CN110990708B - Hot event determination method and device, storage medium and electronic equipment - Google Patents

Hot event determination method and device, storage medium and electronic equipment Download PDF

Info

Publication number
CN110990708B
CN110990708B CN201911269466.0A CN201911269466A CN110990708B CN 110990708 B CN110990708 B CN 110990708B CN 201911269466 A CN201911269466 A CN 201911269466A CN 110990708 B CN110990708 B CN 110990708B
Authority
CN
China
Prior art keywords
search
keyword
event
determining
hot
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
Application number
CN201911269466.0A
Other languages
Chinese (zh)
Other versions
CN110990708A (en
Inventor
刘园林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Oppo Chongqing Intelligent Technology Co Ltd
Original Assignee
Oppo Chongqing Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Oppo Chongqing Intelligent Technology Co Ltd filed Critical Oppo Chongqing Intelligent Technology Co Ltd
Priority to CN201911269466.0A priority Critical patent/CN110990708B/en
Publication of CN110990708A publication Critical patent/CN110990708A/en
Application granted granted Critical
Publication of CN110990708B publication Critical patent/CN110990708B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Abstract

The application discloses a method, a device, a storage medium and electronic equipment for determining a hot event, wherein the method for determining the hot event comprises the following steps: receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text; counting first retrieval times of the first keyword in a first preset time period from the request time, and judging whether the first retrieval times meet a first preset condition or not; if yes, acquiring second retrieval times of the first keyword in a first preset duration before the request time; judging whether the search increment condition of the first keyword meets a second preset condition according to the first search times and the second search times; if yes, the first keywords are used as hot spot keywords, and the event corresponding to the hot spot keywords is determined to be a hot spot event. In the scheme, the search times and the search growth condition are adopted as evaluation indexes, so that the identification accuracy of the hot event can be improved.

