Data display method, device and electronic device
By determining the trigger logo display information based on the data packets and demonstration videos of special effects props to be launched, the problem of inaccurate display of special effects props to be launched in the existing technology is solved, and automated and accurate display of special effects props is realized, improving user experience and classification Recommended effect.
Patent Information
- Application Number
- CN202110294583.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-03-19
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2041-03-19
AI Technical Summary
The prior art is difficult to accurately display the trigger logo of special effects props to be launched, resulting in poor user experience and it is difficult to automatically display the status of special effects props.
By determining the trigger logo display information of the special effect props to be launched based on the data packets and demonstration videos of the special effect props to be launched, the terminal device can automatically and accurately display the trigger logo of the special effect props to be launched, including determining the target prop category and similar special effect props.
It realizes accurate display of online special effects props, improves user experience, enhances automated display capabilities, and ensures accurate classification and recommendation of special effects props.
Smart Images

Figure CN112905291B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of Internet technology, and in particular, to a data display method, device, and electronic device. Background Art
[0002] In order to meet people's increasing entertainment needs, some video editing APPs (Applications) can provide special effects editing functions. In practice, users can use these APPs to add corresponding special effects to videos to increase the fun of video content.
[0003] In addition, users can also publish videos with special effects added so that other users can browse the videos, post comments, etc., thereby enriching the social methods between users. Summary of the invention
[0004] This disclosure section is provided to introduce concepts in a brief form, which will be described in detail in the detailed description section below. This disclosure section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.
[0005] The embodiments of the present disclosure provide a data display method, device and electronic device, which can more accurately display the trigger identifier of the special effect props to be launched online.
[0006] In a first aspect, an embodiment of the present disclosure provides a data display method, the method comprising: determining trigger identification display information of the special effects props to be launched online based on a data packet and a demonstration video of the special effects props to be launched online, wherein the trigger identification display information is used by a terminal device to display the trigger identification of the special effects props to be launched online.
[0007] In a second aspect, an embodiment of the present disclosure provides a data display device, which includes: a determination unit, used to determine the trigger identification display information of the special effects props to be launched online based on the data packet and demonstration video of the special effects props to be launched online, wherein the trigger identification display information is used for the terminal device to display the trigger identification of the special effects props to be launched online.
[0008] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the data display method as described in the first aspect.
[0009] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the data presentation method as described in the first aspect.
[0010] The data display method, device, and electronic device provided by the embodiments of the present disclosure can determine the trigger identification display information of the special effects props to be launched online based on the data packet and demonstration video of the special effects props to be launched online. In practical applications, the trigger identification display information is used by the terminal device to display the trigger identification of the special effects props to be launched online. In other words, the terminal device can display the trigger identification of the special effects props to be launched online based on the trigger identification display information. Thus, the trigger identification of the special effects props to be launched online is displayed on the premise of comprehensively considering the data packet and demonstration video of the special effects props to be launched online. On the one hand, the trigger identification of the special effects props to be launched online can be automatically displayed, and on the other hand, the trigger identification of the special effects props to be launched online can be displayed more accurately. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.
[0012] Figure 1 is a flow chart of some embodiments of the data display method according to the present disclosure;
[0013] Figure 2A , Figure 2B is a flow chart of some embodiments of the data display method according to the present disclosure;
[0014] Figure 3 is a flow chart of some embodiments of the data display method according to the present disclosure;
[0015] Figure 4A , Figure 4B is a flow chart of some embodiments of the data display method according to the present disclosure;
[0016] Figure 5 is a flow chart of some embodiments of the data display method according to the present disclosure;
[0017] Figure 6 is a schematic diagram of the structure of some embodiments of the data display device according to the present disclosure;
[0018] Figure 7 is an exemplary system architecture to which the data presentation methods of some embodiments of the present disclosure may be applied;
[0019] Figure 8 is a schematic diagram of a basic structure of an electronic device provided according to some embodiments of the present disclosure. DETAILED DESCRIPTION
[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0021] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0022] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0023] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0024] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0025] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0026] Please refer to Figure 1 , which shows the process of some embodiments of the data display method according to the present disclosure. Figure 1 As shown, the data display method comprises the following steps:
[0027] Step 101, based on the data packet and demonstration video of the special effect props to be launched, determine the trigger identification display information of the special effect props to be launched.
[0028] In this embodiment, the execution subject of the data display method can obtain the data packet and demonstration video of the special effect props to be launched online.
[0029] Special effect props can be props that add special effects to videos or images. In some scenarios, the video or image that needs to be added with special effects can be shot by the user in real time, or can be selected by the user from a local album.
[0030] The above data packet may include relevant data for realizing the special effects indicated by the special effects props to be launched online.
[0031] The above-mentioned demonstration video may be a video demonstrating the usage and display effect of the special effects props to be launched online.
[0032] It can be seen that the above data package and the above demonstration video both contain relevant features of the special effects props to be launched online.
[0033] It should be noted that the execution subject may be a server (for example, Figure 7 The server 704 shown in FIG. 1 may also be a terminal device (for example, Figure 7 When the execution subject is a server, the data packet and demonstration video of the special effect props to be launched can be obtained from the local or other devices. When the execution subject is a terminal device, the data packet and demonstration video of the special effect props to be launched can be obtained from the local or server (for example, Figure 7 The server 704 shown in the figure obtains the data packet and demonstration video of the special effect props to be launched online.
[0034] In this embodiment, the above-mentioned execution entity can determine the trigger identification display information of the special effect props to be launched online based on the above-mentioned data packet and demonstration video.
