CN111104627B - Hot event prediction method and device - Google Patents
Hot event prediction method and device Download PDFInfo
- Publication number
- CN111104627B CN111104627B CN201811268032.4A CN201811268032A CN111104627B CN 111104627 B CN111104627 B CN 111104627B CN 201811268032 A CN201811268032 A CN 201811268032A CN 111104627 B CN111104627 B CN 111104627B
- Authority
- CN
- China
- Prior art keywords
- information
- increment
- data
- preset
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a method and a device for predicting a hot event, wherein information data of a plurality of published information in a preset time period are acquired, for each published information, the information increase length of each published information in the preset time period is calculated according to the information data, and the plurality of published information are sequenced and sequenced according to the information increase length corresponding to each published information. The method and the device can obtain the sequencing result of the published information, the sequencing result with a smaller serial number can possibly become a hot event, the hot event can be obtained by screening, and the human input in the manual screening process is reduced.
Description
Technical Field
The invention relates to the field of data processing, in particular to a method and a device for predicting a hot event.
Background
Information redundancy and fragmentation on the digital internet are serious, massive information can appear at the same time, and media workers need to extract useful information from the massive information.
In the prior art, a worker manually searches information published on the internet to obtain a hot event, but the manual searching of the hot event wastes manpower.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a method and apparatus for predicting a hot spot event that overcomes or at least partially solves the above problems.
A method for predicting a hotspot event comprises the following steps:
acquiring information data of a plurality of published information in a preset time period;
for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information;
and sequencing the plurality of released information according to the information length increase corresponding to each released information and outputting a sequencing result.
Preferably, for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data, and the method comprises the following steps:
for each piece of published information, calculating the data increasing length of the published information under different preset indexes in the preset time period according to the information data;
acquiring a weight value corresponding to each preset index;
and calculating to obtain the information increasing length according to the data increasing length of the issued information under different preset indexes and the weight value corresponding to each preset index.
Preferably, the sum of products of data increasing lengths under different preset indexes and weight values of corresponding preset indexes is used as the information increasing length.
Preferably, for each piece of published information, calculating, according to the information data, a data increment length of the published information under different preset indexes in the preset time period includes:
for each piece of published information, acquiring data increment of the published information under a preset index according to the information data;
according to the data increment, calculating the increment slope of the issued information under a preset index;
acquiring a historical data increment mean value of the account publishing the published information under the preset index; the historical data increment mean value is an increment mean value in a historical time period corresponding to the preset time period;
and calculating to obtain the data increment length according to the increment slope, the data increment and the historical data increment average value.
Preferably, before obtaining the historical data increment average value of the account publishing the published information under the preset index, the method further includes:
acquiring the increment of each article published by the account in each preset fixed period within a preset historical time period;
determining the average index increment of the account in different fixed time periods according to the increment of each article in each preset fixed period;
acquiring the average increase of the index of the account in each fixed time period from the average increase of the index of the account in the historical time period;
and taking the obtained average increment of the index as the average value of the historical data increment.
Preferably, if the historical data increment mean value of the account publishing the published information under the preset index is not acquired, the method further includes:
acquiring a historical data increment mean value of the preset index of a similar account belonging to the same type as the account within the historical preset time period;
and taking the historical data increment mean value corresponding to the similar account as the historical data increment mean value corresponding to the account.
An apparatus for predicting a hotspot event, comprising:
the data acquisition module is used for acquiring information data of a plurality of published information in a preset time period;
the data calculation module is used for calculating the information increment length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information;
and the sequencing output module is used for sequencing the plurality of issued information according to the information length increment corresponding to each issued information and outputting a sequencing result.
Preferably, the data calculation module comprises:
the first calculation submodule is used for calculating the data increment length of each issued information under different preset indexes in the preset time period according to the information data;
the obtaining submodule is used for obtaining a weight value corresponding to each preset index;
and the second calculation submodule is used for calculating the information increasing length according to the data increasing length of the published information under different preset indexes and the weight value corresponding to each preset index.
A storage medium comprising a stored program, wherein the program performs the above-described method for predicting a hotspot event.
A processor, configured to execute a program, wherein the program executes the method for predicting the hot event.
