CN114003806A - Content display method and device, electronic equipment and readable medium - Google Patents
Content display method and device, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN114003806A CN114003806A CN202111138880.5A CN202111138880A CN114003806A CN 114003806 A CN114003806 A CN 114003806A CN 202111138880 A CN202111138880 A CN 202111138880A CN 114003806 A CN114003806 A CN 114003806A
- Authority
- CN
- China
- Prior art keywords
- target
- content
- initial
- target object
- display processing
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 118
- 238000012549 training Methods 0.000 claims description 82
- 238000004891 communication Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 27
- 230000003313 weakening effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 208000001613 Gambling Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000002574 poison Substances 0.000 description 2
- 231100000614 poison Toxicity 0.000 description 2
- 206010063659 Aversion Diseases 0.000 description 1
- 206010028813 Nausea Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008693 nausea Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a content display method, a content display device, electronic equipment and a readable medium, wherein the method comprises the following steps: in the process of browsing a page by a user, the initial content to be displayed on a target page and the target user portrait of the user are obtained, then a target object contained in the initial content is identified, the target object is displayed according to the target user portrait, target content corresponding to the initial content is generated, and then the target content is displayed on the target page, so that in the process of displaying the page, aiming at the same content, after the contained target object is identified, the target object is subjected to personalized display processing based on the user portrait, and then the target content is displayed, so that different display styles can be displayed when different users browse the same content, further personalized display can be realized aiming at the same content, the matching between the displayed content and the user is ensured, and the browsing experience of the user is improved.
Description
Technical Field
The present invention relates to the field of data technologies, and in particular, to a content display method, a content display apparatus, an electronic device, and a computer-readable medium.
Background
With the rapid development of the internet field, the information which is explosively increased causes that users want to acquire interesting effective contents more and more difficult, and the personalized recommendation system obviously becomes an indispensable basic technology in the internet field, and plays an increasingly important role in content recommendation of news, short videos, music, live broadcasts, online shopping, pictures and the like. In the related art, personalized recommendation is often performed for users, the content recommended to each user is personalized and customized content, and the process is mainly based on the fact that different content is recommended for different users. In some scenarios, for example, under the condition that different users browse the same content, the problem that the content cannot be displayed in a personalized manner exists, which results in mismatching between the displayed content and the actually browsed user, and brings a poor browsing experience to the user.
Disclosure of Invention
The embodiment of the invention provides a content display method, a content display device, electronic equipment and a computer readable medium, which are used for solving or partially solving the problem that content cannot be displayed in a personalized manner in the content display process in the related art.
The embodiment of the invention discloses a content display method, which comprises the following steps:
acquiring initial content to be displayed on a target page;
acquiring a target user portrait;
identifying a target object contained in the initial content;
displaying the target object according to the target user image to generate target content corresponding to the initial content;
and displaying the target content in the target page.
Optionally, the identifying a target object included in the initial content includes:
and inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
Optionally, the identifying a target object included in the initial content includes:
and if the target user portrait contains a target favorite label, inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
Optionally, the parameter information includes object information of the target object, and the displaying the target object according to the target user image to generate target content corresponding to the initial content includes:
performing content matching on the object information by adopting the target user portrait to obtain display processing information aiming at the target object;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
Optionally, the target user representation at least includes a target favorite tag, and the content matching of the object information with the target user representation to obtain display processing information for the target object includes:
matching the target preference label with the object information to obtain a matching result aiming at the target object, wherein the matching result comprises a positive preference result and a negative preference result;
determining forward display processing information corresponding to the positive preference result;
or determining negative display processing information corresponding to the negative preference result.
Optionally, the displaying the processing information includes positive displaying the processing information and negative displaying the processing information, and the displaying the target object with the displaying the processing information to generate the target content corresponding to the initial content includes:
performing first display processing on the target object by adopting the forward display processing information to obtain target content corresponding to the initial content;
or, performing second display processing on the target object by using the negative display processing information to obtain target content corresponding to the initial content.
Optionally, the parameter information further includes position information of the target object in the initial content, and the performing display processing on the target object by using the display processing information to generate target content corresponding to the initial content includes:
identifying a target object corresponding to the position information in the initial content;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
Optionally, the recognition model is generated by:
obtaining user portraits of at least different users, the user portraits including at least a first favorite label;
acquiring initial training data matched with the first favorite label;
and training to obtain the recognition model according to the initial training data.
Optionally, the training to obtain the recognition model according to the initial training data includes:
determining a preset object matched with the first favorite label in the initial training data, marking the preset object, and generating target training data corresponding to the initial training data;
and training to obtain the recognition model by adopting the target training data.
Optionally, the obtaining initial training data matched with the first preference label includes:
counting the number of the first favorite labels;
extracting the first favorite labels with the quantity being TopN as second favorite labels;
and acquiring initial training data matched with the second favorite label.
Optionally, the initial training data includes at least one of picture data, video data, and text data.
