Method, device, medium and equipment for obtaining multimedia resource attention
By obtaining and updating the feature labels and feature weights of multimedia resources, the problems of evaluation lag and high cost in advertising delivery are solved, and accurate evaluation and efficiency improvement of advertising resources are achieved before delivery.
Patent Information
- Application Number
- CN202111057873.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-09-09
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-09-09
AI Technical Summary
Due to the lag and high human and material costs in the prior art, advertising delivery is inefficient, and it is difficult to effectively evaluate the attention of multimedia resources before delivery.
By obtaining the target type of the target multimedia resource, determining its corresponding feature tags and feature weights, predicting its attention based on historical data, periodically update the feature weights to improve accuracy, and evaluate before delivery.
It reduces the human and material costs of advertising, improves the efficiency of advertising, and can accurately predict the attention of multimedia resources before delivery.
Smart Images

Figure CN113724016B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of multimedia technology, and in particular to a method, device, medium and equipment for obtaining multimedia resource attention. Background Art
[0002] With the rapid development of the Internet, the popularization of network applications, and the gradual enrichment of business types in different fields, Internet advertising has gradually become the mainstream of advertising business. Internet advertising can be multimedia resources, such as video resources, image resources, etc., and the attention paid to multimedia resources of advertisements can be an important indicator for evaluating the effectiveness of advertising.
[0003] In related technologies, after an advertisement has been released for a period of time, the effect of the advertisement can be evaluated through user surveys or historical attention data, and then the multimedia resources of the advertisement can be optimized and re-released based on the effect of the advertisement. However, this method has a lag and requires multiple advertisement releases, which wastes a lot of manpower and material costs, resulting in low efficiency of advertisement release. Summary of the invention
[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary 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] In a first aspect, the present disclosure provides a method for obtaining multimedia resource attention, the method comprising:
[0006] Get the target type of the target multimedia resource;
[0007] Determining a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type;
[0008] Obtaining a feature weight corresponding to each second feature tag, wherein the feature weight is used to represent the influence of the second feature tag on the target attention of the target multimedia resource;
[0009] The target attention degree of the target multimedia resource is acquired according to the second feature label and the feature weight.
[0010] Optionally, before obtaining the feature weight corresponding to each second feature label, the method further includes:
[0011] According to a first historical attention degree of a first historical multimedia resource, obtaining a first feature tag corresponding to the target type and a feature weight corresponding to each first feature tag, wherein the target type of the first historical multimedia resource is the same as the target type of the target multimedia resource;
[0012] The obtaining of the feature weight corresponding to each second feature label comprises:
[0013] For each second feature tag, the feature weight of the first feature tag corresponding to the second feature tag is used as the feature weight corresponding to the second feature tag.
[0014] Optionally, the method further comprises:
[0015] Periodically obtain a second historical attention of a second historical multimedia resource within a preset time period, and update a feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource.
[0016] Optionally, updating the feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention includes:
[0017] Extracting features from the second historical multimedia resource according to the target type to obtain a plurality of first feature tags corresponding to the second historical multimedia resource;
[0018] For each first feature tag, obtain the third historical attention of the third historical multimedia resource with the first feature tag, and the fourth historical attention of the fourth historical multimedia resource without the first feature tag; and update the feature weight corresponding to the first feature tag based on the third historical attention and the fourth historical attention.
[0019] Optionally, updating the feature weight corresponding to the first feature tag according to the third historical attention degree and the fourth historical attention degree includes:
[0020] Obtaining a ratio of the third historical attention degree to the fourth historical attention degree;
[0021] When the ratio is greater than or equal to a preset first ratio threshold, increase the feature weight corresponding to the first feature label; or,
[0022] When the ratio is less than or equal to a preset second ratio threshold, the feature weight corresponding to the first feature label is reduced.
[0023] Optionally, acquiring the target attention of the target multimedia resource according to the second feature tag and the feature weight includes:
[0024] Adding the feature weights corresponding to the plurality of second feature labels to obtain a target weight;
[0025] The target attention degree of the target multimedia resource is calculated according to the target weight and the reference weight of the target type.
[0026] Optionally, acquiring the target attention of the target multimedia resource according to the second feature tag and the feature weight includes:
[0027] Determine whether each second feature tag is a preset blacklist tag, wherein the preset blacklist tag is a feature tag whose influence weight on the historical attention is less than or equal to a preset weight threshold;
[0028] The second characteristic tag which is not a preset blacklist tag is used as the third characteristic tag;
[0029] The target attention degree of the target multimedia resource is acquired according to the third feature tag and the feature weight.
[0030] Optionally, the method further comprises:
[0031] Classifying the second feature label according to the feature weight corresponding to the second feature label, and classifying the second feature label into a positive label, a neutral label or a negative label;
[0032] According to the classification result, the second feature label is displayed.
[0033] In a second aspect, the present disclosure provides a device for obtaining multimedia resource attention, the device comprising:
[0034] A target type acquisition module is used to acquire the target type of the target multimedia resource;
[0035] A feature tag determination module, used to determine a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type;
[0036] A feature weight acquisition module, used to acquire a feature weight corresponding to each second feature tag, wherein the feature weight is used to characterize the influence of the second feature tag on the target attention of the target multimedia resource;
[0037] The target attention acquisition module is used to acquire the target attention of the target multimedia resource according to the second feature tag and the feature weight.
[0038] Optionally, the device further comprises:
[0039] A historical feature label and weight acquisition module, used to acquire a first feature label corresponding to the target type and a feature weight corresponding to each first feature label according to a first historical attention of a first historical multimedia resource, wherein the target type of the first historical multimedia resource is the same as the target type of the target multimedia resource;
[0040] The feature weight acquisition module is used to use, for each second feature tag, the feature weight of the first feature tag corresponding to the second feature tag as the feature weight corresponding to the second feature tag.
[0041] Optionally, the device further comprises:
[0042] A historical weight updating module is used to periodically obtain a second historical attention of a second historical multimedia resource within a preset time period, and update the feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource.
[0043] Optionally, the historical weight updating module is used to perform feature extraction on the second historical multimedia resource according to the target type to obtain multiple first feature tags corresponding to the second historical multimedia resource; for each first feature tag, obtain the third historical attention of the third historical multimedia resource with the first feature tag, and the fourth historical attention of the fourth historical multimedia resource without the first feature tag; and update the feature weight corresponding to the first feature tag according to the third historical attention and the fourth historical attention.
[0044] Optionally, the historical weight update module is used to obtain the ratio of the third historical attention to the fourth historical attention; when the ratio is greater than or equal to a preset first ratio threshold, increase the feature weight corresponding to the first feature label; or, when the ratio is less than or equal to a preset second ratio threshold, reduce the feature weight corresponding to the first feature label.
[0045] Optionally, the target attention acquisition module is used to add the feature weights corresponding to multiple second feature tags to obtain a target weight; and calculate the target attention of the target multimedia resource based on the target weight and a benchmark weight of the target type.
[0046] Optionally, the target attention acquisition module is used to determine whether each second feature tag is a preset blacklist tag, wherein the preset blacklist tag is a feature tag whose impact weight on historical attention is preset and is less than or equal to a preset weight threshold; the second feature tag that is not a preset blacklist tag is used as a third feature tag; and the target attention of the target multimedia resource is acquired based on the third feature tag and the feature weight.
[0047] Optionally, the device further comprises:
[0048] A label classification module, used to classify the second feature label according to the feature weight corresponding to the second feature label, and classify the second feature label into a positive label, a neutral label or a negative label;
[0049] The label display module is used to display the second feature label according to the classification result.
[0050] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the method described in the first aspect of the present disclosure.
[0051] In a fourth aspect, the present disclosure provides an electronic device, including:
[0052] a storage device having a computer program stored thereon;
[0053] A processing device is used to execute the computer program in the storage device to implement the steps of the method described in the first aspect of the present disclosure.
[0054] By adopting the above technical solution, the target type of the target multimedia resource is obtained; from the multiple first feature tags corresponding to the target type, the multiple second feature tags corresponding to the target multimedia resource are determined; the feature weight corresponding to each second feature tag is obtained, wherein the feature weight is used to characterize the degree of influence of the second feature tag on the target attention of the target multimedia resource; and the target attention of the target multimedia resource is obtained according to the second feature tag and the feature weight. Since the above feature weight is obtained based on historical data or historical experience, it is possible to predict the target attention of the multimedia resource more accurately and reliably based on the above feature tags and feature weights, so that the multimedia resources of the advertisement can be evaluated before the advertisement is released, thereby reducing the human and material costs of the advertisement and improving the efficiency of the advertisement.
[0055] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] 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 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. In the drawings:
[0057] Figure 1 The figure is a flow chart showing a method for obtaining multimedia resource attention according to an exemplary embodiment.
[0058] Figure 2 The diagram is a schematic diagram showing target attention and feature labels of a target multimedia resource according to an exemplary embodiment.
[0059] Figure 3 The invention is a block diagram showing a device for obtaining multimedia resource attention according to an exemplary embodiment.
[0060] Figure 4 It is a block diagram showing a second apparatus for obtaining multimedia resource attention according to an exemplary embodiment.
[0061] Figure 5 It is a block diagram of a third apparatus for obtaining multimedia resource attention according to an exemplary embodiment.
[0062] Figure 6 It is a block diagram of a fourth apparatus for obtaining multimedia resource attention according to an exemplary embodiment.
[0063] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0064] 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.
[0065] 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.
[0066] 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.
[0067] 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.
[0068] 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".
[0069] 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.
[0070] First, the application scenario of the present disclosure is described. The present disclosure can be applied to the scenario of obtaining the attention of multimedia resources, and in particular, can be applied to the prediction of the attention of multimedia resources before delivery. The multimedia resources can be advertisements, movies, TV series, books, audio-visual products, etc. For example, it can be used to predict the attention of multimedia resources before delivery of advertisements.
