CN108345700B - Article representative picture selection method and device and computer equipment - Google Patents
Article representative picture selection method and device and computer equipment Download PDFInfo
- Publication number
- CN108345700B CN108345700B CN201810270464.2A CN201810270464A CN108345700B CN 108345700 B CN108345700 B CN 108345700B CN 201810270464 A CN201810270464 A CN 201810270464A CN 108345700 B CN108345700 B CN 108345700B
- Authority
- CN
- China
- Prior art keywords
- pictures
- article
- picture
- heat information
- target article
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
Abstract
The application provides a method, a device and computer equipment for selecting article representative pictures, wherein the method for selecting the article representative pictures comprises the following steps: acquiring a target article, wherein an article cluster to which the target article belongs comprises at least one reference article similar to the target article; extracting a plurality of pictures in a target article; respectively generating heat information of the multiple pictures according to the occurrence times of the multiple pictures in the article cluster, and selecting a representative picture of the target article from the multiple pictures according to the heat information of the multiple pictures; and/or respectively generating expected positions of the multiple pictures according to the positions of the multiple pictures in the article cluster, and selecting a representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures. By the method and the device, the article thumbnails in the news list page can represent news contents better, users are attracted to click and read further, user experience is improved, and product stickiness is enhanced.
Description
Technical Field
The present application relates to the field of search technologies, and in particular, to a method and an apparatus for selecting an article representative picture, and a computer device.
Background
When news is shown in a news listing, the news is generally provided with thumbnails to attract users to further click and read detailed contents. The thumbnails shown in the news listing are typically from illustrations within news articles. These illustrations, however, are of varying quality and are not all suitable for representing the content of a news article.
In the prior art, when representative pictures of news articles are selected, the first N pictures are selected according to the sequence of occurrence of the insert pictures in news content, and then thumbnails of the selected pictures are displayed in a news list as representative news pictures. Where the size of N depends on the number of pictures to be shown in the news listing, e.g. if there are many pictures in a news article, 3 are shown in the news listing, otherwise 1 is shown.
However, the sequence of the occurrence of the images in the news content is determined by editing the news content, the first N images selected according to the sequence of the occurrence of the images in the news content are not necessarily high-quality representative images, and a better representative image may appear outside the range, which results in poor user experience.
Disclosure of Invention
The present application is directed to solving, at least in part, one of the technical problems in the related art.
Therefore, a first object of the present application is to provide a method for selecting an article representative picture, so as to enable an article thumbnail in a news list page to represent news content better, attract a user to click and read further, improve user experience, and enhance product stickiness.
A second object of the present application is to provide an apparatus for selecting an article representative picture.
A third object of the present application is to propose a computer device.
A fourth object of the present application is to propose a non-transitory computer-readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present application provides a method for selecting an article representative picture, including: acquiring a target article, wherein an article cluster to which the target article belongs comprises at least one reference article similar to the target article; extracting a plurality of pictures in the target article; respectively generating heat information of the multiple pictures according to the occurrence times of the multiple pictures in the article cluster, and selecting a representative picture of the target article from the multiple pictures according to the heat information of the multiple pictures; and/or respectively generating expected positions of the multiple pictures according to the positions of the multiple pictures in the article cluster, and selecting a representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures.
In the method for selecting the article representative pictures, after a target article is acquired, a plurality of pictures in the target article are extracted, the heat information of the plurality of pictures is respectively generated according to the occurrence frequency of the plurality of pictures in the article cluster, and the representative picture of the target article is selected from the plurality of pictures according to the heat information of the plurality of pictures; and/or respectively generating expected positions of the multiple pictures according to the positions of the multiple pictures in the article cluster, and selecting the representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures, so that article thumbnails in the news list page can represent news contents better, a user is attracted to click and read further, user experience is improved, and product viscosity is enhanced.
To achieve the above object, a second aspect of the present application provides an article representative picture selecting apparatus, including: the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target article, and an article cluster to which the target article belongs comprises at least one reference article similar to the target article; the extraction module is used for extracting a plurality of pictures in the target article; the generating module is used for respectively generating the heat information of the pictures according to the occurrence times of the pictures in the article cluster; the selecting module is used for selecting a representative picture of the target article from the plurality of pictures according to the heat information of the plurality of pictures; and/or the generating module is used for respectively generating expected positions of the pictures according to the positions of the pictures in the article cluster; the selecting module is used for selecting the representative picture of the target article from the plurality of pictures according to the expected positions of the plurality of pictures.