Optionally, the initial content includes an initial picture, and the acquiring of the initial content to be displayed on the target page includes:
responding to an access request of a user, and acquiring page data corresponding to the access request;
displaying a target page corresponding to the page data, and determining a target position of a picture to be displayed in the target page;
and displaying a default preview image at the target position, and acquiring an initial image corresponding to the target position.
The embodiment of the invention also discloses a content display device, which comprises:
the initial content acquisition module is used for acquiring initial content to be displayed on a target page;
the user portrait acquisition module is used for acquiring a target user portrait;
a target object identification module for identifying a target object contained in the initial content;
the target content generation module is used for displaying the target object according to the target user image and generating target content corresponding to the initial content;
and the target content display module is used for displaying the target content in the target page.
Optionally, the target object identification module is specifically configured to:
and inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
Optionally, the target object identification module is specifically configured to:
and if the target user portrait contains a target favorite label, inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
Optionally, the parameter information includes object information of the target object, and the target content generating module includes:
the processing information determining submodule is used for carrying out content matching on the object information by adopting the target user portrait to obtain display processing information aiming at the target object;
and the target content generation submodule is used for displaying the target object by adopting the display processing information and generating target content corresponding to the initial content.
Optionally, the target user representation at least includes a target favorite tag, and the processing information determination sub-module is specifically configured to:
matching the target preference label with the object information to obtain a matching result aiming at the target object, wherein the matching result comprises a positive preference result and a negative preference result;
determining forward display processing information corresponding to the positive preference result;
or determining negative display processing information corresponding to the negative preference result.
Optionally, the display processing information includes positive display processing information and negative display processing information, and the target content generation sub-module is specifically configured to:
performing first display processing on the target object by adopting the forward display processing information to obtain target content corresponding to the initial content;
or, performing second display processing on the target object by using the negative display processing information to obtain target content corresponding to the initial content.
Optionally, the parameter information further includes location information of the target object in the initial content, and the target content generation sub-module is specifically configured to:
identifying a target object corresponding to the position information in the initial content;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
Optionally, the recognition model is generated by:
a data acquisition module for acquiring a user representation of at least different users, the user representation including at least a first favorite label;
the training data acquisition module is used for acquiring initial training data matched with the first favorite label;
and the model training module is used for training to obtain the recognition model according to the initial training data.
Optionally, the model training module is specifically configured to:
determining a preset object matched with the first favorite label in the initial training data, marking the preset object, and generating target training data corresponding to the initial training data;
and training to obtain the recognition model by adopting the target training data.
Optionally, the training data obtaining module includes:
the tag quantity counting submodule is used for counting the quantity of the first favorite tags;
the label extraction submodule is used for extracting the first favorite labels with the quantity being TopN as second favorite labels;
and the training data determining submodule is used for acquiring initial training data matched with the second preference label.
Optionally, the initial training data includes at least one of picture data, video data, and text data.
Optionally, the initial content obtaining module includes:
the page data acquisition sub-module is used for responding to an access request of a user and acquiring page data corresponding to the access request;
the target position determining submodule is used for displaying a target page corresponding to the page data and determining a target position of a picture to be displayed in the target page;
and the initial picture acquisition sub-module is used for displaying a default preview picture at the target position and acquiring an initial picture corresponding to the target position.
The embodiment of the invention also discloses electronic equipment which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory finish mutual communication through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement the method according to the embodiment of the present invention when executing the program stored in the memory.
Also disclosed are one or more computer-readable media having instructions stored thereon, which when executed by one or more processors, cause the processors to perform a method as described in embodiments of the invention.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, in the process of browsing a page by a user, the initial content to be displayed on a target page and the target user portrait of the user are obtained, then a target object contained in the initial content is identified, the target object is displayed according to the target user portrait to generate target content corresponding to the initial content, and then the target content is displayed in the target page, so that in the process of displaying the page, aiming at the same content, after the contained target object is identified, the target object is subjected to personalized display processing based on the user portrait, and then the target object is displayed after the processing is completed, different display styles can be displayed when different users browse the same content, further the personalized display can be realized aiming at the same content, and the matching between the display content and the user is ensured, the browsing experience of the user is improved.
Drawings
Fig. 1 is a flowchart illustrating steps of a method for displaying content according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating the steps of a method for displaying content according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating the steps of a method for displaying content according to an embodiment of the present invention;
fig. 4 is a block diagram of a display device of a content provided in an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device provided in an embodiment of the invention;
fig. 6 is a schematic diagram of a computer-readable medium provided in an embodiment of the invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As an example, when a user browses information through a terminal, the terminal may recommend content that the user may like to the user, for example, when the user browses goods through a shopping application, the user may recommend goods of interest to the user, and the recommendation process may be that the user browses goods or related types of goods once, that is, the terminal may perform personalized recommendation according to the operation behavior of the user. However, in the recommendation process, different contents are often recommended for different users, and when the same contents are recommended, personalized recommendation cannot be implemented, and the same contents can only be uniformly displayed for different users, so that there is a problem that personalized display cannot be performed on the contents, which causes mismatch between the displayed contents and actually browsed users, for example, mismatch between the displayed contents and ages, genders, regions, cities, preferences and the like of the actually browsed users, and brings poor browsing experience to the users.
In view of the above, one of the core invention points of the embodiments of the present invention is that, in the process of browsing a page by a user, by obtaining an initial content to be displayed on a target page and a target user portrait of the user, then identifying a target object included in the initial content, performing display processing on the target object according to the target user portrait to generate a target content corresponding to the initial content, and then displaying the target content on the target page, so that, in the process of displaying the page, for the same content, after identifying the included target object, the target object is subjected to personalized display processing based on the user portrait, and then is displayed after the processing is completed, so that different display styles can be displayed when different users browse the same content, and further personalized display can be realized for the same content, thereby ensuring matching between the display content and the user, the browsing experience of the user is improved.
Specifically, referring to fig. 1, a flowchart illustrating steps of a content display method provided in an embodiment of the present invention is shown, which may specifically include the following steps:
the initial content can be in the form of text, picture, video and the like, and in the process that the user browses the target page, the initial content is the content which needs to be displayed, and the same content can be displayed according to different users by performing personalized processing on the initial content.
In a specific implementation, the terminal may run a corresponding application, and the user may browse corresponding content through the application, such as browsing a website page, news, short video, house source posts, car source posts, and the like, where the content may be displayed in a page form. The page can include different forms of page contents, such as texts, pictures, videos and the like, and the page contents needing personalized processing can be determined first, personalized processing is performed based on the technical scheme of the embodiment of the invention, and then display is performed, so that the same content can be displayed according to different users.
In one example, the terminal may, in response to detecting an access request of a user, acquire page data corresponding to the access request, then display a target page corresponding to the page data, determine a target position of a picture to be displayed in the target page, then display a default preview at the target position, and acquire an initial picture corresponding to the target position. For example, when a user browses a post carrying a picture in an application program, the terminal may display a relevant text content first when displaying a page corresponding to the post, determine a position of the picture to be displayed, and obtain an initial picture corresponding to the target position while displaying a default preview image at the position, so as to perform personalization processing on the initial picture and then display the initial picture at the corresponding position.
It should be noted that, in the embodiment of the present invention, the initial content that needs to be personalized is taken as a picture for exemplary illustration, it can be understood that the initial content may also be a text, a video, and the like, which is not limited in this respect.
102, acquiring a target user portrait;
the target user profile may include attribute tags of the target user, and may be used to represent characteristics of a certain user, for example, the user profile may include an age tag, a gender tag, a region tag, a city tag, a preference tag, and the like, and the user profile may be used to analyze a matching degree, a preference, and the like of the user to the related content.
Optionally, the application program may obtain the user representation corresponding to the user account logged in the application program under the condition of obtaining the related authority, so as to provide personalized service for the user according to the user representation.
in the embodiment of the invention, after the initial content is obtained, the initial content can be input into the recognition model for content recognition, the target object contained in the initial content and the parameter information corresponding to the target object are obtained, and the matching degree of the target object and the user can be judged by recognizing the target object contained in the initial content and combining the user portrait, so that the target object can be displayed in a personalized manner according to the matching degree.
The identification model can be configured locally at the terminal or at the server, and when the identification model is configured locally at the terminal, the initial content can be vectorized after the initial content is obtained, and the identification model is input for content identification, so that a target object contained in the initial content and parameter information of the target object are obtained; when the terminal is configured at the server, the terminal can send the initial content to the server after acquiring the initial content, and the server executes the process of content identification of the initial content and returns the corresponding identification result, so that the system operation of the terminal is reduced and the performance overhead is reduced through data interaction with the server.
The target object may be an article, a person, a thing, a landscape, a character, etc. in the initial content, and the parameter information may include object information of the target object and position information of the target object in the initial content. For the object information, it may be information for describing the target object, for example, assuming that the initial picture is a picture including the sun, the recognition model may recognize the sun in the picture and determine that the object information is "sun"; if the image includes a vehicle, the recognition model may recognize the vehicle in the image and determine that the object information is "vehicle" or the like, and may also recognize an object such as a person or a character, and may recognize at least one target object included in the initial content and position information (or coordinates or the like) of the target object in the initial content.
In one case, for any user, the content of the initial content may be identified through the identification model, so as to perform personalized processing on the initial content; in another case, after the user portrait corresponding to the user is obtained for different users, it may be determined whether the user portrait includes a favorite tag, including a positive favorite and a negative favorite, if the favorite tag exists, the initial content may be personalized, otherwise, the initial content may be directly displayed without being personalized, so as to further improve the pertinence of the personalized processing and improve the matching degree between the content display and the user by determining whether the favorite tag exists.
In an alternative embodiment, the recognition model may be generated by: the method comprises the steps of firstly obtaining user portrayal of at least different users, wherein the user portrayal at least comprises a first favorite label, then obtaining initial training data matched with the first favorite label, and then training according to the initial training data to obtain a recognition model.
In specific implementation, for initial training data, a preset object matched with the first favorite label may be determined in the initial training data, the preset object is labeled to generate target training data corresponding to the initial training data, and then the target training data is input into the initial recognition model to be iterated until a loss function meets a preset condition, and the iteration is stopped to obtain a corresponding recognition model.
Alternatively, for the acquisition of the initial training data, the number of the first favorite labels may be counted, and then the first favorite labels with the number of TopN are extracted as the second favorite labels, and then the initial training data matched with the second favorite labels is acquired. The initial training data at least includes one of picture data, video data, and text data, and the TopN may be Top100, Top50, and the like, which is not limited in the present invention.
In one example, assuming that the initial training data is picture data, the server may collect user profiles of different users, extract favorite labels in the user profiles, summarize all positive favorite and negative favorite (aversion) data, sort according to a cumulative number, wherein the summarized data does not distinguish whether positive favorite or negative favorite, and only sum and accumulate. For example, 100 users prefer "sunset" and 50 users reject "sunset", then the total number of "sunset" labels is 150. The top ranked TopN tags may then be selected, through which process the tags (or items) that the recognition model is able to recognize may be selected. When the number of the selected labels is larger, the workload and the volume of the model are larger, and the obtained recognition model can recognize more and more accurate scenes.
After selecting the corresponding favorite labels, the picture containing the labels, such as a picture containing sunset, can be searched from the picture library according to the selected labels. And then, respectively placing the pictures with the same label in independent folders, marking corresponding objects in the pictures, and marking corresponding articles, people and the like by using a square frame to obtain corresponding target pictures.
One target object may include a plurality of target images, and model training is performed by using an initial image as an input of the recognition model and using the target image as an output of the model, so that the target object included in the image can be recognized, and the recognition model of the position information and the type of the target object in the image can be obtained.
It should be noted that, the embodiment of the present invention includes but is not limited to the above examples, and it is understood that, under the guidance of the idea of the embodiment, a person skilled in the art may also train the recognition model according to videos, texts, and the like, and the present invention is not limited thereto.
104, displaying the target object according to the target user image to generate target content corresponding to the initial content;
in the embodiment of the invention, after the target object contained in the initial content is identified, the target object can be subjected to personalized display processing according to the user image of the user, so that the target content corresponding to the initial content is generated, the personalized display of the same content is realized, the conversion from ' one thousand people to ' thousand patterns ' is realized, the matching between the displayed content and the user is ensured, and the browsing experience of the user is improved.
In a specific implementation, the parameter information may include object information of a target object, and the terminal may perform content matching on the object information using an image of a target user to obtain display processing information for the target object, and then perform display processing on the target object using the display processing information to generate target content corresponding to the initial content. The user portrait can be used for representing characteristics of a certain user, such as age characteristics, gender characteristics, region characteristics, favorite characteristics and the like, personalized display can be performed on the same content according to age, gender, region, favorite and the like, and specifically, when a child browses pictures through an application program, some exposed objects in the pictures can be processed to meet the age characteristics of the children; a person feels particularly dislike (negative preference) to some nausea things, when the picture is browsed, the picture can be fuzzified/weakened, so that personalized processing is carried out according to the portrait of the user in the content display process, the matching between the displayed content and the user is ensured, and the browsing experience of the user is improved.
In an example, taking personalized processing of the initial content by the favorite tag in the user portrait as an example, specifically, the terminal may match the target favorite tag with the object information to obtain a matching result for the target object, where the matching result includes a positive favorite result and a negative favorite result, and then determine positive display processing information corresponding to the positive favorite result, or determine negative display processing information corresponding to the negative favorite result. Then, the target object may be subjected to first display processing using the positive display processing information to obtain target content corresponding to the initial content, or subjected to second display processing using the negative display processing information to obtain target content corresponding to the initial content.
Optionally, the first display processing includes at least one of highlighting, pixel enhancement, brightness enhancement, contrast enhancement, and color enhancement; the second display processing includes at least one of mosaic processing, pixel weakening, brightness weakening, contrast weakening, and color weakening.
In a specific implementation, the favorite label of the user may include positive favorite of the user for some objects and negative favorite of some objects, the target object may be matched with the favorite label of the user, and whether the target object falls into the positive favorite or the negative favorite of the user is determined, if the target object is the positive favorite of the user, the target object may be subjected to display processing such as beautifying, filtering and the like to highlight the object; if the preference is negative, the weakening process such as mosaic or pixel reduction can be performed to avoid causing the user to feel the dislike.
In addition, if the target object does not belong to the positive preference or the negative preference of the user, the initial content can be directly displayed in the target page without performing display processing on the target object.
And 105, displaying the target content in the target page.
In the specific implementation, after the target object is subjected to personalized display processing based on the user portrait, corresponding target content can be displayed in a target page, different display styles can be displayed when different users browse the same content, further, personalized display can be realized for the same content, the matching between the displayed content and the users is ensured, and the browsing experience of the users is improved.
In the embodiment of the invention, in the process of browsing the page by the user, by acquiring the initial content to be displayed on the target page and the target user representation of the user, then, the target object included in the initial content is identified, and the target object is displayed according to the target user portrait to generate the target content corresponding to the initial content, the target content is then displayed in the target page such that, in displaying the page, for the same content, after identifying the target object contained, based on the user representation, the target object is subjected to personalized display processing and then displayed, so that different display styles can be displayed when different users browse the same content, and further, personalized display can be realized for the same content, the matching between the displayed content and the user is ensured, and the browsing experience of the user is improved.
In order to make those skilled in the art better understand the technical solutions of the embodiments of the present invention, the following examples are provided for illustrative purposes, and it is to be understood that the present invention is not limited thereto.
Referring to fig. 2, a flowchart illustrating steps of a content display method provided in an embodiment of the present invention is shown, and an example is given by taking a terminal configured with an identification model, where the identification model is used for identifying a picture. The specific process can comprise the following steps:
1) when a user browses a page with pictures, the page can display text contents firstly, the picture position of a post temporarily displays a default picture firstly, and meanwhile, a real picture is downloaded through a network;
2) and acquiring a user portrait corresponding to a user account registered in the application program, and extracting favorite labels in the user portrait, wherein the favorite labels comprise positive favorites and negative favorites. If the favorite label exists, the picture can be personalized, otherwise, the picture is directly displayed;
3) after the real post picture is downloaded successfully, calling a picture target identification model to identify the picture, and identifying the article in the picture and the position (coordinate) of the article in the picture;
4) comparing the favorite label with the article identified and processed in the picture, and if the favorite label is reset to be crossed, indicating that the article which is favorite or annoying by the user exists in the picture;
5) for the crossed articles, if the articles are the positive preference of the user, the articles can be subjected to treatment of highlighting the articles, such as beautifying, filtering and the like; if the preference is negative, the weakening treatment such as mosaic or pixel reduction can be carried out, so that the user's dislike is avoided;
6) and displaying the processed picture to obtain the picture position of the page.
In the process of displaying the page, after the contained target object is identified according to the same content, personalized display processing is carried out on the target object based on the user portrait, then display is carried out, different display styles can be displayed when different users browse the same picture, further personalized display can be realized according to the same content, the matching between the displayed content and the users is ensured, and the browsing experience of the users is improved.
Referring to fig. 3, a flowchart illustrating steps of a content display method provided in an embodiment of the present invention is shown, and an exemplary description is given by taking an example that an identification model is configured in a server and is used for identifying a picture, where a specific process may include:
1) when a user browses a page with pictures, the page can display text contents firstly, the picture position of a post temporarily displays a default picture firstly, and meanwhile, a real picture is downloaded through a network;
2) the terminal can obtain the user portrait corresponding to the user account logged in the application program, and extracts the favorite labels in the user portrait, wherein the favorite labels comprise positive favorites and negative favorites. If the favorite label exists, the picture can be personalized, otherwise, the picture is directly displayed;
3) after the real post picture is downloaded successfully, the terminal can send the picture to the server, the server calls the picture target recognition model to recognize the picture, the object in the picture and the position (coordinate) of the object in the picture are recognized, and the recognition result is returned to the terminal;
4) the terminal can compare the favorite label with the article identified and processed in the picture, and if the intersection is reset, the user favorite or unpleasant article exists in the picture;
5) aiming at the crossed articles, if the articles are in positive preference of the user, the terminal can perform processing such as beautifying, filtering and the like on the articles to highlight the articles; if the preference is negative, the terminal can perform weakening processing such as mosaic or pixel reduction, so as to avoid causing the user to feel dislike;
6) and displaying the processed picture to obtain the picture position of the page.
In the process of displaying the page, after the contained target object is identified according to the same content, personalized display processing is carried out on the target object based on the user portrait, then display is carried out, different display styles can be displayed when different users browse the same picture, further personalized display can be realized according to the same content, the matching between the displayed content and the users is ensured, and the browsing experience of the users is improved.
