CN111368201A - Hot event detection method and device, electronic equipment and storage medium - Google Patents
Hot event detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111368201A CN111368201A CN202010150392.5A CN202010150392A CN111368201A CN 111368201 A CN111368201 A CN 111368201A CN 202010150392 A CN202010150392 A CN 202010150392A CN 111368201 A CN111368201 A CN 111368201A
- Authority
- CN
- China
- Prior art keywords
- information
- event
- hotspot
- detected
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a method and a device for detecting a hot event, electronic equipment and a storage medium, which relate to the technical field of information processing and comprise the following steps: acquiring information to be detected from a preset information base, wherein the information base is used for storing the information according to an information acquisition channel and an event main body type; extracting the characteristics of the information to be detected, and determining the information label of the information to be detected according to the extracted characteristics; obtaining the determined historical hotspot degree of each information tag; determining an information publisher of the information to be detected, and predicting the current hotspot degree of each determined information tag according to the information publisher; and detecting whether the event reflected by the information to be detected is a hotspot event or not according to the historical hotspot degree and the current hotspot degree of each information tag. Therefore, the scheme provided by the embodiment of the application can improve the detection efficiency of the hotspot event.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to a method and an apparatus for detecting a hot event, an electronic device, and a storage medium.
Background
With the rapid development of information technology, a large amount of information is filled on different network platforms, so that in order to facilitate a user to obtain important information in time, a hotspot event needs to be detected from events reflected by the large amount of information, and the detected hotspot event is presented to the user.
In the prior art, when a hot event is detected, information on a network is usually screened manually, and then information reflecting the hot event is determined. Because the information channels on the network are various and a large amount of useless information and repeated information exist in different channels, a large amount of time is consumed for manual screening, and the hot event detection efficiency is low.
Therefore, a hot event detection scheme is needed to improve the efficiency of detecting hot events.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for detecting a hot event, an electronic device, and a storage medium, so as to improve detection efficiency of the hot event. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a method for detecting a hotspot event, where the method includes:
acquiring information to be detected from a preset information base, wherein the information base is used for storing the information according to an information acquisition channel and an event main body type;
extracting the characteristics of the information to be detected, and determining the information label of the information to be detected according to the extracted characteristics;
obtaining the determined historical hotspot degree of each information tag, wherein the historical hotspot degree of each information tag represents that: the degree to which the obtained information with the information tag belongs to a hot event;
determining an information publisher of the information to be detected, and predicting the current hotspot degree of each determined information tag according to the information publisher;
and detecting whether the event reflected by the information to be detected is a hotspot event or not according to the historical hotspot degree and the current hotspot degree of each information tag.
In one embodiment of the present application, the method further comprises:
under the condition that the event reflected by the information to be detected is detected to be a hot event, obtaining hot spot information reflecting the hot event from the information base;
predicting the effectiveness degree of each obtained hotspot information describing the event reflected by the to-be-detected information according to the information publisher and/or the information publishing time of the obtained hotspot information;
analyzing the preset number of hot spot information with the highest effective degree, and determining the development process of the hot spot event according to the sequence of information release time to obtain the process information of the hot spot event.
In an embodiment of the present application, the analyzing the preset number of hot spot information with the highest validity degree, and determining the development history of the hot spot event according to the sequence of information distribution time to obtain the history information of the hot spot event includes:
analyzing each hotspot information to be analyzed to obtain development node information of the hotspot event reflected by each hotspot information to be analyzed, wherein the hotspot information to be analyzed is as follows: obtaining the hot spot information with the highest effective degree and preset quantity;
determining participation objects supported by information publishers of each hotspot information to be analyzed, wherein the participation objects are as follows: an object participating in the activity of the hotspot event;
and sequencing the obtained development node information according to the information release time sequence and the participation objects supported by the information release person to obtain the course information of the hotspot event.
In an embodiment of the present application, the determining the participating objects supported by the information publisher of each piece of hotspot information to be analyzed includes:
determining the participating objects supported by the information publishers of the hotspot information to be analyzed according to the corresponding relation between the preset information publishers and the supported participating objects; and/or the presence of a gas in the gas,
and performing semantic analysis on each hotspot information to be analyzed, and determining a participating object supported by the information publisher of each hotspot information to be analyzed based on the obtained semantic analysis result.
In an embodiment of the application, the predicting, according to the information publisher, the determined current hotspot degree of each information tag includes:
determining the current hotspot degree of each information label according to the information publisher, the publishing time of the information to be detected, the event subject type of the event reflected by the information to be detected, the first preset weight of the information publisher, the second preset weight of the publishing time and the third preset weight of the event subject type;
after detecting whether the event reflected by the to-be-detected information is a hotspot event, the method further includes:
acquiring deviation correction information which represents whether the event reflected by the information to be detected is a hot event or not;
and when the detection result of whether the information to be detected is the hotspot event is inconsistent with the deviation correction information, adjusting the first preset weight, the second preset weight and the third preset weight.
In an embodiment of the application, after the step of determining the information label of the information to be detected according to the extracted features, the method further includes:
judging whether the determined information tags contain the information tags marked with the hot event marks or not;
if so, directly determining the event reflected by the information to be detected as the hot event.
In a second aspect, an embodiment of the present application provides an apparatus for detecting a hotspot event, where the apparatus includes:
the information acquisition module is used for acquiring information to be detected from a preset information base, wherein the information base is used for storing the information according to the information acquisition channel and the event main body type;
the label determining module is used for extracting the characteristics of the information to be detected and determining the information label of the information to be detected according to the extracted characteristics;
a historical hotspot degree obtaining module, configured to obtain a determined historical hotspot degree of each information tag, where the historical hotspot degree of each information tag represents: the degree to which the obtained information with the information tag belongs to a hot event;
the current hotspot degree determining module is used for determining an information publisher of the information to be detected and predicting the current hotspot degree of each determined information label according to the information publisher;
and the hot event detection module is used for detecting whether the event reflected by the information to be detected is a hot event or not according to the historical hot degree and the current hot degree of each information tag.
In one embodiment of the present application, the apparatus further comprises:
the hotspot information acquisition module is used for acquiring hotspot information reflecting the hotspot event from the information base under the condition that the event reflected by the information to be detected is detected to be the hotspot event;
the effective degree prediction module is used for predicting the effective degree of each obtained hot spot information describing the event reflected by the to-be-detected information according to the information publisher and/or the information publishing time of the obtained hot spot information;
and the history information obtaining module is used for analyzing the hot spot information with the highest effective degree in a preset number, determining the development history of the hot spot event according to the sequence of the information issuing time, and obtaining the history information of the hot spot event.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of the first aspect when executing a program stored in the memory.
In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method steps of any one of the first aspect.
The embodiment of the application has the following beneficial effects:
when the scheme provided by the embodiment of the application is applied to detecting the hotspot event, firstly, the information to be detected is obtained from a preset information base, the characteristics of the information to be detected are extracted, the information tag of the information to be detected is determined according to the extracted characteristics, the historical hotspot degree of each determined information tag is obtained, the information publisher of the information to be detected is determined, the current hotspot degree of each determined information tag is predicted according to the information publisher, and whether the event reflected by the information to be detected is the hotspot event is detected according to the historical hotspot degree and the current hotspot degree of each information tag. And judging whether the event reflected by the information to be detected is a hot event or not according to the historical hotspot degree and the current hotspot degree of the information tag. And manual screening is not needed, so that a large amount of time is avoided. Therefore, the hot event detection scheme provided by the embodiment of the application is applied to detect the hot event, so that the detection efficiency of the hot event can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a hot event detection method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another hot event detection method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for obtaining history information according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a hot spot event detection apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to improve the detection efficiency of a hot event, embodiments of the present application provide a method and an apparatus for detecting a hot event, an electronic device, and a storage medium, which are described in detail below.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for detecting a hot event according to an embodiment of the present disclosure, where the method may be applied to electronic devices such as a desktop computer, a notebook computer, and a mobile phone, and may also be applied to software clients such as news software and event information software. The hot event detection method includes the following steps 101 to 105.
The information base is used for storing information according to the information acquisition channel and the event main body type.
The collection channel represents a source of the information, and the collection channel may include: official websites, microblogs, posts, banners, etc. For example, in terms of athletic events, the acquisition channels may include official microblogs, event websites, athlete personal microblogs, known media microblogs, and the like; in terms of financial events, the collection channels may include a known analyst microblog, a data publishing website, and the like.
The event body type indicates the type of the body of the event reflected by the information. For example, in terms of a sporting event, the body of the event may include: football, basketball, games, etc., in accordance therewith, the event subject types may include football, basketball, games, etc.; in terms of financial events, the body of the event may include: stocks, funds, etc., and in accordance therewith, the event subject types may include stocks, funds, etc.
Specifically, the information belonging to the same collection channel and the same event subject type can be stored together, so that the information of different types can be distinguished conveniently, and when the information is obtained from the database, the information belonging to the same collection channel and the same event subject type can be obtained quickly.
In one embodiment of the application, the web crawler can be used for collecting information of different event main body types from different collecting channels, and the collected information is stored in the database according to the collecting channels and the event main body types of the information.
In an embodiment of the present application, when the information to be detected is obtained from the information base, the latest stored information may be obtained from the information base as the information to be detected. In addition, each piece of information stored in a preset time period in the information base can be respectively used as the information to be detected.
In an embodiment of the present application, before storing the collected information in the database, the collected information may be cleaned to remove the advertisement information included in the information. Specifically, the information including the advertisement identification in the collected information can be identified, and the identified information is removed. In the case that the carrier of the collected information is a web page, since there is usually an advertisement space for placing advertisement information in the web page, the position of the advertisement space may be the lower left end, the lower right end, etc. of the web page. Therefore, when the advertisement information is removed, the position of the advertisement position can be determined, and the information positioned at the position in the information is removed.
And 102, extracting the characteristics of the information to be detected, and determining the information label of the information to be detected according to the extracted characteristics.
In an embodiment of the present application, the feature of the information to be detected may be extracted by using an existing algorithm for extracting information features. In addition, keywords, high-frequency words and the like in the information to be detected can be extracted, and then words used as features of the information to be detected are selected from the extracted keywords and high-frequency words. The number of the words selected as the features of the information to be detected may be 3, 5, 6, or the like.
In another embodiment of the present application, a pre-trained information feature extraction algorithm may be used to extract features of information to be detected, so as to obtain features of the information to be detected. The occurrence frequency of each vocabulary in the information to be detected can be counted, and the preset number of high-frequency words with the highest occurrence frequency can be determined and used as the characteristics of the information to be detected. And semantic analysis can be performed on the information to be detected by using a semantic analysis algorithm to obtain keywords of the information to be detected as the characteristics of the information to be detected.
In an embodiment of the application, when the information tag of the information to be detected is determined according to the characteristics of the information to be detected, the characteristics can be directly used as the information tag of the information to be detected.
In an embodiment of the application, the information tag of the information to be detected can be determined in the preset corresponding relationship between the features and the tag according to the features of the information to be detected. For example, if the label corresponding to the features such as "pre-competition", "playcompetition", and the like is set as "event", when the feature of the event to be detected includes "pre-competition", the event label of the event to be detected may be determined as "event".
And 103, obtaining the determined historical hotspot degree of each information tag.
The historical hotspot degree of each information tag represents that: the obtained information with the information tag belongs to the degree of the hot event.
The hot spot degree of each information tag can be represented by different numerical values, for example, an integer numerical value between 0 and 100, and a decimal value between 0 and 1. When the numerical value representing the hot spot degree of the information tag is larger, the degree that the event with the information tag belongs to the hot spot event is higher; when the number indicating the degree of the hot spot of the information tag is small, it indicates that the event having the information tag belongs to a low degree of the hot spot event.
In an embodiment of the present application, before detecting whether an event reflected by the to-be-detected information is a hot event, it may be detected whether the reflected event is the hot event or not with respect to some information in the information base. In addition, the information base may store the hot spot degree of each obtained information tag. In view of this, in this step, the same hotspot degree of the obtained information tag as the information tag of the information to be detected, which is called as a historical hotspot degree, can be obtained from the information base.
In an embodiment of the present application, an information tag of each piece of information in an information base may be obtained in advance, and a hotspot degree of each information tag may be obtained. After the information tag of the event to be detected is determined, the hotspot degree of the information tag of the event to be detected is directly searched from the obtained hotspot degrees of the information tag, and the hotspot degree is used as the historical hotspot degree.
Specifically, when each piece of information is added to the information base, the information tag of the newly added information is determined, the hotspot degree of the information tag is obtained, and the obtained information tag and the hotspot degree of the information tag are stored. Therefore, when the historical hotspot degree of each information tag is obtained subsequently, the historical hotspot degree of each information tag can be directly obtained from the prestored hotspot degree of each information tag, repeated calculation can be reduced, and the efficiency of obtaining the historical hotspot degree is improved.
And 104, determining an information publisher of the information to be detected, and predicting the current hotspot degree of each determined information label according to the information publisher.
Wherein the information distributor indicates a party that distributes information. In the case where the event subject type is football, the information publisher may be a soccer player, a soccer commentator, a soccer coach, a soccer game organizer, or the like. When the main body of the event is the network game, that is, the event main body type is the network game type, the information publisher may be an event host, an electronic contestant, a responsible person of an electronic contest club, and the like of the network game.
In an embodiment of the present application, a corresponding relationship between each information publisher and a hotspot degree of the information tag may be preset, and after the information publisher of the information to be detected is determined, a corresponding hotspot degree is searched in the corresponding relationship according to the determined information publisher, and the corresponding hotspot degree is used as a current hotspot degree of each information tag of the information to be detected.
Specifically, when the corresponding relationship between the information publisher and the hotspot degree is preset, the corresponding relationship can be set according to the authority of the information publisher, and when the authority of the information publisher is higher, the possibility that the information published by the information publisher becomes a hotspot event is higher, so that the hotspot degree corresponding to the information publisher is higher; when the authority of the information publisher is low, the possibility that the information published by the information publisher becomes a hotspot event is low, so that the hotspot degree corresponding to the information publisher is low.
And 105, detecting whether the event reflected by the information to be detected is a hotspot event or not according to the historical hotspot degree and the current hotspot degree of each information tag.
In an embodiment of the application, the historical hotspot degree and the current hotspot degree of each information tag can be accumulated, and when an accumulation result reaches a preset hotspot degree threshold, the information tag can be regarded as a hotspot tag. Further, the number of hot spot tags included in the information tags of the event to be detected can be counted, and when the number reaches a preset number threshold, the event reflected by the information to be detected is determined to be the hot spot event.
When the scheme provided by the embodiment is applied to detecting the hotspot event, firstly, the information to be detected is obtained from the preset information base, the characteristics of the information to be detected are extracted, the information tag of the information to be detected is determined according to the extracted characteristics, the historical hotspot degree of each determined information tag is obtained, the information publisher of the information to be detected is determined, the current hotspot degree of each determined information tag is predicted according to the information publisher, and whether the event reflected by the information to be detected is the hotspot event is detected according to the historical hotspot degree and the current hotspot degree of each information tag. And judging whether the event reflected by the information to be detected is a hot event or not according to the historical hotspot degree and the current hotspot degree of the information tag. And manual screening is not needed, so that a large amount of time is avoided. Therefore, by applying the hot event detection method provided by the embodiment, the detection efficiency of the hot event can be improved.
Referring to fig. 2, fig. 2 is a schematic flowchart of another hot spot event detection method according to an embodiment of the present application, where the method further includes the following steps 106 to 108.
And 106, under the condition that the event reflected by the information to be detected is detected to be a hot event, obtaining hot spot information reflecting the hot event from the information base.
In an embodiment of the application, when the hotspot information reflecting the hotspot event is obtained from the information base, the information of the information tag with the information to be detected can be searched from the information base to be used as the hotspot information. Under the condition that the information and the information to be detected have the same information label, the information and the information to be detected can be considered to have correlation, and then the information and the event reflected by the information to be detected can be considered to be the same event.
And 107, predicting the effectiveness degree of the event reflected by the acquired hot spot information description information to be detected according to the information issuer and/or the information issuing time of the acquired hot spot information.
For each piece of hotspot information, under the condition that the authority of an information publisher of the hotspot information is higher, the higher the validity degree of the hotspot information describing the event reflected by the information to be detected is; under the condition that the authority of the information publisher of the hotspot information is smaller, the effectiveness degree of the hotspot information describing the event reflected by the information to be detected is considered to be lower. Under the condition that the information release time of the hotspot information is more recent, the effectiveness degree of the hotspot information describing the event reflected by the information to be detected is considered to be higher; under the condition that the information issuing time of the hotspot information is earlier, the effectiveness degree of the hotspot information describing the event reflected by the information to be detected is considered to be lower.
In an embodiment of the present application, a corresponding relationship between each information publisher and the validity degree may be preset, the information publisher of each piece of hotspot information is determined, and according to the determined information publisher, the corresponding validity degree is searched in the corresponding relationship, and the result is used as the validity degree of an event reflected by the hotspot information description information to be detected.
In an embodiment of the present application, a corresponding relationship between the information release time and the validity degree may also be preset, for example, in a case that the interval between the information release time and the current time is within one week, the validity degree of the information is 20; under the condition that the interval between the information release time and the current time is in the range of one week to one month, the validity degree of the information is 10; in the case where the interval between the information distribution time and the current time is in the range of one month to six months, the validity degree of the information is 3. And determining the information release time of each piece of hot spot information, and searching the corresponding effective degree in the corresponding relation according to the determined information release time, wherein the effective degree is used as the effective degree of the event reflected by the hot spot information description information to be detected.
In an embodiment of the application, when the validity degree of the hotspot information is predicted based on the information publisher and the information publishing time, a publisher weight and a publishing time weight can be preset, a first validity degree of the hotspot information is obtained based on the information publisher, a second validity degree of the hotspot information is obtained based on the information publishing time, and the obtained validity degrees are added according to the preset weight to obtain the validity degree of an event reflected by the hotspot information description information to be detected.
For example, assuming that the obtained first validity degree is 20, the second validity degree is 10, the weight of the publisher is 0.4, and the weight of the distribution time is 0.6, the validity degree of the hotspot information can be calculated to be 14.
And 108, analyzing the preset number of hot spot information with the highest effective degree, determining the development process of the hot spot event according to the sequence of the information release time, and obtaining the process information of the hot spot event.
Wherein, the preset number can be 5, 8, 10, etc.
Specifically, a preset number of pieces of hotspot information with the highest degree of effectiveness are obtained through screening, the screened effective information is analyzed, for example, development nodes of a hotspot event reflected by the effective information are analyzed, and according to the sequence of information release time, the development process of the hotspot event can be obtained, so that the process information of the hotspot event is obtained.
The development nodes can be contents with important significance in the event development process. For example, when the subject of the event is a network game, the event may be an online network game, in which case the development node of the event may be an online version 1.0, an online version 2.0, an update of the function of a knight character, an online warrior character, and the like.
Specifically, when the development node of the hot event reflected by the effective information is analyzed, the keyword in the effective information may be determined first, semantic analysis may be performed on the determined keyword, and whether the content expressed by the effective information constitutes the development node of the event reflected by the effective information may be determined according to a semantic analysis result.
When the scheme provided by the embodiment is applied to hot event detection, under the condition that the event reflected by the information to be detected is detected to be the hot event, the hot information related to the hot event can be obtained from the information base, the hot information with high effective degree is selected from the obtained hot information, and finally the history information of the hot event is obtained. The history information can better reflect the history processes of the beginning, the development, the ending and the like of the hot event. The history information is displayed to the user, so that a better experience effect can be brought to the user.
Referring to fig. 3, in an embodiment of the present application, for the step 108, the following steps 1081 to 1083 may be included in obtaining the history information of the hot spot event.
Wherein, the hotspot information to be analyzed is as follows: and obtaining the hot spot information with the highest effective degree and preset quantity.
In an embodiment of the present application, a semantic detection algorithm may be used to analyze hotspot information to be analyzed, and determine a development node of an event reflected by the hotspot information to be analyzed in the whole hotspot event, for example, the development node may be a race entry stage, a pre-selection stage, a match stage, a final-match stage, and the like, so as to obtain development node information of each hotspot information to be analyzed.
Wherein, the participating objects are: an object participating in the activity of a hotspot event. For example, in the case where the hotspot event is a soccer game, the participating objects may include a red team and a blue team participating in the soccer game; in the case where the hotspot event is a network game, the participating objects may include a plurality of competition teams participating in the game competition.
In an embodiment of the present application, the participating objects supported by the information publishers of the hotspot information to be analyzed may be determined according to a preset correspondence between the information publishers and the supported participating objects.
Specifically, the correspondence between each information publisher and the supported participating object may be determined in advance according to the social relationship between the information publisher and the participating object. For example, assuming that the participating objects include S1 and S2, the information publisher a is in a teammate relationship with the participating object S1, and thus the participating object supported by the information publisher a may be set to S1. According to the social relationship between each information publisher and the participatory object, the corresponding relationship between each information publisher and the supported participatory object can be established. Thus, when determining the participating object supported by the information publisher of the hotspot information to be analyzed, the participating object supported by the information publisher can be obtained from the corresponding relationship based on the information publisher of the hotspot information to be analyzed.
In an embodiment of the application, semantic analysis can be performed on each piece of hotspot information to be analyzed, and a participating object supported by an information publisher of each piece of hotspot information to be analyzed is determined based on an obtained semantic analysis result.
Specifically, semantic analysis can be performed on the hotspot information to be analyzed by using a semantic analysis algorithm, evaluation of the hotspot information to be analyzed on a participating object is obtained according to an analysis result, and when the evaluation is forward evaluation, an information publisher of the hotspot information to be analyzed can be considered to support the participating object; when the evaluation is negative evaluation, it may be considered that the information publisher of the hotspot information to be analyzed does not support the participating object.
And 1083, sequencing the obtained development node information according to the information release time sequence and the participation objects supported by the information publisher to obtain the course information of the hot event.
In an embodiment of the application, the information of each development node may be classified according to the participation objects supported by the information publisher, the participation objects supported by the information publishers of the classified information in the same category are the same, and the development node information of each category may be sorted according to the information publishing time sequence, so as to obtain the course information of the hotspot event. The obtained course information is displayed to the user, so that the user can conveniently and intuitively know the development course of the hot events aiming at different supporters of the participated object.
For example, assuming that the participating objects include X and Y, the development node information of the information publisher supporting X includes X1, X2, and X3, and the development node information of the information publisher supporting Y includes Y1, Y2, and Y3, the respective development node information may be classified into two categories according to the difference of the participating objects supported by the information publisher of the respective development node information, the respective development node information in the first category includes X1, X2, and X3, and the respective development node information in the first category includes Y1, Y2, and Y3. And sequencing the development node information in the first type of information and the second type of information according to the information release time sequence respectively to obtain the course information of the hot event.
In an embodiment of the application, the information of each development node may also be sorted directly according to the information publishing time of the information of each development node, and the participation object supported by the information publisher of each development node information is marked on the development node information.
In an embodiment of the application, for step 104, when determining the current hotspot degree of each information tag, the current hotspot degree of each information tag may be determined according to an information publisher, the publishing time of the information to be detected, an event subject type of an event reflected by the information to be detected, a first preset weight of the information publisher, a second preset weight of the publishing time, and a third preset weight of the event subject type.
Specifically, a first corresponding relationship between each information publisher and the hot spot degree of the information tag, a second corresponding relationship between the publication time and the hot spot degree, and a third corresponding relationship between the event subject type and the hot spot degree may be preset, after determining the information publisher, the publication time, and the event subject type of the information to be detected, the first hot spot degree is determined in the first corresponding relationship according to the determined information publisher, the second hot spot degree is determined in the second corresponding relationship according to the publication time, the third hot spot degree is determined in the third corresponding relationship according to the event subject type, and then the first hot spot degree, the second hot spot degree, and the third hot spot degree are added based on the first preset weight, the second preset weight, and the third preset weight to obtain the current hot spot degree of each information tag.
In an embodiment of the application, after detecting whether an event reflected by the to-be-detected information is a hot event, deviation correction information indicating whether the event reflected by the to-be-detected information is the hot event may also be obtained, and when a detection result of whether the to-be-detected information is the hot event is inconsistent with the deviation correction information, the first preset weight, the second preset weight, and the third preset weight are adjusted.
The deviation rectifying information is information for rectifying whether the time reflected by the information to be detected is the detection result of the hot event.
The deviation correcting information may be information input from outside, and specifically may be information input by a worker directly through an electronic device. Or detecting whether the event reflected by the information to be detected is a hotspot event by using other modes to obtain the information.
In an embodiment of the present application, after the information tag of the to-be-detected information is determined in step 102, it may be further determined whether the determined information tag includes an information tag labeled with a hot event mark, and if so, the event reflected by the to-be-detected information is directly determined as the hot event.
Wherein, the hot event mark may be understood as: when the information in the information base is detected to be the hot event, the information label of the information is marked after the information reflecting the hot event is detected.
Specifically, for the information to be detected, if the information tag of the information to be detected includes the labeled information tag, the time reflected by the information to be detected can be directly determined as the hot event, so that it is not necessary to determine whether the event reflected by the information to be detected is the hot event according to the hot degree of the information tag of the information to be detected, and it is not necessary to obtain the historical hot degree and the current hot degree of the information tag of the information to be detected, so that the detection efficiency of the hot event can be further improved.
In an embodiment of the present application, when the information tag is labeled, the information tag of the determined reference information that reflects the event as the hot event may be labeled. For the information to be detected, the information to be detected has the same information tag as the reference information, which indicates that the information to be detected and the reference information have correlation, and the reference information is information reflecting the hot event, so that the information to be detected and the information reflecting the hot event can be obtained.
In one embodiment of the application, when the information of different event main body types of different channels is obtained, each different channel can be monitored so as to obtain the latest updated information of each channel in time. The formats of the information issued by each channel can be monitored, and the formats can be texts, pictures, videos and the like, so that the information with different formats can be acquired according to different information acquisition modes.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a hot spot event detection apparatus provided in an embodiment of the present application, where the apparatus includes:
the information obtaining module 401 is configured to obtain information to be detected from a preset information base, where the information base is configured to store information according to an information acquisition channel and an event subject type;
a tag determining module 402, configured to extract features of the information to be detected, and determine an information tag of the information to be detected according to the extracted features;
a historical hotspot degree obtaining module 403, configured to obtain a determined historical hotspot degree of each information tag, where the historical hotspot degree of each information tag represents: the degree to which the obtained information with the information tag belongs to a hot event;
a current hotspot degree determining module 404, configured to determine an information publisher of the to-be-detected information, and predict a current hotspot degree of each determined information tag according to the information publisher;
and a hot event detection module 405, configured to detect whether an event reflected by the to-be-detected information is a hot event according to the historical hot degree and the current hot degree of each information tag.
In one embodiment of the present application, the apparatus further comprises:
the hotspot information acquisition module is used for acquiring hotspot information reflecting the hotspot event from the information base under the condition that the event reflected by the information to be detected is detected to be the hotspot event;
the effective degree prediction module is used for predicting the effective degree of each obtained hot spot information describing the event reflected by the to-be-detected information according to the information publisher and/or the information publishing time of the obtained hot spot information;
and the history information obtaining module is used for analyzing the hot spot information with the highest effective degree in a preset number, determining the development history of the hot spot event according to the sequence of the information issuing time, and obtaining the history information of the hot spot event.
In an embodiment of the application, the history information obtaining module includes:
the information analysis unit is used for analyzing each piece of hotspot information to be analyzed to obtain development node information of the hotspot event reflected by each piece of hotspot information to be analyzed, wherein the hotspot information to be analyzed is as follows: obtaining the hot spot information with the highest effective degree and preset quantity;
the supporting object determining unit is used for determining participating objects supported by information publishers of the hotspot information to be analyzed, wherein the participating objects are: an object participating in the activity of the hotspot event;
and the history information obtaining unit is used for sequencing the obtained development node information according to the information release time sequence and the participation objects supported by the information publisher to obtain the history information of the hotspot event.
In an embodiment of the application, the supporting object determining unit is specifically configured to:
determining the participating objects supported by the information publishers of the hotspot information to be analyzed according to the corresponding relation between the preset information publishers and the supported participating objects; and/or the presence of a gas in the gas,
and performing semantic analysis on each hotspot information to be analyzed, and determining a participating object supported by the information publisher of each hotspot information to be analyzed based on the obtained semantic analysis result.
In an embodiment of the application, the current hotspot degree determining module 404 is specifically configured to:
determining the current hotspot degree of each information label according to the information publisher, the publishing time of the information to be detected, the event subject type of the event reflected by the information to be detected, the first preset weight of the information publisher, the second preset weight of the publishing time and the third preset weight of the event subject type;
after detecting whether the event reflected by the to-be-detected information is a hotspot event, the method further includes:
acquiring deviation correction information which represents whether the event reflected by the information to be detected is a hot event or not;
and when the detection result of whether the information to be detected is the hotspot event is inconsistent with the deviation correction information, adjusting the first preset weight, the second preset weight and the third preset weight.
In an embodiment of the application, the apparatus further includes an information tag determination module, configured to determine whether the determined information tag includes an information tag labeled with a hot event mark after determining the information tag of the information to be detected according to the extracted feature; if so, directly determining the event reflected by the information to be detected as the hot event.
When the scheme provided by the embodiment is applied to detecting the hotspot event, firstly, the information to be detected is obtained from the preset information base, the characteristics of the information to be detected are extracted, the information tag of the information to be detected is determined according to the extracted characteristics, the historical hotspot degree of each determined information tag is obtained, the information publisher of the information to be detected is determined, the current hotspot degree of each determined information tag is predicted according to the information publisher, and whether the event reflected by the information to be detected is the hotspot event is detected according to the historical hotspot degree and the current hotspot degree of each information tag. And judging whether the event reflected by the information to be detected is a hot event or not according to the historical hotspot degree and the current hotspot degree of the information tag. And manual screening is not needed, so that a large amount of time is avoided. Therefore, by applying the hot event detection method provided by the embodiment, the detection efficiency of the hot event can be improved.
The embodiment of the present application further provides an electronic device, as shown in fig. 5, which includes a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504,
a computer-readable storage medium 503 for storing a computer program;
the processor 901 is configured to implement any of the hot event detection methods described above when executing the program stored on the computer-readable storage medium 503.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the electronic equipment and other equipment.
The computer-readable storage medium may include a Random Access Memory (RAM) and may also include a Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the computer readable storage medium may be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
In yet another embodiment provided by the present application, there is also provided a computer-readable storage medium in an electronic device, the electronic device including a processor, and the computer program, when executed by the processor, implements any of the above hot event detection methods.
In yet another embodiment provided herein, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the above-described hotspot event detection methods.
When the scheme provided by the embodiment is applied to detecting the hotspot event, firstly, the information to be detected is obtained from the preset information base, the characteristics of the information to be detected are extracted, the information tag of the information to be detected is determined according to the extracted characteristics, the historical hotspot degree of each determined information tag is obtained, the information publisher of the information to be detected is determined, the current hotspot degree of each determined information tag is predicted according to the information publisher, and whether the event reflected by the information to be detected is the hotspot event is detected according to the historical hotspot degree and the current hotspot degree of each information tag. And judging whether the event reflected by the information to be detected is a hot event or not according to the historical hotspot degree and the current hotspot degree of the information tag. And manual screening is not needed, so that a large amount of time is avoided. Therefore, by applying the hot event detection method provided by the embodiment, the detection efficiency of the hot event can be improved.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, apparatus embodiments, electronic device embodiments, storage medium embodiments, and computer program product embodiments are substantially similar to method embodiments and therefore are described with relative ease, as appropriate with reference to the partial description of system embodiments.
The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
Claims (10)
1. A method for hot spot event detection, the method comprising:
acquiring information to be detected from a preset information base, wherein the information base is used for storing the information according to an information acquisition channel and an event main body type;
extracting the characteristics of the information to be detected, and determining the information label of the information to be detected according to the extracted characteristics;
obtaining the determined historical hotspot degree of each information tag, wherein the historical hotspot degree of each information tag represents that: the degree to which the obtained information with the information tag belongs to a hot event;
determining an information publisher of the information to be detected, and predicting the current hotspot degree of each determined information tag according to the information publisher;
and detecting whether the event reflected by the information to be detected is a hotspot event or not according to the historical hotspot degree and the current hotspot degree of each information tag.
2. The method of claim 1, further comprising:
under the condition that the event reflected by the information to be detected is detected to be a hot event, obtaining hot spot information reflecting the hot event from the information base;
predicting the effectiveness degree of each obtained hotspot information describing the event reflected by the to-be-detected information according to the information publisher and/or the information publishing time of the obtained hotspot information;
analyzing the preset number of hot spot information with the highest effective degree, and determining the development process of the hot spot event according to the sequence of information release time to obtain the process information of the hot spot event.
3. The method according to claim 2, wherein the analyzing the preset number of hot spot information with the highest validity degree, determining the development history of the hot spot event according to the sequence of information distribution time, and obtaining the history information of the hot spot event comprises:
analyzing each hotspot information to be analyzed to obtain development node information of the hotspot event reflected by each hotspot information to be analyzed, wherein the hotspot information to be analyzed is as follows: obtaining the hot spot information with the highest effective degree and preset quantity;
determining participation objects supported by information publishers of each hotspot information to be analyzed, wherein the participation objects are as follows: an object participating in the activity of the hotspot event;
and sequencing the obtained development node information according to the information release time sequence and the participation objects supported by the information release person to obtain the course information of the hotspot event.
4. The method of claim 3, wherein the determining the participating objects supported by the information publisher of each hotspot information to be analyzed comprises:
determining the participating objects supported by the information publishers of the hotspot information to be analyzed according to the corresponding relation between the preset information publishers and the supported participating objects; and/or the presence of a gas in the gas,
and performing semantic analysis on each hotspot information to be analyzed, and determining a participating object supported by the information publisher of each hotspot information to be analyzed based on the obtained semantic analysis result.
5. The method according to any one of claims 1 to 4,
the predicting the current hotspot degree of each determined information tag according to the information publisher comprises the following steps:
determining the current hotspot degree of each information label according to the information publisher, the publishing time of the information to be detected, the event subject type of the event reflected by the information to be detected, the first preset weight of the information publisher, the second preset weight of the publishing time and the third preset weight of the event subject type;
after detecting whether the event reflected by the to-be-detected information is a hotspot event, the method further includes:
acquiring deviation correction information which represents whether the event reflected by the information to be detected is a hot event or not;
and when the detection result of whether the information to be detected is the hotspot event is inconsistent with the deviation correction information, adjusting the first preset weight, the second preset weight and the third preset weight.
6. The method according to any one of claims 1-4, characterized in that after the step of determining the information label of the information to be detected from the extracted features, the method further comprises:
judging whether the determined information tags contain the information tags marked with the hot event marks or not;
if so, directly determining the event reflected by the information to be detected as the hot event.
7. An apparatus for hot spot event detection, the apparatus comprising:
the information acquisition module is used for acquiring information to be detected from a preset information base, wherein the information base is used for storing the information according to the information acquisition channel and the event main body type;
the label determining module is used for extracting the characteristics of the information to be detected and determining the information label of the information to be detected according to the extracted characteristics;
a historical hotspot degree obtaining module, configured to obtain a determined historical hotspot degree of each information tag, where the historical hotspot degree of each information tag represents: the degree to which the obtained information with the information tag belongs to a hot event;
the current hotspot degree determining module is used for determining an information publisher of the information to be detected and predicting the current hotspot degree of each determined information label according to the information publisher;
and the hot event detection module is used for detecting whether the event reflected by the information to be detected is a hot event or not according to the historical hot degree and the current hot degree of each information tag.
8. The apparatus of claim 7, further comprising:
the hotspot information acquisition module is used for acquiring hotspot information reflecting the hotspot event from the information base under the condition that the event reflected by the information to be detected is detected to be the hotspot event;
the effective degree prediction module is used for predicting the effective degree of each obtained hot spot information describing the event reflected by the to-be-detected information according to the information publisher and/or the information publishing time of the obtained hot spot information;
and the history information obtaining module is used for analyzing the hot spot information with the highest effective degree in a preset number, determining the development history of the hot spot event according to the sequence of the information issuing time, and obtaining the history information of the hot spot event.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-6 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010150392.5A CN111368201A (en) | 2020-03-06 | 2020-03-06 | Hot event detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010150392.5A CN111368201A (en) | 2020-03-06 | 2020-03-06 | Hot event detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111368201A true CN111368201A (en) | 2020-07-03 |
Family
ID=71208712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010150392.5A Pending CN111368201A (en) | 2020-03-06 | 2020-03-06 | Hot event detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111368201A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836307A (en) * | 2021-10-15 | 2021-12-24 | 国网北京市电力公司 | Power supply service work order hotspot discovery method, system and device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110246388A1 (en) * | 2010-04-05 | 2011-10-06 | Kalengo Llc | System and method for providing financial asset pricing chart with aggregated, ranked and filtered articles |
| US20110302103A1 (en) * | 2010-06-08 | 2011-12-08 | International Business Machines Corporation | Popularity prediction of user-generated content |
| CN103532924A (en) * | 2013-03-07 | 2014-01-22 | 上海数字电视国家工程研究中心有限公司 | Digital communication system, information distribution method and receiving terminal |
| CN106202222A (en) * | 2016-06-28 | 2016-12-07 | 北京小米移动软件有限公司 | The determination method and device of focus incident |
| CN110222231A (en) * | 2019-06-11 | 2019-09-10 | 成都澳海川科技有限公司 | A kind of temperature prediction technique of video clip |
| CN110825958A (en) * | 2019-09-24 | 2020-02-21 | 广州数知科技有限公司 | Hot event intelligent sorting algorithm based on network heat |
-
2020
- 2020-03-06 CN CN202010150392.5A patent/CN111368201A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110246388A1 (en) * | 2010-04-05 | 2011-10-06 | Kalengo Llc | System and method for providing financial asset pricing chart with aggregated, ranked and filtered articles |
| US20110302103A1 (en) * | 2010-06-08 | 2011-12-08 | International Business Machines Corporation | Popularity prediction of user-generated content |
| CN103532924A (en) * | 2013-03-07 | 2014-01-22 | 上海数字电视国家工程研究中心有限公司 | Digital communication system, information distribution method and receiving terminal |
| CN106202222A (en) * | 2016-06-28 | 2016-12-07 | 北京小米移动软件有限公司 | The determination method and device of focus incident |
| CN110222231A (en) * | 2019-06-11 | 2019-09-10 | 成都澳海川科技有限公司 | A kind of temperature prediction technique of video clip |
| CN110825958A (en) * | 2019-09-24 | 2020-02-21 | 广州数知科技有限公司 | Hot event intelligent sorting algorithm based on network heat |
Non-Patent Citations (3)
| Title |
|---|
| 王冰玉;吴振宇;沈苏彬;陈佳颖;: "社交媒体事件检测研究综述" * |
| 陈梦秋;周安民;: "基于SVM的新浪热门微博预测" * |
| 黄炜;刘坤;杨青;: "面向复合维信息特征的微博舆情事件感知方法" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836307A (en) * | 2021-10-15 | 2021-12-24 | 国网北京市电力公司 | Power supply service work order hotspot discovery method, system and device and storage medium |
| CN113836307B (en) * | 2021-10-15 | 2024-02-20 | 国网北京市电力公司 | Power supply service work order hot spot discovery method, system, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101999471B1 (en) | Information recommendation methods and devices | |
| US20160285672A1 (en) | Method and system for processing network media information | |
| CN108304426B (en) | Identification obtaining method and device | |
| US9245035B2 (en) | Information processing system, information processing method, program, and non-transitory information storage medium | |
| JP5577385B2 (en) | Content distribution device | |
| CN107832444B (en) | Event discovery method and device based on search log | |
| US11080427B2 (en) | Method and apparatus for detecting label data leakage channel | |
| CN110674345A (en) | Video searching method and device and server | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN116823409A (en) | Intelligent screening method and system based on target search data | |
| WO2016177646A1 (en) | Computer-implemented methods of website analysis | |
| CN112579854A (en) | Information processing method, device, equipment and storage medium | |
| CN110413881B (en) | Method, device, network equipment and storage medium for identifying label accuracy | |
| CN103593355A (en) | User original content recommending method and device | |
| CN111368201A (en) | Hot event detection method and device, electronic equipment and storage medium | |
| Ceroni et al. | Justevents: A crowdsourced corpus for event validation with strict temporal constraints | |
| CN106204163B (en) | Method and device for determining user attribute characteristics | |
| EP3882825A1 (en) | Learning model application system, learning model application method, and program | |
| CN116186119A (en) | User behavior analysis method, device, equipment and storage medium | |
| JP2017167829A (en) | Detection device, detection method, and detection program | |
| CN106919649B (en) | Entry weight calculation method and device | |
| CN113221845A (en) | Advertisement auditing method, device, equipment and storage medium | |
| US20150134445A1 (en) | Intelligent matching of advertisement to content | |
| CN111666749A (en) | Hot article identification method | |
| CN110750238A (en) | Method and device for determining product requirements and electronic equipment |
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 |