In the device for selecting the article representative pictures, after an acquisition module acquires a target article, an extraction module extracts a plurality of pictures in the target article, a generation module respectively generates heat information of the plurality of pictures according to the occurrence frequency of the plurality of pictures in an article cluster, and a selection module selects the representative picture of the target article from the plurality of pictures according to the heat information of the plurality of pictures; and/or the generating module respectively generates expected positions of the multiple pictures according to the positions of the multiple pictures in the article cluster, and the selecting module selects the representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures, so that article thumbnails in the news list page can represent news contents better, a user is attracted to click and read further, user experience is improved, and product stickiness is enhanced.
To achieve the above object, an embodiment of a third aspect of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method as described above when executing the computer program.
In order to achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the method as described above.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of one embodiment of a method for selecting a representative picture in the present application;
FIG. 2 is a flow chart of another embodiment of a method for selecting a representative picture in the present application;
FIG. 3 is a flowchart of another embodiment of a method for selecting a representative picture in the present application;
FIG. 4 is a flowchart of another embodiment of a method for selecting a representative picture in the present application;
FIG. 5 is a flow chart of yet another embodiment of a method for selecting a representative picture in the present application;
FIG. 6 is a flow chart of yet another embodiment of a method for selecting a representative picture in the present application;
FIG. 7 is a flow chart of yet another embodiment of a method for selecting a representative picture in the present application;
FIG. 8 is a schematic diagram of an embodiment of an apparatus for selecting representative pictures in the present application;
FIG. 9 is a schematic diagram of another embodiment of an apparatus for selecting representative pictures in the present application;
FIG. 10 is a schematic block diagram of an embodiment of a computer apparatus of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
Fig. 1 is a flowchart of an embodiment of a method for selecting a representative image of an article in the present application, and as shown in fig. 1, the method for selecting a representative image of an article may include:
And 102, extracting a plurality of pictures in the target article.
103, respectively generating heat information of the plurality of pictures according to the occurrence frequency of the plurality of pictures in the article cluster, and selecting a representative picture of the target article from the plurality of pictures according to the heat information of the plurality of pictures; and/or generating expected positions of the plurality of pictures according to the positions of the plurality of pictures in the article cluster, and selecting a representative picture of the target article from the plurality of pictures according to the expected positions of the plurality of pictures.
Wherein, the plurality of pictures refers to at least two pictures.
The generating of the popularity information of the plurality of pictures according to the number of occurrences of the plurality of pictures in the article cluster may be: and acquiring the occurrence frequency of the picture in the reference article, and generating the heat information of the picture according to the occurrence frequency.
In particular, for each picture pic ' in the target article d ', d ' i The heat information of (a) may be: d 'of each picture pic' i The number of occurrences in the reference article comprised in the cluster of articles to which article d 'belongs is denoted as h (pic' i )。
Wherein, respectively generating the expected positions of the plurality of pictures according to the positions of the plurality of pictures in the article cluster may be: acquiring at least one reference article comprising the picture in the article cluster; and acquiring the position of the picture in the at least one reference article, acquiring an average value of the picture position according to the position of the picture in the at least one reference article, and taking the average value of the picture position as an expected position of the picture.
Specifically, in the article cluster to which the target article d 'belongs, all the articles comprise pictures pic' i In the article of (1), picture pic' i The average value of the positions is picture pic' i Expected location in the article cluster noted pos (pic)' i ). Wherein, the picture position here means that the picture is the second to appear in the article, namely pic' i The position of (1) is i. For example, the positions of a certain picture in 4 articles are respectively the 1 st, the 3 rd, the 4 th and the 5 th, and then the expected positions of this picture in the cluster of the 4 articles are (1 +, 3+, 4+, 5)/4 =3.25.
In the method for selecting the article representative pictures, after a target article is obtained, a plurality of pictures in the target article are extracted, the heat information of the plurality of pictures is respectively generated according to the occurrence frequency of the plurality of pictures in the article cluster, and the representative picture of the target article is selected from the plurality of pictures according to the heat information of the plurality of pictures; and/or respectively generating expected positions of the multiple pictures according to the positions of the multiple pictures in the article cluster, and selecting the representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures, so that article thumbnails in the news list page can represent news contents better, a user is attracted to click and read further, user experience is improved, and product viscosity is enhanced.
Fig. 2 is a flowchart of another embodiment of a method for selecting a representative image of an article in the present application, as shown in fig. 2, in the embodiment shown in fig. 1 in the present application, the step 103 of selecting a representative image of the target article from the plurality of images may include:
And step 202, selecting a predetermined number of pictures as representative pictures of the target article according to the sorting result.
Specifically, a predetermined number of pictures may be selected as the representative pictures of the target article in the order from high to low in rank among the sorted pictures.
The predetermined number may be set in a specific implementation according to system performance and/or implementation requirements, and the size of the predetermined number is not limited in this embodiment, for example, the predetermined number may be 3.
That is, after a plurality of pictures in the target article are sorted, a sequence of pictures can be obtained, and when a representative picture of the target article is selected, top N is only required to be selected from the sequence, where N is the predetermined number.
