CN111381909B - Page display method and device, terminal equipment and storage medium - Google Patents
Page display method and device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN111381909B CN111381909B CN201811614139.XA CN201811614139A CN111381909B CN 111381909 B CN111381909 B CN 111381909B CN 201811614139 A CN201811614139 A CN 201811614139A CN 111381909 B CN111381909 B CN 111381909B
- Authority
- CN
- China
- Prior art keywords
- page
- displayed
- display
- evaluation
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The disclosure discloses a page display method, a page display device, terminal equipment and a storage medium. The method comprises the following steps: acquiring at least one page to be displayed; inputting each page to be displayed into a page evaluation model respectively to obtain a display prediction evaluation result corresponding to each page to be displayed respectively; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer; generating a set of pages to be displayed according to the at least one page to be displayed and a display prediction evaluation result corresponding to the at least one page to be displayed; and selecting a target page to be displayed from the page set to be displayed for displaying according to the display prediction evaluation result and a preset display strategy. The embodiment of the disclosure can improve the generation efficiency and quality of the page to be displayed and reduce the display cost.
Description
Technical Field
The present disclosure relates to data technologies, and in particular, to a page display method and apparatus, a terminal device, and a storage medium.
Background
With the development of communication technology and terminal devices, various terminal devices such as android phones, apple phones, tablet computers and the like have become an indispensable part of people's work and life. In order to meet the demand of people for obtaining information, a large number of pages are usually displayed on an application program developed for a terminal device.
Currently, in the existing page display method, online evaluation needs to be performed according to Identification (ID) features of a page creative and ID features of a user, and for any newly-created page to be displayed, a cold start process needs to be performed to obtain accurate ID features of the page. However, the cold-start device page needs to consume presentation opportunities, and if a large number of new pages to be presented with poor presentation effects exist, a large number of presentation opportunities and presentation time are wasted. At the same time, it also results in a reduced user experience.
Disclosure of Invention
The embodiment of the disclosure provides a page display method, a page display device, a terminal device and a storage medium, which can improve the generation efficiency and quality of a page to be displayed, reduce the display cost and improve the user experience.
In a first aspect, an embodiment of the present disclosure provides a page display method, where the method includes:
acquiring at least one page to be displayed;
inputting each page to be displayed into a page evaluation model respectively to obtain a display prediction evaluation result corresponding to each page to be displayed respectively; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer;
generating a set of pages to be displayed according to the at least one page to be displayed and a display prediction evaluation result corresponding to the at least one page to be displayed;
and selecting a target page to be displayed from the page set to be displayed for displaying according to the display prediction evaluation result and a preset display strategy.
Further, the respectively inputting the pages to be displayed into a page evaluation model to obtain a display prediction evaluation result corresponding to the pages to be displayed includes:
acquiring the image characteristics of the page to be displayed through an image embedding layer in the characteristic extraction layer;
acquiring character features of the page to be displayed through a character embedding layer in the feature extraction layer;
generating a feature vector of the page to be displayed according to the image feature and the character feature;
and obtaining a display prediction evaluation result of the page to be displayed through a full connection layer according to the feature vector.
Further, before obtaining at least one page to be displayed, the method further includes:
acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information;
and taking the historical display page of the additional evaluation data as a training sample to train the page evaluation model.
Further, the display effect data comprises click rate and/or conversion rate.
Further, the evaluation data further comprises at least one of:
the historical display page comprises position information, display time information, display weather information, user information, display context information of a display interface and an operating system of a client side for displaying the historical display page.
Further, the page to be displayed comprises at least one of the following items: title page, picture page, and video page.
Further, after selecting a target page to be displayed from the set of pages to be displayed for displaying, the method further includes:
obtaining evaluation data of the target page to be displayed;
and taking the target page to be displayed with the additional evaluation data as a training sample, and training the page evaluation model.
In a second aspect, an embodiment of the present disclosure further provides a page display apparatus, where the apparatus includes:
the to-be-displayed page acquisition module is used for acquiring at least one to-be-displayed page;
the display prediction evaluation result acquisition module is used for inputting the pages to be displayed into a page evaluation model aiming at each page to be displayed to obtain display prediction evaluation results of the pages to be displayed; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer;
the to-be-displayed page set generating module is used for generating a to-be-displayed page set according to the at least one to-be-displayed page and the display prediction evaluation result corresponding to the at least one to-be-displayed page;
and the to-be-displayed page display module is used for selecting a target to-be-displayed page from the to-be-displayed page set to display according to the display prediction evaluation result and a preset display strategy.
Further, the display prediction evaluation result obtaining module includes:
the image characteristic acquisition module is used for acquiring the image characteristics of the page to be displayed through an image embedding layer in the characteristic extraction layer;
the character characteristic acquisition module is used for acquiring character characteristics of the page to be displayed through a character embedding layer in the characteristic extraction layer;
the feature vector acquisition module is used for generating a feature vector of the page to be displayed according to the image feature and the character feature;
and the display prediction evaluation result determining module is used for acquiring the display prediction evaluation result of the page to be displayed through the full-connection layer according to the characteristic vector.
Further, the page display device further includes:
the historical display page acquisition module is used for acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information;
and the page evaluation model training module is used for taking the historical display page with the additional evaluation data as a training sample and training the page evaluation model.
Further, the display effect data comprises click rate and/or conversion rate.
Further, the evaluation data further comprises at least one of:
the historical display page comprises position information, display time information, display weather information, user information, display context information of a display interface and an operating system of a client side for displaying the historical display page.
Further, the page to be displayed comprises at least one of the following items: title page, picture page, and video page.
Further, the page display device further includes:
the evaluation data acquisition module is used for acquiring evaluation data of the target page to be displayed;
and the training sample acquisition module is used for taking the target page to be displayed with the additional evaluation data as a training sample and training the page evaluation model.
In a third aspect, an embodiment of the present disclosure further provides a terminal device, where the terminal device includes:
one or more processors;
a memory 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 page presentation method according to the embodiment of the disclosure.
In a fourth aspect, the disclosed embodiment also provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the page display method according to the disclosed embodiment.
According to the page evaluation method and device, the pages to be displayed are evaluated through the page evaluation model, the display prediction evaluation results corresponding to the pages to be displayed are obtained, the pages to be displayed are selected according to the preset display strategy to be displayed according to the display prediction evaluation results, the problem that in the prior art, the page evaluation efficiency is low due to the fact that the pages need to be manually evaluated on line is solved, the page evaluation is achieved through the page evaluation model, the subjectivity of the page evaluation can be avoided, meanwhile, the accuracy and the efficiency of the page evaluation are improved, the data do not need to be acquired on line in the evaluation, and the display opportunity and the display time can be saved.
Drawings
Fig. 1a is a flowchart of a page display method according to an embodiment of the disclosure;
FIG. 1b is a functional block diagram of a page evaluation model provided in an embodiment of the present disclosure;
fig. 1c is a schematic view of a page to be displayed according to a first embodiment of the disclosure;
FIG. 1d is a flowchart illustrating a training process of a page evaluation model according to an embodiment of the present disclosure;
fig. 2a is a flowchart of a page display method provided in the second embodiment of the present disclosure;
fig. 2b is a schematic diagram illustrating a result of a prediction evaluation according to a second embodiment of the disclosure;
FIG. 2c is another schematic diagram showing the result of the prediction evaluation according to the second embodiment of the disclosure;
fig. 2d is a schematic structural diagram of a to-be-displayed page evaluation system according to a second embodiment of the disclosure;
fig. 3 is a schematic structural diagram of a page displaying apparatus according to a third embodiment of the disclosure;
fig. 4 is a schematic structural diagram of a terminal device according to a fourth embodiment of the present disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the disclosure and are not limiting of the disclosure. It should be further noted that, for the convenience of description, only some of the structures relevant to the present disclosure are shown in the drawings, not all of them.
Example one
Fig. 1a is a flowchart of a page displaying method provided in an embodiment of the present disclosure, where the present embodiment is applicable to a case of displaying a page, the method may be executed by a page displaying apparatus, the apparatus may be implemented in a software and/or hardware manner, and the apparatus may be configured in a terminal device, for example, typically, a computer, and the like. As shown in fig. 1a, the method specifically includes the following steps:
s110, at least one page to be displayed is obtained.
Specifically, the page to be displayed may refer to a page used for displaying in a display interface of the terminal device, for example, a display interface of a browser in the terminal device, or a display interface of an application in the terminal device. The page to be displayed may specifically include at least one of the following: the system comprises a title page, a picture page and a video page, wherein the title page can be a page only containing text content; the picture page can be a static page containing text content and image content; a video page may refer to a dynamic page containing textual content, image content, and audio content.
In the embodiment of the present disclosure, the page to be displayed is a page that is not displayed, and also refers to a new page designed by a user.
It can be understood that the page to be displayed is not displayed on the network, so that all information of the page to be displayed is obtained offline, that is, the page to be displayed is evaluated according to the offline information. For example, because the page to be displayed is not displayed, the display object of the page to be displayed is actually unknown, that is, when the page to be displayed is evaluated, the user characteristics of the actual display object of the page to be displayed cannot be obtained, so that the page to be displayed cannot be effectively evaluated according to the online data (the user characteristics of the display object).
S120, inputting each page to be displayed into a page evaluation model respectively to obtain a display prediction evaluation result corresponding to each page to be displayed respectively; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer.
The page evaluation model is used for evaluating the page to be displayed, and specifically, the page to be displayed is received and a display prediction evaluation result corresponding to the page to be displayed is output. Specifically, the display prediction evaluation result is display effect data of the page to be displayed after display is predicted, wherein the display effect data can be feedback of the user, specifically click rate and/or conversion rate fed back by the terminal device used by the user.
The page evaluation model may adopt a neural network model, wherein the neural network model may include, but is not limited to, a word vector network (word2vec network), a convolutional neural network (convolutional neural network), a fully connected network (fully connected network), and the like. The specific network structure of the neural network model may include a feature extraction layer and a full connectivity layer. The feature extraction layer is used for extracting image features and character features of the page to be displayed. Each node in the full connection layer is connected with all nodes in the previous layer and is used for integrating the extracted characteristics. More specifically, the fully-connected layer is one layer after the feature extraction layer.
The subjectivity of manually evaluating the page can be avoided through the page evaluation model, the accuracy and efficiency of page evaluation can be improved, and the labor cost is reduced.
Optionally, the respectively inputting the pages to be displayed into a page evaluation model to obtain the display prediction evaluation result corresponding to the pages to be displayed may include: acquiring the image characteristics of the page to be displayed through an image embedding layer in the characteristic extraction layer; acquiring character features of the page to be displayed through a character embedding layer in the feature extraction layer; generating a feature vector of the page to be displayed according to the image feature and the character feature; and obtaining a display prediction evaluation result of the page to be displayed through a full connection layer according to the feature vector.
In one specific example, as shown in FIG. 1b, the page evaluation model 101 includes an image embedding layer 102, a word embedding layer 103, and a full connection layer 104, where the image embedding layer 102 and the word embedding layer 103 may be collectively referred to as a feature extraction layer. Generally, as shown in fig. 1c, the image page includes both text and image, and the text includes text and title in the image. Image features of images in the image page can be identified by the image embedding layer 102. Meanwhile, the characters in the image can be obtained through an optical character recognition (optical character recognition) technology, and the characters and the title characters in the image are input to the character embedding layer 103, so that the character features of the image page can be obtained. And splicing the image features and the character features in the image page to form a high-dimensional vector as the high-dimensional features of the image page. And according to the high-dimensional characteristics of the image page, obtaining a display prediction evaluation result through the full-connection layer 104, and outputting the display prediction evaluation result in a numerical value form.
The image embedding layer may use a mobile terminal network (MobileNet), and more specifically, represent the image feature corresponding to the image by a 1024-dimensional vector of a next to last layer of the image in MobileNet. The word embedding layer may employ the output of the multi-scale convolutional neural network as a word feature.
It should be noted that the presentation form of the image page may also be that the title is below the image, and in addition, the presentation form of the image page also has other forms, and therefore, the embodiment of the present disclosure is not particularly limited. Meanwhile, the method for recognizing characters in the image may be other methods, and both the image embedding layer and the character embedding layer may have other structures.
It is understood that the present embodiment is merely a specific example of providing a page evaluation model for evaluating an image page, and is not limited to the present example. For example, for a headline page, only text is included, so the feature extraction layer of the page evaluation model for evaluating the headline page may be a word embedding layer for extracting text features in the headline. For another example, for a video page, a video may be split into a series of image frames, and each image frame is input into the page evaluation model for evaluating the image page for evaluation, and finally, the sum of the presentation prediction evaluation results of each image frame is obtained and divided by time to obtain a result as the presentation prediction evaluation result of the video page. In addition, there are other network architectures to which the disclosed embodiments are not particularly limited.
Before using the page evaluation model, the page evaluation model needs to be trained in advance, and optionally before obtaining at least one page to be displayed, the method may further include: acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information; and taking the historical display page of the additional evaluation data as a training sample to train the page evaluation model.
The history presentation page may refer to a page already presented in the terminal device. The page information may include type information of the page (e.g., video page), attribute information of the page (e.g., page subject content), source information of the page (e.g., source address or client name), and the like, and different page evaluation models may be trained according to the page information. The display effect data may refer to behavior data of the user on the historical display page, and specifically may include click rate and/or conversion rate. Wherein, the click through rate may refer to the probability that the click through rate is the page clicked by the user group, and the user group may be a set range or a set type of user group (such as a white-collar girl group in 28-32 years); the conversion rate may refer to a ratio of the number of users who perform the set behavior operation after the user clicks the page to the number of all users who click the page.
Optionally, the evaluation data may further comprise at least one of: the method comprises the steps that position information, display time information, display weather information, user information, display context information of a history display page on a display interface and an operating system of a client side displaying the history display page.
The user information may refer to at least one of gender, age, preference information, and the like of a user performing a behavior operation on the history presentation page. The operating system of the client can be an IOS system, an Android system or a Windows system. The presentation context information may refer to at least one of information of a current language environment, a background, and a page content of the page. The presentation time information may be time information such as year, month, day, hour, minute, and second. The exhibition weather information may refer to at least one of temperature, humidity, solar terms, season, and the like. In addition, the assessment data may also include holiday information.
The historical display pages and the evaluation data matched with the historical display pages are collected to be used as training samples of the page evaluation model, and the representativeness of the training samples is increased, so that the accuracy of the evaluation result of the page evaluation model is improved.
In one specific example, the page evaluation model is trained by providing training samples in pairs, as shown in FIG. 1 d. And respectively inputting the first image page and the second image page into a page evaluation model for evaluation, and respectively and correspondingly obtaining a first display prediction evaluation result and a second display prediction evaluation result. Wherein the page evaluation model is weighted (shared weight) in evaluating the first image page and the second image page.