[0071] It should be noted that the attention paid to the multimedia resources of an advertisement can be used as an important indicator for evaluating the effectiveness of advertisement delivery. For example, the attention paid to the multimedia resource can include the consumption (cost) or likes (like, for example, the number of times the multimedia resource is liked) of the multimedia resource; wherein the consumption can include the display volume (displaying the multimedia resource to the user), the click volume (the user clicks to view the multimedia resource), the purchase volume (the user pays for the multimedia resource) or the retention volume (the user leaves contact information and other information through the multimedia resource). In Internet advertising applications, the above-mentioned attention can be used as an important indicator for evaluating the effectiveness of advertisement delivery, and can also be used as an indicator for calculating advertising charges. For example, the Internet platform can charge advertisers according to the number of clicks on the multimedia resources of the advertisement.
[0072] In the related art, the process of advertisement creation, delivery and feedback may include: the designer creates advertisements according to the needs of the advertiser and obtains multimedia resources (video, image or text) of the advertisement; the advertiser, the advertisement designer and the advertisement optimizer can evaluate and optimize the created advertisement; the optimized advertisement is delivered to the market; the effect of advertisement delivery, that is, the attention of the multimedia resources of the advertisement, is obtained, and the multimedia resources are optimized and re-delivered according to the attention, so that after multiple rounds of iterative optimization, an advertisement with a better delivery effect can be obtained. In this process, it is very difficult to evaluate the advertisement before delivery, and it needs to be based on people's subjective experience. For example, advertisers, advertisement designers and advertisement optimizers need to invest a lot of time and energy to watch the multimedia resources of the advertisement and evaluate and optimize them. This process requires experienced advertisement designers or advertisement optimizers to evaluate; even, a large number of alternative advertisement multimedia resources need to be created, and trial and error iterative optimization is performed through a large number of advertisement delivery and acquisition of multimedia resource attention. This will waste a lot of manpower and material costs, resulting in low efficiency of advertisement delivery.
[0073] In order to solve the above problems, the present disclosure provides a method, device, medium and equipment for obtaining the attention of multimedia resources, firstly obtaining the target type of the target multimedia resource, and determining the multiple second feature tags corresponding to the target multimedia resource from the multiple first feature tags corresponding to the target type; obtaining the feature weight corresponding to each second feature tag, wherein the feature weight is used to characterize the degree of influence of the second feature tag on the target attention of the target multimedia resource; and obtaining the target attention of the target multimedia resource according to the second feature tag and the feature weight. Since the above feature weights are obtained based on historical data or historical experience, it is possible to predict the target attention of multimedia resources more accurately and reliably based on the above feature tags and feature weights, so that the multimedia resources of the advertisement can be evaluated before the advertisement is released, thereby reducing the manpower and material costs of the advertisement and improving the efficiency of the advertisement.
[0074] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
[0075] Figure 1 A method for obtaining multimedia resource attention is shown according to an exemplary embodiment. Figure 1 As shown, the method includes:
[0076] Step 101: Obtain the target type of the target multimedia resource.
[0077] For example, the target multimedia resource may be a target multimedia resource of a target advertisement, and the target multimedia resource may include a video, an image, or text. The target type may be a target industry for the target advertisement, for example, the target type may include the food industry, the medical industry, the home industry, or the education industry, etc. In addition, the target type may also be a user group for the target advertisement, for example, the target type may include a juvenile group, a youth group, a middle-aged group, or an elderly group.
[0078] Step 102: Determine a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type.
[0079] The plurality of first characteristic tags corresponding to the target type may be pre-set. For example, the first characteristic tags corresponding to the target type may be determined by an experienced advertising designer based on historical data or historical experience.
[0080] In this step, the second feature tag may be determined by any of the following methods:
[0081] Method 1: The target type and the target multimedia resource may be input into a first preset feature extraction model to perform feature extraction to obtain a plurality of second feature tags corresponding to the target multimedia resource.
[0082] Among them, the first preset feature extraction model can pre-set multiple first feature labels corresponding to the target type, and an extraction sub-model for each first feature label.
[0083] Method 2: The target multimedia resource can be input into a second preset feature extraction model to perform feature extraction to obtain multiple candidate feature tags for the target multimedia resource; then the intersection of the multiple candidate feature tags and the multiple first feature tags is used as the multiple second feature tags corresponding to the target multimedia resource.
[0084] In this way, regardless of the above method 1 or method 2, the obtained second feature labels are all subsets of the first feature labels.
[0085] Step 103: Obtain the feature weight corresponding to each second feature label.
[0086] The feature weight is used to represent the influence of the second feature tag on the target attention of the target multimedia resource.
[0087] For example, the feature weight corresponding to each first feature tag can be obtained based on historical data or historical experience. Since the second feature tag is a subset of the first feature tag, the feature weight corresponding to each second feature tag can be obtained based on the pre-set feature weight of the first feature tag.
[0088] Step 104: Obtain the target attention of the target multimedia resource according to the second feature tag and the feature weight.
[0089] For example, the sum of the feature weights corresponding to the multiple second feature tags may be used as the target attention level of the target multimedia resource.
[0090] Using the above method, the target type of the target multimedia resource is obtained; from the multiple first feature tags corresponding to the target type, multiple second feature tags corresponding to the target multimedia resource are determined; the feature weight corresponding to each second feature tag is obtained, wherein the feature weight is used to characterize the degree of influence of the second feature tag on the target attention of the target multimedia resource; according to the second feature tag and the feature weight, the target attention of the target multimedia resource is obtained. Since the above feature weights are obtained based on historical data or historical experience, it is possible to predict the target attention of multimedia resources more accurately and reliably based on the above feature tags and feature weights, so that the multimedia resources of the advertisement can be evaluated before the advertisement is released, thereby reducing the human and material costs of the advertisement and improving the efficiency of the advertisement.
[0091] It should be noted that the above embodiment is described using advertisements as an example, but the target multimedia resource is not limited to advertisements. The target multimedia resource may also be a movie, a TV series, or a book or audio-visual product, and the target attention may be the ratings of a movie or TV series, the box office revenue of a movie, the purchase rate of a book or audio-visual product, etc.
[0092] In another embodiment of the present disclosure, the first feature tag corresponding to the target type and the feature weight corresponding to each first feature tag can be obtained according to the historical multimedia resources in the following manner: according to the first historical attention of the first historical multimedia resource, the first feature tag corresponding to the target type and the feature weight corresponding to each first feature tag are obtained. The target type of the first historical multimedia resource is the same as the target type of the target multimedia resource. Specifically, the method may include the following steps:
[0093] First, a plurality of first historical multimedia resources are obtained, and the plurality of first historical multimedia resources are input into a pre-trained preset multimedia feature extraction model to obtain a plurality of first feature labels.
[0094] For example, the preset media feature extraction model can be obtained by training a preset neural network model including a twin network, and the sample data used for training can be sample historical multimedia resources with manually labeled feature labels.
[0095] Secondly, the first historical attention of each first historical multimedia resource within a certain period of time (eg, the last week or the last two weeks) is obtained.
[0096] Thirdly, weak supervision training is performed according to the first historical attention and the first feature label of each first historical multimedia resource to obtain a corresponding relationship between the first feature label and the feature weight.
[0097] For example, the first feature label corresponding to the target type and the feature weight corresponding to each first feature label may be shown in the following Table 1:
[0098] Target Type First feature tag Feature weights Education and Training#Primary and Secondary Education Video Type#Graphic#Text on Paper 12.59 Education and Training#Primary and Secondary Education Video Type#Situational Drama#Multi-person Situational Drama 0.43 Education and Training#Primary and Secondary Education Video Aesthetics #Subtitles #SubtitleSize #Large -14.65 Education and Training#Primary and Secondary Education Video aesthetics#falling version#falling version 1.74 Education and Training#Primary and Secondary Education Video Aesthetics #Contrast #Normal 10.57 Education and Training#Primary and Secondary Education Video Aesthetics#Screen Ratio#Part -7.28 Education and Training#Primary and Secondary Education Marketing selling point #School selling point #Leading teaching method #One-to-one Q&A 3.06 Education and Training#Primary and Secondary Education Marketing selling point #Call to action #Call to action #Come and sign up 6 Education and Training#Primary and Secondary Education Marketing selling point #School selling point #Leading teaching method #Live teaching 9.53 Education and Training#Primary and Secondary Education Marketing selling point #School selling point #Good teaching effect #Good teaching effect 3 Education and Training#Primary and Secondary Education Marketing selling point # selling point for users # favorable price # low cost 8.73 Education and Training#Primary and Secondary Education Marketing selling point #School selling point #Strong faculty #Strong faculty 3.08 Education and Training#Primary and Secondary Education Marketing selling point #School selling point #Strong faculty #Tsinghua and Peking University famous teachers 5.35 Education and Training#Primary and Secondary Education Marketing selling point #Selling point for users #Price discount #Free information 7.77
[0099] Table 1
[0100] As shown in Table 1, when the target type is "education and training#primary and secondary education", the first feature label corresponding to the target type is shown in the second column of Table 1, and the feature weight corresponding to each first feature label is shown in the third column of Table 1. The feature weight is a positive number, which can indicate that the first feature label can increase the attention of multimedia resources, thereby improving the effect of advertising; the feature weight is a negative number, which can indicate that the first feature label will reduce the attention of multimedia resources, thereby reducing the effect of advertising.
[0101] In this way, the first feature tag corresponding to the target type and the feature weight corresponding to each first feature tag can be obtained according to the historical multimedia resources in the above manner. Further, for each second feature tag, the feature weight of the first feature tag corresponding to the second feature tag can be used as the feature weight corresponding to the second feature tag.
[0102] Since multimedia resources on the Internet are updated quickly, user preferences will also change accordingly. Therefore, in order to ensure that the feature weight of the first feature tag can accurately represent the influence of the first feature tag on the target attention of the target multimedia resource, the feature weight can also be periodically updated according to the historical attention of the historical multimedia resources. Specifically, the method may include:
[0103] The second historical attention of the second historical multimedia resource in a preset time period is periodically obtained, and the feature weight corresponding to the first feature tag is updated according to the second historical multimedia resource and the second historical attention, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource.