[0035] The trigger mark can be a mark used to trigger the special effect props. For example, the trigger mark can be an icon, a control, a link, etc. Of course, according to actual needs, the trigger mark can take other forms, which are not listed here one by one.
[0036] The trigger identification display information may be information for displaying the trigger identification of the special effect props to be launched. Optionally, the trigger identification display information includes at least one of the following: category information of the target prop category to which the special effect props to be launched belong; and similar prop information of similar special effect props to the special effect props to be launched.
[0037] In this embodiment, the trigger identification display information is used for the terminal device (for example, Figure 7 The terminal devices 701 and 702 shown in FIG. 7 show the triggering mark of the special effect props to be launched. That is, the terminal device can show the triggering mark of the special effect props to be launched based on the triggering mark display information.
[0038] When the above-mentioned execution entity is a server, trigger identification display information can be sent to the terminal device. Further, the terminal device can display the trigger identification of the special effect props to be launched online based on the trigger identification display information. When the above-mentioned subject is a terminal device, the trigger identification of the special effect props to be launched online can be displayed based on the trigger identification display information. In actual applications, the server can send trigger identification display information to the terminal device at various times. In some scenarios, after determining the above-mentioned trigger identification display information, the above-mentioned execution entity can directly send the above-mentioned trigger identification display information to the terminal device. In some scenarios, in response to receiving a special effect prop update request sent by the terminal device, the above-mentioned execution entity can send the above-mentioned trigger identification display information to the terminal device.
[0039] In actual applications, the terminal device can display the trigger mark of the special effects props to be launched online in a variety of ways. In some scenarios, the larger the storage space occupied by the special effects props data packet and the demonstration video, the more complex the special effects achieved by the special effects props. The above-mentioned execution entity can determine the complexity of the special effects props to be launched online based on the storage space occupied by the above-mentioned data packet and the storage space occupied by the above-mentioned demonstration video, and use the determined special effects complexity as the trigger mark display information. Furthermore, the terminal device can display the special effects props to be launched online based on the above-mentioned special effects complexity.
[0040] In this embodiment, the trigger mark of the special effect props to be launched is displayed under the premise of comprehensively considering the data packet and demonstration video of the special effect props to be launched. On the one hand, the trigger mark of the special effect props to be launched can be automatically displayed, and on the other hand, the trigger mark of the special effect props to be launched can be displayed more accurately.
[0041] In some embodiments, the above execution entity may be Figure 2A The steps included in the process shown are to execute the above step 101. The process includes step 201 and step 202.
[0042] Step 201, based on the above data packet and the above demonstration video, determine the target prop category to which the special effect prop to be launched belongs.
[0043] The trigger identification display information includes category information of the target prop category to which the special effect prop to be launched belongs.
[0044] The prop category may be a category pre-divided for special effect props. Usually, special effect props are pre-divided into multiple prop categories. For example, special effect props may be divided into role-playing category, headwear category, beauty category, etc. Here, role-playing special effect props may be special effect props that add special effects for role-playing roles. Headwear special effect props may be special effect props that add headwear special effects. Beauty special effect props may be special effect props that add beauty special effects.
[0045] The above-mentioned category information may be information representing the target prop category to which the special effect prop to be launched belongs.
[0046] In some scenarios, the execution entity may extract the data packet features and video features of the special effects props to be launched from the data packet and the demonstration video, respectively. Then, the execution entity may fuse the extracted data packet features and video features into comprehensive features of the special effects props to be launched. Next, for each prop category in a predetermined number of prop categories, the execution entity may determine the similarity between the comprehensive features set for the prop category and the comprehensive features of the special effects props to be launched. Finally, the execution entity may use the prop category with the highest similarity as the target prop category.
[0047] Step 202: Use the category information of the target item category as trigger identification display information.
[0048] At this time, the terminal device can follow Figure 2B The process shown includes the steps of displaying the trigger mark of the special effect props to be launched. The process includes step 203.
[0049] Step 203: Based on the above category information, a trigger mark of the special effect props to be launched is displayed in the first display interface.
[0050] The trigger mark of the special effect prop belonging to the target prop category is displayed in the first display interface. It can be seen that the first display interface can be an interface for triggering the special effect prop belonging to the target prop category.
[0051] Typically, before displaying the special effect props to be launched, the first display interface may display trigger identifiers of one or more special effect props belonging to the target prop category.
[0052] Thus, under the premise of comprehensively considering the data packet and demonstration video of the special effect props to be launched, the target prop category to which the special effect props to be launched belong is determined. Thus, the special effect props to be launched can be more accurately classified into the target prop category. Furthermore, by displaying the trigger mark of the special effect props to be launched in the first display interface, the trigger mark of the special effect props to be launched can be accurately displayed in the interface for triggering the special effect props of the target prop category.
[0053] In some embodiments, the above execution entity may be Figure 3 The process shown in FIG. 201 is executed in step 201. The process includes steps 2011 to 2013.
[0054] Step 2011, based on the above data packet, determine the first probability that the special effect props to be launched belong to each prop category in a predetermined number of prop categories.
[0055] In some scenarios, the execution subject may extract data packet features of the special effect props to be launched from the data packet. Then, for each prop category in the predetermined number of prop categories, the execution subject may determine a first similarity between the data packet features and a first predetermined feature set for the prop category, and use the proportion of the first similarity in the sum of the first similarities as a first probability that the special effect props to be launched belong to the prop category.
[0056] Step 2012: Based on the above demonstration video, determine the second probability that the special effect props to be launched belong to each prop category in a predetermined number of prop categories.
[0057] In some scenarios, similar to the method of determining the first probability, the execution entity may extract the video features of the special effects props to be launched from the demonstration video. Then, for each prop category in the predetermined number of prop categories, the execution entity may determine the second similarity between the video features and the second predetermined features set for the prop category, and use the proportion of the second similarity in the sum of the second similarities as the second probability that the special effects props to be launched belong to the prop category.
[0058] Step 2013, based on the first probability and the second probability that the special effect props to be launched belong to each prop category, determine the target prop category to which the special effect props to be launched belong.
[0059] In some scenarios, for each of the predetermined number of prop categories, the execution entity may determine the average of the first probability and the second probability that the special effect prop to be launched belongs to the prop category. Further, the execution entity may use the prop category with the highest average value as the target prop category to which the special effect prop to be launched belongs.
[0060] Thus, by comprehensively considering the first probability and the second probability that the special effect props to be launched belong to each prop category, the target prop category to which the special effect props to be launched belong is determined. Thus, the target prop category to which the special effect props to be launched belong can be determined more accurately.
[0061] In some embodiments, the execution entity may execute step 2011 as follows.
[0062] The first step is to obtain the prop description information of the special effect props to be launched from the above data package.
[0063] The prop description information may be information describing a special effect prop.
[0064] Optionally, the above-mentioned prop description information includes at least one of the following: special effect means description information, prop name description information, and trigger method description information.
[0065] The special effect means description information may describe the means used to achieve the special effect. For example, the means used to achieve the special effect may include at least one of the following: face detection, image deformation, and cutout.
[0066] The prop name description information may describe the prop name of the special effect prop. The trigger method description information may describe the trigger method of the special effect prop.
[0067] It should be noted that the prop description information may also include other information describing the special effect props, which will not be listed here one by one. The means used to achieve the special effect may also include other means, which will not be listed here one by one.
[0068] The second step is to determine the description information feature vector of the special effect props to be launched based on the above prop description information.
[0069] The description information feature vector may be a feature vector representing the description information of the prop.
[0070] For different prop description information, the feature vector can be determined in different ways.
[0071] In some scenarios, for the special effect description information, One-Hot Encoding may be used to determine the feature vector.
[0072] In some scenarios, the feature vectors of the prop name description information and the trigger method description information can be determined in a similar manner. As an example, first, at least one word segment is obtained from the prop name description information, then the word vectors of each word segment are queried from the word vector library, and finally, the feature vector of the prop description information can be determined based on the word vectors of each word segment. For example, the average vector of the word vectors of each word segment is used as the feature vector of the prop description information.
[0073] The third step is to input the description information feature vector into the first analysis model to determine the first probability that the special effect props to be launched belong to each prop category.
[0074] In practice, the first analysis model can realize various functions.
[0075] In some scenarios, the first analysis model processes the feature vector of the description information of the special effect prop and outputs a first probability that the special effect prop belongs to each prop category.
[0076] Optionally, the first analysis model processes the input description information feature vector of the special effect prop, and outputs the data packet feature of the special effect prop and the first probability that the special effect prop belongs to each prop category.
[0077] Thus, the execution entity can determine the first probability that the special effect props to be launched belong to each prop category from the result output by the first analysis model.
[0078] In some embodiments, the execution entity may execute step 2012 as follows.
[0079] Specifically, the above demonstration video is input into the second analysis model to determine the second probability that the special effect props to be launched belong to each prop category.
[0080] Similar to the first analysis model, the second analysis model can also realize various functions.
[0081] In some scenarios, the second analysis model processes the demonstration video of the special effect props and outputs the second probability that the special effect props belong to each prop category.
[0082] Optionally, the second analysis model processes the input demonstration video of the special effect prop to output the video features of the special effect prop and the second probability that the special effect prop belongs to each prop category.
[0083] Thus, the execution entity can determine the second probability that the special effect props to be launched belong to each prop category from the result output by the second analysis model.
[0084] In terms of analyzing event probabilities, machine learning models usually have a high degree of analysis accuracy. Therefore, using the first analysis model, the first probability that the special effects tool to be launched belongs to each prop category can be more accurately determined, and using the second analysis model, the second probability that the special effects prop to be launched belongs to each prop category can be more accurately determined. Furthermore, through each first probability determined by the first analysis model and each second probability determined by the second analysis model, the target prop category to which the special effects prop to be launched belongs can be more accurately determined.
[0085] In some embodiments, the execution entity may execute step 2013 as follows.
[0086] In the first step, for each prop category in a predetermined number of prop categories, a weighted probability of a first probability and a second probability that the special effect prop to be launched belongs to the prop category is determined.
[0087] As an example, the first probability and the second probability that the special effects props to be launched online belong to prop category A are f1 and f2 respectively, and the weights of the first probability f1 and the second probability f2 are w1 and w2 respectively. Therefore, the weighted probability that the special effects props to be launched online belong to prop category A is "f1×w1+f2×w2".
[0088] The weights of the first probability and the second probability can be set according to actual needs. In some scenarios, for different prop categories, the same weight (e.g., 1) is set for the first probability, and correspondingly, for different prop categories, the same weight (e.g., 1) is set for the second probability. In some scenarios, for different prop categories, different weights are set for the first probability, and correspondingly, for different prop categories, different weights are set for the first probability.
[0089] In the second step, the prop category with the largest weighted probability among the predetermined number of prop categories is taken as the target prop category.
[0090] Each first probability can be determined based on the data packet of the special effects props to be launched, and each second probability can be determined based on the demonstration video of the special effects props to be launched. It can be seen that the weight of the first probability can reflect the influence of the data packet of the special effects tool to be launched, and the weight of the second probability can reflect the influence of the demonstration video of the special effects tool to be launched. Therefore, the weighted probability can more accurately reflect the probability that the special effects props to be launched belong to a certain prop category, and further, the target prop category to which the special effects props to be launched belong can be more accurately determined.
[0091] In some embodiments, the above execution entity may be Figure 4A The steps included in the process shown are to execute the above step 101. The process includes step 401 and step 402.
[0092] Step 401, based on the above data packet and the above demonstration video, determine similar special effect props to the special effect props to be launched from the popular special effect props collection.
[0093] Popular special effect props may be special effect props that are frequently used by users.
[0094] Similar special effect props may be special effect props similar to the special effect props to be launched online.
[0095] In some scenarios, the execution subject may determine the comprehensive features of the special effects props to be launched in the manner described in the foregoing content. Further, the execution subject may determine the similarity between the comprehensive features of the special effects props to be launched and the comprehensive features of each popular special effects prop in the popular special effects props set. Further, the execution subject may determine similar special effects props to the special effects props to be launched from the popular special effects props set in descending order of similarity.
[0096] It should be noted that the number of similar special effect props can be set according to actual needs and is not specifically limited here.
[0097] Step 402: Use similar prop information of similar special effect props as trigger mark display information.
[0098] The similar props information may be information describing similar special effect props.
[0099] At this time, the terminal device can follow Figure 4B The steps included in the process shown display the trigger mark of the special effect props to be launched online.
[0100] Step 403: Based on the similar props information, the trigger mark of the special effect prop to be launched and the trigger marks of similar special effect props are displayed in the second display interface.
[0101] The second display interface displays the trigger logo of the newly launched special effect props and the trigger logo of the popular special effect props similar to the newly launched special effect props.
[0102] It is not difficult to understand that after the terminal device displays the special effect props to be launched, the special effect props to be launched are launched. At this time, the special effect props to be launched are new special effect props.
[0103] Thus, by displaying the trigger mark of the special effect props to be launched and the trigger mark of similar special effect props in the second display interface, it is possible to recommend the special effect props to be launched to the user and the popular special effect props similar to the special effect props to be launched to the user. In addition, under the premise of comprehensively considering the data packet and demonstration video of the special effect props to be launched, the popular special effect props similar to the special effect props to be launched can be determined more accurately. Furthermore, the popular special effect props similar to the special effect props to be launched can be recommended to the user more accurately.
[0104] In some embodiments, the above execution entity may be Figure 5 The process shown in the figure executes the above step 401. The process includes steps 4011 to 4013.
[0105] Step 4011, extracting the data packet features of the special effect props to be launched online from the above data packet.
[0106] It is not difficult to understand that the above data packet features may be features extracted from the data packet of the special effects props to be launched online.
[0107] Step 4012, extracting video features of the special effects props to be launched online from the above demonstration video.
[0108] It is not difficult to understand that the above video features may be features extracted from a demonstration video of the special effects props to be launched online.
[0109] Step 4013, based on the above data packet features and the above video features, determine similar special effect props to the special effect props to be launched from the set of popular special effect props.
[0110] In some scenarios, the execution subject may merge the data packet features and the video features into comprehensive features of the special effects props to be launched. Furthermore, for each popular special effects prop in the popular special effects props set, the execution subject may determine the similarity between the comprehensive features of the popular special effects prop and the comprehensive features of the special effects props to be launched. Thus, the execution subject may determine similar special effects props of the special effects props to be launched from the popular special effects props set in descending order of similarity.
[0111] Through the above data packet features and video features, the features of the special effects props to be launched can be described in more detail. Therefore, through the above data packet features and video features, popular special effects props similar to the special effects props to be launched can be determined more accurately.
[0112] In some embodiments, the execution entity may execute step 4011 as follows.
[0113] The first step is to obtain the prop description information of the special effect props to be launched from the above data package.
[0114] The second step is to determine the description information feature vector of the special effect props to be launched based on the above prop description information.
[0115] The contents recorded in the first and second steps have been recorded in the above content and will not be repeated here.
[0116] The third step is to input the description information feature vector into the first analysis model to determine the data packet characteristics of the special effect props to be launched.
[0117] In some scenarios, the first analysis model processes the input description information feature vector of the special effect props and outputs the data packet features of the special effect props.
[0118] Therefore, the execution entity can determine the data packet characteristics of the special effect props to be launched from the results output by the first analysis model.
[0119] In some embodiments, the execution entity may execute step 4012 as follows.
[0120] Specifically, the above demonstration video is input into the second analysis model to determine the video features of the special effects props to be launched online.
[0121] In some scenarios, the second analysis model processes the input demonstration video of the special effect props and outputs the video features of the special effect props.
[0122] Therefore, the execution entity can determine the video features of the special effects channel to be launched from the results output by the second analysis model.
[0123] In terms of feature extraction, the machine learning model can extract the correlation between input data and output features with correlation, so it has a higher feature extraction accuracy. It can be seen that the data packet features determined by the first analysis model can reflect the correlation between the various features of the special effects tools to be launched, and the video features determined by the second analysis model can reflect the correlation between the various features of the special effects tools to be launched. Therefore, using the first analysis model and the second analysis model, the data packet features and video features of the special effects tools to be launched can be determined more accurately.
[0124] In some embodiments, the execution entity may execute step 4013 as follows.
[0125] In the first step, for each hot special effect prop in the hot special effect prop set, a similarity determination operation is performed. The similarity determination operation includes steps L1 to L3.
[0126] Step L1, determining a first similarity between a data packet feature of the popular special effect prop and a data packet feature of the special effect prop to be launched.
[0127] The first similarity may be the similarity between the data packet features of the popular special effect props and the data packet features of the special effect props to be launched.
[0128] Step L2, determining a second similarity between the video feature of the popular special effects prop and the video feature of the special effects prop to be launched online.
[0129] The second similarity may be the similarity between the video features of the popular special effects props and the video features of the special effects props to be launched.
[0130] Step L3: determining a weighted similarity between the first similarity and the second similarity.
[0131] As an example, the weight of the first similarity t1 is w3, and the weight of the second similarity t2 is w4, so the weighted similarity of the first similarity t1 and the second similarity t2 is "t1×w3+t2×w4".
[0132] In some scenarios, a weighted similarity may be determined for each hot special effect prop in the hot special effect prop set.
[0133] The second step is to determine similar special effect props to the special effect props to be launched from the set of popular special effect props in order of weighted similarity from largest to smallest.
[0134] In some scenarios, the execution subject may determine at least one popular special effects prop from the set of popular special effects props in descending order of weighted similarity as a similar special effects prop to the special effects prop to be launched.
[0135] By setting the weight of the first similarity, the similarity between the data packet of the special effects props to be launched and the data packet of the popular special effects props can be accurately grasped. By setting the weight of the second similarity, the similarity between the demonstration video of the special effects props to be launched and the demonstration video of the popular special effects props can be accurately grasped. Therefore, through the weighted similarity of the first similarity and the second similarity, the similarity between the special effects props to be launched and the popular special effects props can be more accurately reflected, and further, the popular special effects props similar to the special effects props to be launched can be more accurately determined.
[0136] In some embodiments, if the input of the first analysis model is a descriptive information feature vector of a special effects prop, and the output is a data packet feature of the special effects prop and a first probability that the special effects prop belongs to each prop category, the execution entity that trains the first analysis model can generate the first analysis model by training in the following manner.
[0137] The first step is to obtain the first sample set.
[0138] The first sample in the first sample set includes a sample description information feature vector, a sample data packet feature, and a sample first probability that the sample special effect prop belongs to each prop category.
[0139] The sample description information feature vector is a feature vector that characterizes the prop description information of the sample special effect prop. The prop description information of the sample special effect prop is obtained from the sample data packet of the sample special effect prop. The sample data packet feature is a feature extracted from the sample data packet. The sample first probability includes the first probability that the sample special effect prop belongs to each prop category. In the second step, the sample description information feature vector included in the first sample in the first sample set is used as the input of the first initial model, and the sample data packet feature and each sample first probability included in the input first sample are used as the expected output of the first initial model to train and generate the first analysis model.
[0140] For details, please refer to steps S1 to S5 shown below.
[0141] In step S1, a sample description information feature vector included in a first sample selected from a first sample set is input into a first initial model to obtain a data packet feature output by the first initial model and a first probability that the sample special effect props belong to each prop category.
[0142] Step S2, using a preset loss function, calculates the degree of difference between the data packet characteristics output by the first initial model and the sample data packet characteristics included in the selected first sample, and calculates the degree of difference between each first probability output by the first initial model and each sample first probability included in the selected first sample.
[0143] Step S3: adjusting the model parameters of the first initial model according to the calculated difference degree.
[0144] Step S4, in response to reaching a preset training end condition, using the trained first initial model as the first analysis model.
[0145] Step S5, in response to the above training end condition not being met, continue to execute the above steps S1 to S4.
[0146] In some embodiments, if the input of the second analysis model is a demonstration video of a special effects prop, and the output is the video features of the special effects prop and the second probability of each prop category of the special effects prop, the execution entity of training the second analysis model can generate the second analysis model by training in the following manner.
[0147] The first step is to obtain a second sample set.
[0148] The second samples in the second sample set include the sample demonstration video, the sample video features, and the sample second probabilities that the sample special effect props belong to each prop category.
[0149] The sample demonstration video is a video that demonstrates the usage and display effect of the sample special effect props. The sample video features are features extracted from the sample demonstration video. The sample second probability includes the second probability that the sample special effect props belong to each prop category.
[0150] In the second step, the sample demonstration video included in the second sample in the second sample set is used as the input of the second initial model, and the sample video features included in the input second sample and the second probability of each sample are used as the expected output of the second initial model to train and generate the second analysis model.
[0151] For details, please refer to steps T1 to T5 as shown below.
[0152] In step T1, the sample demonstration video included in the second sample selected from the second sample set is input into the second initial model to obtain the video features output by the second initial model and the second probability that the sample special effect props belong to each prop category.
[0153] Step T2, using a preset loss function, calculates the degree of difference between the video features output by the second initial model and the sample video features included in the selected second sample, and calculates the degree of difference between each second probability output by the second initial model and each sample second probability included in the selected second sample.
[0154] Step T3: adjusting the model parameters of the second initial model according to the calculated difference degree.
[0155] Step T4, in response to reaching a preset training end condition, using the trained second initial model as the second analysis model.
[0156] Step T5, in response to the above training end condition not being met, continue to execute the above steps T1 to T4.
[0157] It should be noted that the training of the first analysis model and the second analysis model have some common characteristics. The loss functions used in the training of the two may include but are not limited to at least one of the following: 0-1 loss function, absolute value loss function, square loss function, exponential loss function, logarithmic loss function, etc. The methods used in the training of the two to adjust the model parameters include but are not limited to at least one of the following: BP (Back Propgation) algorithm, GD (Gradient Descent). The training end conditions used in the training of the two include but are not limited to at least one of the following: the training time exceeds the preset duration, the number of training times exceeds the preset number of times, the calculated difference degree is less than or equal to the preset difference threshold, and the calculated difference degree tends to be stable.
[0158] It should be noted that the execution subject of training the first analysis model and the execution subject of the data display method can be the same execution subject or different execution subjects. When the two are different execution subjects, after the training is completed, the execution subject of training the first analysis model can send the model parameters of the first analysis model to the execution subject of the data display method. Similarly, when the execution subject of training the second analysis model and the execution subject of the special effects props method are different execution subjects, after the training is completed, the execution subject of training the second analysis model can send the model parameters of the second analysis model to the execution subject of the data display method.
[0159] Generally, a trained machine learning model can realize data processing more accurately. Therefore, by using the trained first analysis model, data packet features that can fully reflect the characteristics of special effect props can be obtained, and the first probability that special effect props belong to each prop category can be more accurately determined. Similarly, by using the trained second analysis model, video features that can fully reflect the characteristics of special effect props can be obtained, and the second probability that special effect props belong to each prop category can be more accurately determined.
[0160] Further references Figure 6 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a data display device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0161] like Figure 6As shown, the data display device of this embodiment includes a determination unit 601. The determination unit 601 is used to: determine the trigger identification display information of the special effect props to be launched based on the data packet and demonstration video of the special effect props to be launched, wherein the trigger identification display information is used for the terminal device to display the trigger identification of the special effect props to be launched.
[0162] In this embodiment, the specific processing of the determination unit 601 of the data display device and the technical effects thereof can be referred to in Figure 1 The relevant description of step 101 in the corresponding embodiment will not be repeated here.
[0163] In some embodiments, the determination unit 601 is further used to: determine the target prop category to which the special effect props to be launched belong based on the above data packet and the above demonstration video; and use the category information of the target prop category as trigger identification display information. The above data display device also includes a display unit (not shown in the figure). The display unit is used to: based on the above category information, display the trigger identification of the special effect props to be launched in the first display interface, wherein the trigger identification of the special effect props belonging to the target prop category is displayed in the first display interface.
[0164] In some embodiments, the determination unit 601 is further used to: determine the first probability that the special effects props to be launched online belong to each prop category in a predetermined number of prop categories based on the above data packet; determine the second probability that the special effects props to be launched online belong to each prop category in a predetermined number of prop categories based on the above demonstration video; determine the target prop category to which the special effects props to be launched online belong based on the first probability and the second probability that the special effects props to be launched online belong to each prop category.
[0165] In some embodiments, the determination unit 601 is further used to: obtain prop description information of the special effects props to be launched online from the above-mentioned data packet; determine the description information feature vector of the special effects props to be launched online based on the description vector of the prop description information; input the description information feature vector into the first analysis model to determine the first probability that the special effects props to be launched online belong to each prop category.
[0166] In some embodiments, the determination unit 601 is further used to: input the above-mentioned demonstration video into a second analysis model to determine a second probability that the special effect props to be launched belong to each prop category.
[0167] In some embodiments, the determination unit 601 is further used to: for each prop category in a predetermined number of prop categories, determine the weighted probability of the first probability and the second probability that the special effect props to be launched belong to the prop category; and take the prop category with the largest weighted probability among the predetermined number of prop categories as the target prop category.
[0168] In some embodiments, the determination unit 601 is further used to: determine similar special effects props to the special effects props to be launched from the set of popular special effects props based on the above data packet and the above demonstration video; and use similar prop information of similar special effects props as trigger identification display information. The display unit is used to: display the trigger identification of the special effects props to be launched and the trigger identification of similar special effects props in the second display interface based on the above similar prop information, wherein the trigger identification of the newly launched special effects props and the trigger identification of the popular special effects props similar to the newly launched special effects props are displayed in the second display interface.
[0169] In some embodiments, the determination unit 601 is further used to: extract data packet features of the special effects props to be launched online from the above-mentioned data packet; extract video features of the special effects props to be launched online from the above-mentioned demonstration video; and determine similar special effects props of the special effects props to be launched online from a set of popular special effects props based on the above-mentioned data packet features and the above-mentioned video features.
[0170] In some embodiments, the determination unit 601 is further used to: obtain prop description information of the special effects props to be launched online from the above-mentioned data packet; determine the description information feature vector of the special effects props to be launched online based on the prop description information; and input the description information feature vector into the first analysis model to determine the data packet characteristics of the special effects props to be launched online.
[0171] In some embodiments, the determination unit 601 is further used to: input the above-mentioned demonstration video into the second analysis model to determine the video features of the special effects props to be launched online.
[0172] In some embodiments, the prop description information includes at least one of the following: special effect means description information, prop name description information, and trigger method description information.
[0173] In some embodiments, the determination unit 601 is further used to: perform a similarity determination operation for each popular special effects prop in the set of popular special effects props: determine a first similarity between a data packet feature of the popular special effects prop and a data packet feature of a special effects prop to be launched; determine a second similarity between a video feature of the popular special effects prop and a video feature of the special effects prop to be launched; determine a weighted similarity between the first similarity and the second similarity; and determine, from the set of popular special effects props, similar special effects props to the special effects props to be launched in the order of the weighted similarities from largest to smallest.
[0174] In some embodiments, the first analysis model processes the input description information feature vector of the special effect props, and outputs the data packet features of the special effect props and the first probability that the special effect props belong to each prop category.
[0175] In some embodiments, the first analysis model is trained in the following manner: a first sample set is obtained, wherein the first sample includes a sample description information feature vector, a sample data packet feature, and a sample first probability that the sample special effect prop belongs to each prop category; the sample description information feature vector included in the first sample in the first sample set is used as the input of the first initial model, and the sample data packet feature and each sample first probability included in the input first sample are used as the expected output of the first initial model to train and generate the first analysis model.
[0176] In some embodiments, the second analysis model processes the input demonstration video of the special effect prop and outputs the video features of the special effect prop and the second probability that the special effect prop belongs to each prop category.
[0177] In some embodiments, the second analysis model is trained in the following manner: a second sample set is obtained, wherein the second samples include sample demonstration videos, sample video features, and sample second probabilities that sample special effects props belong to each prop category; the sample demonstration videos included in the second samples in the second sample set are used as input to the second initial model, and the sample video features and each sample second probability included in the input second samples are used as expected outputs of the second initial model to train and generate the second analysis model.
[0178] Further references Figure 7 , Figure 7 An exemplary system architecture is shown in which the data presentation method of some embodiments of the present disclosure can be applied.
[0179] like Figure 7 As shown, the system architecture may include terminal devices 701, 702, a network 703, and a server 704. The network 703 is used to provide a medium for a communication link between the terminal devices 701, 702 and the server 704. The network 703 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0180] The terminal devices 701 and 702 can interact with the server 704 through the network 703 to receive or send messages, etc. Various client applications can be installed on the terminal devices 701 and 702. For example, special effect editing applications can be installed on the terminal devices 701 and 702.
[0181] In some scenarios, terminal devices 701 and 702 can determine the trigger identification display information of the special effects props to be launched online based on the data packet and demonstration video of the special effects props to be launched online. Further, terminal devices 701 and 702 can display the trigger identification of the special effects props to be launched online based on the trigger identification display information.
[0182] In actual application, after displaying the trigger mark of the special effect props to be launched, if the user performs a trigger operation on the trigger mark of the special effect props to be launched, the special effects corresponding to the special effect props to be launched can be added to the video or image.
[0183] Terminal devices 701 and 702 may be hardware or software. When terminal devices 701 and 702 are hardware, they may be various electronic devices having a display screen and supporting information interaction, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc. When terminal devices 701 and 702 are software, they may be installed in the electronic devices listed above. They may be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.
[0184] The server 704 may be a server that provides various services. In some scenarios, the server 704 may determine the trigger identification display information of the special effect props to be launched based on the data packet and demonstration video of the special effect props to be launched, and further, may send the trigger identification display information to the terminal devices 701 and 702. Further, the terminal devices 701 and 702 may display the trigger identification of the special effect props to be launched based on the trigger identification display information.
[0185] The server 704 may be hardware or software. When the server 704 is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server 704 is software, it may be implemented as multiple software or software modules (e.g., multiple software or software modules for providing distributed services), or as a single software or software module. No specific limitation is made here.
[0186] It should be noted that the data display method provided in the embodiments of the present disclosure may be executed by the server 704 , and accordingly, the data display device may be disposed in the server 704 .
[0187] It should be understood that Figure 7 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0188] Reference below Figure 8 , which shows an electronic device (eg, Figure 7 A schematic diagram of the structure of the server in FIG. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0189] like Figure 8 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0190] Typically, the following devices may be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication device 809 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 8 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0191] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 809, or installed from the storage device 808, or installed from the ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
[0192] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0193] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0194] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device determines the trigger identification display information of the special effect props to be launched based on the data packet and demonstration video of the special effect props to be launched, wherein the trigger identification display information is used for the terminal device to display the trigger identification of the special effect props to be launched.
[0195] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0196] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0197] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The names of these units do not limit the units themselves in some cases. For example, the determination unit may also be described as a unit that "determines the trigger identification display information of the special effect props to be launched based on the data packet and demonstration video of the special effect props to be launched."
[0198] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0199] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0200] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) to form a technical solution.
[0201] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0202] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.
Claims
1. A data display method, characterized in that: include: Based on the data packet and demonstration video of the special effects props to be launched, determine the trigger identification display information of the special effects props to be launched, wherein the trigger identification display information is used for the terminal device to display the trigger identification of the special effects props to be launched; The data packet includes prop description information, and the prop description information includes at least one of the following: special effect means description information, prop name description information, and trigger method description information; The special effect means description information is used to describe the means used to achieve the special effect, and the means used to achieve the special effect include at least one of the following: face detection, image deformation, and cutout.
2. The method according to claim 1, characterized in that The determining, based on the data packet and the demonstration video of the special effect props to be launched, the trigger identification display information of the special effect props to be launched, includes: Based on the data packet and the demonstration video, determine the target prop category to which the special effect prop to be launched belongs; Using the category information of the target item category as the trigger identification display information; and The trigger mark of the special effect props to be launched is displayed to the terminal device in the following ways, including: Based on the category information, a trigger identifier of the special effect props to be launched is displayed in a first display interface, wherein the trigger identifier of the special effect props belonging to the target prop category is displayed in the first display interface.
3. The method according to claim 2, characterized in that The determining, based on the data packet and the demonstration video, a target prop category to which the special effect prop to be launched belongs includes: Based on the data packet, determining a first probability that the special effect prop to be launched belongs to each prop category among a predetermined number of prop categories; Based on the demonstration video, determining a second probability that the special effect prop to be launched belongs to each of the predetermined number of prop categories; Based on the first probability and the second probability that the special effect props to be launched belong to each prop category, the target prop category to which the special effect props to be launched belongs is determined.
4. The method according to claim 3, characterized in that The determining, based on the data packet, a first probability that the special effect prop to be launched belongs to each of a predetermined number of prop categories includes: Acquire the item description information of the special effect item to be launched from the data packet; Determine, according to the item description information, a description information feature vector of the special effect item to be put online; The description information feature vector is input into a first analysis model to determine a first probability that the special effect props to be launched belong to each prop category.
5. The method according to claim 3, characterized in that: The determining, based on the demonstration video, a second probability that the special effect prop to be launched belongs to each of the predetermined number of prop categories includes: The demonstration video is input into a second analysis model to determine a second probability that the special effect props to be launched belong to each prop category.
6. The method according to claim 3, characterized in that The determining the target prop category to which the special effect prop to be launched belongs based on the first probability and the second probability that the special effect prop to be launched belongs to each prop category includes: For each prop category in the predetermined number of prop categories, determining a weighted probability of a first probability and a second probability that the special effect prop to be launched belongs to the prop category; The prop category with the largest weighted probability among the predetermined number of prop categories is used as the target prop category.
7. The method according to claim 1, characterized in that The determining, based on the data packet and the demonstration video of the special effect props to be launched, the trigger identification display information of the special effect props to be launched, includes: Based on the data packet and the demonstration video, determine similar special effect props to the special effect props to be launched from a set of popular special effect props; Using similar props information of the similar special effect props as the trigger identification display information; and The trigger mark of the special effect props to be launched is displayed to the terminal device in the following ways, including: Based on the similar props information, the trigger identifier of the special effects props to be launched and the trigger identifier of the similar special effects props are displayed in the second display interface, wherein the trigger identifier of the newly launched special effects props and the trigger identifier of the popular special effects props similar to the newly launched special effects props are displayed in the second display interface.
8. The method according to claim 7, characterized in that The determining, based on the data packet and the demonstration video, from a set of popular special effect props, a similar special effect prop to the special effect prop to be launched, comprises: Extracting data packet features of the special effect props to be launched from the data packet; Extracting video features of the special effects props to be launched from the demonstration video; Based on the data packet features and the video features, special effect props similar to the special effect props to be launched are determined from the set of popular special effect props.
9. The method according to claim 8, characterized in that The step of extracting the data packet features of the special effect props to be put online from the data packet comprises: Acquire the item description information of the special effect item to be launched from the data packet; Determine, according to the item description information, a description information feature vector of the special effect item to be put online; The description information feature vector is input into the first analysis model to determine the data packet features of the special effect props to be put online.
10. The method according to claim 8, characterized in that The step of extracting video features of the special effects props to be launched from the demonstration video includes: The demonstration video is input into a second analysis model to determine the video features of the special effects props to be launched online.
11. The method according to claim 8, characterized in that The determining, based on the data packet feature and the video feature, from the set of popular special effect props, a similar special effect prop to the special effect prop to be launched, comprises: For each hot special effect prop in the hot special effect prop set, a similarity determination operation is performed: determining a first similarity between a data packet feature of the hot special effect prop and a data packet feature of the special effect prop to be launched; determining a second similarity between a video feature of the hot special effect prop and a video feature of the special effect prop to be launched; and determining a weighted similarity between the first similarity and the second similarity; In order of weighted similarity from largest to smallest, special effect props similar to the special effect props to be launched are determined from the set of popular special effect props.
12. The method according to claim 4 or 9, characterized in that: The first analysis model processes the input description information feature vector of the special effect props, and outputs the data packet features of the special effect props and the first probability that the special effect props belong to each prop category.
13. The method according to claim 12, characterized in that The first analysis model is trained in the following manner: Acquire a first sample set, wherein the first sample includes a sample description information feature vector, a sample data packet feature, and a sample first probability that the sample special effect prop belongs to each prop category; The sample description information feature vector included in the first sample in the first sample set is used as the input of the first initial model, and the sample data packet characteristics and the first probability of each sample included in the input first sample are used as the expected output of the first initial model to train and generate the first analysis model.
14. The method according to claim 5 or 10, characterized in that: The second analysis model processes the input demonstration video of the special effect props and outputs the video features of the special effect props and the second probability that the special effect props belong to each prop category.
15. The method according to claim 14, characterized in that The second analysis model is trained in the following manner: Obtain a second sample set, wherein the second sample includes a sample demonstration video, sample video features, and a sample second probability that the sample special effect props belong to each prop category; The sample demonstration video included in the second sample in the second sample set is used as the input of the second initial model, and the sample video features included in the input second sample and the second probability of each sample are used as the expected output of the second initial model to train and generate the second analysis model.
16. A data display device, characterized in that: include: A determination unit for determining, based on the data packet and demonstration video of the special effects props to be launched, the trigger identification display information of the special effects props to be launched, wherein the trigger identification display information is used for the terminal device to display the trigger identification of the special effects props to be launched; The data packet includes prop description information, and the prop description information includes at least one of the following: special effect means description information, prop name description information, and trigger method description information; The special effect means description information is used to describe the means used to achieve the special effect, and the means used to achieve the special effect include at least one of the following: face detection, image deformation, and cutout.
17. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 15.
18. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 15 is implemented.
