CN111460289B - News information pushing method and device - Google Patents
News information pushing method and device Download PDFInfo
- Publication number
- CN111460289B CN111460289B CN202010228073.1A CN202010228073A CN111460289B CN 111460289 B CN111460289 B CN 111460289B CN 202010228073 A CN202010228073 A CN 202010228073A CN 111460289 B CN111460289 B CN 111460289B
- Authority
- CN
- China
- Prior art keywords
- event
- news information
- cluster
- news
- name
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 230000015654 memory Effects 0.000 claims description 19
- 238000010586 diagram Methods 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 206010035664 Pneumonia Diseases 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 208000015181 infectious disease Diseases 0.000 description 2
- 230000002458 infectious effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000009960 carding Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application discloses a method and a device for pushing news information, and relates to the field of knowledge maps. The specific implementation scheme is as follows: acquiring a news headline of current news information, and extracting event names in the news headline according to a preset extraction strategy; if at least one event name is extracted, matching each event name in the at least one event name with a plurality of event clusters in a preset event library, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event; judging whether a target event cluster to which news information belongs exists in a preset event library according to the matching results of all event names; if the target event cluster exists, combining the news information into the target event cluster so as to provide the push service of the news information according to the target event cluster. Therefore, the news information is combed by taking the event as granularity, so that the news information service with high correlation can be conveniently pushed to the user.
Description
Technical Field
The application relates to the technical field of knowledge graphs in the technical field of computers, in particular to a method and a device for pushing news information.
Background
With the rapid popularization of the internet, network information has been increasing explosively, and everyone needs to spend a great deal of effort to screen the information. When a user wants to know what happens recently or pay attention to a person or an organization, important information needs to be selected from a large number of news information which is not filtered and finished.
In the related art, in order to improve the correlation between news information and a user's search request, the user's search request is keyword-matched with the content of the news information, and the news information is ordered according to the matching result, however, in this way, news information containing the same keyword but mainly described events which are not events of interest to the user cannot be identified, so that the news information pushed to the user still contains various events, and the user still needs to manually select the news information of interest.
Disclosure of Invention
The application provides a method and a device for pushing news information. The news information is combed by taking the event as granularity, so that the news information service with high correlation is conveniently pushed to the user.
According to a first aspect, there is provided a push method of news information, including: acquiring a news headline of current news information, and extracting event names in the news headline according to a preset extraction strategy; if at least one event name is extracted, matching each event name in the at least one event name with a plurality of event clusters in a preset event library, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event; judging whether a target event cluster to which the news information belongs exists in the preset event library according to the matching results of all event names; if the target event cluster exists, combining the news information into the target event cluster so as to provide the push service of the news information according to the target event cluster.
Optionally, the extracting the event name in the news headline according to a preset extraction policy includes: and inputting the news headline into a preset event name extraction model, wherein the event name extraction model learns in advance to obtain the corresponding relation between the news headline and the event name.
Optionally, if at least one event name is extracted, matching each event name in the at least one event name with a plurality of event clusters in a preset event library, including: acquiring a theme event name of each event cluster in the plurality of event clusters; and carrying out semantic matching on each event name in the at least one event name and the subject event name of each event cluster to obtain semantic similarity.
Optionally, after the combining the news information into the target event cluster if the target event cluster exists, the method further includes: acquiring a news reading request and determining a reading event corresponding to the news reading request; judging whether the reading event is matched with the event corresponding to the target event cluster; if the news information is matched with the target event cluster, determining the release time of each piece of news information in the target event cluster; selecting a preset number of recommended news from the target event cluster according to the release time and the sequence from the near to the far, and displaying the recommended news according to a preset display strategy.
Optionally, after the combining the news information into the target event cluster if the target event cluster exists, the method further includes: counting the quantity of news information contained in the target event cluster; judging whether the number is larger than a preset threshold value, if so, determining a hot event name according to the event name of each news information in the target event cluster; pushing the hot events according to the hot event names.
Optionally, the merging the news information into the target event cluster includes: storing the corresponding relation between the at least one event name and the news information in the target event cluster.
Optionally, after the determining whether the target event cluster to which the news information belongs exists in the preset event library, the method further includes: and if the target event cluster does not exist, an event cluster corresponding to the news information is newly added.