[0104] For example, the feature weight corresponding to the first feature tag can be updated in the above manner every day, every week, or every month; the preset time period can be the most recent day, the most recent week, the most recent two weeks, or the most recent month. For example, the second historical multimedia resources of the most recent week and the second historical attention of each second historical multimedia resource can be obtained every day, and the feature weight corresponding to the first feature tag can be updated in the above manner.
[0105] Furthermore, the method of updating the feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention may include the following steps:
[0106] First, feature extraction is performed on the second historical multimedia resource according to the target type to obtain a plurality of first feature tags corresponding to the second historical multimedia resource.
[0107] Similarly, the feature extraction method may include: inputting the second historical multimedia resource into a pre-trained preset multimedia feature extraction model to obtain a plurality of first feature tags corresponding to the second historical multimedia resource.
[0108] Then, for each first feature tag, obtain the third historical attention of the third historical multimedia resource with the first feature tag, and the fourth historical attention of the fourth historical multimedia resource without the first feature tag; and update the feature weight corresponding to the first feature tag based on the third historical attention and the fourth historical attention.
[0109] In this step, according to the third historical attention and the fourth historical attention, the feature weight corresponding to the first feature tag may be updated in the following manner:
[0110] Obtain a ratio of the third historical attention to the fourth historical attention; when the ratio is greater than or equal to a preset first ratio threshold, increase the feature weight corresponding to the first feature label; or, when the ratio is less than or equal to a preset second ratio threshold, reduce the feature weight corresponding to the first feature label.
[0111] For example, if the average value of the third historical attention of the third historical multimedia resource with the first feature label is 60, and the average value of the fourth historical attention of the fourth historical multimedia resource without the first feature label is 50, then the ratio of the third historical attention to the fourth historical attention is 1.2. If the above-mentioned first ratio threshold is 1.05, the feature weight corresponding to the first feature label can be increased at this time; conversely, if the average value of the third historical attention of the third historical multimedia resource with the first feature label is 40, and the average value of the fourth historical attention of the fourth historical multimedia resource without the first feature label is 50, then the ratio of the third historical attention to the fourth historical attention is 0.8. If the above-mentioned second ratio threshold is 0.95, the feature weight corresponding to the first feature label can be reduced at this time.
[0112] In this way, by periodically updating the feature weight corresponding to the first feature tag, the accuracy of obtaining the target attention of the multimedia resource can be improved.
[0113] Furthermore, in order to avoid the feature weight from increasing or decreasing without limit, the feature weight range of each first feature tag can be set, that is, the upper and lower limits of the feature weight. If the feature authority reaches the upper limit, the feature weight will no longer be increased; conversely, if the feature authority reaches the lower limit, the feature weight will no longer be reduced. The feature weight ranges of different first feature tags can be different, and can be set by users (such as experienced advertising designers or advertising optimizers) based on historical experience.
[0114] In this way, the feature weight range can be pre-set to avoid adjusting the feature weight too large or too small according to historical data, thereby further improving the accuracy of obtaining the target attention of multimedia resources.
[0115] In another embodiment of the present disclosure, the above step 104, obtaining the target attention of the target multimedia resource according to the second feature tag and the feature weight, may include the following steps:
[0116] First, the feature weights corresponding to the plurality of second feature labels are added together to obtain a target weight;
[0117] Secondly, the target attention degree of the target multimedia resource is calculated according to the target weight and the reference weight of the target type.
[0118] In this way, a more accurate target attention can be calculated.
[0119] In another embodiment of the present disclosure, the above step 104, obtaining the target attention of the target multimedia resource according to the second feature tag and the feature weight, may also include the following steps:
[0120] First, it is determined whether each second characteristic tag is a preset blacklist tag.
[0121] The preset blacklist tag is a feature tag whose influence weight on the historical attention is less than or equal to a preset weight threshold;
[0122] Secondly, the second feature tag that is not a preset blacklist tag is used as the third feature tag;
[0123] Finally, the target attention degree of the target multimedia resource is obtained according to the third feature tag and the feature weight.
[0124] For example, both the presence of a LOGO (trademark or logo) and the absence of a LOGO can be set as preset blacklist tags to indicate that the presence or absence of a LOGO has little impact on the attention of the multimedia resource. In this way, even if the second feature tag of the target multimedia resource includes a feature tag with a LOGO, it will not affect the target attention of the target multimedia resource.
[0125] In this way, by manually setting a preset blacklist tag and screening the second feature tag through the preset blacklist tag, a more accurate target attention degree can be obtained.
[0126] Furthermore, in order to more clearly display the specific evaluation information of the target multimedia resource to the user, the method may further include:
[0127] First, according to the feature weight corresponding to the second feature label, the second feature label is classified into a positive label, a neutral label or a negative label.
[0128] Among them, positive labels are used to represent feature labels that can enhance the target attention of target multimedia resources, negative labels are used to represent feature labels that can reduce the target attention of target multimedia resources, and neutral labels are used to represent feature labels that have no effect on the target attention of target multimedia resources.
[0129] For example, the second feature label with a feature weight greater than 0 can be used as a positive label, the second feature label with a feature weight less than 0 can be used as a negative label, and the second feature label with a feature weight equal to 0 can be used as a neutral label.
[0130] Furthermore, the neutral label may also be customized by the user. For example, a preset blacklist label customized by the user may be used as the neutral label.
[0131] Then, according to the classification result, the second feature label is displayed.
[0132] For example, Figure 2 is a schematic diagram showing a target attention level and feature labels of a target multimedia resource according to an exemplary embodiment. Figure 2 As shown, in the display interface, the target attention of the target multimedia resource can be displayed, and the above-mentioned second feature label can be displayed according to the classification result of the second feature label, wherein the neutral labels include "picture and text display-picture and text flash", "no logo", "no border", "no character sound", "theme-disco" and "theme-DJ"; the positive labels include "vertical screen", "no stickers", "vertical version" and "clear picture"; the negative labels include "no subtitles" and "singing".
[0133] In summary, by obtaining the target type of the target multimedia resource; determining multiple second feature tags corresponding to the target multimedia resource from multiple first feature tags corresponding to the target type; obtaining the feature weight corresponding to each second feature tag, wherein the feature weight is used to characterize the degree of influence of the second feature tag on the target attention of the target multimedia resource; and obtaining the target attention of the target multimedia resource according to the second feature tag and the feature weight. Since the above feature weights are obtained based on historical data or historical experience, it is possible to predict the target attention of multimedia resources more accurately and reliably based on the above feature tags and feature weights, so that the multimedia resources of the advertisement can be evaluated before the advertisement is released, thereby reducing the manpower and material costs of the advertisement and improving the efficiency of the advertisement.
[0134] Figure 3 FIG. 1 is a block diagram of a device for obtaining multimedia resource attention according to an exemplary embodiment. Figure 3 As shown, the device for obtaining multimedia resource attention includes:
[0135] The target type acquisition module 301 is used to acquire the target type of the target multimedia resource;
[0136] A feature tag determination module 302, configured to determine a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type;
[0137] A feature weight acquisition module 303 is used to acquire a feature weight corresponding to each second feature tag, wherein the feature weight is used to represent the influence of the second feature tag on the target attention of the target multimedia resource;
[0138] The target attention acquisition module 304 is used to acquire the target attention of the target multimedia resource according to the second feature tag and the feature weight.
[0139] Figure 4 FIG. 1 is a block diagram of a second device for obtaining multimedia resource attention according to an exemplary embodiment. Figure 4 As shown, the device also includes:
[0140] A historical feature label and weight acquisition module 401 is used to acquire, according to a first historical attention level of a first historical multimedia resource, a first feature label corresponding to the target type and a feature weight corresponding to each first feature label, wherein the target type of the first historical multimedia resource is the same as the target type of the target multimedia resource;
[0141] The feature weight acquisition module 303 is used to use, for each second feature tag, the feature weight of the first feature tag corresponding to the second feature tag as the feature weight corresponding to the second feature tag.
[0142] Figure 5 FIG. 1 is a block diagram of a third device for obtaining multimedia resource attention according to an exemplary embodiment. Figure 5 As shown, the device also includes:
[0143] The historical weight updating module 501 is used to periodically obtain the second historical attention of the second historical multimedia resource within a preset time period, and update the feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource.
[0144] Optionally, the historical weight updating module 501 is used to perform feature extraction on the second historical multimedia resource according to the target type to obtain multiple first feature tags corresponding to the second historical multimedia resource; for each first feature tag, obtain the third historical attention of the third historical multimedia resource with the first feature tag, and the fourth historical attention of the fourth historical multimedia resource without the first feature tag; and update the feature weight corresponding to the first feature tag according to the third historical attention and the fourth historical attention.
[0145] Optionally, the historical weight update module 501 is used to obtain the ratio of the third historical attention to the fourth historical attention; when the ratio is greater than or equal to a preset first ratio threshold, increase the feature weight corresponding to the first feature label; or, when the ratio is less than or equal to a preset second ratio threshold, reduce the feature weight corresponding to the first feature label.
[0146] Optionally, the target attention acquisition module 304 is used to add the feature weights corresponding to the multiple second feature tags to obtain a target weight; and calculate the target attention of the target multimedia resource based on the target weight and a reference weight of the target type.
[0147] Optionally, the target attention acquisition module 304 is used to determine whether each second feature tag is a preset blacklist tag, wherein the preset blacklist tag is a feature tag whose impact weight on historical attention is preset and is less than or equal to a preset weight threshold; the second feature tag that is not a preset blacklist tag is used as a third feature tag; and based on the third feature tag and the feature weight, the target attention of the target multimedia resource is acquired.
[0148] Figure 6 FIG. 4 is a block diagram of a fourth apparatus for obtaining multimedia resource attention according to an exemplary embodiment. Figure 6 As shown, the device also includes:
[0149] A label classification module 601 is used to classify the second feature label according to the feature weight corresponding to the second feature label, and classify the second feature label into a positive label, a neutral label or a negative label;
[0150] The label display module 602 is used to display the second feature label according to the classification result.
[0151] By using the above device, it is possible to predict the target attention of multimedia resources more accurately and reliably based on the above feature labels and feature weights, so that the multimedia resources of the advertisement can be evaluated before the advertisement is released, thereby reducing the human and material costs of advertising and improving the efficiency of advertising.
[0152] Reference below Figure 7 , which shows a schematic diagram of the structure of an electronic device 700 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 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.
[0153] like Figure 7 As shown, the electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0154] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 700 is shown with various devices, 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.
[0155] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes 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 709, or installed from the storage device 708, or installed from the ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
[0156] It should be noted that the computer-readable medium disclosed above 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 the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In 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 an electromagnetic signal, an optical signal, 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.
[0157] 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.
[0158] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0159] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the target type of the target multimedia resource; determines multiple second feature tags corresponding to the target multimedia resource from multiple first feature tags corresponding to the target type; obtains the feature weight corresponding to each second feature tag, wherein the feature weight is used to characterize the influence of the second feature tag on the target attention of the target multimedia resource; and obtains the target attention of the target multimedia resource based on the second feature tag and the feature weight.
[0160] Computer program code for performing the operations 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 through 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).
[0161] 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.
[0162] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a target type acquisition module may also be described as a "module for acquiring the target type of a target multimedia resource".
[0163] 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.
[0164] 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.
[0165] According to one or more embodiments of the present disclosure, Example 1 provides a method for obtaining multimedia resource attention, the method comprising:
[0166] Get the target type of the target multimedia resource;
[0167] Determining a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type;
[0168] Obtaining a feature weight corresponding to each second feature tag, wherein the feature weight is used to represent the influence of the second feature tag on the target attention of the target multimedia resource;
[0169] According to the second feature tag and the feature weight, the target attention degree of the target multimedia resource is obtained.
[0170] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, and before obtaining the feature weight corresponding to each second feature label, the method further includes:
[0171] According to the first historical attention of the first historical multimedia resource, obtaining a first feature tag corresponding to the target type and a feature weight corresponding to each first feature tag, the target type of the first historical multimedia resource being the same as the target type of the target multimedia resource;
[0172] The step of obtaining the feature weight corresponding to each second feature label includes:
[0173] For each second feature tag, the feature weight of the first feature tag corresponding to the second feature tag is used as the feature weight corresponding to the second feature tag.
[0174] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, which further includes:
[0175] Periodically obtain a second historical attention of a second historical multimedia resource within a preset time period, and update a feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource.
[0176] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 3, wherein updating the feature weight corresponding to the first feature tag according to the second historical multimedia resource and the second historical attention includes:
[0177] Extracting features of the second historical multimedia resource according to the target type to obtain a plurality of first feature tags corresponding to the second historical multimedia resource;
[0178] For each first feature tag, obtain the third historical attention of the third historical multimedia resource with the first feature tag, and the fourth historical attention of the fourth historical multimedia resource without the first feature tag; and update the feature weight corresponding to the first feature tag based on the third historical attention and the fourth historical attention.
[0179] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 4, wherein updating the feature weight corresponding to the first feature tag according to the third historical attention and the fourth historical attention includes:
[0180] Obtaining a ratio of the third historical attention level to the fourth historical attention level;
[0181] When the ratio is greater than or equal to a preset first ratio threshold, the feature weight corresponding to the first feature label is increased; or,
[0182] When the ratio is less than or equal to a preset second ratio threshold, the feature weight corresponding to the first feature label is reduced.
[0183] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 1, wherein obtaining the target attention of the target multimedia resource according to the second feature tag and the feature weight includes:
[0184] Adding the feature weights corresponding to the plurality of second feature labels to obtain a target weight;
[0185] The target attention degree of the target multimedia resource is calculated according to the target weight and the reference weight of the target type.
[0186] According to one or more embodiments of the present disclosure, Example 7 provides the method of Example 1, wherein obtaining the target attention of the target multimedia resource according to the second feature tag and the feature weight includes:
[0187] Determine whether each second feature tag is a preset blacklist tag, wherein the preset blacklist tag is a feature tag whose influence weight on the historical attention is less than or equal to a preset weight threshold;
[0188] The second characteristic tag which is not a preset blacklist tag is used as the third characteristic tag;
[0189] According to the third feature tag and the feature weight, the target attention degree of the target multimedia resource is obtained.
[0190] According to one or more embodiments of the present disclosure, Example 8 provides the method of any one of Examples 1 to 7, the method further comprising:
[0191] Classifying the second feature label according to the feature weight corresponding to the second feature label, and classifying the second feature label into a positive label, a neutral label or a negative label;
[0192] According to the classification result, the second feature label is displayed.
[0193] According to one or more embodiments of the present disclosure, Example 9 provides a device for obtaining multimedia resource attention, the device comprising:
[0194] A target type acquisition module is used to acquire the target type of the target multimedia resource;
[0195] A feature tag determination module, used to determine a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type;
[0196] A feature weight acquisition module, used to acquire a feature weight corresponding to each second feature tag, wherein the feature weight is used to characterize the influence of the second feature tag on the target attention of the target multimedia resource;
[0197] The target attention acquisition module is used to acquire the target attention of the target multimedia resource according to the second feature tag and the feature weight.
[0198] According to one or more embodiments of the present disclosure, Example 10 provides a computer-readable medium having a computer program stored thereon, which implements the steps of the method described in any one of Examples 1 to 8 when executed by a processing device.
[0199] According to one or more embodiments of the present disclosure, Example 11 provides an electronic device, comprising: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device to implement the steps of the method described in any one of Examples 1 to 8.
[0200] The above description is only a preferred embodiment 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 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) by each other 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 method logic 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. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims
1. A method for obtaining multimedia resource attention, characterized in that: The method comprises: Get the target type of the target multimedia resource; Determining, from a plurality of first feature tags corresponding to the target type, a plurality of second feature tags corresponding to the target multimedia resource, wherein the plurality of second feature tags are a subset of the plurality of first feature tags; Obtaining a feature weight corresponding to each second feature tag, wherein the feature weight is used to represent the influence of the second feature tag on the target attention of the target multimedia resource; Acquire a target attention degree of the target multimedia resource according to the second feature tag and the feature weight; Before obtaining the feature weight corresponding to each second feature label, the method further includes: According to a first historical attention degree of a first historical multimedia resource, obtaining a first feature tag corresponding to the target type and a feature weight corresponding to each first feature tag, wherein the target type of the first historical multimedia resource is the same as the target type of the target multimedia resource; The obtaining of the feature weight corresponding to each second feature label comprises: For each second feature tag, taking the feature weight of the first feature tag corresponding to the second feature tag as the feature weight corresponding to the second feature tag; The feature weight of the first feature label is periodically updated in the following manner: Periodically acquiring a second historical attention degree of a second historical multimedia resource within a preset time period, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource; Extracting features from the second historical multimedia resource according to the target type to obtain a plurality of first feature tags corresponding to the second historical multimedia resource; For each first feature tag, obtain the third historical attention of the third historical multimedia resource with the first feature tag, and the fourth historical attention of the fourth historical multimedia resource without the first feature tag; and obtain the ratio of the third historical attention to the fourth historical attention; when the ratio is greater than or equal to a preset first ratio threshold, increase the feature weight corresponding to the first feature tag; or, when the ratio is less than or equal to a preset second ratio threshold, reduce the feature weight corresponding to the first feature tag, and the preset first ratio threshold is greater than the preset second ratio threshold.
2. The method according to claim 1, characterized in that The acquiring the target attention degree of the target multimedia resource according to the second feature tag and the feature weight comprises: Adding the feature weights corresponding to the plurality of second feature labels to obtain a target weight; The target attention degree of the target multimedia resource is calculated according to the target weight and the reference weight of the target type.
3. The method according to claim 1, characterized in that The acquiring the target attention degree of the target multimedia resource according to the second feature tag and the feature weight comprises: Determine whether each second feature tag is a preset blacklist tag, wherein the preset blacklist tag is a feature tag whose influence weight on the historical attention is less than or equal to a preset weight threshold; The second characteristic tag which is not a preset blacklist tag is used as the third characteristic tag; According to the third feature tag and the feature weight, a target attention degree of the target multimedia resource is obtained.
4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Classifying the second feature label according to the feature weight corresponding to the second feature label, and classifying the second feature label into a positive label, a neutral label or a negative label; According to the classification result, the second feature label is displayed.
5. A device for obtaining multimedia resource attention, characterized in that: The device comprises: A target type acquisition module is used to acquire the target type of the target multimedia resource; A feature tag determination module, used to determine a plurality of second feature tags corresponding to the target multimedia resource from a plurality of first feature tags corresponding to the target type, wherein the plurality of second feature tags are a subset of the plurality of first feature tags; A feature weight acquisition module, used to acquire a feature weight corresponding to each second feature tag, wherein the feature weight is used to characterize the influence of the second feature tag on the target attention of the target multimedia resource; A target attention acquisition module, used for acquiring the target attention of the target multimedia resource according to the second feature tag and the feature weight; The device also includes: A historical feature tag and weight acquisition module, used to acquire, according to a first historical attention of a first historical multimedia resource, a first feature tag corresponding to the target type and a feature weight corresponding to each first feature tag, wherein the target type of the first historical multimedia resource is the same as the target type of the target multimedia resource; the feature weight acquisition module is used to use, for each second feature tag, the feature weight of the first feature tag corresponding to the second feature tag as the feature weight corresponding to the second feature tag; A historical weight updating module is used to periodically obtain a second historical attention of a second historical multimedia resource within a preset time period, wherein the target type of the second historical multimedia resource is the same as the target type of the target multimedia resource; perform feature extraction on the second historical multimedia resource according to the target type to obtain a plurality of first feature tags corresponding to the second historical multimedia resource; for each first feature tag, obtain a third historical attention of a third historical multimedia resource having the first feature tag, and a fourth historical attention of a fourth historical multimedia resource not having the first feature tag; and obtain a ratio of the third historical attention to the fourth historical attention; when the ratio is greater than or equal to a preset first ratio threshold, increase the feature weight corresponding to the first feature tag; or, when the ratio is less than or equal to a preset second ratio threshold, reduce the feature weight corresponding to the first feature tag, and the preset first ratio threshold is greater than the preset second ratio threshold.
6. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processing device, the steps of the method described in any one of claims 1 to 4 are implemented.
7. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 4.