Fig. 3 is a flowchart of another embodiment of a method for selecting a representative picture in the present application, as shown in fig. 3, in the embodiment shown in fig. 2, step 201 may include:
That is, picture pic 'in the target article d' 1 ，pic′ 2 ，…，pic′ m When sorting is performed, if h (pic' i )>h(pic′ j ) Then picture pic' i Is arranged in picture pic' j Front of (2); and if h (pic' i )＝h(pic′ j ) Then according to picture pic' i And picture pic' j The appearance order in the above-mentioned target article d 'is arranged, that is, if the picture pic' in the above-mentioned target article d 'is' i In picture pic' j When the front appears, picture pic' i Is arranged in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i Front face appears, picture pic' j Is arranged in picture pic' i Before (c) is performed.
Fig. 4 is a flowchart of another embodiment of a method for selecting a representative picture in the present application, as shown in fig. 4, in the embodiment shown in fig. 2 of the present application, step 201 may include:
in step 401, expected positions of a plurality of pictures in the target article are compared.
That is, picture pic 'in the target article d' 1 ，pic′ 2 ，…，pic′ m When sorting is performed, if pos (pic' i )<pos(pic′ j ) Then picture pic' i Is arranged in picture pic' j Front of (2); and if pos (pic' i )＝pos(pic′ j ) Then according to picture pic' i And picture pic' j The appearance order in the above-mentioned target article d 'is arranged, that is, if the picture pic' in the above-mentioned target article d 'is' i In picture pic' j Front face appears, picture pic' i Line in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i When the front appears, picture pic' j Line in picture pic' i Before (c) is performed.
Fig. 5 is a flowchart of another embodiment of a method for selecting a representative picture in the present application, as shown in fig. 5, in the embodiment shown in fig. 2 of the present application, step 201 may include:
and step 501, sequencing according to the heat information of a plurality of pictures in the target article.
Specifically, the heat information of a plurality of pictures in the target article may be compared first, and if the heat information of the plurality of pictures is not equal, a picture with higher heat information is arranged in front of a picture with lower heat information. And if the heat information of the two pictures is equal, further comparing the expected positions of the two pictures, and if the expected positions of the two pictures are not equal, arranging the picture with the smaller expected position in front of the picture with the larger expected position. And if the expected positions of the two pictures are equal, arranging the two pictures according to the appearance sequence of the two pictures in the target article.
That is, picture pic 'in the pair target article d' 1 ，pic′ 2 ，…，pic′ m When sorting is performed, the heat information is compared, if h (pic' i )>h(pic′ j ) Then picture pic' i Is arranged in picture pic' j Front of (2); and if h (pic' i )＝h(pic′ j ) Then the expected locations are compared, if pos (pic' i )<pos(pic′ j ) Then picture pic' i Is arranged in picture pic' j Front of (2); and if pos (pic' i )＝pos(pic′ j ) Then according to picture pic' i And picture pic' j The appearance order in the above target article d 'is arranged, that is, if the picture pic' in the above target article d 'is arranged' i In picture pic' j Front face appears, picture pic' i Is arranged in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i Front face appears, picture pic' j Is arranged in picture pic' i Before (c) is performed.
Fig. 6 is a flowchart of another embodiment of a method for selecting a representative picture in the present application, as shown in fig. 6, in the embodiment shown in fig. 2 of the present application, step 201 may include:
Specifically, the expected positions of the multiple pictures in the target article may be compared first, and if the expected positions of the multiple pictures are not equal, the picture with the smaller expected position is arranged in front of the picture with the larger expected position. And if the expected positions of the two pictures are equal, comparing the heat information of the two pictures, and if the heat information of the two pictures is not equal, arranging the picture with higher heat information in front of the picture with lower heat information. And if the heat information of the two pictures is equal, arranging the two pictures according to the appearance sequence of the two pictures in the target article.
That is, picture pic 'in the pair target article d' 1 ，pic′ 2 ，…，pic′ m When sorting is performed, the expected locations are compared first, if pos (pic' i )<pos(pic′ j ) Then picture pic' i Is arranged in picture pic' j Front of (2); and if pos (pic' i )＝pos(pic′ j ) Comparing the heat information if h (pic' i )>h(pic′ j ) Then picture pic' i Line in picture pic' j Front of (2); and if h (pic' i )＝h(pic′ j ) Then according to picture pic' i And picture pic' j The appearance order in the above target article d 'is arranged, that is, if the picture pic' in the above target article d 'is arranged' i In picture pic' j Front face appears, picture pic' i Is arranged in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i Front face appears, picture pic' j Is arranged in picture pic' i Before (2).