Description

Hot event determination method and device, storage medium and electronic equipment
Technical Field
The application belongs to the technical field of information, and particularly relates to a method and a device for determining a hot event, a storage medium and electronic equipment.
Background
With the continuous development of networks, information inquiry based on search websites has become a common search mode for people. In the related art, an event frequently retrieved by a user is called a hot event. In determining whether an event is frequently retrieved by a user, the evaluation index is single, which may result in low accuracy in determining whether the event is a hotspot event.
Disclosure of Invention
The embodiment of the application provides a method, a device, a storage medium and electronic equipment for determining a hot event, which can improve the identification accuracy of the hot event.
In a first aspect, an embodiment of the present application provides a method for determining a hotspot event, including:
receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text;
counting first retrieval times of the first keyword in a first preset time period from the request moment, and judging whether the first retrieval times meet a first preset condition or not;
if yes, acquiring second retrieval times of the first keyword in the first preset duration before the request time;
judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
If yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
In a second aspect, an embodiment of the present application provides a hotspot event determining apparatus, including:
the extraction module is used for receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text;
the first judging module is used for counting first retrieval times of the first keyword in a first preset duration from the request moment and judging whether the first retrieval times meet a first preset condition or not;
the first acquisition module is used for acquiring second retrieval times of the first keyword in the first preset duration before the request time if the first retrieval times meet the first preset condition;
the second judging module is used for judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
and the first determining module is used for taking the first keyword as a hot spot keyword if the search growth condition of the first keyword meets the second preset condition, acquiring an event corresponding to the hot spot keyword, and determining the event as a hot spot event.
In a third aspect, a storage medium provided in an embodiment of the present application has a computer program stored thereon, which when executed on a computer causes the computer to perform a hotspot event determination method as provided in any embodiment of the present application.
In a fourth aspect, an electronic device provided in an embodiment of the present application includes a processor and a memory, where the memory has a computer program, and the processor is configured to execute a hotspot event determining method provided in any embodiment of the present application by calling the computer program.
According to the hotspot event determination scheme provided by the embodiment of the invention, when the retrieval request is received, the retrieval times and the retrieval growth condition are used as evaluation indexes to determine whether the first keywords extracted from the retrieval text of the retrieval request are the hotspot keywords or not, so that whether the event corresponding to the hotspot keywords is a hotspot event or not is determined, and the identification accuracy of the hotspot event can be improved.
Drawings
The technical solution of the present application and the advantageous effects thereof will be made apparent from the following detailed description of the specific embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a first flowchart illustrating a method for determining a hot event according to an embodiment of the present application.
Fig. 2 is a second flowchart of a method for determining a hot event according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a hotspot event determining apparatus provided in an embodiment of the present application.
Fig. 4 is a schematic diagram of a first structure of an electronic device according to an embodiment of the present application.
Fig. 5 is a second schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description is based on the illustrated embodiments of the present application and should not be taken as limiting other embodiments not described in detail herein. The term "module" as used herein may be considered as a software object executing on the computing system. The various modules, engines, and services herein may be viewed as implementation objects on the computing system.
The embodiment of the application provides a method for determining a hot event, and an execution subject of the method for determining a hot event may be a hot event determining device provided by the embodiment of the application, or an electronic device integrated with the hot event determining device. Wherein the electronic device may be a server or the like.
Specific analysis is described below.
Referring to fig. 1, fig. 1 is a first flow chart of a method for determining a hot event according to an embodiment of the present application, where the method for determining a hot event may include the following steps:
101. And receiving a search request, determining a search text and a request moment according to the search request, and extracting a first keyword from the search text.
In the embodiment of the application, after receiving the search request of the client, the electronic device may determine a request time of the search request, analyze the search request, obtain a search text, and extract a keyword from the search text as the first keyword, in addition to returning the search content to the client according to the search request. It will be appreciated that the client is installed in a user terminal, which establishes a communication connection with an electronic device acting as a server.
Wherein one search request corresponds to one search text. The search text is text entered by the user in the client search field. After receiving the search text input by the user in the search bar, the client generates a search request according to the search text, and then sends the search request to the electronic equipment so that the electronic equipment returns search contents according to the search request.
The request time of the scheme may refer to the time when the client sends the search request, or may refer to the time when the electronic device receives the search request.
In addition, the extraction manner of the keywords is not particularly limited in the embodiments of the present application. For example, the electronic device may analyze the search text by a keyword extraction algorithm, and extract one or more terms from the search text as the first keywords.
102. And counting first retrieval times of the first keyword in a first preset time period from the request time, and judging whether the first retrieval times meet a first preset condition.
In the embodiment of the application, after determining the search text and the request time according to the search request and extracting the first keyword from the search text, the electronic device may use the search text in the search request received in the first preset time period from the request time as a statistical object to count the number of search texts with the first keyword. Then, the number of search texts is used as a first search number of the first keyword within a first preset time period from the request time. Then, whether the first search times meet the first preset condition is judged, if yes, the execution is continued 103 if the first keyword is likely to be a hot spot keyword, and if not, the first keyword is judged not to be a hot spot keyword.
For example, assuming that the first preset duration is 4 minutes, the electronic device a receives a search request at 10 points, determines that the search text in the search request is "double eleven shopping benefits" and the request time is 10 points, and extracts the first keyword "shopping benefits" from the "double eleven shopping benefits". The electronic device A takes the search text in the search request received in the 10-point to 10-point 4-period as a statistical object. And then counting the number of search texts with the shopping benefits, taking the number of search texts as the first search times of the shopping benefits in a first preset time period from the request time, and judging whether the first search times of the shopping benefits meet a first preset condition. If the first search count of "shopping benefits" satisfies the first preset condition, the "shopping benefits" may be hot keywords, and execution continues at 103. If the first search times of the shopping benefits do not meet the first preset condition, the shopping benefits are not determined to be hot keywords.
The first preset duration of the solution may be a duration preset in the electronic device, such as 5 minutes, 4 minutes, 3 minutes, and so on. The first preset duration of the scheme can also be a duration obtained by the electronic device in real time according to the historical hot event.
The first preset condition is preset in the electronic equipment. The first preset condition may be set manually, or may be set by the electronic device according to a certain rule.
The first search times satisfying the first preset condition may refer to a first keyword having a first search time greater than a first threshold, where the first search times satisfy the first preset condition. Or alternatively
The first search times satisfying the first preset condition may refer to a first target keyword whose ranking satisfies the first preset ranking in the ranking of the plurality of first target keywords, where the first search times satisfy the first preset condition. The first target keywords refer to first keywords, wherein the first retrieval times of the first keywords are larger than a second threshold value. Or alternatively
The first search times satisfying the first preset condition may refer to a second target keyword whose ranking satisfies a second preset ranking in ranking of a plurality of second keywords, where the first search times satisfy the first preset condition. The second target keyword refers to a first keyword, of the one or more first keywords, of which the first retrieval times are larger than a third threshold value. The plurality of second keywords are keywords extracted by the electronic device according to the plurality of search texts received within a first preset time period from a request time, and the request time refers to a request time of extracting the search text (1) of the first keywords. That is, from the reception time point of view, the search text for extracting the first keyword is the first search text of the plurality of search texts for extracting the plurality of second keywords. Thus, the first keyword is included in the plurality of second keywords.
103. If yes, obtaining second retrieval times of the first keyword in a first preset duration before the request time.
In the embodiment of the application, after determining that the first search times meet the first preset condition, the electronic device uses the search texts in the search request received in the first preset time before the request time as a statistical object to count the number of the search texts with the first keyword. Then, the number of the search texts is used as the second search times of the first keyword in the first preset time before the request time. It should be noted that the first search number of the first keyword at the time of performing this operation has satisfied the first preset condition.
For example, following the above example of "double eleven shopping benefits", after judging that the first search number of times of "shopping benefits" satisfies the first preset condition, the electronic device a takes as a statistical object the search text in the search request received during the 9 th to 10 th points 56. Then counting the number of search texts with 'shopping benefits', and taking the number of search texts as the second search times of the 'shopping benefits' in the first preset time before the request time.
104. And judging whether the search increment condition of the first keyword meets a second preset condition according to the first search times and the second search times.
In this embodiment of the present application, after obtaining the first search times and the second search times of the first keyword, the electronic device may determine a search growth condition of the first keyword according to the first search times and the second search times, and then determine whether the search growth condition of the first keyword meets a second preset condition, if yes, then the execution is continued 105 if the first keyword meets all conditions of the hot spot keyword, and if not, determine that the first keyword is not the hot spot keyword. The second preset condition is a numerical value preset in the electronic equipment. The second preset condition may be set manually, or may be set by the electronic device according to a certain rule.