According to a second aspect, there is provided a push apparatus of news information, including: the extraction module is used for acquiring the news headline of the current news information and extracting event names in the news headline according to a preset extraction strategy; the matching module is used for matching each event name in the at least one event name with a plurality of event clusters in a preset event library when the at least one event name is extracted, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event; the first judging module is used for judging whether a target event cluster to which the news information belongs exists in the preset event library according to the matching results of all event names; and the merging module is used for merging the news information into the target event cluster when the target event cluster exists, so as to provide the push service of the news information according to the target event cluster.
Optionally, the method further comprises: the first determining module is used for acquiring a news reading request and determining a reading event corresponding to the news reading request; the second judging module is used for judging whether the reading event is matched with the event corresponding to the target event cluster; the second determining module is used for determining the release time of each piece of news information in the target event cluster when the news information is matched with the target event cluster; and the display module is used for selecting a preset number of recommended news in the target event cluster according to the release time from the near to the far and displaying the recommended news according to a preset display strategy.
Optionally, the method further comprises: the statistics module is used for counting the quantity of news information contained in the target event cluster; the third determining module is used for judging whether the number is larger than a preset threshold value or not, and determining a hot event name according to the event name of each news information in the target event cluster when the number is larger than the preset threshold value; and the pushing module is used for pushing the hot event according to the hot event name.
According to a third aspect, there is provided an electronic device comprising: at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for pushing news information described in the embodiment of the first aspect.
According to a fourth aspect, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the pushing method of news information described in the embodiment of the first aspect.
The technical scheme provided by the application has at least the following technical effects:
obtaining a news headline of current news information, extracting event names in the news headline according to a preset extraction strategy, matching each event name in the at least one event name with a plurality of event clusters in a preset event library if at least one event name is extracted, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event, further judging whether a target event cluster to which the news information belongs exists in the preset event library according to the matching result of all the event names, and finally merging the news information into the target event cluster when the target event cluster exists so as to provide a pushing service of the news information according to the target event cluster. Therefore, the news information is combed by taking the event as granularity, so that the news information service with high correlation can be conveniently pushed to the user.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for better understanding of the present solution and do not constitute a limitation of the present application. Wherein:
FIG. 1 is a flowchart of a method for pushing news information according to a first embodiment of the present application;
FIG. 2 is a schematic diagram of an event name extraction model training application according to a second embodiment of the present application;
FIG. 3 is a schematic view of event cluster composition according to a third embodiment of the present application;
FIG. 4 is a schematic diagram of an event classification discriminant model training application according to a fourth embodiment of the present application;
FIG. 5-1 is a schematic diagram of a target event cluster determination flow according to a fifth embodiment of the present application;
fig. 5-2 is a schematic diagram of a target event cluster determination flow according to a sixth embodiment of the present application;
FIG. 6 is a schematic view of a target event cluster structure according to a seventh embodiment of the present application;
FIG. 7 is a flowchart of a method for pushing news information according to an eighth embodiment of the present application;
FIG. 8-1 is a schematic diagram of a news information-pushing scenario according to a ninth embodiment of the present application;
FIG. 8-2 is a schematic diagram of a news information-pushing scenario according to a tenth embodiment of the present application;
FIG. 9 is a flowchart of a method for pushing news information according to an eleventh embodiment of the present application;
FIG. 10 is a schematic diagram of a news information-pushing scenario according to a twelfth embodiment of the present application;
fig. 11 is a schematic structural view of a news information-pushing device according to a thirteenth embodiment of the present application;
fig. 12 is a schematic structural view of a news information-pushing device according to a fourteenth embodiment of the present application;
fig. 13 is a schematic structural view of a news information-pushing device according to a fifteenth embodiment of the present application;
fig. 14 is a block diagram of an electronic device for implementing a method of pushing news information according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In order to solve the problem that in the related art, news information cannot be combed based on events, so that the news information pushed to a user is not really intended to be acquired by the user, and the searching experience of the user is not high, the news information method disclosed by the application is used for arranging the news information based on event granularity, and arranging a large amount of news information into different event clusters, so that push service is provided for the user in a targeted manner, and the purity of the news information pushed for the user is improved. The events in the embodiment of the application include topics described by news information, including parent events and corresponding child events, lower-level events and the like, and the events can include "health", "advertisement" and the like.
Specifically, fig. 1 is a flowchart of a method for pushing news information according to an embodiment of the present application, as shown in fig. 1, the method includes:
step 101, obtaining the news headline of the current news information, and extracting event names in the news headline according to a preset extraction strategy.
