CN108334626B - News column generation method and device and computer equipment - Google Patents
News column generation method and device and computer equipment Download PDFInfo
- Publication number
- CN108334626B CN108334626B CN201810145847.7A CN201810145847A CN108334626B CN 108334626 B CN108334626 B CN 108334626B CN 201810145847 A CN201810145847 A CN 201810145847A CN 108334626 B CN108334626 B CN 108334626B
- Authority
- CN
- China
- Prior art keywords
- articles
- keywords
- matched
- article
- strategy
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a method and a device for generating news columns and computer equipment, wherein the method for generating the news columns comprises the following steps: acquiring keywords input by a user, and acquiring articles matched with the keywords according to the keywords; obtaining a screening strategy selected by the user from a strategy library; screening and sequencing the articles matched with the keywords according to the screening strategy; and generating a content list of the news column according to the sequencing result. According to the method and the device, the time required for creating a new news column can be remarkably shortened, and therefore the online verification can be rapidly realized when some hot events occur and the hot columns need to be created emergently.
Description
Technical Field
The application relates to the technical field of internet, in particular to a news column generation method and device and computer equipment.
Background
One feature of the news recommendation field is that news columns need to be continuously expanded according to current hot spots, and news information of the relevant field needs to be gathered under each news column. When a news column needs to be expanded, a related responsible person manually screens out a part of keywords matched with the column, the keywords are the basis of subsequent article screening, but not all articles screened out through the keywords are placed under the column, and at this time, articles which are more interesting to a user need to be screened out from the articles through a formulated strategy, for example, the articles are sorted. The strategies are generally established according to human experience, in the prior art, a related responsible person establishes some strategies aiming at a newly-added column, then the strategies are delivered to developers to realize the strategies, and the strategies are delivered to the responsible person of the channel to observe the final effect after being on line. And if the effect is not ideal, the responsible person can pick the key words and screen the strategy again. The method has the advantages that the method is repeated in a circulating mode, personnel communication cost and strategy development time cost are high, the flow of the on-line of a column is greatly prolonged, a new channel can be completed comprehensively within a one-month time period, news has high timeliness, scenes of temporary channels are established aiming at hot events, and the existing news column creation method cannot meet requirements after a long period.
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 objective of the present application is to provide a method for generating a news item, so as to significantly reduce the time required for creating a new news item, and further enable fast verification online when some hot spot events need to be created urgently.
A second object of the present application is to provide a news item generating apparatus.
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.
In order to achieve the above object, an embodiment of a first aspect of the present application provides a method for generating a news column, including: acquiring keywords input by a user, and acquiring articles matched with the keywords according to the keywords; obtaining a screening strategy selected by the user from a strategy library; screening and sequencing the articles matched with the keywords according to the screening strategy; and generating a content list of the news column according to the sequencing result.
According to the news column generation method, after the keywords input by the user are obtained, the articles matched with the keywords are obtained according to the keywords, the screening strategies selected by the user from the strategy library are obtained, then the articles matched with the keywords are screened and sequenced according to the screening strategies, and finally the content list of the news columns is generated according to the sequencing results, so that the content list of the screened news columns can be seen immediately only by providing the keywords and selecting the needed strategies, if the effect is not ideal, the keywords and the strategies can be directly adjusted, the adjusted effect is immediately visible, the time for creating a new news column can be remarkably shortened, and further, when some hot events need to be created urgently, the online verification can be quickly realized.
In order to achieve the above object, a second embodiment of the present application provides a device for generating a news item, including: the acquisition module is used for acquiring keywords input by a user and acquiring articles matched with the keywords according to the keywords; and obtaining a screening strategy selected by the user from a strategy library; the screening module is used for screening and sequencing the articles matched with the keywords according to the screening strategy; and the generating module is used for generating a content list of the news column according to the sequencing result.
In the device for generating news items in the embodiment of the application, after the obtaining module obtains the keywords input by the user, obtaining the article matched with the keyword according to the keyword, obtaining the screening strategy selected by the user from the strategy library, then the screening module screens and sorts the articles matched with the keywords according to the screening strategy, and finally the generating module generates a content list of news columns according to the sorting result, thereby realizing that the content list of the screened news column can be seen immediately only by providing the key words and selecting the needed strategy, if the effect is not ideal, the keywords and the strategy can be directly adjusted, the adjusted effect can be immediately seen, the time required for creating a new news column can be obviously reduced, and further, when some hot spot events occur and hot spot columns need to be created urgently, the online verification can be quickly realized.
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 foregoing 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 generating news items of the present application;
FIG. 2 is a flow chart of another embodiment of a method for news section generation of the present application;
FIG. 3 is a flow chart of yet another embodiment of a method for news section generation of the present application;
FIG. 4 is a schematic diagram of a policy repository in the news item generation method of the present application;
FIG. 5 is a schematic structural diagram of an embodiment of a news item generating apparatus according to the present application;
FIG. 6 is a schematic structural diagram of an embodiment of a computer apparatus according to the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function 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 generating a news item in the present application, and as shown in fig. 1, the method for generating a news item may include:
And 102, obtaining the screening strategy selected by the user from the strategy library.