Note that, the embodiment of the present application is not particularly limited as to the manner of searching for the growth condition in this scenario.
In some embodiments, when determining the search growth of the first keyword according to the first search times and the second search times, the electronic device may calculate the growth rate of the first keyword according to the first search times and the second search times, and use the growth rate as the search growth of the first keyword.
Wherein, R represents the growth rate of the first keyword, M1 represents the first retrieval times of the first keyword, M2 represents the second retrieval times of the first keyword, and the calculation formula of the growth rate is as follows:
Figure BDA0002313762210000061
In some embodiments, when determining the search growth of the keyword according to the first search number and the second search number, the electronic device may calculate a difference between the first search number and the second search number, and use the difference as the search growth of the first keyword.
Wherein V represents a difference value of the first keyword, M1 represents a first search number of the first keyword, M2 represents a second search number of the first keyword, and the difference value has the following calculation formula:
V=M1-M2
105. if yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
In the embodiment of the present application, after determining that the search growth condition of the first keyword meets the second preset condition, the electronic device uses the first keyword as a hotspot keyword, acquires an event corresponding to the hotspot keyword, and determines that the event is a hotspot event. The hot event is mainly presented in the form of a short sentence, and the hot event comprises the hot key word. The hotspot event and the search text for extracting the first keyword are similar in content and may be the same or different.
It can be understood that the first search times of the hot key word satisfy the first preset condition, and the search increase condition thereof satisfies the second preset condition.
As can be seen from the above, in the embodiment of the present application, when a search request is received, since the search times and the search growth condition are used as evaluation indexes to determine whether the first keyword extracted from the search text of the search request is a hotspot keyword, and further determine whether the event corresponding to the hotspot keyword is a hotspot event, the identification accuracy of the hotspot event can be improved.
In some embodiments, before counting the first number of searches of the first keyword within the first preset time period from the request time, the electronic device may further perform:
determining the type of a search text, and acquiring the types of a plurality of historical hot events;
matching the type of the search text with the types of the plurality of historical hot events, and taking the successfully matched historical hot event as a second target historical hot event;
and calculating the average hotspot determination time length according to the hotspot determination time length of the second target historical hotspot event, and taking the average hotspot determination time length as a first preset time length.
In the scheme, after determining a search text according to a search request, counting first search times of a first keyword in a first preset duration from a request time, the electronic device can determine the type of the search text, acquire the types of a plurality of historical hot events, and take the historical hot events with the same type as the search text in the plurality of historical hot events as second target historical hot events, wherein the type of the historical hot events is the same as the type of the search text, and then judging that the two historical hot events are matched. Then, the electronic device acquires the hotspot determination duration of the second target historical hotspot event, calculates the average hotspot determination duration, and takes the average hotspot determination duration as the first preset duration.
Wherein, the historical hot event is an event that the electronic device has determined to be a hot event prior to the time of the request. Each historical hotspot event includes at least one hotspot keyword. The hotspot determination duration of each historical hotspot event refers to a period from a request time of the search request for determining that the event is a hotspot event to a time for determining that the event is a hotspot event.
In addition, the embodiments of the present application are not particularly limited with respect to the type of the search text and the type of the history hot event. For example, the type of the search text includes an entertainment type, a natural disaster type, and the like.
It should be noted that, the first preset duration in the scheme is counted by the historical hot events with the same type as the search text, so that the setting of the first preset duration is more reasonable, and the identification accuracy of the hot events is improved.
In some embodiments, after acquiring an event corresponding to a hotspot keyword and determining that the event is a hotspot event, the electronic device may search the information base for push content matching the hotspot event, and set the push content on the recommendation interface. For example, the electronic device may set push content matching the hotspot event on the recommendation interface for a preset time (e.g., 5 minutes). The successfully matched push content may refer to the content with the highest matching degree, or the successfully matched content may refer to the content with the highest matching degree, the second highest matching degree, or the like.
Referring to fig. 2, fig. 2 is a second flowchart of a method for determining a hot event according to an embodiment of the present application, where the method for determining a hot event may include the following steps:
201. and receiving a search request, determining a search text and a request moment according to the search request, and extracting a first keyword from the search text.
In the embodiment of the application, after receiving the search request of the client, the electronic device may determine a request time of the search request, analyze the search request, obtain a search text, and extract a keyword from the search text as the first keyword, in addition to returning the search content to the client according to the search request. Wherein the search text is text entered by the user in the client search bar. The request time may refer to a time when the client transmits the search request, or may refer to a time when the electronic device receives the search request.
In some embodiments, upon extracting the first keyword from the search text, the electronic device may remove invalid characters in the search text; and performing word segmentation and stop word removal on the search text from which the invalid characters are removed to obtain a first keyword. Wherein, the invalid characters of the search text comprise emoji characters, space characters, messy code characters and the like. Stop words are words or characters that are automatically filtered after processing natural language text in order to increase retrieval efficiency. The stop words are mainly divided into functional words and vocabulary words, and functional words such as "yes", "and the like have no actual meaning words or words.
202. The life time of a plurality of historical hot events is obtained.
In the embodiment of the application, after determining the search text and the request time according to the search request and extracting the first keyword from the search text, the electronic device may acquire the life time lengths of the plurality of historical hot events. Wherein, the historical hot event is an event that the electronic device has determined to be a hot event prior to the time of the request. Each historical hot event has a respective life duration, and the life durations between two historical hot events may be the same or different.
It should be noted that the historical hot events can be divided into two categories: events that are still hot events at the time of the request, events that are not hot events at the time of the request. The life duration acquisition modes of the two types of historical hot events are different. For the event which is still a hot event at the request moment, the electronic device acquires the moment of determining the event as the hot event, namely, the starting moment, and determines the time from the starting moment to the request moment as the life duration of the event. For an event which is not a hotspot event at the request time, the electronic device acquires the time when the event is determined to be the hotspot event, namely the starting time, and the time when the event is removed from the hotspot event, namely the ending time, and determines the time from the starting time to the ending time as the life duration of the event.
203. And taking the historical hot events with the life time longer than the second preset time as the first target historical hot events.
In the embodiment of the present application, after acquiring the life time lengths of a plurality of historical hotspot events, the electronic device uses, as a first target historical hotspot event, a historical hotspot event with a life time length longer than a second preset time length in the plurality of historical hotspot events. The second preset duration is preset in the electronic device, and the second preset duration can be manually adjusted.
In some embodiments, after acquiring the life durations of the plurality of historical hotspot events, the electronic device may further use a historical hotspot event with a life duration within a first preset range in the plurality of historical hotspot events as the third target historical hotspot event. And then calculating the average hotspot determination time length according to the hotspot determination time length of the third target historical hotspot event, and taking the average hotspot determination time length as a first preset time length. The first preset range is preset in the electronic equipment, and the first preset range can be manually adjusted.
204. And calculating the average hotspot determination time length according to the hotspot determination time length of the first target historical hotspot event, and taking the average hotspot determination time length as a first preset time length.
In this embodiment of the present invention, after taking a history hotspot event with a life time longer than a second preset time as a first target history hotspot event, the electronic device may obtain respective hotspot determination time lengths of the first target history hotspot event, so as to obtain a plurality of hotspot determination time lengths. And then calculating the average hotspot determining duration of the plurality of hotspot determining durations, and taking the average hotspot determining duration as a first preset duration.
Wherein each historical hotspot event comprises at least one hotspot keyword. The hotspot determination duration of each historical hotspot event refers to a period from a request time of the search request for determining that the event is a hotspot event to a time for determining that the event is a hotspot event.
In some embodiments, before taking the average hotspot determining duration as the first preset duration, the electronic device may further determine whether the average hotspot determining duration is greater than a set value, if so, take the set value as the first preset duration, and if not, take the average hotspot determining duration as the first preset duration. The set value is a maximum value of a first preset duration set in the electronic device, for example, the set value may be 5 minutes.
205. And counting first retrieval times of the first keyword in a first preset time period from the request time, and judging whether the first retrieval times meet a first preset condition.
In this embodiment of the present application, after determining the first preset duration, the electronic device may use, as a statistical object, the search text in the search request received in the first preset duration from the request time, and count the number of search texts having the first keyword. Then, the number of search texts is used as a first search number of the first keyword within a first preset time period from the request time. Then, it is determined whether the first search number satisfies a first preset condition, if yes, then the first keyword is likely to be a hot spot keyword, and if not, then it is determined that the first keyword is not a hot spot keyword, then 206 is executed.