It can be appreciated that, in order to improve the efficiency of the carding, the news headlines of the current news information are obtained, for example, a headline extraction model may be trained in advance, and the headlines of the current news information may be obtained according to the headline extraction model, for example, and the news headlines may be identified according to specific parameters such as format and font of the news headlines.
Further, after the news headline is obtained, event names in the news headline are extracted according to a preset extraction strategy.
It should be noted that, in different application scenarios, the manner of extracting the event name in the news headline according to the preset extraction policy is different, and examples are as follows:
example one:
in this example, an event name extraction model is trained in advance, the event name extraction model learns in advance to obtain a correspondence between a news title and an event name, in the training process, as shown in fig. 2, a large amount of sample data is obtained in advance, each sample data includes a labeled < title, an event name > pair, and according to the labeled < title, the event name > pair is trained to generate an event name extraction model, further, in this embodiment, in order to further improve the determination efficiency of the event name, as shown in fig. 2, a plurality of candidate event names in the news title may be extracted according to a preset event name extraction policy (for example, a plurality of word segments are obtained by word segmentation of the news title, word segments such as nouns are used as candidate event names according to the part of speech of the plurality of word segments), the plurality of candidate event names are input into the event name extraction model, and whether each candidate event name is an event name is determined according to whether the probability value output by the event name extraction model is greater than a preset threshold, thereby the event name in the news title may be extracted.
Example two:
in this example, training an event name extraction neural network according to a large amount of sample data in advance, extracting the word segmentation feature of each word segmentation in a news headline, inputting the word segmentation feature of each word segmentation into the event name extraction neural network, and determining whether each word segmentation is an event name according to the output probability value of the event name extraction neural network.
Step 102, if at least one event name is extracted, matching each event name in the at least one event name with a plurality of event clusters in a preset event library, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event.
In one embodiment of the present application, if the event name cannot be extracted, the news information is sent to an artificial platform for processing, etc.
It may be understood that each generated news information is subjected to event sorting, so that, for the published historical news information, a plurality of event clusters are finally sorted according to the event to which the published historical news information belongs, wherein each event cluster in the plurality of event clusters contains a plurality of news information under the same event, each event cluster may also be provided with a topic event name, which may be manually marked, or the event name with the highest frequency may be regarded as a topic event name according to the occurrence frequency of the event name in the title containing the news information, for example, as shown in fig. 3, for a "pneumonia epidemic situation" event cluster, the event cluster contains 100 news information, and all 100 news information are used for describing a "pneumonia epidemic situation" event, wherein the topic event name of the event cluster is a "2020 pneumonia epidemic situation".
In one embodiment of the present application, if at least one event name is extracted, each event name in the at least one event name is matched with a plurality of event clusters in a preset event library, that is, whether the current news information is a brand new event or the latest news information of a historical event is determined.
It should be noted that, in different application scenarios, the manner of matching each event name in the at least one event name with a plurality of event clusters in a preset event library is different, and examples are as follows:
example one:
in this example, the subject event of each of the plurality of event clusters is obtained, each of the at least one event name is semantically matched with the subject event name of each of the event clusters, and the semantic similarity is obtained.
Example two:
in this example, as shown in fig. 4, an event classification discrimination model is obtained by training in advance according to a large number of samples, and the event classification discrimination model can determine whether the input event name and the event cluster in the corresponding event library belong to the same event according to the input event name and the subject event name of the event cluster. Therefore, in the actual execution process, the topic event names of the event clusters in the event library are retrieved, the event classification judging model matches the topic event names with the event names corresponding to the news headlines, and whether the topic event names and the event names belong to the same event is judged.
And step 103, judging whether a target event cluster to which the news information belongs exists in a preset event library according to the matching results of all event names.
Specifically, in the matching process in the above case, as shown in fig. 5-1, all event names corresponding to news headlines are simultaneously involved in matching with event clusters in an event library, so as to obtain a total matching result of all event names at one time, and an event cluster with highest probability is obtained as a target event cluster according to the matching probability in the total matching result; or, as shown in fig. 5-2, each event name may be respectively matched with an event cluster in the event library to obtain a matching result corresponding to each event name, in this embodiment, when all event clusters matched by the event names are inconsistent, the event cluster with the largest matching success number is used as the target event cluster.
Step 104, if the target event cluster exists, combining the news information into the target event cluster so as to provide the push display service of the news information according to the target event cluster.
Specifically, if the target event cluster exists, the current news information is the news information of the historical event, and at the moment, the news information is combined into the target event cluster so as to provide the pushing display service of the news information according to the target event cluster.