Fig. 7 is a flowchart of another embodiment of a method for selecting a representative picture in the present application, as shown in fig. 7, in the embodiment shown in fig. 1 of the present application, before step 101, the method may further include:
In step 702, if the average similarity is greater than the predetermined threshold, the article cluster to which the target article currently belongs and the article cluster to which the reference article currently belongs are merged into one article cluster.
And repeating the steps 701 to 702 until the article cluster to which the target article belongs currently cannot be combined with other article clusters in the database, so as to obtain the article cluster to which the target article belongs.
That is, before step 101, the articles stored in the database need to be clustered to obtain the article cluster to which the target article belongs.
The predetermined threshold may be set according to system performance and/or implementation requirements, and the size of the predetermined threshold is not limited in this embodiment.
In specific implementation, the articles are clustered by adopting a hierarchical clustering method, and firstly, each article is considered to be an article cluster; second, for any two article clusters, if the average similarity between them is greater than a predetermined threshold, the two article clusters can be merged into one article cluster until merging cannot be continued.
The method for calculating the average similarity between the two article clusters comprises the following steps: similarity calculation is carried out on the articles in the two article clusters pairwise, and then the average value of the obtained similarities is calculated.
Thus, through the clustering process, at least one article cluster is obtained, each article cluster comprises at least one article, and the similarity between the articles contained in each article cluster is higher.
The following describes a method for calculating the similarity between the two articles.
For two articles d (1) And d (2) Calculating d (1) And d (2) Similarity between them sim (d) (1) ，d (2) ). There are many methods for calculating similarity, and this embodiment calculates d by using cosine (cosine) distance of article words (1) And d (2) The similarity between them. In particular, article d (1) And d (2) Can be represented by a set of word-weight vectors:
and
wherein
And
respectively represent articles d (1) And d (2) The words and phrases in (1) or (b),
and
respectively represent articles d (1) And d (2) Weight of the word in (1), n (1) And n (2) Respectively represent articles d (1) And d (2) The number of the Chinese words. The word weight can be calculated by a conventional Term Frequency-Inverse file Frequency (TF-IDF) method. Article d (1) And d (2) The similarity of (c) can be represented by formula (1):
wherein, the first and the second end of the pipe are connected with each other,
and
representing article d (1) And d (2) The same words in (1).
Fig. 8 is a schematic structural diagram of an embodiment of a device for selecting an article representative picture in the present application, where the device for selecting an article representative picture in the present application may implement the method for selecting an article representative picture provided in the present application. As shown in fig. 8, the selecting device for the article representative picture may include: the system comprises an acquisition module 81, an extraction module 82, a generation module 83 and a selection module 84;
the obtaining module 81 is configured to obtain a target article, where an article cluster to which the target article belongs includes at least one reference article similar to the target article.
The extraction module 82 is used for extracting a plurality of pictures in the target article;
a generating module 83, configured to generate heat information of the multiple pictures according to the number of occurrences of the multiple pictures in the article cluster;
a selecting module 84, configured to select a representative picture of the target article from the multiple pictures according to the heat information of the multiple pictures; and/or the presence of a gas in the atmosphere,
a generating module 83, configured to generate expected positions of the multiple pictures according to positions of the multiple pictures in the article cluster;
a selecting module 84, configured to select a representative picture of the target article from the multiple pictures according to expected positions of the multiple pictures.
The generating module 83 is specifically configured to obtain the number of occurrences of the picture in the reference article, and generate the heat information of the picture according to the number of occurrences.
In particular, for each picture pic ' in the target article d ', d ' i The heat information of (a) may be: d 'of each picture pic' i The number of occurrences in the reference article included in the article cluster to which article d 'belongs is denoted as h (pic' i )。
A generating module 83, configured to specifically acquire at least one reference article including the picture in the article cluster; and acquiring the position of the picture in the at least one reference article, acquiring an average value of the picture position according to the position of the picture in the at least one reference article, and taking the average value of the picture position as an expected position of the picture.
Specifically, in the article cluster to which the target article d 'belongs, all include the picture pic' i In the article ofPicture pic' i The average value of the positions is picture pic' i The expected location in the cluster of articles to which the above-mentioned target article d 'belongs is denoted as pos (pic' i ). Wherein, the picture position here refers to the picture appearing the next in the article, namely pic' i The position of (1) is i. For example, the positions of a certain picture in 4 articles are respectively the 1 st, the 3 rd, the 4 th and the 5 th, and then the expected positions of this picture in the cluster of the 4 articles are (1 +, 3+, 4+, 5)/4 =3.25.
In the device for selecting the representative images of the articles, after the acquisition module 81 acquires a target article, the extraction module 82 extracts a plurality of images in the target article, the generation module 83 generates heat information of the plurality of images according to the occurrence frequency of the plurality of images in the article cluster, and the selection module 84 selects the representative image of the target article from the plurality of images according to the heat information of the plurality of images; and/or the generating module 83 generates expected positions of the multiple pictures in the article cluster according to the positions of the multiple pictures in the article cluster, and the selecting module 84 selects a representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures, so that article thumbnails in a news list page can represent news contents better, users are attracted to click and read further, user experience is improved, and product viscosity is enhanced.
Fig. 9 is a schematic structural diagram of another embodiment of an apparatus for selecting a representative image according to the present application, which is different from the apparatus for selecting a representative image shown in fig. 8 in that, in the apparatus for selecting a representative image shown in fig. 9, the selecting module 84 may include: a sorting sub-module 841 and a selection sub-module 842;
the sorting submodule 841 is configured to sort the multiple pictures according to the heat information and/or expected positions of the multiple pictures;
the selecting sub-module 842 is used for selecting a predetermined number of pictures as the representative pictures of the target article according to the sorting result.
Specifically, the selecting sub-module 842 may select a predetermined number of pictures in the ranked pictures in order from high to low as the representative pictures of the target article.
The predetermined number may be set according to system performance and/or implementation requirements during specific implementation, and the size of the predetermined number is not limited in this embodiment, for example, the predetermined number may be 3.
That is to say, after the sorting sub-module 841 sorts a plurality of pictures in the target article, a sequence of pictures can be obtained, and when the selecting sub-module 842 selects the representative picture of the target article, it is only necessary to select top N on the sequence, where N is the predetermined number.
In an implementation manner of this embodiment, the sorting sub-module 841 is specifically configured to compare heat information of multiple pictures in the target article; if the heat information of the plurality of pictures is not equal, arranging the picture with higher heat information in front of the picture with lower heat information; and if the heat information of the two pictures is equal, arranging the two pictures according to the appearance sequence of the two pictures in the target article.
That is, picture pic 'in the pair target article d' 1 ，pic′ 2 ，…，pic′ m When sorting is performed, if h (pic' i )>h(pic′ j ) Then sorting submodule 841 sorts picture pic' i Is arranged in picture pic' j Front of (2); and if h (pic' i )＝h(pic′ j ) Then sort submodule 841 orders according to picture pic' i And picture pic' j The appearance order in the above target article d 'is arranged, that is, if the picture pic' in the above target article d 'is arranged' i In picture pic' j As before, the ordering submodule 841 sorts the pictures pic' i Is arranged in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i If it occurs ahead, then the ordering submodule 841 will take picture pic' j Is arranged in picture pic' i Before (c) is performed.
In another implementation manner of this embodiment, the sorting sub-module 841 is specifically configured to compare expected positions of multiple pictures in the target article; if the expected positions of the pictures are not equal, arranging the picture with the smaller expected position in front of the picture with the larger expected position; and if the expected positions of the two pictures are equal, arranging the two pictures according to the appearance sequence of the two pictures in the target article.
That is, picture pic 'in the target article d' 1 ，pic′ 2 ，…，pic′ m When sorting is performed, if pos (pic' i )<pos(pic′ j ) Then sorting submodule 841 sorts picture pic' i Is arranged in picture pic' j Front of (2); and if pos (pic' i )＝pos(pic′ j ) Then ordering submodule 841 orders according to picture pic' i And picture pic' j The appearance order in the above-mentioned target article d 'is arranged, that is, if the picture pic' in the above-mentioned target article d 'is' i In picture pic' j As before, the ordering submodule 841 sorts the pictures pic' i Line in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i As before, the ordering submodule 841 sorts the pictures pic' j Is arranged in picture pic' i Before (2).
In another implementation manner of this embodiment, the sorting submodule 841 is specifically configured to sort according to the heat information of multiple pictures in the target article; and if the heat information of the two pictures is equal, further sorting according to the expected positions of the two pictures.
Specifically, the heat information of a plurality of pictures in the target article may be compared first, and if the heat information of the plurality of pictures is not equal, a picture with higher heat information is arranged in front of a picture with lower heat information; if the heat information of the two pictures is equal, comparing the expected positions of the two pictures, and if the expected positions of the two pictures are not equal, arranging the picture with the smaller expected position in front of the picture with the larger expected position; and if the expected positions of the two pictures are equal, arranging the two pictures according to the appearance sequence of the two pictures in the target article.
That is, picture pic 'in the target article d' 1 ，pic′ 2 ，…，pic′ m In sorting, the sorting sub-module 841 first compares the heat information if h (pic' i )>h(pic′ j ) Then sorting submodule 841 sorts picture pic' i Line in picture pic' j Front of (2); and if h (pic' i )＝h(pic′ j ) Then the order submodule 841 compares the expected locations if pos (pic' i )<pos(pic′ j ) Then sort submodule 841 sorts picture pic' i Line in picture pic' j Front of (2); and if pos (pic' i )＝pos(pic′ j ) Then sort submodule 841 orders according to picture pic' i And picture pic' j The appearance order in the above-mentioned target article d 'is arranged, that is, if the picture pic' in the above-mentioned target article d 'is' i In picture pic' j As before, the ordering submodule 841 sorts the pictures pic' i Line in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i If it occurs ahead, then the ordering submodule 841 will take picture pic' j Is arranged in picture pic' i Before (2).
In another implementation manner of this embodiment, the sorting submodule 841 is specifically configured to sort according to expected positions of multiple pictures in the target article; and if the expected positions of the two pictures are equal, further sorting the two pictures according to the heat information of the two pictures.
Specifically, expected positions of a plurality of pictures in the target article may be compared first, and if the expected positions of the plurality of pictures are not equal, a picture with a smaller expected position is arranged in front of a picture with a larger expected position; if the expected positions of the two pictures are equal, comparing the heat information of the two pictures, and if the heat information of the two pictures is not equal, arranging the picture with higher heat information in front of the picture with lower heat information; and if the heat information of the two pictures is equal, arranging the two pictures according to the appearance sequence of the two pictures in the target article.
That is, picture pic 'in the target article d' 1 ，pic′ 2 ，…，pic′ m In sorting, the sorting submodule 841 first compares the expected locations if pos (pic' i )＜pos(pic′ j ) Then sort submodule 841 sorts picture pic' i Is arranged in picture pic' j Front of (2); and if pos (pic' i )＝pos(pic′ j ) Then the rank submodule 841 compares the heat information if h (pic' i )>h(pic′ j ) Then sort submodule 841 sorts picture pic' i Line in picture pic' j Front of (2); and if h (pic' i )＝h(pic′ j ) Then sort submodule 841 orders according to picture pic' i And picture pic' j The appearance order in the above target article d 'is arranged, that is, if the picture pic' in the above target article d 'is arranged' i In picture pic' j As before, the ordering submodule 841 sorts the pictures pic' i Is arranged in picture pic' j If it is in the above target article d ', picture pic' j In picture pic' i As before, the ordering submodule 841 sorts the pictures pic' j Is arranged in picture pic' i Before (2).
Further, the article representative picture selecting device may further include: a clustering module 85;
a clustering module 85, configured to calculate an average similarity between an article cluster to which the target article currently belongs and an article cluster to which the reference article currently belongs; and if the average similarity is larger than a preset threshold value, combining the article cluster to which the target article belongs and the article cluster to which the reference article belongs into one article cluster.
Repeating the above process until the article cluster to which the target article belongs currently cannot be combined with other article clusters in the database, and obtaining the article cluster to which the target article belongs.
That is, before the obtaining module 81 obtains the target article, the clustering module 85 needs to cluster the articles stored in the database to obtain the article cluster to which the target article belongs.
The predetermined threshold may be set according to system performance and/or implementation requirements, and the size of the predetermined threshold is not limited in this embodiment.
In specific implementation, the clustering module 85 clusters the articles by using a hierarchical clustering method, and firstly, considers that each article is an article cluster; second, for any two article clusters, if the average similarity between them is greater than a predetermined threshold, the two article clusters can be merged into one article cluster until merging cannot be continued.
The method for calculating the average similarity between the two article clusters comprises the following steps: and carrying out similarity calculation on the articles in the two article clusters pairwise, and then calculating the average value of the obtained similarities.
Thus, through the clustering process, at least one article cluster is obtained, each article cluster comprises at least one article, and the similarity between the articles contained in each article cluster is higher. The method for calculating the similarity of the two articles can be referred to the contents in the method embodiments, and is not repeated herein.
The article representative picture selecting device can realize that the article thumbnail in the news list page can represent news content better, attract users to click and read further, improve user experience and enhance product viscosity.
Fig. 10 is a schematic structural diagram of an embodiment of a computer device according to the present application, where the computer device may include a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method for selecting an article representative picture according to the embodiment of the present application may be implemented.
The computer device may be a server or a terminal device, and the embodiment does not limit the specific form of the computer device.
FIG. 10 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present application. The computer device 12 shown in fig. 10 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in FIG. 10, computer device 12 is embodied in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 10 and commonly referred to as a "hard drive"). Although not shown in FIG. 10, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the embodiments described herein.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public Network such as the Internet via Network adapter 20. As shown in FIG. 10, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be appreciated that although not shown in FIG. 10, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, to name a few.
The processing unit 16 executes programs stored in the system memory 28 to execute various functional applications and data processing, such as implementing a method for selecting a representative picture of an article provided in an embodiment of the present application.
The embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for selecting the article representative picture provided in the embodiment of the present application may be implemented.
The non-transitory computer readable storage medium described above may take any combination of one or more computer readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. 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 (a non-exhaustive list) of the computer readable storage medium would include the following: 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), a 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 context of this document, 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.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of 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 wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application 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).
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer case (magnetic device), a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM) or flash Memory, an optical fiber device, and a portable Compact Disc Read Only Memory (CD-ROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic Gate circuit for implementing a logic function on a data signal, an asic having an appropriate combinational logic Gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), and the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method for selecting an article representative picture is characterized by comprising the following steps:
acquiring a target article, wherein an article cluster to which the target article belongs comprises at least one reference article similar to the target article;
extracting a plurality of pictures in the target article;
respectively generating heat information of the multiple pictures according to the occurrence times of the multiple pictures in the article cluster, and selecting a representative picture of the target article from the multiple pictures according to the heat information of the multiple pictures; and/or respectively generating expected positions of the multiple pictures according to the positions of the multiple pictures in the article cluster, and selecting a representative picture of the target article from the multiple pictures according to the expected positions of the multiple pictures;
the selecting a representative picture of the target article from the plurality of pictures comprises:
sorting the plurality of pictures according to the heat information and/or the expected positions of the plurality of pictures, including:
comparing the heat information of a plurality of pictures in the target article, and if the heat information of the plurality of pictures is not equal, arranging the picture with higher heat information in front of the picture with lower heat information;
if the pictures with the same heat information exist in the plurality of pictures, comparing the expected positions of the pictures with the same heat information;
if the expected positions of the pictures with the same heat information are not equal, arranging the picture with the smaller expected position in front of the picture with the larger expected position;
if the expected positions of the pictures with the same heat information are equal, arranging the pictures with the same heat information and the same expected positions according to the appearance sequence of the pictures in the target article;
selecting a preset number of pictures as representative pictures of the target article according to the sorting result;
the generating the expected positions of the plurality of pictures according to the positions of the plurality of pictures in the article cluster comprises:
acquiring at least one reference article comprising the picture in the article cluster;
and acquiring the position of the picture in the at least one reference article, acquiring an average value of the picture position according to the position of the picture in the at least one reference article, and taking the average value of the picture position as an expected position of the picture.
2. The method of claim 1, wherein the generating the popularity information of the plurality of pictures according to the number of occurrences of the plurality of pictures in the article cluster comprises:
and acquiring the occurrence times of the pictures in the reference article, and generating the heat information of the pictures according to the occurrence times.
3. The method of claim 1, wherein the ordering the plurality of pictures according to the popularity information and the expected locations of the plurality of pictures comprises:
sequencing according to expected positions of a plurality of pictures in the target article;
and if the expected positions of the two pictures are equal, further sorting the two pictures according to the heat information of the two pictures.
4. The method of claim 1, wherein prior to obtaining the target article, further comprising:
calculating the average similarity of the article cluster to which the target article currently belongs and the article cluster to which the reference article currently belongs;
and if the average similarity is larger than a preset threshold value, combining the article cluster to which the target article currently belongs and the article cluster to which the reference article currently belongs into one article cluster.
5. An article representative picture selection device, comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target article, and an article cluster to which the target article belongs comprises at least one reference article similar to the target article;
the extraction module is used for extracting a plurality of pictures in the target article;
the generating module is used for respectively generating the heat information of the pictures according to the occurrence times of the pictures in the article cluster;
the selecting module is used for selecting a representative picture of the target article from the plurality of pictures according to the heat information of the plurality of pictures; and/or the presence of a gas in the gas,
the generation module is used for respectively generating expected positions of the pictures according to the positions of the pictures in the article cluster;
the selecting module is used for selecting a representative picture of the target article from the plurality of pictures according to the expected positions of the plurality of pictures;
the selecting module comprises:
a sorting submodule, configured to sort the multiple pictures according to the heat information and/or expected positions of the multiple pictures, and specifically configured to:
comparing the heat information of a plurality of pictures in the target article, and if the heat information of the plurality of pictures is not equal, arranging the picture with higher heat information in front of the picture with lower heat information;
if the pictures with the same heat information exist in the plurality of pictures, comparing the expected positions of the pictures with the same heat information;
if the expected positions of the pictures with the same heat information are not equal, arranging the picture with the smaller expected position in front of the picture with the larger expected position;
if the expected positions of the pictures with the same heat information are equal, arranging the pictures with the same heat information and the same expected positions according to the appearance sequence of the pictures in the target article;
the selection sub-module is used for selecting a preset number of pictures as representative pictures of the target article according to the sorting result;
the generating module is specifically configured to acquire at least one reference article including the picture in the article cluster; and acquiring the position of the picture in the at least one reference article, acquiring an average value of the picture position according to the position of the picture in the at least one reference article, and taking the average value of the picture position as an expected position of the picture.
6. The apparatus of claim 5,
the generating module is specifically configured to acquire the occurrence times of the picture in the reference article, and generate the heat information of the picture according to the occurrence times.
7. The apparatus of claim 5,
the sequencing sub-module is specifically used for sequencing according to expected positions of a plurality of pictures in the target article; and if the expected positions of the two pictures are equal, further sorting the two pictures according to the heat information of the two pictures.
8. The apparatus of claim 5,
the clustering module is used for calculating the average similarity of the article cluster to which the target article currently belongs and the article cluster to which the reference article currently belongs; and if the average similarity is larger than a preset threshold value, combining the article cluster to which the target article belongs and the article cluster to which the reference article belongs into one article cluster.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-4 when executing the computer program.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810270464.2A CN108345700B (en) | 2018-03-29 | 2018-03-29 | Article representative picture selection method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810270464.2A CN108345700B (en) | 2018-03-29 | 2018-03-29 | Article representative picture selection method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108345700A CN108345700A (en) | 2018-07-31 |
| CN108345700B true CN108345700B (en) | 2023-01-31 |
Family
ID=62958335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810270464.2A Active CN108345700B (en) | 2018-03-29 | 2018-03-29 | Article representative picture selection method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108345700B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109115221A (en) * | 2018-08-02 | 2019-01-01 | 北京三快在线科技有限公司 | Indoor positioning, air navigation aid and device, computer-readable medium and electronic equipment |
| CN110209854B (en) * | 2019-05-06 | 2021-08-31 | 无线生活(北京)信息技术有限公司 | Picture determination method and device |
| CN110162653B (en) * | 2019-05-13 | 2021-07-30 | 北京百度网讯科技有限公司 | Image-text sequencing recommendation method and terminal equipment |
| CN113921082B (en) * | 2021-10-27 | 2023-04-07 | 云舟生物科技(广州)股份有限公司 | Gene search weight adjustment method, computer storage medium, and electronic device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1710563A (en) * | 2005-07-18 | 2005-12-21 | 北大方正集团有限公司 | Method for detecting and abstracting importent new case |
| CN101976252B (en) * | 2010-10-26 | 2012-10-10 | 百度在线网络技术（北京）有限公司 | Picture display system and display method thereof |
| CN102411638B (en) * | 2011-12-30 | 2013-06-19 | 中国科学院自动化研究所 | Method for generating multimedia summary of news search result |
| US9589184B1 (en) * | 2012-08-16 | 2017-03-07 | Groupon, Inc. | Method, apparatus, and computer program product for classification of documents |
| CN102937960B (en) * | 2012-09-06 | 2015-06-17 | 北京邮电大学 | Device for identifying and evaluating emergency hot topic |
| CN105975507B (en) * | 2016-04-28 | 2018-07-03 | 南京理工大学 | A kind of Questions ＆. Answers on Multimedia method based on multi-source network news data |
-
2018
- 2018-03-29 CN CN201810270464.2A patent/CN108345700B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108345700A (en) | 2018-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210173530A1 (en) | Hierarchical, Zoomable Presentations Of Media Sets | |
| CN108345700B (en) | Article representative picture selection method and device and computer equipment | |
| US8280158B2 (en) | Systems and methods for indexing presentation videos | |
| US10073861B2 (en) | Story albums | |
| CN107633023B (en) | Image duplicate removal method and device | |
| WO2017124116A1 (en) | Searching, supplementing and navigating media | |
| WO2020233269A1 (en) | Method and apparatus for reconstructing 3d model from 2d image, device and storage medium | |
| US20180032882A1 (en) | Method and system for generating recommendations based on visual data and associated tags | |
| CN108460098B (en) | Information recommendation method and device and computer equipment | |
| US11704357B2 (en) | Shape-based graphics search | |
| SG194442A1 (en) | In-video product annotation with web information mining | |
| US9734599B2 (en) | Cross-level image blending | |
| US9081822B2 (en) | Discriminative distance weighting for content-based retrieval of digital pathology images | |
| CN111836118B (en) | Video processing method, device, server and storage medium | |
| CN108182457B (en) | Method and apparatus for generating information | |
| CN113204691B (en) | Information display method, device, equipment and medium | |
| CN108431800B (en) | Image processing apparatus and display method of image search interface | |
| CN114565768A (en) | Image segmentation method and device | |
| GB2555168A (en) | Using labels to track high-frequency offsets for patch-matching algorithms | |
| CN112883218A (en) | Image-text combined representation searching method, system, server and storage medium | |
| CN104850600A (en) | Method and device for searching images containing faces | |
| US20180189602A1 (en) | Method of and system for determining and selecting media representing event diversity | |
| CN113221572A (en) | Information processing method, device, equipment and medium | |
| WO2015100070A1 (en) | Presenting information based on a video | |
| CN111866609A (en) | Method and apparatus for generating video |
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 |