The first preset condition is preset in the electronic equipment. The first preset condition may be set manually, or may be set by the electronic device according to a certain rule.
The first search times satisfying the first preset condition may refer to a first keyword having a first search time greater than a first threshold, where the first search times satisfy the first preset condition. Or alternatively
The first search times satisfying the first preset condition may refer to a first target keyword whose ranking satisfies the first preset ranking in the ranking of the plurality of first target keywords, where the first search times satisfy the first preset condition. The first target keywords refer to first keywords, wherein the first retrieval times of the first keywords are larger than a second threshold value. Or alternatively
The first search times satisfying the first preset condition may refer to a second target keyword whose ranking satisfies a second preset ranking in ranking of a plurality of second keywords, where the first search times satisfy the first preset condition. The second target keyword refers to a first keyword, of the one or more first keywords, of which the first retrieval times are larger than a third threshold value. The plurality of second keywords are keywords extracted by the electronic device according to the plurality of search texts received within a first preset time period from a request time, and the request time refers to a request time of extracting the search text (1) of the first keywords. That is, from the reception time point of view, the search text for extracting the first keyword is the first search text of the plurality of search texts for extracting the plurality of second keywords. Thus, the first keyword is included in the plurality of second keywords.
In some embodiments, when determining whether the first search number of times satisfies the first preset condition, the electronic device may determine whether the first search number of times is greater than a first threshold, where it is determined that the first search number of times satisfies the first preset condition when the first search number of times is greater than the first threshold.
It should be noted that, in this solution, the first threshold is preset in the electronic device. The first search times meeting the first preset condition means that a first keyword with the first search times being larger than a first threshold value exists.
For example, assume that the first preset time period is 3 minutes, the search text of one search request is "national celebration reader", and the request time is 12 points. The keyword extracted from the national celebration reader is the reader. The electronic equipment acquires 700 search requests received in 12-12 points 3 and determines 700 search texts of the 700 search requests. Then, the number of search texts with "reader" in the 700 search texts is counted and used as the first search times of "reader". And then, the electronic equipment judges whether the first search times of the 'reading soldier' are larger than a first threshold value, if so, the first search times of the 'reading soldier' are judged to meet a first preset condition, if not, the first search times of the 'reading soldier' are judged to not meet the first preset condition, and the 'reading soldier' is not a hot spot keyword.
In some embodiments, if there are a plurality of first keywords, when determining whether the first search times meet the first preset condition, the electronic device may determine, as the first target keyword, a first keyword whose first search times are greater than a second threshold value from the plurality of first keywords, where the first target keyword is a plurality of first target keywords; and sorting the plurality of first target keywords according to the first search times, and judging that the first search times of the first target keywords with the ranking meeting the first preset ranking in the sorting meet the first preset condition.
The second threshold and the first preset ranking are preset in the electronic equipment. The first target keyword is a first keyword whose first search number is greater than a second threshold value.
For example, assume that the first preset time period is 3 minutes, the search text of one search request is "XXX and YYY officers are wedding", and the request time is 13 points. The keywords extracted from "XXX and YYY officials" are "XXX", "YYY" and "wedding", i.e. the first keywords are "XXX", "YYY" and "wedding". The electronic equipment acquires 500 search requests received in 13-13 points 3 and determines 500 search texts of the 500 search requests. Then, the number of search texts having "XXX" among the 500 search texts is counted as the first search number of "XXX". Similarly, the first search times of "YYY" and the first search times of "wedding" are counted. Then, the electronic device determines whether the first search number of times "XXX" is greater than a second threshold, and if yes, determines that "XXX" is the first target keyword. Similarly, whether "YYY" is the first target keyword and whether "wedding" is the first target keyword are determined. When it is determined that "XXX" is the first target keyword, "YYY" is the first target keyword, and "wedding" is the first target keyword, the electronic device ranks "XXX", "YYY" and "wedding" by the first search number. If the first target keywords with the ranking meeting the first preset ranking in the ranking are XXX and wedding, the electronic equipment judges that the first retrieval times of XXX and wedding meet the first preset condition and judges that the first retrieval times of YYY do not meet the first preset condition, namely the YYY is not a hot spot keyword.
In some embodiments, when counting the first search times of the first keyword within a first preset time period from the request time and judging whether the first search times meet a first preset condition, the electronic device may acquire a plurality of search requests received within the first preset time period from the request time, and determine a plurality of search texts of the plurality of search requests; counting the number of search texts with first keywords in the plurality of search texts, wherein the number of the search texts is used as the first search times of the first keywords in a first preset time period from a request moment; determining a first keyword with the first retrieval times being larger than a third threshold value as a second target keyword, and extracting a plurality of different second keywords from the plurality of retrieval texts, wherein the plurality of second keywords comprise the first keyword; and sorting the plurality of second keywords based on the search times, and judging that the first search times of the second target keywords with the ranking meeting the second preset ranking in the sorting meet the first preset condition, wherein the plurality of second keywords comprise the second target keywords.
For example, assume that the first preset time period is 3 minutes, the search text of one search request is "XXX and YYY officers are wedding", and the request time is 13 points. The keywords extracted from "XXX and YYY officials" are "XXX", "YYY" and "wedding", i.e. the first keywords are "XXX", "YYY" and "wedding". The electronic device acquires 500 search requests received in 13-13 points 3, and determines 500 search texts of the 500 search requests, wherein the search texts of the ' XXX and YYY officers ' wedding ' are the first search texts in the 500 search texts according to the receiving time. Then, the number of search texts having "XXX" among the 500 search texts is counted as the first search number of "XXX". Similarly, the first search times of "YYY" and the first search times of "wedding" are counted. Then, the electronic device determines whether the first search number of times "XXX" is greater than a third threshold, and if yes, determines that "XXX" is the second target keyword. And similarly, judging whether YYY is a second target keyword and judging whether wedding is a second target keyword. When the XXX is judged to be the second target keyword, the YYY is judged to be the second target keyword and the wedding is judged to be the second target keyword, the electronic equipment extracts keywords of the determined 500 search texts to obtain 100 different second keywords. Among the 100 different second keywords, 3 keywords of "XXX", "YYY" and "wedding" are included. For each second keyword, the number of search texts having it among 500 search texts is counted as the number of search times. And then sorting the 100 second keywords according to the search times. If the second target keywords with the ranking meeting the second preset ranking in the ranking are XXX and wedding, the electronic equipment judges that the first search times of XXX and wedding meet the first preset condition and judges that the first search times of YYY do not meet the first preset condition, namely the YYY is not a hot spot keyword.
The third threshold and the second preset ranking are preset in the electronic equipment. The second target keyword refers to a first keyword whose first search number is greater than a third threshold value. The plurality of second keywords are a plurality of different keywords extracted by the electronic device according to the plurality of search texts received within a first preset time period from the request time.
In addition, the embodiment of the present application is not specifically limited as to the extraction manner of the second keyword. For example, the electronic device may analyze the plurality of search texts through a keyword extraction algorithm, and extract one or more word keywords from each search text, resulting in a plurality of different second keywords. Any two second keywords are different from each other.
The request time is the request time of the search text (1) from which the first keyword is extracted. That is, from the reception time point of view, the search text for extracting the first keyword is the first search text of the plurality of search texts for extracting the plurality of second keywords. Therefore, the plurality of second keywords include the first keywords and keywords other than the first keywords.
206. If yes, obtaining second retrieval times of the first keyword in a first preset duration before the request time.
In the embodiment of the application, after determining that the first search times meet the first preset condition, the electronic device uses the search texts in the search request received in the first preset time before the request time as a statistical object to count the number of the search texts with the first keyword. Then, the number of the search texts is used as the second search times of the first keyword in the first preset time before the request time. It should be noted that the first search number of the first keyword at the time of performing this operation has satisfied the first preset condition.
207. And judging whether the search increment condition of the first keyword meets a second preset condition according to the first search times and the second search times.
In this embodiment of the present application, after obtaining the first search times and the second search times of the first keyword, the electronic device may determine a search growth condition of the first keyword according to the first search times and the second search times, and then determine whether the search growth condition of the first keyword meets a second preset condition, if yes, then the execution is continued 105 if the first keyword meets all conditions of the hot spot keyword, and if not, determine that the first keyword is not the hot spot keyword. The second preset condition is a numerical value preset in the electronic equipment. The second preset condition may be set manually, or may be set by the electronic device according to a certain rule.
Note that, the embodiment of the present application is not particularly limited as to the manner of searching for the growth condition in this scenario. For example, the search growth condition is represented by the growth rate of the first keyword, or the like.
208. If yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
In the embodiment of the present application, after determining that the search growth condition of the first keyword meets the second preset condition, the electronic device uses the first keyword as a hotspot keyword, acquires an event corresponding to the hotspot keyword, and determines that the event is a hotspot event. The hot event is mainly presented in the form of a short sentence, and the hot event comprises the hot key word. The hotspot event and the search text for extracting the first keyword are similar in content and may be the same or different.