It should be noted that, in the above example, personalized display processing is performed on the picture as an example, it may be understood that, in the display process of the page, the text, the video, the audio and other contents may also be related, and accordingly, if personalized display is performed on the text, personalized display processing may be performed on the text content according to the user picture, for example, illegal contents related to yellow gambling poison and the like are replaced, and related texts are replaced with preset texts (for example,); if the video needs to be displayed in an individualized way, the video frame can be displayed in an individualized way, and the relevant process can refer to the process of the image individualized display processing; if the audio needs to be personalized, the audio can be subjected to voice recognition to obtain a corresponding text, then illegal contents related to yellow gambling poison and the like in the recognized text are extracted, a corresponding audio segment is positioned in the audio, and then the corresponding audio segment is replaced, for example, the corresponding audio segment is replaced by a corresponding preset audio. In addition, the highlight display, the playing and the like can be performed according to the user portrait, so that different users can output the same content in different modes when browsing the same content, further personalized output can be realized for the same content, the matching between the output content and the user is ensured, and the browsing experience of the user is improved.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 4, a block diagram of a display device for displaying content provided in the embodiment of the present invention is shown, and specifically, the display device may include the following modules:
an initial content obtaining module 401, configured to obtain initial content to be displayed on a target page;
a user representation acquisition module 402 for acquiring a target user representation;
a target object identification module 403, configured to identify a target object included in the initial content;
a target content generating module 404, configured to perform display processing on the target object according to the target user image, and generate target content corresponding to the initial content;
a target content display module 405, configured to display the target content in the target page.
In an optional embodiment of the present invention, the target object identifying module 403 is specifically configured to:
and inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
In an optional embodiment of the present invention, the target object identifying module 403 is specifically configured to:
and if the target user portrait contains a target favorite label, inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
In an optional embodiment of the present invention, the parameter information includes object information of the target object, and the target content generating module 404 includes:
the processing information determining submodule is used for carrying out content matching on the object information by adopting the target user portrait to obtain display processing information aiming at the target object;
and the target content generation submodule is used for displaying the target object by adopting the display processing information and generating target content corresponding to the initial content.
In an optional embodiment of the present invention, the target user representation at least includes a target favorite tag, and the processing information determination sub-module is specifically configured to:
matching the target preference label with the object information to obtain a matching result aiming at the target object, wherein the matching result comprises a positive preference result and a negative preference result;
determining forward display processing information corresponding to the positive preference result;
or determining negative display processing information corresponding to the negative preference result.
In an optional embodiment of the present invention, the display processing information includes positive display processing information and negative display processing information, and the target content generation sub-module is specifically configured to:
performing first display processing on the target object by adopting the forward display processing information to obtain target content corresponding to the initial content;
or, performing second display processing on the target object by using the negative display processing information to obtain target content corresponding to the initial content.
In an optional embodiment of the present invention, the parameter information further includes position information of the target object in the initial content, and the target content generating sub-module is specifically configured to:
identifying a target object corresponding to the position information in the initial content;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
In an alternative embodiment of the invention, the recognition model is generated by:
a data acquisition module for acquiring a user representation of at least different users, the user representation including at least a first favorite label;
the training data acquisition module is used for acquiring initial training data matched with the first favorite label;
and the model training module is used for training to obtain the recognition model according to the initial training data.
In an optional embodiment of the present invention, the model training module is specifically configured to:
determining a preset object matched with the first favorite label in the initial training data, marking the preset object, and generating target training data corresponding to the initial training data;
and training to obtain the recognition model by adopting the target training data.
In an optional embodiment of the present invention, the training data obtaining module comprises:
the tag quantity counting submodule is used for counting the quantity of the first favorite tags;
the label extraction submodule is used for extracting the first favorite labels with the quantity being TopN as second favorite labels;
and the training data determining submodule is used for acquiring initial training data matched with the second preference label.
In an optional embodiment of the present invention, the initial training data comprises at least one of picture data, video data, and text data.
In an optional embodiment of the present invention, the initial content obtaining module 401 includes:
the page data acquisition sub-module is used for responding to an access request of a user and acquiring page data corresponding to the access request;
the target position determining submodule is used for displaying a target page corresponding to the page data and determining a target position of a picture to be displayed in the target page;
and the initial picture acquisition sub-module is used for displaying a default preview picture at the target position and acquiring an initial picture corresponding to the target position.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
In addition, an embodiment of the present invention further provides an electronic device, as shown in fig. 5, which includes a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504,
a memory 503 for storing a computer program;
the processor 501, when executing the program stored in the memory 503, implements the following steps:
acquiring initial content to be displayed on a target page;
acquiring a target user portrait;
identifying a target object contained in the initial content;
displaying the target object according to the target user image to generate target content corresponding to the initial content;
and displaying the target content in the target page.
In an optional embodiment of the present invention, the identifying the target object included in the initial content includes:
and inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
In an optional embodiment of the present invention, the identifying the target object included in the initial content includes:
and if the target user portrait contains a target favorite label, inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
In an optional embodiment of the present invention, the parameter information includes object information of the target object, and the displaying the target object according to the target user image to generate target content corresponding to the initial content includes:
performing content matching on the object information by adopting the target user portrait to obtain display processing information aiming at the target object;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
In an optional embodiment of the present invention, the target user representation at least includes a target favorite tag, and the performing content matching on the object information with the target user representation to obtain display processing information for the target object includes:
matching the target preference label with the object information to obtain a matching result aiming at the target object, wherein the matching result comprises a positive preference result and a negative preference result;
determining forward display processing information corresponding to the positive preference result;
or determining negative display processing information corresponding to the negative preference result.
In an optional embodiment of the present invention, the displaying processing information includes positive displaying processing information and negative displaying processing information, and the performing, by using the displaying processing information, the displaying processing on the target object to generate the target content corresponding to the initial content includes:
performing first display processing on the target object by adopting the forward display processing information to obtain target content corresponding to the initial content;
or, performing second display processing on the target object by using the negative display processing information to obtain target content corresponding to the initial content.
In an optional embodiment of the present invention, the parameter information further includes position information of the target object in the initial content, and the performing display processing on the target object by using the display processing information to generate target content corresponding to the initial content includes:
identifying a target object corresponding to the position information in the initial content;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
In an alternative embodiment of the present invention, the recognition model is generated by:
obtaining user portraits of at least different users, the user portraits including at least a first favorite label;
acquiring initial training data matched with the first favorite label;
and training to obtain the recognition model according to the initial training data.
In an optional embodiment of the present invention, the training to obtain the recognition model according to the initial training data includes:
determining a preset object matched with the first favorite label in the initial training data, marking the preset object, and generating target training data corresponding to the initial training data;
and training to obtain the recognition model by adopting the target training data.
In an optional embodiment of the present invention, the obtaining initial training data matching the first preference label includes:
counting the number of the first favorite labels;
extracting the first favorite labels with the quantity being TopN as second favorite labels;
and acquiring initial training data matched with the second favorite label.
In an optional embodiment of the present invention, the initial training data comprises at least one of picture data, video data, and text data.
In an optional embodiment of the present invention, the acquiring the initial content to be displayed on the target page includes:
responding to an access request of a user, and acquiring page data corresponding to the access request;
displaying a target page corresponding to the page data, and determining a target position of a picture to be displayed in the target page;
and displaying a default preview image at the target position, and acquiring an initial image corresponding to the target position.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
As shown in fig. 6, in a further embodiment provided by the present invention, there is also provided a computer-readable storage medium 601, which stores therein instructions that, when run on a computer, cause the computer to perform the display method of contents described in the above-described embodiment.
In yet another embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method of displaying content described in the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (15)
1. A method for displaying content, comprising:
acquiring initial content to be displayed on a target page;
acquiring a target user portrait;
identifying a target object contained in the initial content;
displaying the target object according to the target user image to generate target content corresponding to the initial content;
and displaying the target content in the target page.
2. The method of claim 1, wherein the identifying the target object contained in the initial content comprises:
and inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
3. The method of claim 2, wherein the identifying the target object contained in the initial content comprises:
and if the target user portrait contains a target favorite label, inputting the initial content into a recognition model for content recognition to obtain a target object contained in the initial content and parameter information corresponding to the target object.
4. The method according to claim 2 or 3, wherein the parameter information includes object information of the target object, and the displaying the target object according to the target user image to generate target content corresponding to the initial content includes:
performing content matching on the object information by adopting the target user portrait to obtain display processing information aiming at the target object;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
5. The method of claim 4, wherein the target user representation includes at least a target preference tag, and wherein said content matching the object information using the target user representation to obtain display processing information for the target object comprises:
matching the target preference label with the object information to obtain a matching result aiming at the target object, wherein the matching result comprises a positive preference result and a negative preference result;
determining forward display processing information corresponding to the positive preference result;
or determining negative display processing information corresponding to the negative preference result.
6. The method according to claim 4, wherein the display processing information includes positive display processing information and negative display processing information, and the performing display processing on the target object using the display processing information to generate target content corresponding to the initial content includes:
performing first display processing on the target object by adopting the forward display processing information to obtain target content corresponding to the initial content;
or, performing second display processing on the target object by using the negative display processing information to obtain target content corresponding to the initial content.
7. The method according to claim 4, wherein the parameter information further includes position information of the target object in the initial content, and the generating of the target content corresponding to the initial content by performing display processing on the target object using the display processing information includes:
identifying a target object corresponding to the position information in the initial content;
and displaying the target object by adopting the display processing information to generate target content corresponding to the initial content.
8. A method according to claim 2 or 3, characterized in that the recognition model is generated by:
obtaining user portraits of at least different users, the user portraits including at least a first favorite label;
acquiring initial training data matched with the first favorite label;
and training to obtain the recognition model according to the initial training data.
9. The method of claim 8, wherein training the recognition model based on the initial training data comprises:
determining a preset object matched with the first favorite label in the initial training data, marking the preset object, and generating target training data corresponding to the initial training data;
and training to obtain the recognition model by adopting the target training data.
10. The method of claim 8, wherein obtaining initial training data that matches the first preference label comprises:
counting the number of the first favorite labels;
extracting the first favorite labels with the quantity being TopN as second favorite labels;
and acquiring initial training data matched with the second favorite label.
11. The method of claim 8, wherein the initial training data comprises at least one of picture data, video data, and text data.
12. The method of claim 1, wherein the initial content comprises an initial picture, and wherein the obtaining the initial content to be displayed on the target page comprises:
responding to an access request of a user, and acquiring page data corresponding to the access request;
displaying a target page corresponding to the page data, and determining a target position of a picture to be displayed in the target page;
and displaying a default preview image at the target position, and acquiring an initial image corresponding to the target position.
13. A display device for content, comprising:
the initial content acquisition module is used for acquiring initial content to be displayed on a target page;
the user portrait acquisition module is used for acquiring a target user portrait;
a target object identification module for identifying a target object contained in the initial content;
the target content generation module is used for displaying the target object according to the target user image and generating target content corresponding to the initial content;
and the target content display module is used for displaying the target content in the target page.
14. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
the memory is used for storing a computer program;
the processor, when executing a program stored on the memory, implementing the method of any of claims 1-12.
15. One or more computer-readable media having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method of any of claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111138880.5A CN114003806A (en) | 2021-09-27 | 2021-09-27 | Content display method and device, electronic equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111138880.5A CN114003806A (en) | 2021-09-27 | 2021-09-27 | Content display method and device, electronic equipment and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114003806A true CN114003806A (en) | 2022-02-01 |
Family
ID=79921772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111138880.5A Pending CN114003806A (en) | 2021-09-27 | 2021-09-27 | Content display method and device, electronic equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114003806A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110489582A (en) * | 2019-08-19 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Personalization shows the generation method and device, electronic equipment of image |
| CN111506849A (en) * | 2020-04-07 | 2020-08-07 | 口碑(上海)信息技术有限公司 | Page generation method and device |
| CN111753219A (en) * | 2019-03-29 | 2020-10-09 | 北京奇虎科技有限公司 | Method and system for displaying search result page |
| CN112685641A (en) * | 2020-12-31 | 2021-04-20 | 五八有限公司 | Information processing method and device |
| CN113382301A (en) * | 2021-04-30 | 2021-09-10 | 阿里巴巴新加坡控股有限公司 | Video processing method, storage medium and processor |
-
2021
- 2021-09-27 CN CN202111138880.5A patent/CN114003806A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753219A (en) * | 2019-03-29 | 2020-10-09 | 北京奇虎科技有限公司 | Method and system for displaying search result page |
| CN110489582A (en) * | 2019-08-19 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Personalization shows the generation method and device, electronic equipment of image |
| CN111506849A (en) * | 2020-04-07 | 2020-08-07 | 口碑(上海)信息技术有限公司 | Page generation method and device |
| CN112685641A (en) * | 2020-12-31 | 2021-04-20 | 五八有限公司 | Information processing method and device |
| CN113382301A (en) * | 2021-04-30 | 2021-09-10 | 阿里巴巴新加坡控股有限公司 | Video processing method, storage medium and processor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110309388B (en) | Method and device for identifying illegal risk of data object information and computer system | |
| CN112507125A (en) | Triple information extraction method, device, equipment and computer readable storage medium | |
| CN107562939B (en) | Vertical domain news recommendation method and device and readable storage medium | |
| TWI781554B (en) | Method of determining item name of object, device, computer equipment and storage medium | |
| CN113824972B (en) | Live video processing method, device, equipment and computer readable storage medium | |
| US10176500B1 (en) | Content classification based on data recognition | |
| KR20190042984A (en) | System for monitoring digital works distribution | |
| CN111461767B (en) | Deep learning-based Android deceptive advertisement detection method, device and equipment | |
| US9665574B1 (en) | Automatically scraping and adding contact information | |
| CN112200844A (en) | Method, device, electronic equipment and medium for generating image | |
| CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN111292153A (en) | Information recommendation method, device, system and storage medium | |
| CN110781388A (en) | Information recommendation method and device for image information | |
| CN110569429A (en) | method, device and equipment for generating content selection model | |
| CN106776634A (en) | A kind of method for network access, device and terminal device | |
| CN114003806A (en) | Content display method and device, electronic equipment and readable medium | |
| CN110942070B (en) | Content display method, device, electronic equipment and computer readable storage medium | |
| CN111209488B (en) | Information sharing method and device | |
| CN111050194B (en) | Video sequence processing method, video sequence processing device, electronic equipment and computer readable storage medium | |
| CN112950167A (en) | Design service matching method, device, equipment and storage medium | |
| CN112818984A (en) | Title generation method and device, electronic equipment and storage medium | |
| KR101242878B1 (en) | Method and system for extracting and providing item having annotation on electronic book | |
| CN111915637A (en) | Picture display method and device, electronic equipment and storage medium | |
| CN111221989A (en) | Display control method, device and system, electronic equipment and storage medium | |
| CN112948629A (en) | Content distribution method and device, electronic equipment and computer storage medium |
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 |