Method and apparatus for determining recommendation information, electronic device, and storage medium

Abstract

Embodiments of the present application provide a method and device for determining recommendation information, electronic equipment and computer readable medium, the method comprising: in response to an object selection operation, determining an object to be recommended, and displaying an information recommendation page corresponding to the object to be recommended; wherein the information recommendation page comprises a plurality of object feature information of the object to be recommended, the object feature information of the object to be recommended is determined according to the multimedia information corresponding to the object to be recommended which satisfies a preset condition; in response to a determination operation for at least one object feature information of the object to be recommended, the at least one object feature information is taken as the recommendation information of the object to be recommended.

Description

Technical Field

[0001] This application relates to the field of multimedia technology, and in particular to a method, apparatus, electronic device, and storage medium for determining recommendation information. Background Technology

[0002] In the process of introducing recommended objects through multimedia, the mining of object feature information is a crucial criterion for multimedia quality. Effective feature expression and contextualized presentation can deliver high-quality output of the object's feature information. For example, when introducing a product through multimedia, it is important to effectively convey its selling points, such as its advantages and usage scenarios. To better mine the object feature information of recommended objects, cross-referencing and learning from multiple multimedia resources can improve the quality and efficiency of the introduction.

[0003] However, related technologies require multimedia creators to manually review a large amount of multimedia resources, record information, and extract object feature information to provide information for the multimedia creation process. This method of introducing the objects to be recommended is inefficient, the amount of data reviewed manually is limited, and the quality of the information introduced is also low. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, electronic device, and storage medium for determining recommendation information, which can improve the quality and efficiency of obtaining recommendation information for objects to be recommended.

[0005] To solve the above-mentioned technical problems, the embodiments of this application are implemented through the following aspects.

[0006] In a first aspect, embodiments of this application provide a method for determining recommendation information, comprising: in response to an object selection operation, determining an object to be recommended, and displaying an information recommendation page corresponding to the object to be recommended; wherein the information recommendation page includes several object feature information of the object to be recommended, the object feature information of the object to be recommended being determined based on multimedia information corresponding to the object to be recommended that meets preset conditions; in response to a determination operation for at least one object feature information of the object to be recommended, using the at least one object feature information as recommendation information for the object to be recommended.

[0007] Secondly, embodiments of this application provide an apparatus for determining recommendation information, comprising: a first determining module, configured to determine an object to be recommended in response to an object selection operation, and to display an information recommendation page corresponding to the object to be recommended; wherein the information recommendation page includes several object feature information of the object to be recommended, and the object feature information of the object to be recommended is determined based on multimedia information corresponding to the object to be recommended that meets preset conditions; and a second determining module, configured to, in response to a determining operation of at least one object feature information of the object to be recommended, use the at least one object feature information as recommendation information of the object to be recommended.

[0008] Thirdly, embodiments of this application provide an electronic device, including: a memory, a processor, and computer-executable instructions stored in the memory and executable on the processor, wherein the computer-executable instructions, when executed by the processor, implement the method for determining recommendation information as described in the first aspect.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium for storing computer-executable instructions, which, when executed by a processor, implement the method for determining recommendation information as described in the first aspect.

[0010] In this embodiment, in response to an object selection operation, an object to be recommended is determined, and an information recommendation page corresponding to the object to be recommended is displayed. The information recommendation page includes several object feature information of the object to be recommended, which is determined based on multimedia information corresponding to the object to be recommended that meets preset conditions. In response to an operation to determine at least one object feature information of the object to be recommended, using that at least one object feature information as the recommendation information for the object to be recommended improves the quality and efficiency of obtaining the recommendation information for the object to be recommended, helping multimedia creators to accurately and quickly determine the recommendation information for the object to be recommended. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1a This illustration shows a flowchart of a method for determining recommendation information according to an embodiment of this application;

[0013] Figure 1bA schematic diagram of the information recommendation page provided in the embodiments of this application;

[0014] Figure 1c A schematic diagram of a selection page provided in an embodiment of this application;

[0015] Figure 2 Another schematic diagram of an information recommendation page for object feature information provided in an embodiment of this application;

[0016] Figure 3 This illustration shows another flowchart of a method for determining recommendation information provided in an embodiment of this application;

[0017] Figure 4 A schematic diagram of an editing page provided in an embodiment of this application;

[0018] Figure 5 A schematic diagram of a guide page provided in an embodiment of this application;

[0019] Figure 6 This diagram illustrates the structure of an apparatus for determining recommendation information according to an embodiment of this application.

[0020] Figure 7 A schematic diagram of the hardware structure of an electronic device for performing a method for determining recommendation information provided in an embodiment of this application. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0022] Figure 1a This illustration shows a flowchart of a method for determining recommendation information according to an embodiment of this application. This method can be executed by an electronic device, such as a terminal device or a server device. In other words, the method can be executed by software or hardware installed on the terminal device or server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0023] Users applying this solution can be providers or publishers of multimedia information, such as live-streaming hosts, merchant operators, or short video creators, collectively referred to as merchants. In scenarios where multimedia information is used to introduce a recommended object, there is a need for high-quality and efficient output of the object's characteristic information. To better mine the object's characteristic information, it may be necessary to learn from other multimedia information. When merchants need to create recommendation text for a product, they can learn from the recommendation information in other multimedia information related to that product to create their own product recommendation script (understandably, the recommendation script is reusable text). This allows merchants to create product recommendation text (e.g., product selling points) for short videos or live streams based on this script, eliminating the need for merchants to manually input the product recommendation text multiple times in different scenarios. Based on this, combined with... Figure 1a As shown, the following steps can be performed.

[0024] Step S110: In response to the object selection operation, determine the object to be recommended, and display the information recommendation page corresponding to the object to be recommended.

[0025] The objects to be recommended can include products that merchants are currently recommending or will recommend, and objects that short video publishers are currently recommending or will recommend. The objects to be recommended can be tangible or intangible, such as a service. The information recommendation page includes several object feature information of the objects to be recommended, which is determined based on multimedia information corresponding to the objects to be recommended that meets preset conditions.

[0026] The information recommendation page is used to display several object feature information of the object to be recommended, so that merchants can easily and quickly browse several object feature information of the object to be recommended, and can select and confirm at least one object feature information in subsequent steps through the information recommendation page. Figure 1b The illustration shows a schematic diagram of an information recommendation page provided in an embodiment of this application. Each recommended object may contain one or more object feature information. Object feature information can be used to represent the attributes, characteristics, or usage scenarios of the recommended object. For example, if the recommended object is a face cream, its object feature information may include "King of Cost-Effectiveness" and "Hydrating Champion," etc. Furthermore, object feature information can also be feature information reflecting dimensions such as usage scenarios, such as gifting to parents or relatives. The display format of object feature information may include at least one of the following: feature words, example sentences containing feature words, and multimedia content examples. For example, the feature word corresponding to the face cream may be "Hydrating," the example sentence containing the feature word may be "Hydrating expert, buy it!", and the multimedia content may be a live broadcast by a streamer selling the face cream.

[0027] Optionally, the multimedia information may take the form of short videos or live streams. It can be a complete short video or live stream content, or a segment of the short video or live stream corresponding to the object to be recommended. Merchants can view the corresponding multimedia information by triggering object feature information.

[0028] The multimedia information meets preset conditions. These preset conditions may include a predetermined parameter exceeding a preset threshold, and the predetermined parameter may include at least one of the following: multimedia information completion rate, number of comments, number of likes, and number of shares. Specifically, the multimedia information meets at least one of the following:

[0029] The completion rate of multimedia information is greater than the preset completion rate threshold;

[0030] The number of comments on this multimedia information exceeds a preset comment threshold;

[0031] The number of likes for this multimedia message exceeds a preset likes threshold;

[0032] The number of shares of this multimedia information exceeds the preset share threshold.

[0033] Therefore, by setting predetermined conditions, the quality of multimedia information can be improved, as well as the quality of the recommendation information for the objects to be recommended ultimately determined from the multimedia information.

[0034] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the intellectual property rights, types of personal information, scope of use, and usage scenarios involved in the application through appropriate means, and user authorization will be obtained. For example, before determining at least one multimedia corresponding to the object to be recommended in this step, as an optional but not limited implementation, authorization from the copyright holder of the multimedia should also be received. This authorization can be achieved by sending a prompt message to the user, for example, through a pop-up window, in which the authorization prompt message can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide copyright authorization to the electronic device, and realize the user's confirmation of the scope of use, usage scenarios, etc. of the copyright. Similarly, similar technical processing can be performed when it is necessary to obtain the personal information of the user, such as the copyright holder of the multimedia. It is understood that the above notification and user authorization process is only illustrative and does not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations can also be applied to the implementation of this disclosure.

[0035] Step S120: In response to the determination operation of at least one object feature information for the object to be recommended, the at least one object feature information is used as the recommendation information for the object to be recommended.

[0036] Combination Figure 1b Users can select either "King of Cost-Effectiveness" (object feature information 1) or "Champion of Moisturizing" (object feature information 2). If "Champion of Moisturizing" is selected, it will be used as the recommended information for the object to be recommended in this step.

[0037] This invention provides a method for determining recommendation information, comprising, in response to an object selection operation, determining an object to be recommended, and displaying an information recommendation page corresponding to the object to be recommended; wherein the information recommendation page includes several object feature information of the object to be recommended, the object feature information of the object to be recommended being determined based on multimedia information corresponding to the object to be recommended that meets preset conditions; in response to a determination operation of at least one object feature information of the object to be recommended, the at least one object feature information is used as the recommendation information of the object to be recommended. The information recommendation page allows merchants to conveniently and quickly browse several object feature information of the object to be recommended and make selections, thereby improving the efficiency of obtaining recommendation information for the object to be recommended. The preset conditions can improve the quality of the obtained recommendation information, thus helping multimedia creators to accurately and quickly determine the recommendation information for the object to be recommended.

[0038] In one implementation, step S110 may display a selection page for the objects to be recommended, which displays multiple objects; on the selection page, a selection operation is received to select at least one object from the multiple objects; the at least one object corresponding to the selection operation is determined as the object to be recommended. The selection page can be used to store multiple objects selected by the merchant. This step allows merchants to select from the objects stored on the selection page to determine the object to be recommended through a simple operation. See also Figure 1c The illustrated embodiment of this application provides a selection page for recommended objects. This page lists at least one or more objects 16, and optionally, it can also display identification information for the recommended objects. This identification information includes at least one of the following: image, name, model, features, sales volume, etc. After the streamer selects at least one product to sell, the product can be displayed on the information recommendation page corresponding to the recommended object, such as the showcase management page shown in the figure. In this step, selection can be made on this selection page. For example, a user can click the "Get Creative Inspiration" button and select one of the recommended objects as the recommended object.

[0039] In one implementation, the multimedia information may include a first video. Before displaying the information recommendation page corresponding to the object to be recommended in step S110, the text and / or speech in the first video may be recognized to obtain a recognition result; semantic analysis may be performed on the recognition result to determine the object feature information of the object to be recommended. Specifically, the text in the first video may be recognized to obtain a text recognition result; semantic analysis may be performed on the text recognition result to determine a portion of the text corresponding to the object to be recommended, and based on this portion of the text, a first statement that can reflect the attributes, characteristics, or usage scenarios of the object to be recommended may be determined. Optionally, the first statement may be used as object feature information. In addition, cluster analysis may be further performed on the first statement to obtain a tag corresponding to the first statement. The tag corresponding to the first statement may also be used as object feature information. Similarly, the speech in the first video may be recognized to obtain a speech recognition result, which may be converted into text format and processed similarly to the text recognition result. Optionally, before step S110, a correspondence can be established between the object to be recommended and a first video that meets preset conditions. For example, if the object to be recommended is product A, then the first video a posted by anchor #1 when selling product A can be obtained, and the first video a has more than 100,000 likes. Then, in this step, the object feature information of the object to be recommended can be analyzed from the first video, and a corresponding correspondence can be established between the first video and the object feature information of the object to be recommended. For example, the correspondence between first video a and "moisturizing" or "moisturizing expert," and a correspondence can be established between the object to be recommended, the first video, and the object feature information. In step S110, through the object to be recommended, the object feature information is determined from the above correspondence and displayed on the information recommendation page. The first video can also be determined, and the corresponding first video can be played by triggering the object feature information. Specifically, the part of the first video that matches the object to be recommended can be played, rather than the entire content of the first video.

[0040] See Figure 2This illustration shows another schematic diagram of an information recommendation page for object feature information provided in an embodiment of this application. In one possible implementation, the object feature information includes: object feature tags and feature text information corresponding to the object feature tags. The feature text information is obtained based on multimedia information that meets preset conditions. For example, the feature text information can be text information obtained by semantic analysis of multimedia information, and the object feature tags can be obtained by cluster analysis of the feature text information. There is a correspondence between the text information and the tags; the text information can reflect the information of the tags, and the tags are obtained based on text analysis and can also reflect the features of the text. The information recommendation page includes a first area 12 and a second area 11. The first area 12 is used to display the object feature tags, and the second area 11 is used to display several feature text information items.

[0041] Optionally, if the object feature information includes multiple object feature tags, then the multiple object feature tags are displayed in the first region 12. For example... Figure 2 The object feature information includes multiple object feature tags "moisturizing" and "affordable," and corresponding feature text information such as "moisturizing expert" and "moisturizing champion." Another example is, "You'll definitely regret buying this moisturizing expert, because you'll regret not buying it sooner," etc. (not shown in the figure). The first area 12 is used to display multiple object feature tags "moisturizing" and "affordable," and the second area 11 is used to display "moisturizing expert" and "moisturizing champion." Thus, through a reasonable layout of the information recommendation page, it is convenient for merchants to browse.

[0042] In one implementation, in response to a selection operation of a first tag among the plurality of object feature tags, the displayed content in the second area of ​​the information recommendation page is adjusted to the feature text information corresponding to the first tag. Here, the first tag is one of the plurality of object feature tags. The display method of the second area can include two types:

[0043] Method 1: The second area only displays the feature text information corresponding to the first label, and does not display the feature text information corresponding to other labels. The other labels are those other than the first label among the multiple object feature labels. For example... Figure 2As shown, object feature information 12 contains multiple pieces of information related to moisturizing and affordability. The user selects the object feature information "moisturizing". When the user clicks "moisturizing", the content displayed in the second area 11 of the information recommendation page is adjusted to include example sentences related to "moisturizing" such as "moisturizing expert" and "moisturizing champion", instead of displaying feature text information related to "affordability". Conversely, if the user clicks "affordability", the content displayed in the second area 11 of the information recommendation page is adjusted to include example sentences related to "affordability" such as "the most affordable price on the entire network, you'll definitely regret it if you don't buy it now", instead of displaying the aforementioned example sentences related to "moisturizing".

[0044] Method 2: The information recommendation page can display the feature text information corresponding to each tag. In this step, in response to the selection operation of the first tag among the multiple object feature tags, the feature text information corresponding to the first tag can be displayed in the second area. Through interface jumps or switches, the second area is placed in the user's visible interface position, while the feature text information corresponding to other tags is placed in the user's invisible interface. For example, in the split-screen display mode, the second area is the currently displayed screen, which the user can view. However, the feature text information corresponding to other tags can be in the next screen, which the user cannot view temporarily. When the user selects different first tags, the interfaces automatically jump or switch, displaying the feature text information corresponding to the first tag in the currently visible second area. In this way, multiple multimedia are classified and filtered, making it easier for users to browse.

[0045] Optionally, on this information recommendation page, object feature information can serve as a control to trigger the display of multimedia information. Clicking on object feature information allows users to view the corresponding multimedia information. In this step, the number of object feature information items that can be displayed on each information recommendation page can be set, i.e., the number of multimedia information items that can be linked to, such as a maximum of five. Multimedia includes videos and live stream clips. If the content is video, each example sentence displays the sales volume of the corresponding video and the video related to the author's nickname, with sales volume expressed in a range, such as over 300,000. Similarly, if the multimedia is live stream, each example sentence displays the sales volume of the product in the corresponding live stream and the live stream related to the author's nickname, also with sales volume expressed in a range. Therefore, when there are many object feature information items, the object feature information can be displayed to users more clearly and in a more targeted manner.

[0046] In one implementation, the information recommendation page for the object feature information can also display at least one multimedia and at least one of the object feature information according to the category of the multimedia or the category of the object to be recommended. Combined with... Figure 2 Multimedia categories include, for example, short videos and live videos. The information recommendation page categorizes and displays multimedia content according to these categories. For example, Figure 2 This illustrates the multimedia category corresponding to live video 13, allowing users to view multimedia of different categories and obtain more valuable content. The categories of the objects to be recommended include multiple categories 13, such as explanations of similar products, explanations of related products, and videos of popular products. If the live video category does not contain corresponding multimedia, the corresponding module, such as the "Essential Inspiration" module, may not be displayed. Therefore, by displaying at least one multimedia and at least one object feature information according to the multimedia category or the category of the object to be recommended, users can more conveniently obtain the multimedia they need for their creations.

[0047] In one possible implementation, the determination operation of at least one object feature information of the object to be recommended in step S120 includes at least one of the following operation methods: Operation method 1: Perform a preset trigger gesture on at least one feature text information in the second area, such as a preset trigger gesture such as a single click or double click on the feature text information itself in the second area. For example, if the second area includes the feature text information "moisturizing expert", the feature text information "moisturizing expert" itself in the second area can be clicked. Operation method 2: Perform a preset trigger operation on the selection control of at least one feature text information in the second area; wherein, in the second area of ​​the information recommendation page, each feature text information is provided with a corresponding selection control, such as the control "adopt". This method, for example, can be achieved by clicking the control "adopt".

[0048] Combination Figure 2 As shown, in one possible implementation, the information recommendation page may further include a third area 15, wherein the third area is used to display the identification information of the object to be recommended. Optionally, the identification information of the object to be recommended includes at least one of the following: name, number, characteristics, and image. For example, name: face cream; characteristics: whitening and moisturizing, etc. Therefore, this embodiment of the application can conveniently and efficiently provide merchants with high-quality recommendation information through a reasonable layout of the information recommendation page.

[0049] Figure 3 This is a schematic diagram of another method for determining recommendation information provided by an embodiment of the present invention. As shown in the figure, the method includes:

[0050] S310: In response to the object selection operation, determine the object to be recommended, and display the information recommendation page corresponding to the object to be recommended.

[0051] This step can be described using the steps corresponding to the embodiment in Figure 1, and will not be repeated here.

[0052] S320: In response to the operation of determining at least one object feature information for the object to be recommended, the at least one object feature information is used as recommendation information for the object to be recommended.

[0053] This step can be described using the steps corresponding to the embodiment in Figure 1, and will not be repeated here.

[0054] S330: Display the information editing page corresponding to the object to be recommended.

[0055] The information editing page includes an editing area for displaying the recommended information and receiving edited text information related to the recommended information. The editing page receives edits from merchants on the recommended information. Merchants can create content based on the recommended information in the editing area, such as adding, modifying, or deleting content. This input can be text input, or it can be voice or video input. The text information is obtained through voice or video input recognition and used as the aforementioned text input. Figure 4 This diagram illustrates an editing page provided in an embodiment of this application. For example, on the "My Inspiration" page 40, the editing area displays recommended information determined in the previous step, such as "King of Cost-Effectiveness" and "Hydrating Champion," while the information displayed... Figure 2 The information recommendation page shows other object feature information that was not selected, such as... Figure 2 The "moisturizing expert" information is not included as a recommendation and will not be displayed. Figure 4 The editing page shown.

[0056] In one implementation, after this step, image data for the object to be recommended can be acquired first. This image data may include images or videos. Then, a recommended video corresponding to the object to be recommended can be generated based on the image data, the edited text information, and the recommendation information. For example, the author of a short video can input image data introducing product A, and by combining it with the edited text information generated in the previous step and the recommendation information, the selling points of product A, the title of the short video, etc., can be determined, thereby generating a short video introducing product A for the author. For example, if product A is a face cream, the selling points of product A determined in this step could be something like "a moisturizing miracle suitable for all sensitive skin," which can be output by a character through voice in the short video. The title of the short video could be something like "Moisturizing, moisturizing, ridiculously moisturizing," and can be output in text form through the short video's identifier information, etc.

[0057] In one implementation, after this step, explanation prompts corresponding to the object to be recommended can be generated based on the edited text information and the recommendation information. Optionally, if the object to be recommended is detected as an object to be explained in the live stream, the explanation prompts corresponding to the object to be recommended can be displayed on the live stream prompt page. Specifically, the object to be recommended can be an object currently being explained in the live stream, or it can be an object that is not currently being explained but is in the live stream's list of objects to be explained, such as an object in the shared bike list.

[0058] As an example, editing operations such as adding, modifying, or deleting information can be performed on the recommended information to generate explanatory prompts. Based on these prompts, a prompt page corresponding to the recommended object can be generated. This prompt page can be displayed on the monitor or terminal screen of the user on the operation side, but it is not visible to buyers or other viewers of the live stream. This allows users to fluently output text content without memorizing it when recording videos or live streams. The prompt page can include a first area and a second area. The first area displays the edited text information, and the second area displays the recommended information.

[0059] In one implementation, when the determination of at least one object feature information of the object to be recommended is a first-time operation, the method further includes displaying a guidance page before displaying the editing page corresponding to the object to be recommended. This guidance page indicates how the recommendation information is recorded on the editing page and how it is used, introducing the editing page to the user and helping new users perform the correct application operations. Figure 5 As shown, for example, it can introduce to users that they can click on the editing area to enter text, or long-press the editing area to input voice, etc.

[0060] In one implementation, the triggering method for displaying the editing page may include the following: Method 1: Perform a preset triggering operation on the selection control of at least one characteristic text information in the second area, combined with... Figure 2 Users can click the "Adopt" button corresponding to the control. After clicking "Adopt," the button will change to "Adopted," and the adopted content will be visible in the "My Inspirations" section of the editing page. Method 2: Execute a trigger operation on the selection control for the recommended object. See also... Figure 2 Users can also access the editing page by triggering the "first button".

[0061] Figure 6 The diagram shows a structural schematic of an apparatus for determining recommendation information according to an embodiment of this application. The apparatus 600 includes: a first determining module 610 and a second determining module 620.

[0062] The first determining module 610 is configured to, in response to an object selection operation, determine an object to be recommended and display an information recommendation page corresponding to the object to be recommended; wherein the information recommendation page includes several object feature information of the object to be recommended, and the object feature information of the object to be recommended is determined based on multimedia information corresponding to the object to be recommended that meets preset conditions. The second determining module 620 is configured to, in response to a determining operation of at least one object feature information of the object to be recommended, use the at least one object feature information as recommendation information for the object to be recommended.

[0063] In one implementation, the object feature information includes: object feature tags and feature text information corresponding to the object feature tags; the information recommendation page includes a first area and a second area, wherein the first area is used to display the object feature tags, and the second area is used to display several feature text information; the feature text information is obtained based on the multimedia information that meets the preset conditions.

[0064] In one implementation, if the object feature information includes multiple object feature tags, then the multiple object feature tags are displayed in the first area; after displaying the information recommendation page corresponding to the object to be recommended, the first determining module 610 further responds to the selection operation of the first tag among the multiple object feature tags by adjusting the displayed content in the second area of ​​the information recommendation page to the feature text information corresponding to the first tag; wherein, the first tag is an object feature tag among the multiple object feature tags.

[0065] In one implementation, the information recommendation page further includes a third area, wherein the third area is used to display the identification information of the object to be recommended.

[0066] In one implementation, the determination operation of the second determining module 620 for at least one object feature information of the object to be recommended includes at least one of the following:

[0067] A preset trigger gesture is executed on at least one feature text information in the second region;

[0068] A preset trigger operation is performed on the selection control of at least one feature text information in the second area; wherein, in the second area of ​​the information recommendation page, each feature text information is provided with a corresponding selection control.

[0069] In one implementation, after the second determining module 620 determines at least one object feature information as the recommended information of the object to be recommended in response to the determining operation of at least one object feature information of the object to be recommended, the second determining module 620 further displays an information editing page corresponding to the object to be recommended, wherein the information editing page includes an editing area for displaying the recommended information and receiving edit text information for the recommended information.

[0070] In one implementation, after displaying the information editing page corresponding to the object to be recommended, the second determining module 620 further acquires image data for the object to be recommended; and generates a recommended video corresponding to the object to be recommended based on the image data, the edited text information, and the recommendation information.

[0071] In one implementation, after displaying the editing page corresponding to the object to be recommended, the second determining module 620 further generates explanation prompt information corresponding to the object to be recommended based on the edited text information and the recommendation information; if the object to be recommended is detected to be a live broadcast room explanation object, the explanation prompt information corresponding to the object to be recommended is displayed on the live broadcast room prompt page.

[0072] In one implementation, when the determination operation for at least one object feature information of the object to be recommended is the first operation, the second determination module 620 also displays a guide page before displaying the editing page corresponding to the object to be recommended. The guide page is used to indicate the application method of recording the recommendation information on the editing page.

[0073] In one implementation, the multimedia information includes a first video. Before displaying the information recommendation page corresponding to the object to be recommended, the second determining module 620 further identifies the text and / or speech in the first video to obtain an identification result; performs semantic analysis on the identification result to determine the object feature information of the object to be recommended.

[0074] In one implementation, the first determining module 610 is used to display a selection page for the object to be recommended, the selection page for the object to be recommended displaying multiple objects; on the selection page for the object to be recommended, a selection operation is received to select at least one object from the multiple objects; and the at least one object corresponding to the selection operation is determined as the object to be recommended.

[0075] In one implementation, the preset condition includes a predetermined parameter being greater than a preset threshold, and the predetermined parameter includes at least one of the following: the completion rate of multimedia information, the number of comments, the number of likes, and the number of shares.

[0076] The device 600 provided in this application embodiment can execute the methods described in the preceding method embodiments and achieve the functions and beneficial effects of the methods described in the preceding method embodiments, which will not be repeated here.

[0077] Figure 7 This diagram illustrates the hardware structure of an electronic device 1000 that performs the data processing method provided in the embodiments of this application. At the hardware level, the electronic device includes a processor 1010, and optionally, an internal bus 1020, a network interface 1030, and a memory. The memory may include main memory 1040, such as high-speed random-access memory (RAM), and may also include non-volatile memory 1050, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0078] The processor 1010, network interface 1030, and memory can be interconnected via an internal bus 1020. This internal bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be categorized as an address bus, data bus, control bus, etc. For ease of illustration, only a single bidirectional arrow is used in this diagram, but this does not imply that there is only one bus or one type of bus.

[0079] The memory is used to store programs. Specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory 1040 and non-volatile memory 1050, and provides instructions and data to the processor 1010.

[0080] Processor 1010 reads the corresponding computer program from non-volatile memory 1050 into memory 940 and then runs it, forming a device for locating the target user at the logical level. Processor 1010 executes the program stored in memory and specifically performs... Figures 1a-5 The method described in the embodiments achieves the same or corresponding technical effects.

[0081] The above is as stated in this application. Figures 1a-3The methods disclosed in the illustrated embodiments can be applied to a processor or implemented by processor 1010. Processor 1010 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware of processor 1010 or by instructions in software form. The processor 1010 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in the memory, and the processor 1010 reads the information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0082] The electronic device can also execute the methods described in the preceding method embodiments and achieve the functions and beneficial effects of the methods described in the preceding method embodiments, which will not be repeated here.

[0083] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0084] This application also proposes a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the aforementioned... Figures 1a-3 The methods described in the method embodiments achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0085] The computer-readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, etc.

[0086] Furthermore, embodiments of this application also provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, implement the following process: implementing the foregoing... Figures 1a-3 The methods described in the method embodiments achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0087] In summary, the above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

[0088] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0089] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0091] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

Claims

1. A method for determining recommendation information, comprising: In response to an object selection operation, a target object is determined, and an information recommendation page corresponding to the target object is displayed. The information recommendation page includes several object feature information of the target object, which is determined based on multimedia information corresponding to the target object that meets preset conditions. These preset conditions include a predetermined parameter greater than a preset threshold, and the predetermined parameters include at least one of the following: multimedia information completion rate, number of comments, number of likes, and number of shares. The object feature information includes object feature tags and corresponding feature text information. The feature text information is obtained through semantic analysis of the multimedia information, and the object feature tags are obtained through cluster analysis of the feature text information. In response to the operation of determining at least one object feature information of the object to be recommended, the at least one object feature information is used as the recommendation information of the object to be recommended; Based on the edited text information and the recommendation information, explanatory prompt information corresponding to the recommended object is generated, wherein the edited text information is obtained by the merchant editing the recommendation information; If the object to be recommended is detected as a subject to be explained in the live broadcast room, the explanation prompt information corresponding to the object to be recommended will be displayed to the broadcaster on the live broadcast room prompt page, which is not visible to the live broadcast viewers.

2. The method according to claim 1, wherein, The information recommendation page includes a first area and a second area, wherein the first area is used to display the object feature tags, and the second area is used to display several feature text information; the feature text information is obtained based on the multimedia information that meets the preset conditions.

3. The method according to claim 2, wherein, If the object feature information includes multiple object feature tags, then the multiple object feature tags are displayed in the first area; After displaying the information recommendation page corresponding to the object to be recommended, the method further includes: In response to the selection operation of the first tag among the plurality of object feature tags, the displayed content in the second area of ​​the information recommendation page is adjusted to the feature text information corresponding to the first tag; wherein, the first tag is an object feature tag among the plurality of object feature tags.

4. The method according to claim 2, wherein, The information recommendation page also includes a third area, which is used to display the identification information of the object to be recommended.

5. The method according to claim 2, wherein, The operation of determining at least one object feature information of the object to be recommended includes at least one of the following: A preset trigger gesture is executed on at least one feature text information in the second region; A preset trigger operation is performed on the selection control of at least one feature text information in the second area; wherein, in the second area of ​​the information recommendation page, each feature text information is provided with a corresponding selection control.

6. The method according to claim 1, wherein, After determining at least one object feature information as recommendation information for the object to be recommended in response to the operation of determining at least one object feature information for the object to be recommended, the method further includes: The information editing page corresponding to the object to be recommended is displayed. The information editing page includes an editing area for displaying the recommendation information and for receiving edit text information for the recommendation information.

7. The method according to claim 6, wherein, After displaying the information editing page corresponding to the object to be recommended, the following is also included: Obtain image data for the object to be recommended; Based on the image data, the edited text information, and the recommendation information, a recommended video corresponding to the object to be recommended is generated.

8. The method according to claim 6, wherein, If the operation of determining at least one object feature information of the object to be recommended is the first operation, the following steps are included before displaying the editing page corresponding to the object to be recommended: A guidance page is displayed, which indicates how to record the recommendation information on the editing page and how to use the editing page.

9. The method according to claim 1, wherein, The multimedia information includes a first video, and before displaying the information recommendation page corresponding to the object to be recommended, it also includes: The text and / or speech in the first video are identified to obtain the recognition result; Semantic analysis is performed on the recognition results to determine the object feature information of the object to be recommended.

10. The method according to claim 1, wherein, The process of determining the object to be recommended in response to the object selection operation includes: The page for selecting the objects to be recommended is displayed, and the page for selecting the objects to be recommended displays multiple objects; On the selection page for the recommended objects, a selection operation is received to select at least one object from a plurality of objects; At least one object corresponding to the selection operation is identified as the object to be recommended.

11. An apparatus for determining recommendation information, comprising: A first determining module is configured to, in response to an object selection operation, determine an object to be recommended and display an information recommendation page corresponding to the object to be recommended; wherein, the information recommendation page includes several object feature information of the object to be recommended, the object feature information of the object to be recommended is determined based on multimedia information corresponding to the object to be recommended that meets preset conditions, the preset conditions include a predetermined parameter greater than a preset threshold, the predetermined parameter including at least one of the following: completion rate of multimedia information, number of comments, number of likes, and number of shares; the object feature information includes: object feature tags and feature text information corresponding to the object feature tags, the feature text information is obtained by semantic analysis of the multimedia information, and the object feature tags are obtained by cluster analysis of the feature text information; The second determining module is configured to, in response to a determining operation of at least one object feature information of the object to be recommended, use the at least one object feature information as the recommendation information of the object to be recommended. The second determining module is further configured to generate explanation prompt information corresponding to the object to be recommended based on the edited text information and the recommendation information, wherein the edited text information is obtained by the merchant editing the recommendation information; if the object to be recommended is detected to be a live broadcast object, the explanation prompt information corresponding to the object to be recommended is displayed to the host on the live broadcast prompt page, wherein the live broadcast prompt page is not visible to the live broadcast audience.

12. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, use the processor to perform the method for determining recommendation information as described in any one of claims 1-10.

13. A computer-readable medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method for determining recommendation information according to any one of claims 1-10.

Images