And 103, screening and sequencing the articles matched with the keywords according to the screening strategy.
And 104, generating a content list of the news items according to the sequencing result.
In this embodiment, the user is a channel owner, that is, a person responsible for creating a news bulletin, and in the related art, a main problem is that a policy defined manually by the channel owner needs to be developed by a special developer, and such a process is time-consuming and labor-consuming. In the embodiment, the strategies possibly used for article screening are sorted and summarized to generate a strategy library to support automatic analysis of various strategies, so that a channel leader can immediately see a content list of screened news columns only by inputting the keywords and selecting the required screening strategies from the strategy library, and if the effect is not ideal, the keywords and the screening strategies can be directly adjusted, and the adjusted effect is immediately visible.
According to the news column generation method, after keywords input by a user are obtained, articles matched with the keywords are obtained according to the keywords, a screening strategy selected by the user from a strategy library is obtained, then the articles matched with the keywords are screened and sequenced according to the screening strategy, and finally a content list of the news column is generated according to a sequencing result, so that the content list of the screened news column can be seen immediately only by providing the keywords and selecting the required screening strategy, if the effect is not ideal, the keywords and the screening strategy can be directly adjusted, the adjusted effect is immediately visible, the time required for creating a new news column can be remarkably shortened, and further, when some hot events occur and the hot columns need to be created urgently, the online verification can be quickly realized.
Fig. 2 is a flowchart of another embodiment of a method for generating a news item in the present application, in this embodiment, the filtering policy in the embodiment shown in fig. 1 in the present application includes a weighting policy, as shown in fig. 2, in the embodiment shown in fig. 1 in the present application, step 103 may include:
And step 202, sorting the articles which accord with the weighting strategy according to the weighting scores.
Specifically, the articles may obtain a corresponding basic score through an auditing and scoring mechanism on the data stream, and in this embodiment, the basic score of the article that meets the weighting policy is weighted and calculated to obtain the weighted score of the article that meets the weighting policy.
Then, the articles which accord with the weighting strategy are sorted according to the weighting scores.
In an implementation manner of this embodiment, the weighting policy includes content quality; thus, step 201 may be: acquiring articles with content quality greater than or equal to a preset threshold value from the articles matched with the keywords; and calculating the product of the basic score of the obtained article and the weight corresponding to the content quality dimension as the weighted score of the obtained article.
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 this embodiment, the article may obtain a corresponding content quality score through an auditing scoring mechanism on the data stream, where the content quality greater than or equal to the predetermined threshold may be that the content quality score of the article is greater than or equal to the predetermined threshold.
In the weighting strategy, a weight corresponding to the content quality dimension is set, and for the article with the content quality being greater than or equal to a predetermined threshold value, the product of the basic score of the article and the weight corresponding to the content quality dimension is calculated as the weighted score of the article.
In another implementation manner of this embodiment, the weighting policy may include a keyword; in this case, step 201 may be: acquiring an article comprising a specified keyword from the articles matched with the keyword; and calculating the product of the basic score of the obtained article and the weight corresponding to the keyword dimension as the weighted score of the obtained article.
Specifically, the user may specify at least one keyword among the input keywords, and set a weight corresponding to a keyword dimension in the weighting policy, so that if the article includes the specified keyword, a product of a basic score of the article and the weight corresponding to the keyword dimension is calculated as a weighted score of the article.
In yet another implementation manner of this embodiment, the weighting policy includes an aging; in this case, step 201 may be: acquiring articles with the release time within a set time range from the articles matched with the keywords; and calculating the product of the basic score of the obtained article and the weight corresponding to the aging dimension as the weighted score of the obtained article.
News columns are created, and news has a high requirement on timeliness, so that timeliness is required for the release time of an article. In the weighting strategy, the weight corresponding to the timeliness dimension can be set, the article with the release time in the set timeliness range is obtained, and then the product of the basic score of the obtained article and the weight corresponding to the timeliness dimension is calculated and used as the weighting score of the obtained article.
In yet another implementation manner of this embodiment, the weighting policy includes a region; step 201 may then be: acquiring an article matching the place of occurrence of the described event and the place of the browser from the article matching the keywords; and calculating the product of the basic score of the obtained article and the weight corresponding to the region dimension as the weighted score of the obtained article.
Specifically, the matching of the place of occurrence of the event described in the article with the location of the viewer may be: the place of occurrence of the event described in the article is the same as the location of the browser, or the place of occurrence of the event described in the article is different from the location of the browser, but the distance is within a set distance range. The browser refers to a user browsing news items, and the location of the browser can be determined through a terminal used by the browser.
And setting a weight corresponding to the region dimension in the weighting strategy, and calculating the product of the basic score of the article and the weight corresponding to the region dimension as the weighted score of the article for the article of which the occurrence place of the described event is matched with the place of the browser.
In yet another implementation manner of this embodiment, the weighting policy includes a picture; in this case, step 201 may be: acquiring an article comprising a picture from the article matched with the keyword; and calculating the product of the basic score of the obtained article and the weight corresponding to the dimension of the picture as the weighted score of the obtained article.
Specifically, a weight corresponding to a picture dimension in the weighting policy may be set, and for an article including a picture, a product of a basic score of the article and the weight corresponding to the picture dimension may be calculated as a weighted score of the article.
The weighting strategies may be used alone or in combination. When the articles are used in combination, the product of the weights corresponding to the weighting strategies used in combination needs to be calculated, and then the product is multiplied by the basic score of the article which accords with the weighting strategy used in combination to serve as the weighting score. For example, the weighting policy may include content quality, specified keywords, and pictures, and then the content quality, including the specified keywords and the pictures, may be obtained from the articles matching the keywords, where the content quality is greater than or equal to a predetermined threshold value; and calculating the product of the weight corresponding to the content dimension, the weight corresponding to the keyword dimension and the weight corresponding to the picture dimension, and multiplying the product by the basic score of the obtained article to obtain the weighted score of the obtained article.
The embodiment can realize the weighted sorting of the articles meeting the weighting strategy according to the selected weighting strategy, so that the articles meeting the weighting strategy have higher possibility to appear in the finally created news column.
Fig. 3 is a flowchart of a further embodiment of the method for generating a news item in the present application, in this embodiment, the filtering policy in the embodiment shown in fig. 1 in the present application includes a filtering policy, as shown in fig. 3, in the embodiment shown in fig. 1 in the present application, step 103 may include:
In an implementation manner of this embodiment, the filtering policy includes content quality; in this case, step 301 may be: acquiring articles with content quality smaller than a preset threshold value from the articles matched with the keywords; and deleting the acquired articles from the articles matched with the keywords.
In this embodiment, the article may obtain a corresponding content quality score through an audit scoring mechanism on the data stream, where the content quality being less than the predetermined threshold may be that the content quality score of the article is less than the predetermined threshold.
When the filtering strategy comprises the content quality, the articles with the content quality smaller than the preset threshold value are deleted.
In another implementation manner of this embodiment, the filtering policy includes aging; step 301 may then be: acquiring articles of which the release time is not within a set time range from the articles matched with the keywords; and deleting the acquired articles from the articles matched with the keywords.
News columns are created, and news has a high requirement on timeliness, so that timeliness is required for the release time of an article. When the filtering strategy comprises the aging, deleting the articles of which the release time is not in the set aging range.
In yet another implementation manner of this embodiment, the filtering policy includes a region; in this case, step 301 may be: in the articles matched with the keywords, acquiring the articles of which the occurrence places of the described events are not matched with the places of the browsers; and deleting the acquired articles from the articles matched with the keywords.
Specifically, the place of occurrence of the described event not matching the location of the viewer may be: the place of occurrence of the event described in the article is different from the place of the viewer, and the distance is not within the set distance range. When the filtering strategy comprises a region, the article of which the occurrence place of the described event does not match with the place of the browser is deleted.
In yet another implementation manner of this embodiment, the filtering policy includes user preferences; in this case, step 301 may be: acquiring articles of which the interest points are not matched with the preference of a browser from the articles matched with the keywords; and deleting the acquired articles from the articles matched with the keywords.
Specifically, the mismatch between the interest point and the preference of the browsing user may be: the points of interest of the article do not match the points of interest in the user model of the browsing user. And when the filtering strategy comprises user preference, deleting the articles of which the interest points are not matched with the preference of the browsing user.
In yet another implementation manner of this embodiment, the filtering policy includes a picture; in this case, step 301 may be: acquiring an article not including a picture from the articles matched with the keywords; and deleting the acquired articles from the articles matched with the keywords.
When the filtering strategy comprises pictures, deleting the articles which do not comprise the pictures.
Also, the above filtering strategies may be used singly or in combination. For example, the filtering policy may include content quality, age, and pictures, and then articles with content quality less than a predetermined threshold, articles with publication time not within a set age range, and articles without pictures may be respectively obtained from the articles matched with the keywords, and then the obtained articles are deleted, so that the articles are screened from different dimensions.
The embodiment can realize screening of the articles matched with the keywords according to the selected filtering strategy and delete the articles meeting the filtering strategy.
In the embodiment of the present application, reference may be made to fig. 4 for a main configuration of the policy library, where fig. 4 is a schematic diagram of the policy library in the news item generation method of the present application, and the policy library mainly includes two parts of content, a weighting policy and a filtering policy. The weighting strategy judges the articles according to the content quality, keywords, timeliness, regions and/or the existence of pictures, the priority of the articles conforming to the weighting strategy is improved, and the articles with high priority have higher possibility to appear in the finally created news columns. The filtering strategy can remove the articles expected to be removed according to the conditions of content quality, timeliness, regions, user preference and/or the existence of pictures and the like.
For the articles which do not accord with the weighting strategy and the filtering strategy in the articles matched with the keywords, the articles which do not accord with the weighting strategy and the filtering strategy can be sorted according to the basic scores after the articles which accord with the weighting strategy are sorted and after the article sequence which accords with the weighting strategy.
Fig. 5 is a schematic structural diagram of an embodiment of a device for generating a news item in the present application, where the device for generating a news item in the present application may be used as a news item generation engine to implement the method for generating a news item provided in the present application. As shown in fig. 5, the apparatus for generating a news item may include: an obtaining module 51, a screening module 52 and a generating module 53;
the obtaining module 51 is configured to obtain a keyword input by a user, and obtain an article matching the keyword according to the keyword; and obtaining the screening strategy selected by the user from the strategy library;
a screening module 52, configured to screen and sort the articles matching the keyword according to the screening policy;
and a generating module 53, configured to generate a content list of the news item according to the sorting result.
In this embodiment, the user is a channel owner, that is, a person responsible for creating a news bulletin, and in the related art, a main problem is that a policy defined manually by the channel owner needs to be developed by a special developer, and such a process is time-consuming and labor-consuming. In the embodiment, the strategies possibly used for article screening are sorted and summarized to generate a strategy library to support automatic analysis of various strategies, so that a channel leader can immediately see a content list of screened news columns only by inputting the keywords and selecting the required screening strategies from the strategy library, and if the effect is not ideal, the keywords and the screening strategies can be directly adjusted, and the adjusted effect is immediately visible.
In this embodiment, the screening module 52 is specifically configured to, when the screening policy includes a weighting policy, perform weighting calculation on the basic scores of articles that meet the weighting policy in the articles that match the keyword, to obtain the weighting scores of the articles that meet the weighting policy, and rank the articles that meet the weighting policy according to the weighting scores.
Specifically, the articles may obtain a corresponding basic score through an auditing and scoring mechanism on the data stream, in this embodiment, the screening module 52 performs weighting calculation on the basic scores of the articles that meet the weighting policy to obtain the weighted scores of the articles that meet the weighting policy, and then sorts the articles that meet the weighting policy according to the weighted scores.
In an implementation manner of this embodiment, the screening module 52 is specifically configured to, when the weighting policy includes content quality, acquire an article with content quality greater than or equal to a predetermined threshold from articles matching the keyword, and calculate a product of a basic score of the acquired article and a weight corresponding to a content quality dimension as a weighting score of the acquired article.
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 this embodiment, the article may pass through an audit scoring mechanism on the data stream to obtain a corresponding content quality score, where the content quality greater than or equal to the predetermined threshold may be that the content quality score of the article is greater than or equal to the predetermined threshold.
In the weighting policy, a weight corresponding to the content quality dimension is set, and for an article whose content quality is greater than or equal to a predetermined threshold, the filtering module 52 calculates a product of a base score of the article and the weight corresponding to the content quality dimension as a weighted score of the article.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the weighting policy includes a keyword, obtain an article including a specified keyword from articles matched with the keyword; and calculating the product of the basic score of the obtained article and the weight corresponding to the keyword dimension to be used as the weighted score of the obtained article.
Specifically, the user may specify at least one keyword from the input keywords and set a weight corresponding to the keyword dimension in the weighting policy, so that if the article includes the specified keyword, the filtering module 52 calculates a product of the basic score of the article and the weight corresponding to the keyword dimension as the weighting score of the article.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the weighting policy includes an age, obtain, from the articles matched with the keyword, an article whose release time is within a set age range; and calculating the product of the basic score of the obtained article and the weight corresponding to the aging dimension as the weighted score of the obtained article.
News is created as news items, which have a high requirement on timeliness, and thus timeliness is required for the release time of an article. In the weighting policy, a weight corresponding to the timeliness dimension may be set, an article whose release time is within the set timeliness range is acquired, and then the screening module 52 calculates a product of a basic score of the acquired article and the weight corresponding to the timeliness dimension as a weighting score of the acquired article.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the weighting policy includes a region, obtain, from the articles matched with the keyword, an article in which an occurrence location of the described event matches with a location of the browser; and calculating the product of the basic score of the obtained article and the weight corresponding to the region dimension to be used as the weighted score of the obtained article.
Specifically, the matching of the place of occurrence of the event described in the article with the location of the viewer may be: the place of occurrence of the event described in the article is the same as the location of the browser, or the place of occurrence of the event described in the article is different from the location of the browser, but the distance is within a set distance range. The browser refers to a user browsing news items, and the location of the browser can be determined through a terminal used by the browser.
In the weighting strategy, the weight corresponding to the region dimension is set, and then for the article of which the location of the described event matches with the location of the viewer, the screening module 52 calculates the product of the basic score of the article and the weight corresponding to the region dimension as the weighted score of the article.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the weighting policy includes a picture, obtain an article including the picture from articles matched with the keyword; and calculating the product of the basic score of the obtained article and the weight corresponding to the dimension of the picture as the weighted score of the obtained article.
Specifically, a weight corresponding to a picture dimension in the weighting policy may be set, and for an article including a picture, the filtering module 52 calculates a product of a base score of the article and the weight corresponding to the picture dimension as a weighted score of the article.
The weighting strategies may be used alone or in combination. When the articles are used in combination, the product of the weights corresponding to the weighting strategies used in combination needs to be calculated, and then the product is multiplied by the basic score of the article which meets the weighting strategy used in combination to serve as the weighting score. For example, the weighting policy may include content quality, a specified keyword, and a picture, and then the content quality, including the specified keyword and the article including the picture, may be obtained from the article matching with the keyword, where the content quality is greater than or equal to a predetermined threshold; the screening module 52 calculates the product of the weight corresponding to the content dimension, the weight corresponding to the keyword dimension, and the weight corresponding to the picture dimension, and multiplies the product by the basic score of the obtained article to serve as the weighted score of the obtained article.
The screening module 52 may perform a weighted ranking of the articles that meet the weighting policy according to the selected weighting policy, so that the articles that meet the weighting policy have a higher probability of appearing in the finally created news section.
On the other hand, the filtering module 52 is specifically configured to delete the articles that meet the filtering policy from the articles that match the keyword when the filtering policy includes the filtering policy.
In an implementation manner of this embodiment, the screening module 52 is specifically configured to, when the filtering policy includes content quality, obtain, from the articles matched with the keyword, an article whose content quality is smaller than a predetermined threshold; and deleting the acquired articles from the articles matched with the keywords.
In this embodiment, the article may obtain a corresponding content quality score through an audit scoring mechanism on the data stream, where the content quality being less than the predetermined threshold may be that the content quality score of the article is less than the predetermined threshold.
When the filtering policy includes content quality, the filtering module 52 deletes articles whose content quality is less than a predetermined threshold.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the filtering policy includes an age, acquire an article whose release time is not within a set age range from articles that are matched with the keyword; and deleting the acquired articles from the articles matched with the keywords.
News is created as news items, which have a high requirement on timeliness, and thus timeliness is required for the release time of an article. When the filtering policy includes the aging, the filtering module 52 deletes the articles whose release time is not within the set aging range.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the filtering policy includes a region, obtain, from the articles matched with the keyword, an article in which an occurrence location of the described event is not matched with a location of the browser; and deleting the acquired articles from the articles matched with the keywords.
Specifically, the place of occurrence of the described event not matching the viewer's place may be: the place of occurrence of the event described in the article is different from the place of the viewer, and the distance is not within the set distance range. When the filtering policy includes a region, the filtering module 52 deletes the article whose place of occurrence of the described event does not match the place of the viewer.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the filtering policy includes a user preference, obtain an article whose interest point does not match with the preference of the browser from the articles matching with the keyword; and deleting the acquired articles from the articles matched with the keywords.
Specifically, the mismatch between the interest point and the preference of the browsing user may be: the points of interest of the article do not match the points of interest in the user model of the browsing user. When the filtering policy includes the user preference, the filtering module 52 deletes the articles whose interest points do not match the preference of the browsing user.
In another implementation manner of this embodiment, the screening module 52 is specifically configured to, when the filtering policy includes a picture, obtain an article that does not include the picture from articles that are matched with the keyword; and deleting the acquired articles from the articles matched with the keywords.
When the filtering policy includes pictures, the filtering module 52 deletes the articles that do not include pictures.
Also, the above filtering strategies may be used singly or in combination. For example, the filtering policy may include content quality, age, and pictures, and then articles with content quality less than a predetermined threshold, articles with publication time not within a set age range, and articles without pictures may be respectively obtained from the articles matched with the keywords, and then the filtering module 52 deletes the obtained articles, thereby filtering the articles from different dimensions.
The screening module 52 may screen the articles matching the keyword according to the selected filtering policy, and delete the articles meeting the filtering policy.
In the embodiment of the present application, reference may be made to fig. 4 for a main composition of a policy library, where the policy library mainly includes two parts of content, a weighting policy and a filtering policy. The weighting strategy judges the articles according to the content quality, keywords, timeliness, regions and/or the existence of pictures, the priority of the articles conforming to the weighting strategy is improved, and the articles with high priority have higher possibility to appear in the finally created news columns. The filtering strategy can remove the articles expected to be removed according to the conditions of content quality, timeliness, regions, user preference and/or the existence of pictures and the like.
For the articles that do not meet the weighting policy and the filtering policy among the articles matching the keyword, the filtering module 52 may rank the articles that do not meet the weighting policy and the filtering policy according to the basic score after ranking the articles that do meet the weighting policy and after ranking the article sequences that do meet the weighting policy.
In the device for generating news items, after the obtaining module 51 obtains the keywords input by the user, the articles matched with the keywords are obtained according to the keywords, the screening strategy selected by the user from the strategy library is obtained, then the screening module 52 screens and sorts the articles matched with the keywords according to the screening strategy, and finally the generating module 53 generates the content list of the news items according to the sorting result, so that the content list of the screened news items can be immediately seen only by providing the keywords and selecting the required screening strategy, if the effect is not ideal, the keywords and the screening strategy can be directly adjusted, the adjusted effect is immediately visible, the time required for creating a new news item can be remarkably reduced, and further, when some hot events need to urgently create the hot items, and the quick verification online is realized.
Fig. 6 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 generating a news item according to the embodiment of the present application may be implemented.
The computer device may be a server, for example: the present embodiment does not limit the specific form of the computer device described above, and the server includes a news item generating engine.
FIG. 6 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. 6 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present application.
As shown in FIG. 6, computer device 12 is 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.
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. 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. 6, and commonly referred to as a "hard drive"). Although not shown in FIG. 6, a magnetic 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 perform the functions and/or methodologies of the embodiments described herein.
The processing unit 16 executes various functional applications and data processing by running a program stored in the system memory 28, for example, to implement the method for generating a news item provided in the 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, where the computer program, when executed by a processor, can implement the method for generating news items provided in the embodiment of the present application.
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 to implicitly indicate 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 portion (electronic device) having one or more wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM) or a 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 by the method for 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 when the program is executed, the program 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 (14)
1. A method for generating a news item, comprising:
obtaining keywords input by a user, and obtaining an article matched with the keywords according to the keywords, wherein the user is a person responsible for creating a news column;
obtaining a screening strategy selected by the user from a strategy library, wherein the screening strategy comprises the following steps: the method comprises the steps of weighting strategies and filtering strategies, wherein the weighting strategies judge articles according to content quality, keywords, timeliness, regions and/or the existence of pictures; the filtering strategy is used for removing articles expected to be removed according to the content quality, the timeliness, the regions, the user preference and/or the existence of pictures;
screening and sequencing the articles matched with the keywords according to the screening strategy;
generating a content list of news columns according to the sequencing result, wherein the content list is displayed in the news columns;
Wherein the method further comprises:
the user adjusts the keywords and the screening strategy, and a new content list is generated according to the adjusted keywords and the screening strategy;
the screening and sequencing of the articles matched with the keywords according to the screening strategy comprises:
deleting articles which accord with the filtering strategy from the articles which are matched with the keywords; carrying out weighted calculation on the basic scores of the articles which accord with the weighted strategy in the articles matched with the keywords to obtain the weighted scores of the articles which accord with the weighted strategy; sorting the articles according with the weighting strategy according to the weighting scores;
the weighting calculation of the basic scores of the articles which are matched with the keywords and accord with the weighting strategy to obtain the weighting scores of the articles which are matched with the weighting strategy comprises the following steps: acquiring articles with content quality greater than or equal to a preset threshold value from the articles matched with the keywords; calculating the product of the basic score of the obtained article and the weight corresponding to the content quality dimension as the weighted score of the obtained article; and/or acquiring an article comprising a specified keyword from the articles matched with the keyword; and/or when the weighting strategy comprises the aging, acquiring an article with the release time within a set aging range from the articles matched with the keywords; calculating the product of the basic score of the obtained article and the weight corresponding to the keyword dimension as the weighted score of the obtained article; and/or acquiring an article matching the place of occurrence of the described event and the place of the browser from the article matching the keyword; calculating the product of the basic score of the obtained article and the weight corresponding to the region dimension as the weighted score of the obtained article; and/or acquiring an article comprising a picture from the article matched with the keyword; and calculating the product of the basic score of the obtained article and the weight corresponding to the dimension of the picture as the weighted score of the obtained article.
2. The method of claim 1, wherein the filtering policy comprises content quality;
the deleting of the articles meeting the filtering strategy from the articles matched with the keywords comprises:
acquiring articles with content quality smaller than a preset threshold value from the articles matched with the keywords;
and deleting the acquired articles from the articles matched with the keywords.
3. The method of claim 1, wherein the filtering strategy comprises aging;
the deleting of the articles meeting the filtering policy from the articles matching the keyword comprises:
acquiring articles of which the release time is not within a set time limit range from the articles matched with the keywords;
and deleting the acquired articles from the articles matched with the keywords.
4. The method of claim 1, wherein the filtering policy comprises a region;
the deleting of the articles meeting the filtering strategy from the articles matched with the keywords comprises:
in the articles matched with the keywords, acquiring the articles of which the occurrence places of the described events are not matched with the places of the browsers;
and deleting the acquired articles from the articles matched with the keywords.
5. The method of claim 1, wherein the filtering policy comprises user preferences;
the deleting of the articles meeting the filtering strategy from the articles matched with the keywords comprises:
acquiring articles of which the interest points are not matched with the preference of a browser from the articles matched with the keywords;
and deleting the acquired articles from the articles matched with the keywords.
6. The method of claim 1, wherein the filtering policy comprises a picture;
the deleting of the articles meeting the filtering strategy from the articles matched with the keywords comprises:
acquiring an article not including a picture from the articles matched with the keywords;
and deleting the acquired articles from the articles matched with the keywords.
7. A news item generating apparatus, comprising:
the acquisition module is used for acquiring keywords input by a user and acquiring articles matched with the keywords according to the keywords; obtaining a screening strategy selected by the user from a strategy library, wherein the user is a person responsible for creating a news column;
the screening module is used for screening and sequencing the articles matched with the keywords according to the screening strategy, wherein the screening strategy comprises the following steps: the method comprises the steps of weighting strategies and filtering strategies, wherein the weighting strategies judge articles according to content quality, keywords, timeliness, regions and/or the existence of pictures; the filtering strategy is used for removing articles expected to be removed according to the content quality, the timeliness, the regions, the user preference and/or the existence of pictures;
The generating module is used for generating a content list of the news column according to the sequencing result, and the content list is displayed in the news column;
the adjustment module is used for adjusting the keywords and the screening strategy by the user and generating a new content list according to the adjusted keywords and the screening strategy;
the screening module is specifically configured to delete articles that meet the filtering policy from the articles that match the keyword, perform weighted calculation on the basic scores of the articles that meet the weighting policy in the articles that match the keyword to obtain weighted scores of the articles that meet the weighting policy, and sort the articles that meet the weighting policy according to the weighted scores;
the screening module is specifically configured to, when the weighting policy includes content quality, acquire an article whose content quality is greater than or equal to a predetermined threshold value from articles matched with the keyword, and calculate a product of a basic score of the acquired article and a weight corresponding to a content quality dimension as a weighting score of the acquired article; and/or when the weighting strategy comprises keywords, acquiring an article comprising specified keywords from the articles matched with the keywords; calculating the product of the basic score of the obtained article and the weight corresponding to the keyword dimension as the weighted score of the obtained article; and/or when the weighting strategy comprises the aging, acquiring an article with the release time within a set aging range from the articles matched with the keywords; calculating the product of the basic score of the obtained article and the weight corresponding to the timeliness dimension to be used as the weighted score of the obtained article; and/or when the weighting strategy comprises a region, acquiring an article matching the place of occurrence of the described event and the location of the browser from the article matching the keyword; calculating the product of the basic score of the obtained article and the weight corresponding to the region dimension as the weighted score of the obtained article; and/or when the weighting strategy comprises pictures, acquiring the articles comprising the pictures from the articles matched with the keywords; and calculating the product of the basic score of the obtained article and the weight corresponding to the dimension of the picture as the weighted score of the obtained article.
8. The apparatus of claim 7,
the screening module is specifically configured to, when the filtering policy includes content quality, acquire an article whose content quality is less than a predetermined threshold value from articles matched with the keyword; and deleting the acquired articles from the articles matched with the keywords.
9. The apparatus of claim 7,
the screening module is specifically used for acquiring articles of which the release time is not within a set aging range from the articles matched with the keywords when the filtering strategy comprises aging; and deleting the acquired articles from the articles matched with the keywords.
10. The apparatus of claim 7,
the screening module is specifically configured to, when the filtering policy includes a region, acquire an article in which an occurrence location of the described event does not match a location of the viewer from the article matching the keyword; and deleting the acquired articles from the articles matched with the keywords.
11. The apparatus of claim 7,
the filtering module is specifically used for acquiring articles of which the interest points are not matched with the preference of the browser from the articles matched with the keywords when the filtering strategy comprises the preference of the user; and deleting the acquired articles from the articles matched with the keywords.
12. The apparatus of claim 7,
the screening module is specifically configured to, when the filtering policy includes a picture, acquire an article that does not include the picture from the articles that are matched with the keyword; and deleting the acquired articles from the articles matched with the keywords.
13. 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 1-6 when executing the computer program.
14. 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 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810145847.7A CN108334626B (en) | 2018-02-12 | 2018-02-12 | News column generation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810145847.7A CN108334626B (en) | 2018-02-12 | 2018-02-12 | News column generation method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108334626A CN108334626A (en) | 2018-07-27 |
| CN108334626B true CN108334626B (en) | 2022-06-10 |
Family
ID=62929241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810145847.7A Active CN108334626B (en) | 2018-02-12 | 2018-02-12 | News column generation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108334626B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635082B (en) * | 2018-11-26 | 2024-08-02 | 平安科技（深圳）有限公司 | Policy influence analysis method, device, computer equipment and storage medium |
| CN111737580B (en) * | 2020-06-30 | 2021-01-29 | 深圳市中电网络技术有限公司 | Information verification method and device, computer equipment and readable storage medium |
| CN111859887A (en) * | 2020-07-21 | 2020-10-30 | 北京北斗天巡科技有限公司 | Scientific and technological news automatic writing system based on deep learning |
| CN113221010B (en) * | 2021-05-26 | 2023-06-02 | 支付宝(杭州)信息技术有限公司 | Event propagation state display method and device and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8849809B1 (en) * | 2010-03-11 | 2014-09-30 | Google Inc. | Automated identification of news events |
| CN105404699A (en) * | 2015-12-29 | 2016-03-16 | 广州神马移动信息科技有限公司 | Method, device and server for searching articles of finance and economics |
| CN106776741A (en) * | 2016-11-18 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of searching method and device |
| CN107025312A (en) * | 2017-05-19 | 2017-08-08 | 北京金山安全软件有限公司 | Information providing method and device based on video content |
| CN107077509A (en) * | 2016-11-25 | 2017-08-18 | 深圳前海达闼云端智能科技有限公司 | A kind of method, device and equipment for improving viewing experience |
| CN107436922A (en) * | 2017-07-05 | 2017-12-05 | 北京百度网讯科技有限公司 | Text label generation method and device |
| CN107679038A (en) * | 2017-10-16 | 2018-02-09 | 北京神州泰岳软件股份有限公司 | The abstracting method and device of a kind of text fragment |
-
2018
- 2018-02-12 CN CN201810145847.7A patent/CN108334626B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8849809B1 (en) * | 2010-03-11 | 2014-09-30 | Google Inc. | Automated identification of news events |
| CN105404699A (en) * | 2015-12-29 | 2016-03-16 | 广州神马移动信息科技有限公司 | Method, device and server for searching articles of finance and economics |
| CN106776741A (en) * | 2016-11-18 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of searching method and device |
| CN107077509A (en) * | 2016-11-25 | 2017-08-18 | 深圳前海达闼云端智能科技有限公司 | A kind of method, device and equipment for improving viewing experience |
| CN107025312A (en) * | 2017-05-19 | 2017-08-08 | 北京金山安全软件有限公司 | Information providing method and device based on video content |
| CN107436922A (en) * | 2017-07-05 | 2017-12-05 | 北京百度网讯科技有限公司 | Text label generation method and device |
| CN107679038A (en) * | 2017-10-16 | 2018-02-09 | 北京神州泰岳软件股份有限公司 | The abstracting method and device of a kind of text fragment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108334626A (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108334626B (en) | News column generation method and device and computer equipment | |
| CN108197198B (en) | Interest point searching method, device, equipment and medium | |
| CN105528392B (en) | Classification label ordering method and device | |
| JP5353148B2 (en) | Image information retrieving apparatus, image information retrieving method and computer program therefor | |
| CN109522950B (en) | Image scoring model training method and device and image scoring method and device | |
| CN107633023B (en) | Image duplicate removal method and device | |
| CN109753601B (en) | Method and device for determining click rate of recommended information and electronic equipment | |
| US20150096041A1 (en) | Identifying and ranking pirated media content | |
| CN109977300A (en) | Enterprise's public sentiment acquisition methods, device, terminal and computer storage medium | |
| CN111125574A (en) | Method and apparatus for generating information | |
| CN108377417B (en) | Video reviewing method, device, computer equipment and storage medium | |
| CN111783812B (en) | Forbidden image recognition method, forbidden image recognition device and computer readable storage medium | |
| CN108804452B (en) | Multimedia resource cover display method and device | |
| CN113076416A (en) | Information heat evaluation method and device and electronic equipment | |
| CN107766316B (en) | Evaluation data analysis method, device and system | |
| CN108345700B (en) | Article representative picture selection method and device and computer equipment | |
| JP2020042771A (en) | Data analysis method and data analysis system | |
| CN109949090B (en) | Client recommendation method and device, electronic equipment and medium | |
| CN105912549A (en) | Content recommendation method and device thereof | |
| CN111263241A (en) | Method, device and equipment for generating media data and storage medium | |
| US11341138B2 (en) | Method and system for query performance prediction | |
| CN111797258A (en) | Image pushing method, system, equipment and storage medium based on aesthetic evaluation | |
| CN102236652B (en) | Method and device for classifying information | |
| JP2020123321A (en) | Method and apparatus for search processing based on clipboard data | |
| CN109034085B (en) | Method and apparatus for generating information |
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 |