Obtaining a difference value between the first display prediction evaluation result and the second display prediction evaluation result, mapping the difference value into a range of [0,1] through a nonlinear function (such as a Sigmoid function), and using the difference value as a prediction difference value of the page evaluation model, wherein the prediction difference value can represent prediction good and bad results of the first image page and the second image page, for example, when the prediction difference value is greater than zero, the first image page is better than the second image page; when the prediction difference value is equal to zero, the quality degrees of the first image page and the second image page are the same; the first image page is inferior to the second image page when the prediction difference is less than zero.
And meanwhile, determining an actual difference value between the first image page and the second image page according to the actual conversion rate of the first image page and the actual conversion rate of the second image page, wherein the actual difference value is used for representing actual quality results of the first image page and the second image page. The cross entropy (cross entropy) between the predicted difference value and the actual difference value is used as a loss function (loss function), and a convex optimization (covex optimization) method is used for solving the minimum value of the loss function, so that the model can be trained.
It should be noted that the page to be displayed can be acquired online by setting up an evaluation service platform, the page to be displayed is evaluated by loading a pre-trained page evaluation model through the evaluation service platform, and a display prediction evaluation result of the page to be displayed is sent out through the evaluation service platform. The method may further include directly obtaining a matched page evaluation model as needed, and performing offline evaluation on the to-be-displayed page with a set requirement, for example, evaluating the to-be-displayed page with the position information and the display time information attached to the display interface to obtain the optimal display time of the to-be-displayed page and the optimal display position on the display interface.
S130, generating a set of pages to be displayed according to the at least one page to be displayed and the display prediction evaluation result corresponding to the at least one page to be displayed.
The page set to be displayed comprises pages to be displayed and display prediction evaluation results matched with the pages to be displayed, and the page set to be displayed also comprises evaluation data matched with the pages to be displayed.
The page set to be displayed can be generated according to all the pages to be displayed which are evaluated by the page evaluation model, or the page set to be displayed can be generated according to at least one page to be displayed of which the display prediction evaluation result exceeds a set threshold value.
And S140, selecting a target page to be displayed from the page set to be displayed for displaying according to the display prediction evaluation result and a preset display strategy.
The display strategy can refer to a display method or a display form of at least one to-be-displayed page, for example, displaying the to-be-displayed page with the top 10 in the prediction evaluation result, and circularly displaying online from high to low in the ranking order. Or, each page to be displayed may be displayed at a display position in the display interface that is matched with the page to be displayed, and the page to be displayed may be displayed within a display time period that is matched with the page to be displayed, specifically according to the evaluation data of at least one page to be displayed. The target to-be-presented page may refer to a to-be-presented page that is currently being presented.
According to the page evaluation method and device, the pages to be displayed are evaluated through the page evaluation model, the display prediction evaluation results corresponding to the pages to be displayed are obtained, the pages to be displayed are selected according to the preset display strategy to be displayed according to the display prediction evaluation results, the problem that in the prior art, the page evaluation efficiency is low due to the fact that the pages need to be manually evaluated on line is solved, the page evaluation is achieved through the page evaluation model, the subjectivity of the page evaluation can be avoided, meanwhile, the accuracy and the efficiency of the page evaluation are improved, the data do not need to be acquired on line in the evaluation, and the display opportunity and the display time can be saved.
On the basis of the foregoing embodiment, optionally, after selecting a target page to be displayed from the page set to be displayed for displaying, the method may further include: obtaining evaluation data of the target page to be displayed; and taking the target page to be displayed with the additional evaluation data as a training sample, and training the page evaluation model.
Specifically, after the target page to be displayed is displayed, the evaluation data of the target page to be displayed is collected, the target page to be displayed with the additional evaluation data is used as a new training sample, and the page evaluation model is trained, so that the training sample of the page evaluation model is updated in real time, the representativeness of the training sample is improved, the evaluation result of the page evaluation model is corrected, and the evaluation accuracy of the page evaluation model is improved.
Example two
Fig. 2a is a flowchart of a page display method according to a second embodiment of the disclosure. The present embodiment is optimized on the basis of the alternatives in the above-described embodiment. In this embodiment, before obtaining at least one page to be displayed, the method further includes: acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information; and taking the historical display page of the additional evaluation data as a training sample to train the page evaluation model. Meanwhile, after a target page to be displayed is selected from the page set to be displayed for displaying, the method further comprises the following steps: obtaining evaluation data of the target page to be displayed; and taking the target page to be displayed with the additional evaluation data as a training sample, and training the page evaluation model.
Correspondingly, the method of the embodiment may include:
s201, obtaining a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information.
S202, taking the history display page with the additional evaluation data as a training sample, and training a page evaluation model.
S203, at least one page to be displayed is obtained.
It should be noted that, the page to be displayed, the page evaluation model, the neural network model, the feature extraction layer, the full connection layer, the historical display page, the display effect data, the page information, the display prediction evaluation result, the page set to be displayed, and the display policy in this embodiment may all refer to the description of the above embodiment.
S204, inputting each page to be displayed into the page evaluation model respectively to obtain a display prediction evaluation result corresponding to each page to be displayed respectively; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer.
In a specific example, fig. 2b and fig. 2c respectively show two pages to be shown and corresponding predictive evaluation results of the display. The content shown in fig. 2b is obtained by a page evaluation model according to the image page shown in fig. 1 c. Meanwhile, as shown in fig. 2b and 2c, the two pages to be displayed are both image pages, and the image of the page to be displayed, the title of the page to be displayed, the optical character recognition result in the image of the title of the page to be displayed, and the score given by the page evaluation model (i.e., the display prediction evaluation result) are respectively from top to bottom. The image page shown in fig. 2b can be preferentially displayed according to the scoring results of the two image pages.
S205, generating a set of pages to be displayed according to the at least one page to be displayed and the display prediction evaluation result corresponding to the at least one page to be displayed.
And S206, selecting a target page to be displayed from the page set to be displayed for displaying according to the display prediction evaluation result and a preset display strategy.
And S207, obtaining the evaluation data of the target page to be displayed.
And S208, taking the target page to be displayed with the additional evaluation data as a training sample, and training the page evaluation model.
In a specific example, fig. 2d is a schematic structural diagram of a to-be-displayed page evaluation system according to a second embodiment of the disclosure, as shown in fig. 2d, the to-be-displayed page evaluation system includes an posterior data collection and storage module 201, a model training module 202, a to-be-displayed page effect prediction module 203, an online display module 204, and an online learning (online learning) module 205. The posterior data collecting and storing module 201 needs to collect all data required by the training of the page evaluation model, such as page information, user information, context information, behavior information of the user on the page, and the like of all pages displayed on the historical line, and store the data in a database in a ground manner; the model training module 202 needs to preprocess the stored data into an input format required by the page evaluation model, perform the page evaluation model training, perform offline evaluation, and select an optimal model according to the offline evaluation index; the to-be-displayed page effect prediction module 203 is used for online and offline evaluation of the to-be-displayed pages, scoring each to-be-displayed page and outputting a scoring result; the online display module 204 is used for displaying the pages to be displayed to the user according to the scoring condition of each page to be displayed by combining a specific strategy; and the online learning module 205 is configured to collect behavior data of a page to be displayed of a user on line in real time, and use the behavior data as an actual value of the displayed page, so that the page evaluation model performs online learning, thereby implementing correction on an evaluation result.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a page display apparatus according to an embodiment of the present disclosure, which is applicable to a case of generating a display page. The apparatus may be implemented in software and/or hardware, and may be configured in a terminal device. As shown in fig. 3, the apparatus may include: a to-be-displayed page obtaining module 310, a display prediction evaluation result obtaining module 320, a to-be-displayed page set generating module 330, and a to-be-displayed page displaying module 340.
A to-be-displayed page obtaining module 310, configured to obtain at least one to-be-displayed page;
the display prediction evaluation result obtaining module 320 is configured to, for each to-be-displayed page, input the to-be-displayed page into a page evaluation model to obtain a display prediction evaluation result of the to-be-displayed page; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer;
a to-be-displayed page set generating module 330, configured to generate a to-be-displayed page set according to the at least one to-be-displayed page and a display prediction evaluation result corresponding to the at least one to-be-displayed page;
and the to-be-displayed page display module 340 is configured to select a target to-be-displayed page from the to-be-displayed page set for display according to the display prediction evaluation result and a preset display policy.
According to the page evaluation method and device, the pages to be displayed are evaluated through the page evaluation model, the display prediction evaluation results corresponding to the pages to be displayed are obtained, the pages to be displayed are selected according to the preset display strategy to be displayed according to the display prediction evaluation results, the problem that in the prior art, the page evaluation efficiency is low due to the fact that the pages need to be manually evaluated on line is solved, the page evaluation is achieved through the page evaluation model, the subjectivity of the page evaluation can be avoided, meanwhile, the accuracy and the efficiency of the page evaluation are improved, the data do not need to be acquired on line in the evaluation, and the display opportunity and the display time can be saved.
Further, the display prediction evaluation result obtaining module 320 includes: the image characteristic acquisition module is used for acquiring the image characteristics of the page to be displayed through an image embedding layer in the characteristic extraction layer; the character characteristic acquisition module is used for acquiring character characteristics of the page to be displayed through a character embedding layer in the characteristic extraction layer; the feature vector acquisition module is used for generating a feature vector of the page to be displayed according to the image feature and the character feature; and the display prediction evaluation result determining module is used for acquiring the display prediction evaluation result of the page to be displayed through the full-connection layer according to the characteristic vector.
Further, the page display device further includes: the historical display page acquisition module is used for acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information; and the page evaluation model training module is used for taking the historical display page with the additional evaluation data as a training sample and training the page evaluation model.
Further, the display effect data comprises click rate and/or conversion rate.
Further, the evaluation data further comprises at least one of: the method comprises the steps that position information, display time information, display weather information, user information, display context information of a history display page on a display interface and an operating system of a client side displaying the history display page.
Further, the page to be displayed comprises at least one of the following items: title page, picture page, and video page.
Further, the page display device further includes: the evaluation data acquisition module is used for acquiring evaluation data of the target page to be displayed; and the training sample acquisition module is used for taking the target page to be displayed with the additional evaluation data as a training sample and training the page evaluation model.
The page display device provided by the embodiment of the disclosure and the page display method provided by the first embodiment belong to the same inventive concept, technical details which are not described in detail in the embodiment of the disclosure can be referred to in the first embodiment, and the first embodiment and the second embodiment of the disclosure have the same beneficial effects.
Example four
The disclosed embodiment provides a terminal device, and referring to fig. 4 below, a schematic structural diagram of a terminal device (e.g., a client or a server) 400 suitable for implementing the disclosed embodiment is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a Personal Digital Assistant (PDA), a tablet computer (PAD), a Portable Multimedia Player (PMP), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The terminal device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 4, the terminal device 400 may include a processing means (e.g., a central processing unit, a graphic processor, etc.) 401 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the terminal apparatus 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
Generally, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the terminal device 400 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 illustrates a terminal apparatus 400 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication device 409, or from the storage device 408, or from the ROM 402. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 401.
EXAMPLE five
Embodiments of the present disclosure also provide a computer readable storage medium, which may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, Radio Frequency (RF), etc., or any suitable combination of the foregoing.
The computer readable medium may be included in the terminal device; or may exist separately without being assembled into the terminal device.
The computer readable medium carries one or more programs which, when executed by the terminal device, cause the terminal device to: acquiring at least one page to be displayed; inputting each page to be displayed into a page evaluation model respectively to obtain a display prediction evaluation result corresponding to each page to be displayed respectively; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer; generating a set of pages to be displayed according to the at least one page to be displayed and a display prediction evaluation result corresponding to the at least one page to be displayed; and selecting a target page to be displayed from the page set to be displayed for displaying according to the display prediction evaluation result and a preset display strategy.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of 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 the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. The name of the module does not in some cases constitute a limitation on the module itself, for example, the to-be-presented page acquiring module may also be described as a "module acquiring at least one to-be-presented page".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (16)
1. A page display method is characterized by comprising the following steps:
acquiring at least one page to be displayed, wherein all information of the page to be displayed is acquired offline;
inputting each page to be displayed into a page evaluation model respectively to obtain a display prediction evaluation result corresponding to each page to be displayed respectively; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer; the display prediction evaluation result is display effect data of a page to be displayed after display is predicted, and the display effect data is feedback conditions of a user;
generating a set of pages to be displayed according to the at least one page to be displayed and a display prediction evaluation result corresponding to the at least one page to be displayed;
and selecting a target page to be displayed from the page set to be displayed for displaying according to the display prediction evaluation result and a preset display strategy.
2. The method according to claim 1, wherein the step of inputting the pages to be displayed into a page evaluation model respectively to obtain a display prediction evaluation result corresponding to the pages to be displayed comprises:
acquiring the image characteristics of the page to be displayed through an image embedding layer in the characteristic extraction layer;
acquiring character features of the page to be displayed through a character embedding layer in the feature extraction layer;
generating a feature vector of the page to be displayed according to the image feature and the character feature;
and obtaining a display prediction evaluation result of the page to be displayed through a full connection layer according to the feature vector.
3. The method according to claim 2, before obtaining at least one page to be presented, further comprising:
acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information;
and taking the historical display page of the additional evaluation data as a training sample to train the page evaluation model.
4. The method of claim 3, wherein the presentation effect data comprises click through rate and/or conversion rate.
5. The method of claim 4, wherein the assessment data further comprises at least one of:
the historical display page comprises position information, display time information, display weather information, user information, display context information of a display interface and an operating system of a client side for displaying the historical display page.
6. The method according to any of claims 1-5, characterized in that the page to be presented comprises at least one of the following: title page, picture page, and video page.
7. The method according to claim 6, wherein after selecting a target page to be shown from the set of pages to be shown for showing, further comprising:
obtaining evaluation data of the target page to be displayed;
and taking the target page to be displayed with the additional evaluation data as a training sample, and training the page evaluation model.
8. A page display apparatus, comprising:
the system comprises a to-be-displayed page acquisition module, a to-be-displayed page acquisition module and a display module, wherein the to-be-displayed page acquisition module is used for acquiring at least one to-be-displayed page, and all information of the to-be-displayed page is acquired in an off-line manner;
the display prediction evaluation result acquisition module is used for respectively inputting each page to be displayed into a page evaluation model to obtain a display prediction evaluation result corresponding to each page to be displayed; the page evaluation model comprises a neural network model, and the neural network model comprises a feature extraction layer and a full connection layer; the display prediction evaluation result is display effect data of a page to be displayed after display is predicted, and the display effect data is feedback conditions of a user;
the to-be-displayed page set generating module is used for generating a to-be-displayed page set according to the at least one to-be-displayed page and the display prediction evaluation result corresponding to the at least one to-be-displayed page;
and the to-be-displayed page display module is used for selecting a target to-be-displayed page from the to-be-displayed page set to display according to the display prediction evaluation result and a preset display strategy.
9. The apparatus of claim 8, wherein the presentation prediction evaluation result obtaining module comprises:
the image characteristic acquisition module is used for acquiring the image characteristics of the page to be displayed through an image embedding layer in the characteristic extraction layer;
the character characteristic acquisition module is used for acquiring character characteristics of the page to be displayed through a character embedding layer in the characteristic extraction layer;
the feature vector acquisition module is used for generating a feature vector of the page to be displayed according to the image feature and the character feature;
and the display prediction evaluation result determining module is used for acquiring the display prediction evaluation result of the page to be displayed through the full-connection layer according to the characteristic vector.
10. The apparatus of claim 9, further comprising:
the historical display page acquisition module is used for acquiring a historical display page and evaluation data of the historical display page, wherein the evaluation data comprises display effect data and page information;
and the page evaluation model training module is used for taking the historical display page with the additional evaluation data as a training sample and training the page evaluation model.
11. The apparatus of claim 10, wherein the presentation data comprises click through rate and/or conversion rate.
12. The apparatus of claim 11, wherein the assessment data further comprises at least one of:
the historical display page comprises position information, display time information, display weather information, user information, display context information of a display interface and an operating system of a client side for displaying the historical display page.
13. The apparatus according to any of claims 8-12, wherein the page to be presented comprises at least one of: title page, picture page, and video page.
14. The apparatus of claim 13, further comprising:
the evaluation data acquisition module is used for acquiring evaluation data of the target page to be displayed;
and the training sample acquisition module is used for taking the target page to be displayed with the additional evaluation data as a training sample and training the page evaluation model.
15. A terminal device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the page presentation method of any one of claims 1-7.
16. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the page presentation method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811614139.XA CN111381909B (en) | 2018-12-27 | 2018-12-27 | Page display method and device, terminal equipment and storage medium |
| PCT/CN2019/115205 WO2020134571A1 (en) | 2018-12-27 | 2019-11-04 | Page display method and apparatus, terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811614139.XA CN111381909B (en) | 2018-12-27 | 2018-12-27 | Page display method and device, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111381909A CN111381909A (en) | 2020-07-07 |
| CN111381909B true CN111381909B (en) | 2022-03-04 |
Family
ID=71128406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811614139.XA Active CN111381909B (en) | 2018-12-27 | 2018-12-27 | Page display method and device, terminal equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111381909B (en) |
| WO (1) | WO2020134571A1 (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113760272A (en) * | 2020-08-24 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information display method, device, equipment and storage medium |
| CN112051953B (en) * | 2020-09-29 | 2021-09-14 | 中国银行股份有限公司 | Output control method and device for page column and electronic equipment |
| CN112307966B (en) * | 2020-10-30 | 2023-09-05 | 京东方科技集团股份有限公司 | Event display method and device, storage medium and electronic equipment |
| CN112256537B (en) * | 2020-11-12 | 2024-03-29 | 腾讯科技（深圳）有限公司 | Model running state display method and device, computer equipment and storage medium |
| CN114690996A (en) * | 2020-12-31 | 2022-07-01 | Oppo广东移动通信有限公司 | Content display method and device and electronic equipment |
| CN112734523A (en) * | 2021-01-11 | 2021-04-30 | 北京城市网邻信息技术有限公司 | Information display method and device, electronic equipment and computer readable medium |
| CN113158102A (en) * | 2021-02-23 | 2021-07-23 | 北京三快在线科技有限公司 | Page configuration method and device, electronic equipment and computer readable medium |
| CN113077305B (en) * | 2021-03-23 | 2024-03-29 | 上海尊溢商务信息咨询有限公司 | Page processing method, system, electronic device and storage medium |
| CN113378097B (en) * | 2021-07-08 | 2024-05-24 | 北京安天网络安全技术有限公司 | WEB page display method and device, electronic equipment and storage medium |
| CN113713378A (en) * | 2021-09-02 | 2021-11-30 | 北京百度网讯科技有限公司 | Content generation method and device |
| CN113794604A (en) * | 2021-09-09 | 2021-12-14 | 北京恒安嘉新安全技术有限公司 | Network security situation display method, device, equipment and storage medium |
| CN113835582B (en) * | 2021-09-27 | 2024-03-15 | 青岛海信移动通信技术有限公司 | Terminal equipment, information display method and storage medium |
| CN115035192B (en) * | 2022-06-21 | 2023-04-14 | 北京远舢智能科技有限公司 | Method and device for determining positions of tobacco leaf distributing vehicle and conveying belt |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897892A (en) * | 2015-12-18 | 2017-06-27 | 北京奇虎科技有限公司 | Advertisement placement method and device |
| CN107545301A (en) * | 2016-06-23 | 2018-01-05 | 阿里巴巴集团控股有限公司 | Page display method and device |
| CN108416625A (en) * | 2018-02-28 | 2018-08-17 | 阿里巴巴集团控股有限公司 | The recommendation method and apparatus of marketing product |
| CN109086439A (en) * | 2018-08-15 | 2018-12-25 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7822636B1 (en) * | 1999-11-08 | 2010-10-26 | Aol Advertising, Inc. | Optimal internet ad placement |
| US8533043B2 (en) * | 2010-03-31 | 2013-09-10 | Yahoo! Inc. | Clickable terms for contextual advertising |
| WO2012075600A1 (en) * | 2010-12-06 | 2012-06-14 | Yahoo! Inc. | System and method for list ranking and ads placement using interaction features |
| US9298763B1 (en) * | 2013-03-06 | 2016-03-29 | Google Inc. | Methods for providing a profile completion recommendation module |
| CN104992348B (en) * | 2015-06-24 | 2018-07-10 | 深圳市腾讯计算机***有限公司 | A kind of method and apparatus of information displaying |
| CN105208113A (en) * | 2015-08-31 | 2015-12-30 | 北京百度网讯科技有限公司 | Information pushing method and device |
| CN105678335B (en) * | 2016-01-08 | 2019-07-02 | 车智互联（北京）科技有限公司 | It estimates the method, apparatus of clicking rate and calculates equipment |
| CN106484913B (en) * | 2016-10-26 | 2021-09-07 | 腾讯科技（深圳）有限公司 | Target picture determining method and server |
| CN106557556A (en) * | 2016-11-08 | 2017-04-05 | 北京奇虎科技有限公司 | A kind of methods of exhibiting of Webpage, device, server and system |
| CN106682144B (en) * | 2016-12-20 | 2018-07-13 | 深圳壹账通智能科技有限公司 | page display method and device |
| CN107391538B (en) * | 2017-04-26 | 2020-08-14 | 阿里巴巴集团控股有限公司 | Click data acquisition, processing and display method, device, equipment and storage medium |
| CN108804469B (en) * | 2017-05-04 | 2021-10-29 | 腾讯科技（深圳）有限公司 | Webpage identification method and electronic equipment |
| CN108021626B (en) * | 2017-11-22 | 2020-06-09 | 阿里巴巴集团控股有限公司 | Page layout method, device and equipment |
| CN108182472A (en) * | 2018-01-30 | 2018-06-19 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN108959619A (en) * | 2018-07-17 | 2018-12-07 | 武汉市冰盒网络科技有限公司 | Content screen method, user equipment, storage medium and device |
-
2018
- 2018-12-27 CN CN201811614139.XA patent/CN111381909B/en active Active
-
2019
- 2019-11-04 WO PCT/CN2019/115205 patent/WO2020134571A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897892A (en) * | 2015-12-18 | 2017-06-27 | 北京奇虎科技有限公司 | Advertisement placement method and device |
| CN107545301A (en) * | 2016-06-23 | 2018-01-05 | 阿里巴巴集团控股有限公司 | Page display method and device |
| CN108416625A (en) * | 2018-02-28 | 2018-08-17 | 阿里巴巴集团控股有限公司 | The recommendation method and apparatus of marketing product |
| CN109086439A (en) * | 2018-08-15 | 2018-12-25 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111381909A (en) | 2020-07-07 |
| WO2020134571A1 (en) | 2020-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111381909B (en) | Page display method and device, terminal equipment and storage medium | |
| CN110458107B (en) | Method and device for image recognition | |
| WO2022022152A1 (en) | Video clip positioning method and apparatus, and computer device and storage medium | |
| CN109919244B (en) | Method and apparatus for generating a scene recognition model | |
| CN110633423B (en) | Target account identification method, device, equipment and storage medium | |
| US11182447B2 (en) | Customized display of emotionally filtered social media content | |
| CN110598157A (en) | Target information identification method, device, equipment and storage medium | |
| CN113723087B (en) | Information processing method, device, equipment, readable storage medium and product | |
| WO2021135319A1 (en) | Deep learning based text generation method and apparatus and electronic device | |
| CN110278447B (en) | Video pushing method and device based on continuous features and electronic equipment | |
| CN110674349B (en) | Video POI (Point of interest) identification method and device and electronic equipment | |
| CN110880324A (en) | Voice data processing method and device, storage medium and electronic equipment | |
| EP4113376A1 (en) | Image classification model training method and apparatus, computer device, and storage medium | |
| CN111897950A (en) | Method and apparatus for generating information | |
| CN110379406B (en) | Voice comment conversion method, system, medium and electronic device | |
| CN111738316A (en) | Image classification method and device for zero sample learning and electronic equipment | |
| CN109816023B (en) | Method and device for generating picture label model | |
| US20240079002A1 (en) | Minutes of meeting processing method and apparatus, device, and medium | |
| CN113868538B (en) | Information processing method, device, equipment and medium | |
| CN112182255A (en) | Method and apparatus for storing media files and for retrieving media files | |
| CN112069786A (en) | Text information processing method and device, electronic equipment and medium | |
| CN113706663B (en) | Image generation method, device, equipment and storage medium | |
| CN116958852A (en) | Video and text matching method and device, electronic equipment and storage medium | |
| CN113033552B (en) | Text recognition method and device and electronic equipment | |
| CN115292487A (en) | Text classification method, device, equipment and medium based on naive Bayes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |