Information recommendation method and apparatus, computer device and storage medium

By displaying information tags and recommendation dimensions associated with the target entity in the video, the time and complexity issues caused by users' active search are solved, and fast and accurate information acquisition and rich recommendation information display are achieved.

WO2024230496A1PCT designated stage expired Publication Date: 2024-11-14BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/089722
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-10
Filing Date
2024-04-25
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

While watching videos, users need to actively initiate searches to obtain detailed information about recommended entities, which increases time and complexity and may prevent them from accurately finding the information they need.

Method used

By displaying information tags associated with target entities in videos, generating tags of different information recommendation dimensions based on entity type, and responding to triggers to display corresponding recommended information, the information acquisition path is simplified and the diversity and accuracy of information are improved.

Benefits of technology

It enables the rapid and efficient acquisition of information recommendations of interest, reduces the complexity of acquisition, and improves the richness and accuracy of information, thus supporting better consumption decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024089722_14112024_PF_FP_ABST
    Figure CN2024089722_14112024_PF_FP_ABST
Patent Text Reader

Abstract

Provided are an information recommendation method and apparatus, a computer device and a storage medium. The method comprises: playing back a target video on an information recommendation page (S101); displaying each information label associated with a target entity in the target video, each information label being generated according to at least one information recommendation dimension corresponding to the entity type of the target entity, and different entity types corresponding to different information recommendation dimensions (S102); and, in response to triggering an information label, displaying target recommendation information under the information recommendation dimension corresponding to the information label (S103).
Need to check novelty before this filing date? Find Prior Art

Description

Information recommendation method, device, computer equipment and storage medium

[0001] This application claims priority to Chinese Patent Application No. 202310525087.3 filed on May 10, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] The present disclosure relates to an information recommendation method, apparatus, computer equipment, and storage medium. Background Art

[0003] Videos often contain a variety of entities, especially recommended entities, often recommended by users. While watching a video, users may need to obtain detailed information about a recommended entity. To meet this need, video viewers are often required to proactively search for the recommended entity based on their knowledge of the entity and obtain a specific search result page.

[0004] However, the method of actively initiating a search not only increases the time and complexity of obtaining detailed information of the recommended entity, but may also result in the problem of not being able to accurately search for the recommended entity, thus affecting the search effect.

[0005] Summary of the Invention

[0006] The embodiments of the present disclosure at least provide an information recommendation method, apparatus, computer device, and storage medium.

[0007] In a first aspect, an embodiment of the present disclosure provides an information recommendation method, comprising:

[0008] Play the target video on the information recommendation page;

[0009] Displaying information tags associated with a target entity in the target video; each information tag is generated based on at least one information recommendation dimension corresponding to the entity type of the target entity; wherein different entity types correspond to different information recommendation dimensions;

[0010] In response to triggering the information tag, target recommended information under the information recommendation dimension corresponding to the information tag is displayed.

[0011] In a possible implementation, the displaying of information tags associated with the target entity in the target video includes:

[0012] In response to the presence of multiple candidate entities in the target video, the target entity is determined from the multiple candidate entities based on historical behavior data obtained with user authorization, and each information tag associated with the target entity is displayed; or

[0013] In response to the presence of multiple candidate entities in the target video, each candidate entity is used as the target entity, and entity information of each target entity and various information tags associated with the target entity are displayed respectively.

[0014] In a possible implementation, the displaying of information tags associated with the target entity in the target video includes:

[0015] In response to the existence of multiple information recommendation dimensions corresponding to the entity type of the target entity, multiple information tags associated with the target entity are switched and displayed according to the playback progress information of the target video.

[0016] In a possible implementation, the displaying of information tags associated with the target entity in the target video includes:

[0017] In response to the presence of multiple target entities in the target video, information tags associated with the target entities are displayed according to the time when the target entities appear in the target video.

[0018] In a possible implementation, in response to triggering the information tag, displaying target recommended information under the information recommendation dimension corresponding to the information tag includes:

[0019] In the case that there are multiple target entities corresponding to the same entity type in the target video, in response to triggering any information tag corresponding to the entity type, a recommended information set under the information recommendation dimension corresponding to the information tag is displayed, and the recommended information set includes target recommendation information of the multiple target entities.

[0020] In a possible implementation, the candidate entity is determined according to the following steps:

[0021] Deduplication processing is performed on the video frame images according to the image similarity between the video frame images of the target video to obtain the deduplication video frame images;

[0022] Performing image recognition on each of the deduplicated video frames to determine the initial entities included in each of the video frames;

[0023] The candidate entities are screened out from the initial entities according to the recognition accuracy, the number of appearances and the display area of ​​each of the initial entities in the target video.

[0024] In a possible implementation, when the initial entity belongs to a preset type, screening the candidate entity from the initial entity according to the recognition accuracy, the number of appearances in the target video, and the display area of ​​each initial entity includes:

[0025] Filtering at least one intermediate entity from the initial entities based on the recognition accuracy, the number of appearances in the target video, and the display area of ​​each initial entity;

[0026] The candidate entities are screened out from the intermediate entities according to the number of entities matching the intermediate entity in a preset entity library.

[0027] In a second aspect, an embodiment of the present disclosure further provides an information recommendation device, comprising:

[0028] Playback module, used to play the target video on the information recommendation page;

[0029] A first display module is configured to display information tags associated with a target entity in the target video; the information tags are generated based on at least one information recommendation dimension corresponding to the entity type of the target entity; different entity types correspond to different information recommendation dimensions;

[0030] The second display module is used to display the target recommended information under the information recommendation dimension corresponding to the information tag in response to triggering the information tag.

[0031] In a third aspect, an optional implementation of the present disclosure further provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the machine-readable instructions perform the steps of the above-mentioned first aspect, or any possible implementation of the first aspect.

[0032] In a fourth aspect, an optional implementation of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, it executes the steps of the above-mentioned first aspect or any possible implementation of the first aspect.

[0033] The effects of the above-mentioned information recommendation device, computer equipment, and computer-readable storage medium are described in the description of the above-mentioned information recommendation method, which will not be repeated here.

[0034] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0036] FIG1 shows a flow chart of an information recommendation method provided by an embodiment of the present disclosure;

[0037] FIG2 shows a schematic diagram of an information label provided by an embodiment of the present disclosure;

[0038] FIG3 shows a schematic diagram showing another information label provided by an embodiment of the present disclosure;

[0039] FIG4 shows a schematic diagram of a dimension information display page provided by an embodiment of the present disclosure;

[0040] FIG5 shows a schematic diagram of a floating card provided by an embodiment of the present disclosure;

[0041] FIG6 shows a schematic diagram of a process for displaying a recommended information set provided by an embodiment of the present disclosure;

[0042] FIG7 shows a schematic diagram of an information recommendation device provided by an embodiment of the present disclosure;

[0043] FIG8 shows a schematic structural diagram of a computer device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0045] In addition, the terms "first," "second," and the like in the description and claims of the embodiments of the present disclosure and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments described herein can be practiced in an order other than that shown or described herein.

[0046] In this document, "multiple or several" refers to two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0047] Research has found that for videos, if there is a need to obtain detailed information about a recommended entity in the video, it is necessary to actively initiate a search based on the user's existing understanding of the recommended entity to obtain the detailed information of the recommended entity. This not only takes a large amount of time, but may also lead to the problem of not being able to accurately search for the recommended entity.

[0048] Based on the above research, the present disclosure provides an information recommendation method, apparatus, computer equipment and storage medium. By displaying various information tags associated with the target entity, it is possible to identify the recommended information under each information recommendation dimension corresponding to the entity type of the target entity, thereby improving the diversity of the displayed information. By displaying the target recommendation information under the information recommendation dimension corresponding to the information tag in response to the triggering information tag, it is possible to directly use the tag information displayed in the information recommendation page to quickly and efficiently obtain the target recommendation information under the information recommendation dimension of interest, thereby shortening the acquisition path of the target recommendation information and reducing the complexity of obtaining the recommended information, and achieving accurate recommendation of information related to the target video content. Moreover, since different information tags can correspond to different information recommendation dimensions, different information tags can be used to obtain information under different dimensions, thereby improving the richness of the target recommendation information, and thus facilitating the use of rich target recommendation information to better form consumption decisions for the target entity.

[0049] The defects in the above solutions are the results obtained by the inventors after practice and careful research. Therefore, the process of discovering the above problems and the solutions proposed by this disclosure for the above problems below should be the contributions made by the inventors to this disclosure during the disclosure process.

[0050] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0051] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0052] To facilitate understanding of this embodiment, an information recommendation method disclosed in an embodiment of the present disclosure is first introduced in detail. The executor of the information recommendation method provided in the embodiment of the present disclosure is generally a terminal device or other processing device with certain computing capabilities, where the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a personal digital assistant (PDA), a handheld device, a computer device, etc.; in some possible implementation methods, the information recommendation method can be implemented by a processor calling computer-readable instructions stored in a memory.

[0053] The information recommendation method provided by the embodiment of the present disclosure is described below by taking a computer device as an example.

[0054] As shown in FIG1 , which is a flowchart of an information recommendation method provided by an embodiment of the present disclosure, the method may include the following steps:

[0055] S101: Play the target video on the information recommendation page.

[0056] Here, the information recommendation page may be a page for displaying and recommending multimedia information. For example, the information recommendation page may be a video playback page.

[0057] The target video can be a video containing any video content, for example, an information recommendation video, a landscape video, an item introduction video, etc. The target video can include multiple video frames, and different video frames can include the same or different target entities, such as physical objects, physical landscapes, etc.

[0058] For example, in response to a play operation on the target video, the target video may be played within the information recommendation page.

[0059] S102: Displaying various information tags associated with a target entity in a target video; each information tag is generated according to at least one information recommendation dimension corresponding to an entity type of the target entity; wherein different entity types correspond to different information recommendation dimensions.

[0060] Here, the target entity can be all entities included in the video frame images of the target video, or it can be an entity of a preset type. A target entity can appear in at least one video frame image in the target video, and the target video can include one or more target entities. For example, the target entity can be a commodity in the target video, such as clothing, electronic equipment, or food, or it can be a landscape entity in the target video, such as the sea, temples, streets, scenic spots, etc.

[0061] An information tag is a label used to identify recommended information. An information tag can be used to recommend information within at least one information recommendation dimension. A target entity can be associated with one or more information tags, and different target entities can be associated with different information tags. Recommended information within an information recommendation dimension has the information attributes indicated by that information recommendation dimension. For example, if the information recommendation dimension is the XX video category dimension, the recommended information within that information recommendation dimension can include all videos within that XX category related to the target entity.

[0062] The entity type is the type of the target entity. Various possible entity types can be divided in advance. After obtaining the target entity, the entity type corresponding to the target entity is determined. An entity type can be associated with at least one information recommendation dimension, and different entity types may have different associated information recommendation dimensions. Exemplarily, multiple information recommendation dimensions can be pre-set, and the association relationship between each entity type and the associated information recommendation dimension can be pre-established. For example, in the case where the entity type is a clothing type, the associated information recommendation dimensions may include obtaining link dimensions, preferential information dimensions, dressing video dimensions, etc.; in the case where the entity type is an electronic device type, the associated information recommendation dimensions may include evaluation video dimensions, obtaining link dimensions, preferential information dimensions; in the case where the entity type is a food type, the associated information recommendation dimensions may include obtaining link dimensions, life service tool dimensions, preferential information dimensions, eating suggestion information dimensions, food science video dimensions, etc.; in the case where the entity type is a scenery entity type, it may include travel guide dimensions, accommodation service dimensions, travel service dimensions, scenery evaluation dimensions, etc.

[0063] During specific implementation, for each video frame image, it can be determined whether the target entity exists in the video frame image. If so, the various information recommendation dimensions corresponding to the entity type can be determined based on the entity type and association relationship of the target entity. Then, the recommended information under the information recommendation dimension can be determined, and information tags corresponding to each information recommendation dimension can be generated. Here, in the case where there are multiple information recommendation dimensions, information tags corresponding to each information recommendation dimension can be generated respectively, that is, one information tag can correspond to one information recommendation dimension. Optionally, one information tag corresponding to multiple information recommendation dimensions can also be generated, that is, one information tag can correspond to multiple information recommendation dimensions.

[0064] After obtaining the information tags corresponding to the target entities included in the target video, the information tags can be displayed during the playback of the target video. For example, the information tags can be displayed on at least a portion of the video frames during the playback of the target video, or the information tags can be displayed below the target video.

[0065] For example, regarding the method of displaying information tags, each information tag may be displayed in the form of an anchor point, or in the form of a floating layer.

[0066] As shown in Figure 2, it is a schematic diagram of the display of information tags provided by an embodiment of the present disclosure, wherein the target video is currently played to video frame picture 1, the target entity 1 in the video frame picture 1 is clothing, and the target entity 1 corresponds to multiple information tags under multiple information recommendation dimensions (specifically, information tag 1 corresponding to the acquisition link dimension, information tag 2 corresponding to the discount information dimension, and information tag 3 corresponding to the dressing video dimension). The three information tags are displayed on the target entity 1 in the form of anchor points.

[0067] As shown in Figure 3, it is a schematic diagram of another information tag display provided by an embodiment of the present disclosure, wherein the target video is currently playing to video frame picture 1, the target entity in video frame picture 1 is clothing, and target entity 1 corresponds to multiple information tags under multiple information recommendation dimensions (specifically, information tag 1 corresponding to the acquisition link dimension, information tag 2 corresponding to the discount information dimension, and information tag 3 corresponding to the dressing video dimension). The three information tags are displayed in the form of a floating layer below the target video, and each information tag can have corresponding tag information (such as the tag picture and tag name in Figure 3), wherein the tag information can be determined based on the entity information of the target entity.

[0068] S103: In response to triggering the information tag, display target recommended information under the information recommendation dimension corresponding to the information tag.

[0069] Here, the target recommendation information can be the recommended information that matches the target entity under the information recommendation dimension corresponding to the information tag. The recommended information can have any information genre, such as video genre, graphic genre, card genre, etc. The target recommendation information under an information recommendation dimension can include at least one item.

[0070] For example, if an information tag corresponds to only one information recommendation dimension, in response to triggering the information tag, the page can jump to the dimension information display page, and display the target recommended information under the information recommendation dimension corresponding to the triggered information tag on the dimension information display page; or, in response to triggering the information tag, the target recommended information under the information recommendation dimension corresponding to the triggered information tag can be displayed in the form of a floating card. If an information tag corresponds to only multiple information recommendation dimensions, the target recommended information of each information recommendation dimension can also be directly mixed and displayed on the dimension information display page; similarly, the target recommended information of each information recommendation dimension can also be directly mixed and displayed on the floating card.

[0071] Optionally, if an information tag only corresponds to multiple information recommendation dimensions, it can jump to the dimension information display page in response to triggering the information tag, and display the dimension filter items corresponding to the multiple information recommendation dimensions corresponding to the information tag in the dimension information display page, and display the various target recommendation information under the currently selected dimension filter item. As shown in Figure 4, it is a schematic diagram of a dimension information display page provided by an embodiment of the present disclosure, wherein Figure 4a is a display schematic diagram of an information tag, wherein an information tag 4 corresponding to item 1 (i.e., the mobile phone in Figure 4) is displayed, and the multiple information recommendation dimensions corresponding to the information tag 4 are respectively the evaluation video dimension, the acquisition link dimension, and the discount information dimension. Figure 4b is a schematic diagram of the dimension information display page after the information tag is triggered, wherein the dimension information display page displays the evaluation video filter item corresponding to the evaluation video dimension, the entity acquisition filter item corresponding to the acquisition link dimension, and the discount information filter item corresponding to the discount information dimension, and in Figure 4b, the currently selected dimension filter item is the evaluation video filter item, so the dimension information display page also displays the various target recommendation information under the dimension filter item (i.e., test videos 1 to 4).

[0072] Similarly, if an information tag only corresponds to multiple information recommendation dimensions, it can respond to the triggering of the information tag, or it can display the dimension filter items corresponding to the multiple information recommendation dimensions in the floating card, and display the various target recommendation information under the currently selected dimension filter item. As shown in Figure 5, it is a schematic diagram of a floating card provided by an embodiment of the present disclosure, wherein Figure 5c is a display schematic diagram of the information tag, wherein the information tag 4 corresponding to item 1 is displayed, and the multiple information recommendation dimensions corresponding to the information tag 4 are the evaluation video dimension, the acquisition link dimension, and the preferential information dimension. Figure 5d is a schematic diagram of the floating card after the information tag is triggered, wherein the floating card displays the evaluation video filter item corresponding to the evaluation video dimension, the entity acquisition filter item corresponding to the acquisition link dimension, and the preferential information filter item corresponding to the preferential information dimension, and in Figure 5d, the currently selected dimension filter item is the evaluation video filter item, so the floating card also displays the various target recommendation information under the dimension filter item (i.e., test videos 1 to 4).

[0073] Optionally, if an information tag corresponds only to multiple information recommendation dimensions, in response to triggering the information tag, the page can be redirected to the dimension filtering page, where multiple information recommendation dimensions can be displayed. Afterwards, in response to triggering any one of the multiple information recommendation dimensions, each target recommendation information under the triggered information recommendation dimension can be displayed on the dimension information display page. Similarly, in response to triggering the information tag, multiple information recommendation dimensions can be displayed in a floating card. Afterwards, in response to triggering any one of the multiple information recommendation dimensions, each target recommendation information under the triggered information recommendation dimension can be displayed in a floating card.

[0074] In one embodiment, the target video often includes multiple video frames, and the various video frames often have certain content differences. Therefore, for the target video, there is a high probability that multiple entities will appear in it. In the case of multiple entities, how to display information tags (that is, how to perform the above S102) can specifically include the following two methods:

[0075] Method 1: In response to the presence of multiple candidate entities in the target video, a target entity is determined from the multiple candidate entities based on historical behavior data obtained with user authorization, and various information tags associated with the target entity are displayed.

[0076] Here, the candidate entities may be entity objects identified from each video frame in the target video. For example, the candidate entities may be clothing 1 and clothing 2 identified from video frame 1, object 1 identified from video frame 2, and scenic spot 1 identified from video frame 3.

[0077] Historical behavior data is data that users authorize to obtain, and may include, for example, entity search data, entity browsing data, entity collection data, entity acquisition data, etc.

[0078] In a specific implementation, after identifying multiple candidate entities from the target video, the entity content that the user is interested in can be determined based on the user's historical behavior data. The entity content can be an entity type, a specific entity, etc. Then, the entity that matches the entity content that the user is interested in can be screened out from the candidate entities as the target entity.

[0079] For example, based on the user's entity favorites and entity search data, the user's entities of interest and their entity types can be determined. Then, from the candidate entities, target entities that are identical or similar to the user's entities of interest can be filtered out. Furthermore, from the candidate entities, target entities that match the entity type of interest can be filtered out based on the entity types of the candidate entities.

[0080] Furthermore, after determining the target entity from the candidate entities, at least one information recommendation dimension corresponding to the target entity and the recommended information under each information recommendation dimension can be determined based on the entity type of each target entity. At the same time, information tags associated with the target entity can be generated based on the information recommendation dimension. In this way, the information tags associated with the target entity can be obtained and displayed on the information recommendation page.

[0081] In this way, by screening out the target entity from the candidate entities, the information tags corresponding to the target entity that the user is interested in can be displayed, thereby improving the pertinence of the displayed information tags.

[0082] Method 2: In response to the presence of multiple candidate entities in the target video, each candidate entity is used as a target entity, and entity information of each target entity and various information tags associated with the target entity are displayed respectively.

[0083] Here, the entity information may include the entity name, entity picture, entity introduction, and other information of the target entity.

[0084] In specific implementations, if there are multiple candidate entities in the target video, each candidate entity can be directly used as the target entity. Subsequently, the entity information of each target entity and the corresponding information tags can be obtained. The entity information of each target entity and the information tags associated with the target entity can then be displayed separately on the information recommendation page.

[0085] In this way, by treating each candidate entity as a target entity and displaying the information label of each target entity, it can be ensured that the label information of each entity in the target video is displayed, thereby improving the comprehensiveness of the displayed label information.

[0086] In one embodiment, candidate entities in a target video may be determined according to the following steps:

[0087] Step 1: Deduplication is performed on the video frame images according to the image similarity between the video frame images of the target video to obtain deduplication video frame images.

[0088] In a specific implementation, in a target video, there are often small differences between adjacent video frames and they often include the same candidate entities. Therefore, in order to reduce the computational complexity of identifying candidate entities, the similarity between each video frame can be calculated first, and then the video frames with a similarity greater than a preset similarity threshold can be deduplicated to obtain deduplicated video frames. In this way, for deduplicated video frames, different deduplicated video frames will likely include different candidate entities.

[0089] Step 2: Perform image recognition on each of the deduplicated video frames to determine the initial entities included in each of the video frames.

[0090] Here, the initial entity may be an entity identified from the deduplicated video frame image.

[0091] In specific implementation, a pre-trained visual search model can be used to perform image recognition on each video frame after deduplication to obtain the initial entities included in each video frame.

[0092] Optionally, image recognition may be performed on each video frame in the target video to obtain the initial entity included in each video frame. Here, the initial entity in a video frame may be empty.

[0093] Step 3: Filter candidate entities from the initial entities based on their recognition accuracy, number of appearances in the target video, and display area.

[0094] Here, the number of occurrences of the initial entity in the target video can be determined based on the number of video frames whose similarity with the deduplicated video frames containing the initial entity is greater than a preset similarity threshold. The display area of ​​the initial entity in the target video can be the area occupied by the target entity in the video frame.

[0095] In specific implementation, initial entities with recognition accuracy greater than a preset accuracy, occurrence times greater than a preset number, and display area greater than a preset ratio of the total area of ​​the video frame image can be selected as candidate entities.

[0096] In one embodiment, when the initial entity is of a preset type, the above step three may be further implemented according to the following sub-steps:

[0097] Sub-step 1: Filter out at least one intermediate entity from the initial entities based on the recognition accuracy, number of appearances in the target video, and display area of ​​each initial entity.

[0098] Here, the preset type can be set based on experience and is not specifically limited in the embodiment of the present disclosure. For example, the preset type can be a commodity type.

[0099] For example, the initial entities whose recognition accuracy is greater than a preset accuracy, whose number of occurrences is greater than a preset number, and whose display area accounts for a proportion of the total area of ​​the video frame image greater than a preset proportion can be selected as the intermediate entities.

[0100] Sub-step 2: Filter candidate entities from the intermediate entities based on the number of entities matching the intermediate entity in the preset entity library.

[0101] Here, the preset entity library includes multiple preset entities, and the preset entities can be displayed as target recommendation information.

[0102] In specific implementations, for each intermediate entity, a similarity recall method can be used to recall preset entities that match the preset entity from a preset entity library. If the number of preset entities that match the preset entity is greater than a preset number, the intermediate entity can be used as a candidate entity; otherwise, the intermediate entity is ignored.

[0103] In one embodiment, in a target video, a target entity may often appear in multiple consecutive video frames. The entity type of the target entity may correspond to multiple information recommendation dimensions. Therefore, for a target entity, when one information recommendation dimension corresponds to one information tag, the target entity may have multiple information tags. In the case of multiple information tags, the above S102 may also be implemented according to the following steps:

[0104] In response to the existence of multiple information recommendation dimensions corresponding to the entity type of the target entity, multiple information tags associated with the target entity are switched and displayed according to the playback progress information of the target video.

[0105] Here, the playback progress information is used to indicate the video frame picture that the target video is currently playing to.

[0106] During specific implementation, when there are multiple information recommendation dimensions corresponding to the entity type of the target entity, the target entity may also correspond to multiple information tags. According to the playback progress information, it can be determined to which frame the continuous multi-frame video frame image including the target entity has been played, and the user may have different needs to understand the target entity at different times when the target video displays the target entity. For example, in the case where the target entity is an electronic product, at the initial moment of displaying the electronic product, there may be a need to obtain recommended information of the electronic product under the evaluation video dimension. At the middle moment of displaying the electronic product, there may be a need to obtain recommended information of the electronic product under the discount information dimension. At the end moment of displaying the electronic product, there may be a need to obtain recommended information of the electronic product under the link acquisition dimension. Therefore, in the case where the target entity corresponds to multiple information tags, after obtaining multiple information tags, you can switch to display multiple information tags on the information recommendation page according to the playback progress information of the target video.

[0107] Exemplarily, when the target entity is food 1, the information recommendation dimensions corresponding to food 1 include an acquisition link dimension, an eating suggestion information dimension, and a food science video dimension. The acquisition link dimension corresponds to information tag 5, the eating suggestion information dimension corresponds to information tag 6, and the food science video dimension corresponds to information tag 7. Food 1 corresponds to 15 consecutive video frame images. Then, during the playback of the first 5 video frame images corresponding to food 1, information tag 7 can be displayed. In this way, the user can obtain multiple science videos related to food 1 according to information tag 7; during the playback of the middle 5 video frame images corresponding to food 1, information tag 6 can be displayed. In this way, the user can obtain recommended information related to food 1 (such as recipes, eating methods, eating precautions, etc.) according to information tag 6; during the playback of the last 5 video frame images corresponding to food 1, information tag 5 can be displayed. In this way, the user can obtain acquisition link information related to food 1 (such as food 1 acquisition links from different providers) according to information tag 5.

[0108] In this way, displaying information tags according to the playback progress information of the target video can improve the simplicity and rationality of the displayed tag information when playing each frame of the video.

[0109] In one embodiment, the above S102 may be implemented as follows:

[0110] In response to the presence of multiple target entities in the target video, information tags associated with the target entities are displayed according to the time when the target entities appear in the target video.

[0111] Here, the time when the target entity appears in the target video is the time when the video frame image including the target entity appears in the target video. Each target entity can be associated with one or more information tags.

[0112] In a specific implementation, when there are multiple target entities in the target video, for each target entity, multiple information tags corresponding to the target entity can be displayed during the process of playing the video frame image including the target entity.

[0113] For example, the target video includes target entity 1 appearing in video frame pictures 1 to 5, target entity 2 appearing in video frame pictures 6 to 20, and target entity 3 appearing in video frame pictures 21 to 30. During the playback of video frame pictures 1 to 5, various information tags associated with target entity 1 can be displayed in the form of anchor points or floating layers; during the playback of video frame pictures 6 to 20, various information tags associated with target entity 2 can be displayed in the form of anchor points or floating layers; and during the playback of video frame pictures 21 to 30, various information tags associated with target entity 3 can be displayed in the form of anchor points or floating layers.

[0114] Optionally, when there are multiple target entities, in addition to displaying the information tags of the target entities according to the time when the target entities appear in the target video, the information tags corresponding to each target entity can also be displayed during the entire process of playing the target video, that is, the information tags corresponding to each target entity can be displayed when playing each frame of the video.

[0115] In one embodiment, multiple target entities corresponding to the same entity type may appear in the target video. In this case, the above S103 may be implemented according to the following steps:

[0116] In the case where there are multiple target entities corresponding to the same entity type in the target video, in response to triggering any information tag corresponding to the entity type, a recommended information set under the information recommendation dimension corresponding to the information tag is displayed, and the recommended information set includes target recommendation information of the multiple target entities.

[0117] Here, the information tag corresponding to the entity type can specifically be the information tag corresponding to the information recommendation dimension associated with the entity type. For any entity type, when there are multiple target entities under the entity type, for each information recommendation dimension associated with the entity type, the recommended information of each target entity under the information recommendation dimension can be aggregated to obtain the recommended information set corresponding to the information recommendation dimension. An information tag can correspond to an information recommendation dimension, and an information recommendation dimension can correspond to a recommended information set. The recommended information set can include multiple target entities of the same entity type and the recommended information of each target under the information recommendation dimension corresponding to the recommended information set.

[0118] Among them, for multiple target entities of the same entity type, information tags corresponding to the target entity under each information recommendation dimension associated with the entity type can be generated (that is, each target entity has an information tag under each information recommendation dimension). Then, after the information tag corresponding to any target entity in any information recommendation dimension is triggered, the recommended information set corresponding to the information tag under the information recommendation dimension can be displayed.

[0119] Exemplarily, entities 1 to 3 correspond to the same entity type, and the information recommendation dimensions associated with the entity type include dimensions 1 and 2. Entities 1 to 3 each have a corresponding information tag in dimensions 1 and 2 (e.g., entity 1 corresponds to tag a in dimension 1 and tag b in dimension 2, entity 2 corresponds to tag c in dimension 1 and tag d in dimension 2, entity 3 corresponds to tag e in dimension 1 and tag f in dimension 2). Dimension 1 corresponds to information recommendation set 1, which includes target recommendation information for entities 1 to 3 under dimension 1; dimension 2 corresponds to information recommendation set 2, which includes target recommendation information for entities 1 to 3 under dimension 2. Furthermore, in response to triggering any information tag corresponding to dimension 1 (i.e., triggering tag a, c, or e), information recommendation set 1 can be displayed; or, in response to triggering any information tag corresponding to dimension 2 (i.e., triggering tag b, d, or f), information recommendation set 2 can be displayed.

[0120] Optionally, for multiple target entities of the same entity type, an information tag corresponding to each information recommendation dimension associated with the entity type can be generated (that is, multiple target entities only correspond to one information tag under the information recommendation dimension). After the information tag is triggered, the recommended information set corresponding to the information tag under the information recommendation dimension can be displayed.

[0121] Exemplarily, entities 1 to 3 correspond to the same entity type, and the information recommendation dimensions associated with this entity type include dimensions 1 and 2. Entities 1 to 3 correspond to a unique information tag (comprehensive tag g) in dimension 1 and a unique information tag (comprehensive tag h) in dimension 2. Dimension 1 corresponds to information recommendation set 1, which includes target recommendation information for entities 1 to 3 under dimension 1; dimension 2 corresponds to information recommendation set 2, which includes target recommendation information for entities 1 to 3 under dimension 2. Furthermore, in response to triggering the information tag under dimension 1 (i.e., triggering the comprehensive tag g), information recommendation set 1 can be displayed; or, in response to triggering the information tag under dimension 2 (i.e., triggering the comprehensive tag h), information recommendation set 2 can be displayed.

[0122] As shown in Figure 6, it is a schematic diagram of the process of displaying an information recommendation set provided by an embodiment of the present disclosure, wherein e in Figure 6 is an information recommendation page, which displays information tag g (such as the seaside guide in e) and information tag h (such as travel in e), and the video frame picture currently displayed in the information recommendation page only includes entity 1 (such as the sea in e), then in response to triggering information tag g, the information aggregation page shown in f in Figure 6 can be displayed, wherein the information aggregation page is displayed on the information recommendation page in the form of a floating card, wherein information recommendation set 1 is displayed, and information recommendation set 1 includes each target recommendation information of entities 1 to 3 under dimension 1 (such as the guide dimension in f) (such as target recommendation information 1 to 7 in Figure 6, wherein target recommendation information 1 and 2 are target recommendation information corresponding to entity 1, target recommendation information 3 to 5 are target recommendation information corresponding to entity 2, and target recommendation information 6 and 7 are target recommendation information corresponding to entity 3).

[0123] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0124] Based on the same inventive concept, an information recommendation device corresponding to the information recommendation method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to that of the above-mentioned information recommendation method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0125] FIG7 is a schematic diagram of an information recommendation device provided by an embodiment of the present disclosure, including:

[0126] Play module 701, used to play the target video on the information recommendation page;

[0127] A first display module 702 is configured to display information tags associated with a target entity in the target video; each information tag is generated based on at least one information recommendation dimension corresponding to the entity type of the target entity; different entity types correspond to different information recommendation dimensions;

[0128] The second display module 703 is configured to display target recommended information under the information recommendation dimension corresponding to the information tag in response to triggering the information tag.

[0129] In a possible implementation, the first display module 702, when displaying the information tags associated with the target entity in the target video, is configured to:

[0130] In response to the presence of multiple candidate entities in the target video, the target entity is determined from the multiple candidate entities based on historical behavior data obtained with user authorization, and each information tag associated with the target entity is displayed; or

[0131] In response to the presence of multiple candidate entities in the target video, each candidate entity is used as the target entity, and entity information of each target entity and various information tags associated with the target entity are displayed respectively.

[0132] In a possible implementation, the first display module 702, when displaying the information tags associated with the target entity in the target video, is configured to:

[0133] In response to the existence of multiple information recommendation dimensions corresponding to the entity type of the target entity, multiple information tags associated with the target entity are switched and displayed according to the playback progress information of the target video.

[0134] In a possible implementation, the first display module 702, when displaying the information tags associated with the target entity in the target video, is configured to:

[0135] In response to the presence of multiple target entities in the target video, information tags associated with the target entities are displayed according to the time when the target entities appear in the target video.

[0136] In a possible implementation, the second display module 703, in response to triggering the information tag, displays the target recommended information under the information recommendation dimension corresponding to the information tag, for:

[0137] In the case that there are multiple target entities corresponding to the same entity type in the target video, in response to triggering any information tag corresponding to the entity type, a recommended information set under the information recommendation dimension corresponding to the information tag is displayed, and the recommended information set includes target recommendation information of the multiple target entities.

[0138] In a possible implementation, the device further includes:

[0139] The determination module 704 is configured to determine the candidate entity according to the following steps:

[0140] Deduplication processing is performed on the video frame images according to the image similarity between the video frame images of the target video to obtain the deduplication video frame images;

[0141] Performing image recognition on each of the deduplicated video frames to determine the initial entities included in each of the video frames;

[0142] The candidate entities are screened out from the initial entities according to the recognition accuracy, the number of appearances and the display area of ​​each of the initial entities in the target video.

[0143] In a possible implementation, when the initial entity belongs to a preset type, the determination module 704, when screening the candidate entities from the initial entities based on the recognition accuracy, the number of appearances in the target video, and the display area of ​​each initial entity, is configured to:

[0144] Filtering at least one intermediate entity from the initial entities based on the recognition accuracy, the number of appearances in the target video, and the display area of ​​each initial entity;

[0145] The candidate entities are screened out from the intermediate entities according to the number of entities matching the intermediate entity in a preset entity library.

[0146] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0147] Based on the same technical concept, the embodiment of the present application also provides a computer device. Referring to FIG8 , a schematic diagram of the structure of a computer device provided in the embodiment of the present application is shown, including:

[0148] Processor 81, memory 82, and bus 83. The memory 82 stores machine-readable instructions executable by the processor 81. The processor 81 is configured to execute the machine-readable instructions stored in the memory 82. When the machine-readable instructions are executed by the processor 81, the processor 81 performs the following steps: S101: playing a target video on an information recommendation page; S102: displaying information tags associated with a target entity in the target video; each information tag is generated based on at least one information recommendation dimension corresponding to the entity type of the target entity; different entity types correspond to different information recommendation dimensions; and S103: in response to triggering an information tag, displaying target recommended information under the information recommendation dimension corresponding to the information tag.

[0149] The above-mentioned memory 82 includes internal memory 821 and external memory 822; the memory 821 here is also called internal memory, which is used to temporarily store the calculation data in the processor 81, as well as the data exchanged with the external memory 822 such as the hard disk. The processor 81 exchanges data with the external memory 822 through the memory 821. When the computer device is running, the processor 81 and the memory 82 communicate through the bus 83, so that the processor 81 executes the execution instructions mentioned in the above method embodiment.

[0150] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the information recommendation method described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0151] The computer program product of the information recommendation method provided in the embodiments of the present disclosure includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the steps of the information recommendation method described in the above method embodiments. For details, please refer to the above method embodiments and will not be repeated here.

[0152] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0153] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0156] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0157] If the technical solution of this application involves personal information, the product that applies the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of this application involves sensitive personal information, the product that applies the technical solution of this application has obtained the individual's separate consent before processing sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, a clear and prominent sign is set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that they agree to the collection of their personal information; or on the personal information processing device, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload their personal information; among which, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0158] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be subject to the scope of protection of the claims.

Claims

1. An information recommendation method, comprising: Play the target video on the information recommendation page; Displaying information tags associated with a target entity in the target video; Each information tag is generated according to at least one information recommendation dimension corresponding to the entity type of the target entity; wherein different entity types correspond to different information recommendation dimensions; In response to triggering the information tag, target recommended information under the information recommendation dimension corresponding to the information tag is displayed.

2. The method according to claim 1, wherein: The display of each information tag associated with the target entity in the target video includes: In response to the presence of multiple candidate entities in the target video, the target entity is determined from the multiple candidate entities according to the historical behavior data obtained with user authorization, and each information tag associated with the target entity is displayed; or, In response to the presence of multiple candidate entities in the target video, each of the candidate entities is used as the target entity, and entity information of each target entity and information tags associated with the target entity are displayed respectively.

3. The method according to claim 1 or 2, wherein: The display of each information tag associated with the target entity in the target video includes: In response to the existence of multiple information recommendation dimensions corresponding to the entity type of the target entity, multiple information tags associated with the target entity are switched for display according to the playback progress information of the target video.

4. The method according to any one of claims 1 to 3, wherein: The display of each information tag associated with the target entity in the target video includes: In response to the presence of multiple target entities in the target video, information tags associated with the target entities are displayed according to the time when the target entities appear in the target video.

5. The method according to any one of claims 1 to 4, wherein: In response to triggering the information tag, displaying target recommended information under the information recommendation dimension corresponding to the information tag, including: When there are multiple target entities corresponding to the same entity type in the target video, in response to triggering any information tag corresponding to the entity type, display the information corresponding to the information tag A recommendation information set under the recommendation dimension, wherein the recommendation information set includes target recommendation information of the multiple target entities.

6. The method according to claim 2, wherein: The candidate entity is determined according to the following steps: According to the picture similarity between each video frame picture of the target video, the video frame picture is deduplicated to obtain the deduplicated video frame picture; Performing image recognition on each of the deduplicated video frame images to determine the initial entities included in each of the video frame images; The candidate entities are screened out from the initial entities according to the recognition accuracy, the number of appearances and the display area of ​​each of the initial entities in the target video.

7. The method according to claim 6, wherein: In the case where the initial entity belongs to a preset type, screening the candidate entity from the initial entity according to the recognition accuracy, the number of appearances in the target video and the display area of ​​each of the initial entities includes: Filtering at least one intermediate entity from the initial entities according to the recognition accuracy, the number of appearances in the target video, and the display area of ​​each of the initial entities; The candidate entity is screened out from the intermediate entity according to the number of entities matching the intermediate entity in a preset entity library.

8. An information recommendation device, comprising: A playback module, configured to play a target video on an information recommendation page; A first display module is configured to display information tags associated with a target entity in the target video; each information tag is generated according to at least one information recommendation dimension corresponding to an entity type of the target entity; wherein different entity types correspond to different information recommendation dimensions; The second display module is configured to display target recommended information under the information recommendation dimension corresponding to the information tag in response to triggering the information tag.

9. A computer device comprising: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the processor performs the steps of the information recommendation method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a computer device, the computer device executes the steps of the information recommendation method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Commodity recommendation method and system based on video content

    CN104715023A

  • Product recommendation method, terminal equipment, and computer readable storage medium

    CN109495780A

  • Push processing method and device, equipment and medium

    CN115086700A

  • Method, device, equipment and medium for providing video related information

    CN115955596A

  • Information recommendation method and device, computer equipment and storage medium

    CN116561420A