As a possible implementation manner, the correspondence between at least one event name and news information may be stored in the target event cluster, so as to obtain events corresponding to each news information clearly, where when at least one event name is multiple, an event name with the lowest level may also be randomly extracted from at least one event name, as an event name when the correspondence is stored, for example, when the event name includes both a parent event name and a child event name, a child event name may be stored.
As shown in fig. 6, when the target event cluster is a "pneumonia epidemic situation", the event name displaying each news information is stored in the target event cluster, and of course, different news information may be ordered according to the distribution time so as to further facilitate management, wherein, taking the example shown in fig. 6 as an example, the event name corresponding to each news information stored in the target event cluster is "infectious source", "place", "safeguard", "infectious route", or the like.
In the actual execution process, advertisement news information which does not contain an event can be filtered according to the need, after news information is obtained, whether the current news information contains the event or not is analyzed according to a pre-selected training information event discrimination model, if so, the title of the news information is input into an event name extraction model, the event name in the news title is extracted according to the event name extraction model, then the event name is input into an event classification discrimination model, the event classification discrimination model recalls the subject event name of an event cluster in an event library as a candidate event, further, whether the event name is matched with the subject event name is judged, if so, a target event cluster is determined, and the news information is classified into the target event cluster.
In one embodiment of the present application, if the target event cluster does not exist, an event cluster corresponding to the news information is newly added, for example, a subject event name serving as the newly added event cluster is extracted from the at least one event name, and the first news information in the newly added event cluster is the current news information and is fed in after the subsequent published news information.
It should be emphasized that the foregoing embodiments describe in detail how to comb the event clusters to which the news information belongs, and have an important meaning for pushing the news information after the combing is completed, and are described below in connection with two embodiments.
Embodiment one:
in this embodiment, as shown in fig. 7, after the step 104, the method further includes:
step 201, a news reading request is acquired, and a reading event corresponding to the news reading request is determined.
In practical application, a user searches news in a browser or the like, in order to provide news information with higher relevance to the user, in this embodiment, a news reading request is acquired, and a reading event corresponding to the news reading request is determined, where the extracting manner of the reading event may be an event name in the reading request, and the extracting manner of the event name may refer to the extracting manner of the event name in the foregoing embodiment, and in this embodiment, the event name may be regarded as a reading event.
Step 202, determining whether the reading event is matched with the event corresponding to the target event cluster.
As one possible implementation manner, the event name may be matched with the topic event name in the event cluster to determine whether an event corresponding to the target event cluster in which the news information is located is an event, for example, the event name of the reading request may be matched with the event name of the target event cluster, and whether the reading event is matched with the event corresponding to the target event cluster may be determined according to the matching result.
Step 203, if the news information is matched, determining the release time of each news information in the target event cluster.
The release time of each news information can be determined according to the time information identified in each news information, or the time of receiving the news information by the Internet is the corresponding release time when pushing the news information.
And 204, selecting a preset number of recommended news from the target event cluster according to the release time from the near to the far, and displaying the recommended news according to a preset display strategy.
It can be understood that, in order to improve the reading experience of the user, in principle, the latest news information corresponding to the reading event is provided for the user, and a preset number of recommended news is selected from the target event cluster according to the release time from the near to the far, where the preset number can be calibrated by the system, and can also be determined by the storage space of the device for displaying the news information.
Furthermore, the recommended news is displayed according to a preset display strategy, for example, as shown in fig. 8-1, after 20 pieces of news information are determined, news can be pushed in the form of a theme folder, when a user clicks the corresponding theme folder, the cover of the theme folder can display the theme event names of the corresponding event clusters, and then the 20 pieces of news information (not shown in the figure) are displayed, so that the display neatness is improved.
For another example, as shown in fig. 8-2, after 20 pieces of news information are determined, the news information can be pushed in a time axis manner, wherein each time node of the time axis displays an event name of the news information, and a user can intuitively select news information of new interest according to needs. Wherein each event name links the corresponding news information, and when the user clicks the corresponding event name, the user jumps to the corresponding news information.
Embodiment two:
in this embodiment, as shown in fig. 9, after the step 104, the method further includes:
in step 301, the number of news information contained in the target event cluster is counted.
Specifically, the number of news information contained in the target event cluster is counted, so that hot events can be actively mined according to the number.
Step 302, determining whether the number is greater than a preset threshold, and if so, determining a hot event name according to the event name of each piece of news information in the target event cluster.
Specifically, whether the number is greater than a preset threshold value is judged, if so, a hot event name is determined according to the event name of each news information in the target event cluster, for example, the subject event name of the event cluster is used as the hot event name, and for example, one or more event names with highest occurrence frequency are selected in the corresponding event cluster to be used as the hot event name.
Of course, in order to further ensure timeliness of the hot spot, the number of news information in a preset duration from the current time can be counted when counting the number.
Step 303, pushing the hot event according to the hot event name.
Specifically, a hotspot event is pushed according to the hotspot event name, and the hotspot is actively discovered and pushed, in some possible examples, as shown in fig. 10, the hotspot event name is displayed in a form of a suspension control, and when a user clicks a corresponding suspension control, the user jumps to a corresponding event cluster or news information, and in an actual application, the topic and the like of the hotspot event name can be displayed in a preset area of the application as in a microblog and the like.
In summary, according to the news information pushing method in the embodiment of the present application, a news headline of current news information is obtained, an event name in the news headline is extracted according to a preset extraction strategy, if at least one event name is extracted, each event name in the at least one event name is matched with a plurality of event clusters in a preset event library, wherein each event cluster in the plurality of event clusters contains a plurality of news information under the same event, further, according to the matching result of all event names, whether a target event cluster to which the news information belongs exists in the preset event library is judged, and finally, when the target event cluster exists, the news information is merged into the target event cluster so as to provide a news information pushing service according to the target event cluster. Therefore, the news information is combed by taking the event as granularity, so that the news information service with high correlation can be conveniently pushed to the user.
In order to achieve the above embodiments, the present application further provides a device for pushing news information. Fig. 11 is a schematic structural view of a news information-pushing device according to an embodiment of the present application, and as shown in fig. 11, the news information-pushing device includes: the device comprises an extraction module 10, a matching module 20, a first judging module 30 and a combining module 40, wherein,
the extraction module 10 is used for acquiring the news headline of the current news information and extracting event names in the news headline according to a preset extraction strategy;
the matching module 20 is configured to match each event name in the at least one event name with a plurality of event clusters in a preset event library when the at least one event name is extracted, where each event cluster in the plurality of event clusters includes a plurality of news information under the same event;
a first judging module 30, configured to judge whether a target event cluster to which news information belongs exists in a preset event library according to the matching results of all event names;
and the merging module 10 is used for merging the news information into the target event cluster when the target event cluster exists, so as to provide a push service of the news information according to the target event cluster.
In one embodiment of the present application, as shown in fig. 12, the apparatus further includes, on the basis of that shown in fig. 11: a first determination module 50, a second determination module 60, a second determination module 70, and a display module 80, wherein,
a first determining module 50, configured to obtain a news reading request, and determine a reading event corresponding to the news reading request;
a second judging module 60, configured to judge whether the reading event matches an event corresponding to the target event cluster;
a second determining module 70, configured to determine, when matching, a release time of each news information in the target event cluster;
the display module 80 is configured to select a preset number of recommended news in the target event cluster according to the release time from the near to the far, and display the recommended news according to a preset display policy.
In one embodiment of the present application, as shown in fig. 13, the apparatus further includes, on the basis of that shown in fig. 11: the statistics module 90, the third determining module 100 and the pushing module 110, wherein the statistics module 90 is configured to count the number of news information contained in the target event cluster;
a third determining module 100, configured to determine whether the number is greater than a preset threshold, and determine a hot event name according to an event name of each news information in the target event cluster when the number is greater than the preset threshold;
the pushing module 110 is configured to push the hotspot event according to the hotspot event name.
It should be noted that the foregoing explanation of the method for pushing news information is also applicable to the device for pushing news information in the embodiment of the present application, and the implementation principle is similar, and details of the related technology are not repeated here.
In summary, the news information pushing device in the embodiment of the present application obtains a news headline of current news information, extracts an event name in the news headline according to a preset extraction policy, and matches each event name in at least one event name with a plurality of event clusters in a preset event library if at least one event name is extracted, where each event cluster in the plurality of event clusters includes a plurality of news information under the same event, further, according to a matching result of all event names, determines whether a target event cluster to which the news information belongs exists in the preset event library, and finally, when the target event cluster exists, merges the news information into the target event cluster so as to provide a pushing service of the news information according to the target event cluster. Therefore, the news information is combed by taking the event as granularity, so that the news information service with high correlation can be conveniently pushed to the user.
…
According to embodiments of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 14, there is a block diagram of an electronic device according to a method of pushing news information according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.
As shown in fig. 14, the electronic device includes: one or more processors 1401, memory 1402, and interfaces for connecting the components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 1401 is illustrated in fig. 14.
Memory 1402 is a non-transitory computer-readable storage medium provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a method of pushing news information provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform a method of pushing news information provided by the present application.
The memory 1402 is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules (e.g., the extraction module 10, the matching module 20, the first determination module 30, and the merging module 40 shown in fig. 11) corresponding to the method of pushing news information in the embodiments of the present application. The processor 1401 performs various functional applications of the server and data processing, that is, a method of pushing news information in the above-described method embodiment, by running a non-transitory software program, instructions, and modules stored in the memory 1402.
Memory 1402 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the electronic device of the push method of news information, etc. Further, memory 1402 can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 1402 optionally includes memory remotely located relative to processor 1401, which may be connected via a network to an electronic device performing the push method of news information. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device performing the method of pushing news information may further include: an input device 1403 and an output device 1404. The processor 1401, memory 1402, input device 1403, and output device 1404 may be connected by a bus or otherwise, for example in fig. 14.
The input device 1403 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic device performing the push method of news information, such as input devices for a touch screen, a keypad, a mouse, a track pad, a touch pad, a joystick, one or more mouse buttons, a track ball, a joystick, and the like. The output devices 1404 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.
Claims (10)
1. A method for pushing news information, comprising:
acquiring a news headline of current news information, and extracting event names in the news headline according to a preset extraction strategy;
if at least one event name is extracted, matching each event name in the at least one event name with a plurality of event clusters in a preset event library, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event;
judging whether a target event cluster to which the news information belongs exists in the preset event library according to the matching results of all event names;
if the target event cluster exists, combining the news information into the target event cluster so as to provide the push service of the news information according to the target event cluster, and storing the corresponding relation between at least one event name and the news information into the target event cluster;
and if at least one event name is extracted, matching each event name in the at least one event name with a plurality of event clusters in a preset event library, wherein the steps include:
acquiring a theme event name of each event cluster in the plurality of event clusters;
carrying out semantic matching on each event name in the at least one event name and the subject event name of each event cluster to obtain semantic similarity;
and judging whether a target event cluster to which the news information belongs exists in the preset event library according to the matching results of all event names, wherein the method comprises the following steps:
when all event clusters with the matched event names are inconsistent, the event cluster with the largest matching success times is used as the target event cluster.
2. The method of claim 1, wherein the extracting the event name in the news headline according to a preset extraction policy comprises:
and inputting the news headline into a preset event name extraction model, wherein the event name extraction model learns in advance to obtain the corresponding relation between the news headline and the event name.
3. The method of claim 1, further comprising, after said merging the news information into the target event cluster if the target event cluster exists:
acquiring a news reading request and determining a reading event corresponding to the news reading request;
judging whether the reading event is matched with the event corresponding to the target event cluster;
if the news information is matched with the target event cluster, determining the release time of each piece of news information in the target event cluster;
selecting a preset number of recommended news from the target event cluster according to the release time and the sequence from the near to the far, and displaying the recommended news according to a preset display strategy.
4. The method of claim 1, further comprising, after said merging the news information into the target event cluster if the target event cluster exists:
counting the quantity of news information contained in the target event cluster;
judging whether the number is larger than a preset threshold value, if so, determining a hot event name according to the event name of each news information in the target event cluster;
pushing the hot events according to the hot event names.
5. The method of claim 1, further comprising, after said determining whether a target event cluster to which said news information belongs exists in said preset event library:
and if the target event cluster does not exist, an event cluster corresponding to the news information is newly added.
6. A push device for news information, comprising:
the extraction module is used for acquiring the news headline of the current news information and extracting event names in the news headline according to a preset extraction strategy;
the matching module is used for matching each event name in the at least one event name with a plurality of event clusters in a preset event library when the at least one event name is extracted, wherein each event cluster in the plurality of event clusters comprises a plurality of news information under the same event;
the first judging module is used for judging whether a target event cluster to which the news information belongs exists in the preset event library according to the matching results of all event names;
the merging module is used for merging the news information into the target event cluster when the target event cluster exists, so as to provide a pushing service of the news information according to the target event cluster, and storing the corresponding relation between at least one event name and the news information into the target event cluster;
the matching module is specifically configured to:
acquiring a theme event name of each event cluster in the plurality of event clusters;
carrying out semantic matching on each event name in the at least one event name and the subject event name of each event cluster to obtain semantic similarity;
the first judging module is specifically configured to, when all event clusters matched with the event names are inconsistent, use the event cluster with the largest number of successful matching times as the target event cluster.
7. The apparatus as recited in claim 6, further comprising:
the first determining module is used for acquiring a news reading request and determining a reading event corresponding to the news reading request;
the second judging module is used for judging whether the reading event is matched with the event corresponding to the target event cluster;
the second determining module is used for determining the release time of each piece of news information in the target event cluster when the news information is matched with the target event cluster;
and the display module is used for selecting a preset number of recommended news in the target event cluster according to the release time from the near to the far and displaying the recommended news according to a preset display strategy.
8. The apparatus as recited in claim 6, further comprising:
the statistics module is used for counting the quantity of news information contained in the target event cluster;
the third determining module is used for judging whether the number is larger than a preset threshold value or not, and determining a hot event name according to the event name of each news information in the target event cluster when the number is larger than the preset threshold value;
and the pushing module is used for pushing the hot event according to the hot event name.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of pushing news information according to any one of claims 1-5.
10. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the push method of news information according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228073.1A CN111460289B (en) | 2020-03-27 | 2020-03-27 | News information pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228073.1A CN111460289B (en) | 2020-03-27 | 2020-03-27 | News information pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111460289A CN111460289A (en) | 2020-07-28 |
| CN111460289B true CN111460289B (en) | 2024-03-29 |
Family
ID=71683305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010228073.1A Active CN111460289B (en) | 2020-03-27 | 2020-03-27 | News information pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111460289B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580355B (en) * | 2020-12-30 | 2021-08-31 | 中科院计算技术研究所大数据研究院 | News information topic detection and real-time aggregation method |
| CN113343687B (en) * | 2021-05-25 | 2023-09-05 | 北京奇艺世纪科技有限公司 | Event name determining method, device, equipment and storage medium |
| CN113836448B (en) * | 2021-09-22 | 2023-10-20 | 抖音视界有限公司 | Information display method, device, computer equipment and storage medium |
| CN114491102B (en) * | 2022-04-14 | 2022-06-28 | 深圳格隆汇信息科技有限公司 | Database monitoring method and system based on big data |
| CN117763223A (en) * | 2022-09-23 | 2024-03-26 | 花瓣云科技有限公司 | Information pushing method, electronic equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8051088B1 (en) * | 2010-04-07 | 2011-11-01 | The Boeing Company | Document analysis |
| CN103793418A (en) * | 2012-10-31 | 2014-05-14 | 珠海富讯网络科技有限公司 | Search method of real-time vertical search engine for security industry |
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN105677894A (en) * | 2016-02-02 | 2016-06-15 | 清华大学 | Network event model based news event monitoring method and device |
| WO2017020451A1 (en) * | 2015-08-03 | 2017-02-09 | 百度在线网络技术（北京）有限公司 | Information push method and device |
| CN106446179A (en) * | 2016-09-28 | 2017-02-22 | 东软集团股份有限公司 | Hot topic generation method and device |
| CN107798147A (en) * | 2017-12-05 | 2018-03-13 | 李贺满 | A kind of news client and its information push method |
| CN108829699A (en) * | 2018-04-19 | 2018-11-16 | 北京奇艺世纪科技有限公司 | A kind of polymerization and device of focus incident |
| CN109857859A (en) * | 2018-12-24 | 2019-06-07 | 北京百度网讯科技有限公司 | Processing method, device, equipment and the storage medium of news information |
| CN109947935A (en) * | 2018-08-17 | 2019-06-28 | 麒麟合盛网络技术股份有限公司 | The generation method and device of media event |
| CN109960756A (en) * | 2019-03-19 | 2019-07-02 | 国家计算机网络与信息安全管理中心 | Media event information inductive method |
| CN110134787A (en) * | 2019-05-15 | 2019-08-16 | 北京信息科技大学 | A kind of news topic detection method |
| CN110399478A (en) * | 2018-04-19 | 2019-11-01 | 清华大学 | Event finds method and apparatus |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130290232A1 (en) * | 2012-04-30 | 2013-10-31 | Mikalai Tsytsarau | Identifying news events that cause a shift in sentiment |
| WO2016182774A1 (en) * | 2015-05-08 | 2016-11-17 | Thomson Reuters Global Resources | Social Media Events Detection and Verification |
| US11663254B2 (en) * | 2016-01-29 | 2023-05-30 | Thomson Reuters Enterprise Centre Gmbh | System and engine for seeded clustering of news events |
-
2020
- 2020-03-27 CN CN202010228073.1A patent/CN111460289B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8051088B1 (en) * | 2010-04-07 | 2011-11-01 | The Boeing Company | Document analysis |
| CN103793418A (en) * | 2012-10-31 | 2014-05-14 | 珠海富讯网络科技有限公司 | Search method of real-time vertical search engine for security industry |
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| WO2017020451A1 (en) * | 2015-08-03 | 2017-02-09 | 百度在线网络技术（北京）有限公司 | Information push method and device |
| CN105677894A (en) * | 2016-02-02 | 2016-06-15 | 清华大学 | Network event model based news event monitoring method and device |
| CN106446179A (en) * | 2016-09-28 | 2017-02-22 | 东软集团股份有限公司 | Hot topic generation method and device |
| CN107798147A (en) * | 2017-12-05 | 2018-03-13 | 李贺满 | A kind of news client and its information push method |
| CN108829699A (en) * | 2018-04-19 | 2018-11-16 | 北京奇艺世纪科技有限公司 | A kind of polymerization and device of focus incident |
| CN110399478A (en) * | 2018-04-19 | 2019-11-01 | 清华大学 | Event finds method and apparatus |
| CN109947935A (en) * | 2018-08-17 | 2019-06-28 | 麒麟合盛网络技术股份有限公司 | The generation method and device of media event |
| CN109857859A (en) * | 2018-12-24 | 2019-06-07 | 北京百度网讯科技有限公司 | Processing method, device, equipment and the storage medium of news information |
| CN109960756A (en) * | 2019-03-19 | 2019-07-02 | 国家计算机网络与信息安全管理中心 | Media event information inductive method |
| CN110134787A (en) * | 2019-05-15 | 2019-08-16 | 北京信息科技大学 | A kind of news topic detection method |
Non-Patent Citations (3)
| Title |
|---|
| Event extraction from heterogeneous news sources;M naughton;《RESEARCHGATE》;20060131;全文 * |
| 基于事件关联网络的用户兴趣话题发现算法;乌吉斯古愣;刘晓影;鄢楚平;;现代电子技术;20150315(第06期);全文 * |
| 新闻事件的分布式混合推荐算法;牛振东;王帅;王诗航;陈杰;;北京理工大学学报;20170715(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111460289A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460289B (en) | News information pushing method and device | |
| US9753909B2 (en) | Advanced field extractor with multiple positive examples | |
| US8756231B2 (en) | Search using proximity for clustering information | |
| JP2021101361A (en) | Method, device, apparatus and storage medium for generating event topics | |
| CN111949814A (en) | Searching method, searching device, electronic equipment and storage medium | |
| CN111475750A (en) | Page preloading control method, device, system, equipment and storage medium | |
| CN112052397B (en) | User characteristic generation method and device, electronic equipment and storage medium | |
| CN111858905B (en) | Model training method, information identification device, electronic equipment and storage medium | |
| CN110727668A (en) | Data cleaning method and device | |
| CN112115313B (en) | Regular expression generation and data extraction methods, devices, equipment and media | |
| US10915592B2 (en) | Indexing native application data | |
| CN111984774B (en) | Searching method, searching device, searching equipment and storage medium | |
| CN111310058B (en) | Information theme recommendation method, device, terminal and storage medium | |
| CN111460296B (en) | Method and apparatus for updating event sets | |
| CN111291184B (en) | Expression recommendation method, device, equipment and storage medium | |
| CN112818230A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN113516491A (en) | Promotion information display method and device, electronic equipment and storage medium | |
| CN111460257B (en) | Thematic generation method, apparatus, electronic device and storage medium | |
| CN111310044B (en) | Page element information extraction method, device, equipment and storage medium | |
| CN112650919A (en) | Entity information analysis method, apparatus, device and storage medium | |
| CN111666417A (en) | Method and device for generating synonyms, electronic equipment and readable storage medium | |
| CN111680508B (en) | Text processing method and device | |
| CN111984883B (en) | Label mining method, device, equipment and storage medium | |
| KR20140135100A (en) | Method for providing program using semantic mashup technology | |
| CN111125362B (en) | Abnormal text determination method and device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |