and the recommendation package is created in the input method, the information recommendation method provided by the embodiment of the present application can be implemented through the input method. Figure 14 , Figure 14 This is a schematic diagram of information recommendation processing provided in the embodiment of this application. Figure 14 The information recommendation method provided in the embodiment of the present application is described.
[0127] 1. Determine the target application scenario
[0128] When the user opens the input method in the client on the terminal to edit information, the terminal determines that the application scenario of the information editing interface is the target application scenario based on the editing prompt information in the information editing interface, and displays the recommended prompt information corresponding to the target application scenario, wherein the editing prompt information can be the default copy displayed in the edit box or input box in the information editing interface. The default copy can be used to determine the application scenario of the information editing interface, and the application scenario includes but is not limited to application scenarios such as posting barrage, commenting, chatting or posting to Moments, such as Figure 4A As shown, in the information editing interface 401A of the video playback application, an editing prompt message such as "Send a friendly barrage to witness the moment" (i.e., the default text) is displayed. When the user has not entered any content, the terminal can determine that the application scenario of the current information editing interface is the barrage application scenario through the editing prompt message.
[0129] The recommended prompt information is used to indicate that there is recommended information corresponding to the target application scenario, such as Figure 5A As shown, assuming that the target application scenario is a circle of friends application scenario, an application icon 501A in the style of a "circle" is displayed in the toolbar of the virtual keyboard in the information editing interface, and the application icon is displayed in a special effect form (such as a flipping animation). The application icon displayed in this way will be used as recommended prompt information for the corresponding circle of friends application scenario.
[0130] 2. Display the first candidate recommendation information
[0131] Here, in response to the triggering operation for the recommendation prompt information, the terminal displays at least one first recommendation package corresponding to the target application scenario, wherein the first recommendation package contains at least one first candidate recommendation information. For example, when the user clicks Figure 5A When the "circle" style application icon 501A is shown, the terminal responds to the trigger operation and displays a recommendation package in the application scenario of posting to the circle of friends, and the recommendation package includes at least one first candidate recommendation information.
[0132] 3. Determine the target intent scenario
[0133] Here, the target intent scenario can also be called a sub-scenario of the target application scenario. In actual applications, the terminal pre-creates multiple intent scenarios under the target application scenario (i.e., the candidate intent scenarios mentioned above). For example, when the target application scenario is a circle of friends application scenario, its corresponding intent scenarios may include but are not limited to: travel, food, sports, baby show, etc. When the user inputs the target content based on the information editing interface (such as editable text or uploaded pictures, etc.), the terminal can perform intent scenario recognition on the target content, such as using a pre-trained intent recognition model to perform intent scenario recognition on the target content, obtain the recognized intent scenario corresponding to the target content, and match the recognized intent scenario with each candidate intent scenario corresponding to the target application scenario (such as calculating the cosine similarity value between the recognized intent scenario and each candidate intent scenario), and use the candidate intent scenario that matches the recognized intent scenario (such as the cosine similarity value between the two exceeds the similarity threshold) as the target intent scenario.
[0134] 4. Display the second candidate recommendation information
[0135] When the target application scenario corresponds to multiple intent scenarios, the recommendation information (or recommendation packages) corresponding to different intent scenarios are different. When the intent scenario corresponding to the target content input by the user based on the information editing interface is the target intent scenario, the terminal filters out at least one second recommendation package corresponding to the target intent scenario from at least one first recommendation package corresponding to the target application scenario for user selection. The second recommendation package includes at least one second candidate recommendation information, and the second candidate recommendation information is obtained by filtering from the first candidate recommendation information.
[0136] Still taking the above-mentioned target application scenario as the application scenario of posting on Moments as an example, the application scenario of posting on Moments corresponds to multiple first recommendation packages (or multiple first candidate recommendation information) for intention scenarios such as travel, food, sports, and showing off children. When the target intention scenario is travel, the second recommendation package (or multiple second candidate recommendation information) corresponding to the intention scenario of travel is filtered out from the first recommendation package for the user to choose.
[0137] 5. Display target recommendation information
[0138] When the user selects target recommended information from at least one second candidate recommended information, the selected target recommended information can be displayed in the information editing interface for the user to share (such as publish or forward, etc.).
[0139] Through the above method, in the process of editing information through the input method, the recommended information finally displayed after two screenings is the recommended information corresponding to the information editing interface and the target content, which improves the pertinence and accuracy of the information recommendation, and reduces the number of recommended information available for selection, making it easier for users to choose the most suitable recommended information at the moment, which is conducive to improving selection efficiency.
[0140] The following describes an exemplary structure of the information recommendation device 555 provided in the embodiment of the present application as a software module. In some embodiments, the information recommendation device 555 is stored in Figure 2 The software modules in the information recommendation device 555 of the memory 550 may include: a first display module 5551, used to display an information editing interface including editing prompt information, wherein the editing prompt information is used to determine the application scenario of the information editing interface; a second display module 5552, used to display recommendation prompt information corresponding to the target application scenario in response to the application scenario of the information editing interface determined based on the editing prompt information as the target application scenario, wherein the recommendation prompt information is used to prompt that there is recommendation information corresponding to the target application scenario; a third display module 5553, used to display at least one first candidate recommendation information corresponding to the target application scenario in response to a trigger operation for the recommendation prompt information; a fourth display module 5554, used to display at least one second candidate recommendation information corresponding to the target intent scenario in response to the intent scenario corresponding to the target content input based on the information editing interface being the target intent scenario, wherein the second candidate recommendation information is screened from the first candidate recommendation information; a fifth display module 5555, used to display the target recommendation information in the information editing interface in response to a selection operation for the target recommendation information in the at least one second candidate recommendation information.
[0141] In some embodiments, the second display module is also used to display a virtual keyboard in the information editing interface, dynamically display an application icon corresponding to the target application scenario in the toolbar of the virtual keyboard, and use the dynamically displayed application icon as the recommended prompt information; or, in the information editing interface, display the recommended prompt information corresponding to the target application scenario through a pop-up window.
[0142] In some embodiments, the third display module is also used to display an application scenario category selection interface through a sub-interface independent of the information editing interface, and highlight the target application scenario in the application scenario category selection interface; in response to a trigger operation for the target application scenario, display at least one first candidate recommendation information corresponding to the target application scenario.
[0143] In some embodiments, the device also includes: a sixth display module, used to display a switching control in the associated display area of the target application scenario during the process of highlighting the target application scenario; wherein the switching control is used to switch the target application scenario to other application scenarios to recommend information in the other application scenarios.
[0144] In some embodiments, the third display module is further used to determine the recommendation priority of each first candidate recommendation information when the number of the first candidate recommendation information is at least two; and display the corresponding first candidate recommendation information using a display method that is compatible with the recommendation priority.
[0145] In some embodiments, the third display module is also used to obtain recommendation reference parameters, which include at least one of the following: the matching degree between the current object and each of the first candidate recommendation information, and the historical interaction rate corresponding to each of the first candidate recommendation information; based on the recommendation reference parameters, the machine learning model is called to perform recommendation priority prediction to obtain the recommendation priority of each of the first candidate recommendation information.
[0146] In some embodiments, the third display module is further used to display each first candidate recommendation information in a manner such that the higher the recommendation priority, the earlier the corresponding first candidate recommendation information is; or, according to the recommendation priority, each first candidate recommendation information is displayed in a different display style.
[0147] In some embodiments, when the at least one first candidate recommendation information is located in the target recommendation package, before displaying at least one first candidate recommendation information corresponding to the target application scenario, the device also includes: a recommendation package creation module, used to display a creation entry for creating a recommendation package; in response to a recommendation package creation operation triggered based on the creation entry, displaying the recommendation package parameters of the created target recommendation package, the recommendation package parameters including at least one of the following: the name, cover, directory, and at least one first candidate recommendation information of the recommendation package; in response to a determination operation on the recommendation package parameters, establishing an association relationship between the target recommendation package and the recommendation package parameters, and displaying at least one candidate application scenario option for selection; in response to an application scenario association operation, establishing an association relationship between the target recommendation package and the selected target application scenario.
[0148] In some embodiments, when the recommendation package parameters include: the name of the target recommendation package and at least one associated first candidate recommendation information, the recommendation package creation module is also used to display a recommendation package creation interface in response to a trigger operation on the creation entry, and display a first creation area for creating a recommendation package name and a second creation area for creating candidate recommendation information in the recommendation package creation interface; in response to the recommendation package name creation operation, the name of the created target recommendation package is displayed in the first creation area, and in response to the candidate recommendation information creation operation, the at least one first candidate recommendation information created is displayed in the second creation area.
[0149] In some embodiments, the device also includes: a details display module for displaying a details viewing entry for the recommended package corresponding to the target application scenario; in response to a trigger operation for the details viewing entry for the recommended package, displaying at least one recommended package corresponding to the target application scenario, wherein the at least one recommended package includes at least the target recommended package.
[0150] In some embodiments, the fourth display module is also used to display a search control for searching for recommended information in the information editing interface; in response to the intention scenario corresponding to the target content input based on the search control being a target intention scenario, at least one second candidate recommended information corresponding to the target intention scenario is displayed.
[0151] In some embodiments, after the information editing interface including editing prompt information is displayed, the device also includes: an application scenario determination module, which is used to extract keywords from the editing prompt information to obtain a first keyword corresponding to the editing prompt information; obtain a second keyword corresponding to at least one application scenario corresponding to the information editing interface, and match the first keyword with each of the second keywords; when the first keyword matches the second keyword corresponding to the target application scenario, determine that the application scenario of the information editing interface is the target application scenario.
[0152] In some embodiments, before displaying at least one second candidate recommendation information corresponding to the target intention scenario, the device also includes: an intention scenario determination module, which is used to perform intention scenario identification on the target content input based on the information editing interface to obtain the identified intention scenario corresponding to the target content; obtain at least one candidate intention scenario under the target application scenario, and match the identified intention scenario with each of the candidate intention scenarios; when the identified intention scenario matches the target intention scenario in the at least one candidate intention scenario, determine that the intention scenario corresponding to the target content is the target intention scenario.
[0153] The present invention provides a computer program product including a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the information recommendation method described in the present invention.
[0154] The embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor will execute the information recommendation method in the simulated scenario provided by the embodiment of the present application, for example, Figure 3 The method shown.
[0155] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or various devices including one or any combination of the above memories.
[0156] In some embodiments, computer-executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
[0157] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).
[0158] By way of example, computer-executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed across multiple sites and interconnected by a communication network.
[0159] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the scope of protection of the present application.
Claims
1. An information recommendation method, characterized in that: The method comprises: Displaying an information editing interface including editing prompt information, wherein the editing prompt information is used to determine an application scenario of the information editing interface; In response to determining that the application scenario of the information editing interface is a target application scenario based on the editing prompt information, displaying recommendation prompt information corresponding to the target application scenario, wherein the recommendation prompt information is used to indicate that there is recommended information corresponding to the target application scenario; In response to a triggering operation on the recommendation prompt information, displaying at least one first candidate recommendation information corresponding to the target application scenario; In response to the target intent scenario corresponding to the target content input based on the information editing interface being a target intent scenario, displaying at least one second candidate recommendation information corresponding to the target intent scenario, where the second candidate recommendation information is obtained by screening from the first candidate recommendation information; In response to a selection operation on target recommended information in the at least one second candidate recommended information, the target recommended information is displayed in the information editing interface.
2. The method according to claim 1, wherein The displaying of recommendation prompt information corresponding to the target application scenario includes: Displaying a virtual keyboard in the information editing interface, dynamically displaying an application icon corresponding to the target application scenario in the toolbar of the virtual keyboard, and using the dynamically displayed application icon as the recommendation prompt information; or In the information editing interface, recommended prompt information corresponding to the target application scenario is displayed through a pop-up window.
3. The method according to claim 1, wherein The displaying of at least one first candidate recommendation information corresponding to the target application scenario includes: Displaying an application scenario category selection interface through a sub-interface independent of the information editing interface, and highlighting the target application scenario in the application scenario category selection interface; In response to a triggering operation for the target application scenario, at least one first candidate recommendation information corresponding to the target application scenario is displayed.
4. The method according to claim 3, wherein The method further comprises: During the process of highlighting the target application scenario, displaying a switching control at a display area associated with the target application scenario; The switching control is used to switch the target application scenario to another application scenario, so as to recommend information in the other application scenario.
5. The method according to claim 1, wherein The displaying of at least one first candidate recommendation information corresponding to the target application scenario includes: When the number of the first candidate recommendation information is at least two, determining a recommendation priority of each of the first candidate recommendation information; The corresponding first candidate recommendation information is displayed in a display manner that is compatible with the recommendation priority.
6. The method according to claim 5, wherein The determining the recommendation priority of each of the first candidate recommendation information includes: Acquire recommendation reference parameters, where the recommendation reference parameters include at least one of the following: a matching degree between a current object and each of the first candidate recommendation information, and a historical interaction rate corresponding to each of the first candidate recommendation information; Based on the recommendation reference parameters, a machine learning model is called to predict the recommendation priority to obtain the recommendation priority of each of the first candidate recommendation information.
7. The method according to claim 5, wherein The displaying of the corresponding first candidate recommendation information in a display manner adapted to the recommendation priority includes: Displaying each piece of first candidate recommendation information in a manner such that the higher the recommendation priority, the earlier the corresponding first candidate recommendation information; or, Different display styles are used to display each first candidate recommendation information according to the recommendation priority.
8. The method according to claim 1, wherein When the at least one first candidate recommendation information is located in the target recommendation package, before displaying the at least one first candidate recommendation information corresponding to the target application scenario, the method further includes: Displays the creation entry for creating a recommended package; In response to a recommendation package creation operation triggered by the creation entry, displaying recommendation package parameters of the created target recommendation package, the recommendation package parameters including at least one of the following: a name, a cover, a directory, and at least one first candidate recommendation information of the recommendation package; In response to a determination operation on the recommendation package parameters, establishing an association relationship between the target recommendation package and the recommendation package parameters, and displaying at least one candidate application scenario option for selection; In response to the application scenario association operation, an association relationship between the target recommendation package and the selected target application scenario is established.
9. The method according to claim 8, wherein When the recommendation package parameters include: the name of the target recommendation package and at least one associated first candidate recommendation information, The displaying of the recommended package parameters of the created target recommended package in response to the recommended package creation operation triggered by the creation entry includes: In response to a trigger operation on the creation entry, displaying a recommendation package creation interface, and displaying a first creation area for creating a recommendation package name and a second creation area for creating candidate recommendation information in the recommendation package creation interface; In response to the recommendation package name creation operation, the name of the created target recommendation package is displayed in the first creation area, and in response to the candidate recommendation information creation operation, the at least one first candidate recommendation information created is displayed in the second creation area.
10. The method according to claim 8, wherein The method further comprises: Display the recommended package details corresponding to the target application scenario; In response to a triggering operation on the recommended package detail viewing entry, at least one recommended package corresponding to the target application scenario is displayed, and the at least one recommended package at least includes the target recommended package.
11. The method according to claim 1, wherein The step of: responding to the target content input based on the information editing interface corresponding to the target intent scenario as the target intent scenario, and displaying at least one second candidate recommendation information corresponding to the target intent scenario, including: Displaying a search control for searching for recommended information in the information editing interface; In response to the intention scenario corresponding to the target content input based on the search control being a target intention scenario, at least one second candidate recommendation information corresponding to the target intention scenario is displayed.
12. The method according to claim 1, wherein After displaying the information editing interface including the editing prompt information, the method further includes: Perform keyword extraction on the editing prompt information to obtain a first keyword corresponding to the editing prompt information; Obtaining a second keyword for at least one application scenario corresponding to the information editing interface, and matching the first keyword with each of the second keywords; When the first keyword matches a second keyword corresponding to the target application scenario, the application scenario of the information editing interface is determined to be the target application scenario.
13. The method according to claim 1, wherein Before displaying at least one second candidate recommendation information corresponding to the target intention scenario, the method further includes: Performing intent scene recognition on the target content input based on the information editing interface to obtain a recognition intent scene corresponding to the target content; Acquire at least one candidate intention scenario under the target application scenario, and match the identified intention scenario with each of the candidate intention scenarios; When the identified intention scene matches the target intention scene in the at least one candidate intention scene, the intention scene corresponding to the target content is determined to be the target intention scene.
14. An information recommendation device, characterized in that: The device comprises: A first display module is configured to display an information editing interface including editing prompt information, wherein the editing prompt information is used to determine an application scenario of the information editing interface; a second display module, configured to, in response to determining that the application scenario of the information editing interface is a target application scenario based on the editing prompt information, display recommendation prompt information corresponding to the target application scenario, wherein the recommendation prompt information is used to indicate that there is recommended information corresponding to the target application scenario; a third display module, configured to display at least one first candidate recommendation information corresponding to the target application scenario in response to a triggering operation on the recommendation prompt information; a fourth display module, configured to, in response to the target intent scenario corresponding to the target content input based on the information editing interface being a target intent scenario, display at least one second candidate recommendation information corresponding to the target intent scenario, where the second candidate recommendation information is obtained by screening from the first candidate recommendation information; The fifth display module is configured to display the target recommended information in the information editing interface in response to a selection operation on the target recommended information in the at least one second candidate recommended information.
15. An electronic device, characterized in that: include: a memory for storing computer-executable instructions; The processor is configured to implement the information recommendation method according to any one of claims 1 to 13 when executing the computer-executable instructions stored in the memory.
16. A computer-readable storage medium, characterized in that Computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the information recommendation method according to any one of claims 1 to 13 is implemented.
17. A computer program product comprising a computer program or computer executable instructions, characterized in that When the computer program or computer executable instructions are executed by a processor, the information recommendation method according to any one of claims 1 to 13 is implemented.
Citation Information
Patent Citations
Barrage display method and device
CN108668176A
Display method and device, electronic equipment and storage medium
CN114285988A