In some embodiments, when acquiring an event corresponding to a hotspot keyword, the electronic device may acquire a plurality of search requests received within a first preset duration from a request time, and determine a plurality of search texts of the plurality of search requests; taking a search text with a hot keyword in the plurality of search texts as a target search text; and generating an event corresponding to the hot spot keyword according to the target retrieval text.
For example, assuming that the first preset duration is 5 minutes, the search text of a certain search request is "GGG officer announces wedding" and the request time is 18 points, 700 search texts are received from 18 points to 18 points 5, and the keywords "GGG" and "wedding" extracted from the search texts are determined as hot spot keywords. The electronic device can take a plurality of pieces of search texts with GGG and wedding in 700 search texts as target search texts, and generate topic information corresponding to the multi-item target search texts according to a document topic generation model so as to represent events corresponding to GGG and wedding. For example, "GGG and DDD officers announce weddings.
209. Searching a plurality of push contents matched with the hot events in an information base.
In the embodiment of the present application, after determining that the event corresponding to the hotspot keyword is a hotspot event, the electronic device may match the hotspot event with the push content in the information base, and obtain a plurality of push contents successfully matched with the hotspot event. It will be appreciated that the information base of the electronic device stores a large amount of push content, which is mainly information uploaded by other devices that establish a communication connection with the electronic device.
210. And acquiring the basic weights and the hot point weights of the plurality of push contents, and calculating the recommendation scores of the push contents according to the basic weights and the hot point weights.
In the embodiment of the application, after searching a plurality of push contents matched with a hot event in an information base, an electronic device acquires a basic weight and a hot weight, and calculates the recommendation score of each push content according to the basic weight and the hot weight. Wherein the base weight may be one or more. It should be noted that push content in the information base can be divided into two types, one type is matched with a hotspot event, the push content is required to be calculated according to a basic weight and a hotspot weight when the push score is calculated, and the other type is not matched with the hotspot event, and the push content is calculated according to the basic weight when the push score is calculated.
For example, assuming that the basis weights include a first basis weight, a second basis weight, and a third basis weight, the recommendation score for push content matching a hotspot event is calculated as follows:
P=k 1 p 1 +k 2 p 2 +k 3 p 3 +k 4 p 4
the recommendation score for push content that does not match a hotspot event is calculated as follows:
P=k 1 p 1 +k 2 p 2 +k 3 p 3
where P represents the recommendation score of the push content, P 1 Representing the scoring of push content on a first basis weight, p 2 Representing the scoring of the pushed content on a second basis weight, p 3 Representing the scoring of the pushed content on a third basis weight, p 4 Representing push content on hotspot weights Score of k 1 Represents a first basis weight, k 2 Representing the second basis weight, k 3 Represents a third basis weight, k 4 Representing hotspot weights.
211. And setting the push content with the recommendation score larger than the preset score on the recommendation interface.
In the embodiment of the present application, after obtaining the recommendation score of each push content in the information base, the electronic device sets the push content with the recommendation score greater than the preset score on the recommendation interface.
In some embodiments, after obtaining the recommendation score of each push content in the information base, the electronic device may sort the push content in the information base according to the recommendation score, and set the push content with the ranking within the second preset range on the recommendation interface. For example, push content with a ranking of 1-50 is placed on the recommendation interface.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a hot event determining apparatus according to an embodiment of the present application. The hot event determination apparatus 300 includes: the device comprises an extraction module 301, a first judgment module 302, a first acquisition module 303, a second judgment module 304 and a first determination module 305.
An extracting module 301, configured to receive a search request, determine a search text and a request time according to the search request, and extract a first keyword from the search text;
A first determining module 302, configured to count a first search number of times of the first keyword within a first preset duration from the request time, and determine whether the first search number of times meets a first preset condition;
a first obtaining module 303, configured to obtain a second search number of times of the first keyword within the first preset duration before the request time if the first search number of times meets the first preset condition;
a second judging module 304, configured to judge whether a search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
the first determining module 305 is configured to, if the search growth condition of the first keyword meets the second preset condition, use the first keyword as a hotspot keyword, obtain an event corresponding to the hotspot keyword, and determine that the event is a hotspot event.
In some embodiments, when acquiring the event corresponding to the hotspot keyword, the first determining module 305 may be configured to:
acquiring a plurality of search requests received within a first preset time period from the request time, and determining a plurality of search texts of the plurality of search requests;
Taking the search text with the hot key words in the plurality of search texts as a target search text;
and generating an event corresponding to the hot key word according to the target retrieval text.
In some embodiments, after determining that the event is a hot event, the hot event determining apparatus 300 further includes:
and the first setting module is used for searching push contents matched with the hot events in the information base and setting the push contents on a recommendation interface.
In some embodiments, after determining that the event is a hot event, the hot event determining apparatus 300 further includes:
the searching module is used for searching a plurality of push contents matched with the hot event in the information base;
the second acquisition module is used for acquiring the basic weights and the hot point weights of the plurality of push contents and calculating the recommendation scores of the push contents according to the basic weights and the hot point weights;
and the second setting module is used for setting the push content with the recommendation score larger than the preset score on the recommendation interface.
In some embodiments, when determining whether the first search number meets the first preset condition, the first determining module 302 is further configured to:
Judging whether the first retrieval times are larger than a first threshold value or not, wherein when the first retrieval times are larger than the first threshold value, judging that the first retrieval times meet a first preset condition.
In some embodiments, when determining whether the first search number meets the first preset condition, the first determining module 302 is further configured to:
when a plurality of first keywords are provided, determining a first keyword with a first retrieval frequency larger than a second threshold value in the plurality of first keywords as a first target keyword, wherein the plurality of first target keywords are provided;
and sorting the plurality of first target keywords according to the first search times, and judging that the first search times of the first target keywords with the ranking meeting the first preset ranking in the sorting meet a first preset condition.
In some embodiments, when counting the first search times of the first keyword within a first preset duration from the request time, and determining whether the first search times meet a first preset condition, the first determining module 302 is further configured to:
acquiring a plurality of search requests received within a first preset time period from the request time, and determining a plurality of search texts of the plurality of search requests;
Counting the number of search texts with the first keyword in the plurality of search texts, and taking the number of the search texts as a first search number of the first keyword in a first preset duration from the request moment;
determining a first keyword with the first retrieval times being larger than a third threshold value as a second target keyword, and extracting a plurality of different second keywords from the plurality of retrieval texts, wherein the plurality of second keywords comprise the first keyword;
and sorting the plurality of second keywords based on the search times, and judging that the first search times of the second target keywords with the ranking meeting the second preset ranking in the sorting meet a first preset condition, wherein the plurality of second keywords comprise the second target keywords.
In some embodiments, prior to receiving the retrieval request, the hotspot event determination apparatus 300 further comprises:
the third acquisition module is used for acquiring the life time lengths of a plurality of historical hot events;
the second determining module is used for taking the historical hot events with the life time longer than the second preset time as the first target historical hot events;
and the third determining module is used for calculating the average hotspot determining duration according to the hotspot determining duration of the first target historical hotspot event, and taking the average hotspot determining duration as a first preset duration.
In some embodiments, before counting the first search times of the first keyword within a first preset duration from the request time, the hotspot event determining apparatus 300 further includes:
a fourth obtaining module, configured to determine a type of the search text, and obtain types of a plurality of historical hotspot events;
the matching module is used for matching the type of the search text with the types of the plurality of historical hot events and taking the successfully matched historical hot event as a second target historical hot event;
the calculation module is used for calculating an average hotspot determination duration according to the hotspot determination duration of the second target historical hotspot event, and the average hotspot determination duration is used as a first preset duration.
In some embodiments, when extracting the first keyword from the search text, the extracting module 301 is further configured to:
removing invalid characters in the search text;
and performing word segmentation and stop word removal on the search text from which the invalid characters are removed to obtain a first keyword.
As can be seen from the foregoing, in the hotspot event determining apparatus 300 provided in this embodiment of the present application, the extracting module 301 receives a search request, determines a search text and a request time according to the search request, and extracts a first keyword from the search text, then the first judging module 302 counts a first search number of times of the first keyword within a first preset duration from the request time, and judges whether the first search number of times meets a first preset condition, if the first search number of times meets the first preset condition, the first obtaining module 303 obtains a second search number of times of the first keyword within a first preset duration before the request time, and the second judging module 304 judges whether a search growth condition of the first keyword meets a second preset condition according to the first search number of times and the second search number of times, and if the search growth condition of the first keyword meets the second preset condition, the first determining module 305 uses the first keyword as a hotspot keyword, obtains an event corresponding to the hotspot keyword, and determines that the event is a hotspot event. According to the method and the device, the first search times and the search growth conditions are adopted as evaluation indexes for determining that the event corresponding to the hot spot keyword is the hot spot event, so that the identification accuracy of the hot spot event can be improved.
It should be noted that, the hotspot event determining device provided in the embodiment of the present application and the hotspot event determining method in the foregoing embodiment belong to the same concept, and any method provided in the hotspot event determining method embodiment may be run on the hotspot event determining device, and a detailed implementation process of the method is referred to in the hotspot event determining method embodiment and will not be repeated herein.
The embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed on a computer, causes the computer to perform the steps in the hotspot event determination method as provided in the embodiments of the present application. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
Referring to fig. 4, an electronic device 400 includes a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.
The processor 401 is a control center of the electronic device 400, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device 400 and processes data by running or loading computer programs stored in the memory 402, and calling data stored in the memory 402.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by running the computer programs and modules stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, a computer program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc.
In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.
In the embodiment of the present application, the processor 401 in the electronic device 400 loads the instructions corresponding to the processes of one or more computer programs into the memory 402 according to the following steps, and the processor 401 executes the computer programs stored in the memory 402, so as to implement various functions, as follows:
Receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text;
counting first retrieval times of the first keyword in a first preset time period from the request moment, and judging whether the first retrieval times meet a first preset condition or not;
if yes, acquiring second retrieval times of the first keyword in the first preset duration before the request time;
judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
if yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
Referring to fig. 5, fig. 5 is a second schematic structural diagram of an electronic device according to an embodiment of the present application, which is different from the electronic device shown in fig. 4 in that the electronic device further includes: a display component 503, radio frequency circuitry 504, and a power source 505. The display component 503, the rf circuit 504, and the power source 505 are electrically connected to the processor 501.
The display component 503 may be used to display information entered by a user or provided to a user as well as various graphical user interfaces that may be composed of graphics, text, icons, video, and any combination thereof.
The radio frequency circuitry 504 may be used to transceive radio frequency signals to establish wireless communications with a network device or other electronic device via wireless communications.
The power source 505 may be used to power the various components of the electronic device 500. In some embodiments, the power source 505 may be logically connected to the processor 501 through a power management system, so as to perform functions of managing charging, discharging, and power consumption management through the power management system.
In the embodiment of the present application, the processor 501 in the electronic device 500 loads the instructions corresponding to the processes of one or more computer programs into the memory 502 according to the following steps, and the processor 501 executes the computer programs stored in the memory 502, so as to implement various functions, as follows:
receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text;
Counting first retrieval times of the first keyword in a first preset time period from the request moment, and judging whether the first retrieval times meet a first preset condition or not;
if yes, acquiring second retrieval times of the first keyword in the first preset duration before the request time;
judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
if yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
In some embodiments, when acquiring the event corresponding to the hotspot keyword, the processor 501 may execute:
acquiring a plurality of search requests received within a first preset time period from the request time, and determining a plurality of search texts of the plurality of search requests;
taking the search text with the hot key words in the plurality of search texts as a target search text;
and generating an event corresponding to the hot key word according to the target retrieval text.
In some embodiments, after determining that the event is a hotspot event, processor 501 may further perform:
And searching push contents matched with the hot events in an information base, and setting the push contents on a recommendation interface.
In some embodiments, after determining that the event is a hotspot event, processor 501 may further perform:
searching a plurality of push contents matched with the hot events in an information base;
acquiring basic weights and hot spot weights of the plurality of push contents, and calculating recommendation scores of the push contents according to the basic weights and the hot spot weights;
and setting the push content with the recommendation score larger than the preset score on the recommendation interface.
In some embodiments, when determining whether the first search number meets the first preset condition, the processor 501 may perform:
judging whether the first retrieval times are larger than a first threshold value or not, wherein when the first retrieval times are larger than the first threshold value, judging that the first retrieval times meet a first preset condition.
In some embodiments, when determining whether the first search number meets the first preset condition, the processor 501 may perform:
when a plurality of first keywords are provided, determining a first keyword with a first retrieval frequency larger than a second threshold value in the plurality of first keywords as a first target keyword, wherein the plurality of first target keywords are provided;
And sorting the plurality of first target keywords according to the first search times, and judging that the first search times of the first target keywords with the ranking meeting the first preset ranking in the sorting meet a first preset condition, wherein the plurality of second keywords comprise the second target keywords.
In some embodiments, when counting the first search times of the first keyword within a first preset time period from the request time, and determining whether the first search times meet a first preset condition, the processor 501 may execute:
acquiring a plurality of search requests received within a first preset time period from the request time, and determining a plurality of search texts of the plurality of search requests;
counting the number of search texts with the first keyword in the plurality of search texts, and taking the number of the search texts as a first search number of the first keyword in a first preset duration from the request moment;
determining a first keyword with the first retrieval times being larger than a third threshold value as a second target keyword, and extracting a plurality of different second keywords from the plurality of retrieval texts, wherein the plurality of second keywords comprise the first keyword;
And sorting the plurality of second keywords based on the search times, and judging that the first search times of the second target keywords with the ranking meeting the second preset ranking in the sorting meet a first preset condition, wherein the plurality of second keywords comprise the second target keywords.
In some embodiments, prior to receiving the retrieval request, the processor 501 may further perform:
acquiring life time lengths of a plurality of historical hot events;
taking the historical hot events with the life time length longer than the second preset time length as first target historical hot events;
and calculating average hotspot determining duration according to the hotspot determining duration of the first target historical hotspot event, and taking the average hotspot determining duration as a first preset duration.
In some embodiments, before counting the first search times of the first keyword within a first preset duration from the request time, the processor 501 may further perform:
determining the type of the search text, and acquiring the types of a plurality of historical hot events;
matching the type of the search text with the types of the plurality of historical hot events, and taking the successfully matched historical hot event as a second target historical hot event;
And calculating average hotspot determining duration according to the hotspot determining duration of the second target historical hotspot event, and taking the average hotspot determining duration as a first preset duration.
In some embodiments, when extracting the first keyword from the search text, the processor 501 may perform:
removing invalid characters in the search text;
and performing word segmentation and stop word removal on the search text from which the invalid characters are removed to obtain a first keyword.
As can be seen from the foregoing, when a search request is received, the electronic device provided in the embodiment of the present application determines a search text and a request time according to the search request, extracts a first keyword from the search text, counts a first search number of times of the first keyword within a first preset duration from the request time, determines whether the first search number of times meets a first preset condition, when the first preset condition is met, obtains a second search number of times of the first keyword within the first preset duration before the request time, and then determines whether a search growth condition of the first keyword meets a second preset condition according to the first search number of times and the second search number of times, and when the second preset condition is met, uses the first keyword as a hot keyword, and determines that an event corresponding to the hot keyword is a hot event. As the first retrieval times and the retrieval increment condition are adopted as the evaluation indexes for determining that the event corresponding to the hot spot keyword is the hot spot event, the identification accuracy of the hot spot event can be improved.
The present application also provides a storage medium storing a computer program, which when executed on a computer, causes the computer to perform the hotspot event determining method in any one of the above embodiments, for example: receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text; counting first retrieval times of the first keyword in a first preset time period from the request moment, and judging whether the first retrieval times meet a first preset condition or not; if yes, acquiring second retrieval times of the first keyword in the first preset duration before the request time; judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times; if yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
It should be noted that, for the hotspot event determining method according to the embodiment of the present application, it will be understood by those skilled in the art that all or part of the procedure for implementing the hotspot event determining method according to the embodiment of the present application may be implemented by controlling related hardware through a computer program, where the computer program may be stored in a computer readable storage medium, such as a memory of an electronic device, and executed by at least one processor within the electronic device, and the execution may include, for example, the procedure of the embodiment of the hotspot event determining method. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.
For the hotspot event determining device of the embodiment of the present application, each functional module may be integrated in one processing chip, or each module may exist alone physically, or two or more modules may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated module, if implemented as a software functional module and sold or used as a stand-alone product, may also be stored on a computer readable storage medium such as read-only memory, magnetic or optical disk, etc.
The foregoing describes in detail a method, an apparatus, a storage medium, and an electronic device for determining a hotspot event provided in the embodiments of the present application, and specific examples are applied to illustrate principles and implementations of the present application, where the foregoing description of the embodiments is only for helping to understand the method and core ideas of the present application; meanwhile, those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, and the present description should not be construed as limiting the present application in view of the above.

Claims (12)

1. A method for determining a hot event, comprising:
receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text;
determining the type of the search text, and acquiring the types of a plurality of historical hot events;
matching the type of the search text with the types of the plurality of historical hot events, and taking the successfully matched historical hot event as a second target historical hot event;
calculating average hotspot determining duration according to the hotspot determining duration of the second target historical hotspot event, and taking the average hotspot determining duration as a first preset duration;
Counting first retrieval times of the first keyword in the first preset time from the request time, and judging whether the first retrieval times meet a first preset condition or not;
if yes, acquiring second retrieval times of the first keyword in the first preset duration before the request time;
judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
if yes, taking the first keywords meeting the second preset conditions as hot spot keywords, acquiring events corresponding to the hot spot keywords, and determining that the events are hot spot events.
2. The method for determining a hotspot event according to claim 1, wherein the obtaining the event corresponding to the hotspot keyword includes:
acquiring a plurality of search requests received within a first preset time period from the request time, and determining a plurality of search texts of the plurality of search requests;
taking the search text with the hot key words in the plurality of search texts as a target search text;
and generating an event corresponding to the hot key word according to the target retrieval text.
3. The method for determining a hot event according to claim 1, wherein after determining that the event is a hot event, further comprising:
and searching push contents matched with the hot events in an information base, and setting the push contents on a recommendation interface.
4. The method for determining a hot event according to claim 1, wherein after determining that the event is a hot event, further comprising:
searching a plurality of push contents matched with the hot events in an information base;
acquiring basic weights and hot spot weights of the plurality of push contents, and calculating recommendation scores of the push contents according to the basic weights and the hot spot weights;
and setting the push content with the recommendation score larger than the preset score on the recommendation interface.
5. The method for determining a hot event according to claim 1, wherein the determining whether the first search number meets a first preset condition includes:
judging whether the first retrieval times are larger than a first threshold value or not, wherein when the first retrieval times are larger than the first threshold value, judging that the first retrieval times meet a first preset condition.
6. The method for determining a hot event according to claim 1, wherein the determining whether the first search number meets a first preset condition includes:
when a plurality of first keywords are provided, determining a first keyword with a first retrieval frequency larger than a second threshold value in the plurality of first keywords as a first target keyword, wherein the plurality of first target keywords are provided;
and sorting the plurality of first target keywords according to the first search times, and judging that the first search times of the first target keywords with the ranking meeting the first preset ranking in the sorting meet a first preset condition.
7. The method of claim 1, wherein the counting the first search times of the first keyword within a first preset time period from the request time, and determining whether the first search times meet a first preset condition, comprises:
acquiring a plurality of search requests received within a first preset time period from the request time, and determining a plurality of search texts of the plurality of search requests;
counting the number of search texts with the first keyword in the plurality of search texts, and taking the number of the search texts as a first search number of the first keyword in a first preset duration from the request moment;
Determining a first keyword with the first retrieval times being larger than a third threshold value as a second target keyword, and extracting a plurality of different second keywords from the plurality of retrieval texts, wherein the plurality of second keywords comprise the first keyword;
and sorting the plurality of second keywords based on the search times, and judging that the first search times of the second target keywords with the ranking meeting the second preset ranking in the sorting meet a first preset condition, wherein the plurality of second keywords comprise the second target keywords.
8. The hotspot event determination method according to any one of claims 1 to 7, wherein before the receiving the retrieval request, further comprising:
acquiring life time lengths of a plurality of historical hot events;
taking the historical hot events with the life time length longer than the second preset time length as first target historical hot events;
and calculating average hotspot determining duration according to the hotspot determining duration of the first target historical hotspot event, and taking the average hotspot determining duration as a first preset duration.
9. The method for determining a hot event according to claim 8 or 1, wherein the extracting the first keyword from the search text comprises:
Removing invalid characters in the search text;
and performing word segmentation and stop word removal on the search text from which the invalid characters are removed to obtain a first keyword.
10. A hotspot event determining apparatus, comprising:
the extraction module is used for receiving a search request, determining a search text and a request time according to the search request, and extracting a first keyword from the search text;
a fourth obtaining module, configured to determine a type of the search text, and obtain types of a plurality of historical hotspot events;
the matching module is used for matching the type of the search text with the types of the plurality of historical hot events and taking the successfully matched historical hot event as a second target historical hot event;
the calculation module is used for calculating average hotspot determination duration according to the hotspot determination duration of the second target historical hotspot event, and taking the average hotspot determination duration as a first preset duration;
the first judging module is used for counting first retrieval times of the first keyword in a first preset duration from the request moment and judging whether the first retrieval times meet a first preset condition or not;
the first acquisition module is used for acquiring second retrieval times of the first keyword in the first preset duration before the request time if the first retrieval times meet the first preset condition;
The second judging module is used for judging whether the search growth condition of the first keyword meets a second preset condition according to the first search times and the second search times;
and the first determining module is used for taking the first keyword as a hot spot keyword if the search growth condition of the first keyword meets the second preset condition, acquiring an event corresponding to the hot spot keyword, and determining the event as a hot spot event.
11. A storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the hotspot event determination method of any of claims 1 to 9.
12. An electronic device comprising a processor, a memory, the memory having a computer program, wherein the processor is configured to perform the hotspot event determination method of any of claims 1 to 9 by invoking the computer program.
CN201911269466.0A 2019-12-11 2019-12-11 Hot event determination method and device, storage medium and electronic equipment Active CN110990708B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911269466.0A CN110990708B (en) 2019-12-11 2019-12-11 Hot event determination method and device, storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911269466.0A CN110990708B (en) 2019-12-11 2019-12-11 Hot event determination method and device, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN110990708A CN110990708A (en) 2020-04-10
CN110990708B true CN110990708B (en) 2023-05-02

Family

ID=70092478

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911269466.0A Active CN110990708B (en) 2019-12-11 2019-12-11 Hot event determination method and device, storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN110990708B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111782924B (en) * 2020-06-30 2023-09-29 北京百度网讯科技有限公司 Content processing method, device, equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968439A (en) * 2012-10-11 2013-03-13 微梦创科网络科技(中国)有限公司 Method and device for sending microblogs
CN103440286A (en) * 2013-08-14 2013-12-11 北京百度网讯科技有限公司 Method and system for providing recommended information on the basis of search results
CN107423444A (en) * 2017-08-10 2017-12-01 世纪龙信息网络有限责任公司 Hot word phrase extracting method and system
CN108170692A (en) * 2016-12-07 2018-06-15 腾讯科技(深圳)有限公司 A kind of focus incident information processing method and device
CN108304371A (en) * 2017-07-14 2018-07-20 腾讯科技(深圳)有限公司 Method, apparatus, computer equipment and the storage medium that Hot Contents excavate
CN108572990A (en) * 2017-03-14 2018-09-25 百度在线网络技术(北京)有限公司 Information-pushing method and device
CN109151498A (en) * 2018-09-03 2019-01-04 北京达佳互联信息技术有限公司 Focus incident processing method, device, server and storage medium
CN110457580A (en) * 2019-07-31 2019-11-15 百度时代网络技术(北京)有限公司 Focus recommendation method and device based on search

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014130445A (en) * 2012-12-28 2014-07-10 Toshiba Corp Information extraction server, information extraction client, information extraction method, and information extraction program

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968439A (en) * 2012-10-11 2013-03-13 微梦创科网络科技(中国)有限公司 Method and device for sending microblogs
CN103440286A (en) * 2013-08-14 2013-12-11 北京百度网讯科技有限公司 Method and system for providing recommended information on the basis of search results
CN108170692A (en) * 2016-12-07 2018-06-15 腾讯科技(深圳)有限公司 A kind of focus incident information processing method and device
CN108572990A (en) * 2017-03-14 2018-09-25 百度在线网络技术(北京)有限公司 Information-pushing method and device
CN108304371A (en) * 2017-07-14 2018-07-20 腾讯科技(深圳)有限公司 Method, apparatus, computer equipment and the storage medium that Hot Contents excavate
CN107423444A (en) * 2017-08-10 2017-12-01 世纪龙信息网络有限责任公司 Hot word phrase extracting method and system
CN109151498A (en) * 2018-09-03 2019-01-04 北京达佳互联信息技术有限公司 Focus incident processing method, device, server and storage medium
CN110457580A (en) * 2019-07-31 2019-11-15 百度时代网络技术(北京)有限公司 Focus recommendation method and device based on search

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
《基于语义统计分析的网络舆情挖掘技术研究》;万源;《万方数据知识服务平台》;20120929;1-117 *

Also Published As

Publication number Publication date
CN110990708A (en) 2020-04-10

Similar Documents

Publication Publication Date Title
US11194965B2 (en) Keyword extraction method and apparatus, storage medium, and electronic apparatus
US20160269326A1 (en) Information replying method and apparatus
CN109815314B (en) Intent recognition method, recognition device and computer readable storage medium
CN107092588B (en) Text information processing method, device and system
CN105022761B (en) Group searching method and device
EP3232336A1 (en) Method and device for recognizing stop word
CN103324745A (en) Text garbage identifying method and system based on Bayesian model
CN110069769B (en) Application label generation method and device and storage device
CN112765499A (en) Ranking list processing method, device, equipment and storage medium
CN110245357B (en) Main entity identification method and device
CN110990708B (en) Hot event determination method and device, storage medium and electronic equipment
CN110162769B (en) Text theme output method and device, storage medium and electronic device
CN111737443B (en) Answer text processing method and device and key text determining method
CN110555092B (en) Public opinion processing method, apparatus and computer readable storage medium
KR101918358B1 (en) A Data Center System Providing Customized Information
CN112565471B (en) Information pushing method, pushing robot, computer device and storage medium
CN110598100B (en) Hot word recommendation method, device, equipment and storage medium
CN112925912A (en) Text processing method, and synonymous text recall method and device
CN111930884A (en) Method and equipment for determining reply sentence and man-machine conversation system
CN111031118A (en) Information pushing method and device, electronic equipment and computer readable storage medium
CN112015888B (en) Abstract information extraction method and abstract information extraction system
CN111611489B (en) Search processing method and device, electronic equipment and storage medium
CN106528525A (en) Method and device for recognizing cheating of ranking list
CN109697250B (en) Bill information extraction method and device and storage medium
CN108306811B (en) Message processing method and device

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