By means of the technical scheme, the method and the device for predicting the hot event, provided by the invention, information data of a plurality of published information in a preset time period are obtained, for each published information, the information increase length of each published information in the preset time period is calculated according to the information data, and the published information is sequenced and a sequencing result is output according to the information increase length corresponding to each published information. The method and the device can obtain the sequencing result of the published information, the sequencing result with a smaller serial number can possibly become a hot event, and the hot event can be obtained by screening, so that the manpower input in the manual screening process is reduced.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a method for predicting a hotspot event according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for predicting a hotspot event according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a method of predicting a hot event according to another embodiment of the present invention;
fig. 4 is a schematic structural diagram illustrating an apparatus for predicting a hotspot event according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
An embodiment of the present invention provides a method for predicting a hot event, and with reference to fig. 1, the method may include:
s11, acquiring information data of a plurality of published information in a preset time period;
specifically, information data (for example, data of published information obtained from software such as microblogs and wechat) is periodically obtained through crawlers, purchases and the like, and the data includes but is not limited to: account basic information (number of fans, account id, etc.), article url, content, title, reading number, forwarding number, comment number, praise number, etc.
It should be noted that, for each piece of published information on the microblog, information data of the published information within several hours after being published is acquired at intervals of a specified period, such as half an hour. Generally, six hours can be set, because the change of the basic reading number, the forwarding number, the comment number and the like number is small after the published information is published for six hours, it is preferable to pay attention to the data within six hours after the published information is published.
It should be noted that the above example is only one embodiment, and does not indicate that after all published information is published for six hours, the changes of the basic reading number, the forwarding number, the comment number, and the approval number are small, and it is necessary to focus on data within several hours after the published information is published according to the actual situations of different published information.
S12, for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data;
wherein the information growth degree characterizes a degree of hotness of the published information.
And S13, sequencing the plurality of published information according to the information length increase corresponding to each published information and outputting a sequencing result.
Specifically, the issued information is sorted according to the sequence of the information growth degree from large to small, and the sorting result is output, so that the probability that the smaller sorting serial number becomes hot is higher, and the probability that the larger sorting serial number becomes hot is lower.
In this embodiment, information data of a plurality of pieces of published information in a preset time period is acquired, for each piece of published information, an information increase length of each piece of published information in the preset time period is calculated according to the information data, and the plurality of pieces of published information are sorted according to the information increase length corresponding to each piece of published information and a sorting result is output. The method and the device can obtain the sequencing result of the published information, the sequencing result with a smaller serial number can possibly become a hot event, and the hot event can be obtained by screening, so that the manpower input in the manual screening process is reduced.
Alternatively, on the basis of the foregoing embodiment, referring to fig. 2, step S12 may include:
s21, for each piece of published information, calculating data increasing length of the published information under different preset indexes in the preset time period according to the information data;
wherein the preset index comprises at least one of reading, forwarding, commenting, praise and playing amount.
Optionally, on the basis of this embodiment, referring to fig. 3, step S21 may include:
s31, for each piece of published information, acquiring data increment of the published information under a preset index according to the information data;
specifically, the published information is obtained from the information data, and the data increment of reading, forwarding, commenting and/or praise, i.e. the reading increment, the forwarding increment, the comment increment and/or the praise increment, is read, forwarded, commented and/or praise increment within a preset time period, for example, within one hour.
S32, calculating the increment slope of the issued information under a preset index according to the data increment;
specifically, the incremental slope may be k = [ INC (n) -INC (n-1) ]/([ (INC (n) + INC (n-1) ]/2)
Where INC (n) -INC (n-1) is a difference between the data increment of the predetermined time period and the data increment of the previous predetermined time period, such as a difference between the praise increment of the predetermined time period and the praise increment of the previous predetermined time period, and INC (n) + INC (n-1) is a sum of the data increment of the predetermined time period and the data increment of the previous predetermined time period.
As can be seen from the above formula, the incremental slope k is the ratio of the data increment difference to the average value of the increment.
S33, acquiring a historical data increment mean value of the account issuing the issued information under the preset index;
and the historical data increment mean value is an increment mean value in a historical time period corresponding to the preset time period.
Specifically, if the preset time period is 1.30-2.00, the historical time period is a historical data increment average value of 1.30-2.00 in a certain historical time period, such as the last month.
The average value of each historical data increment needs to be calculated in advance.
And S34, calculating to obtain the data increment length according to the increment slope, the data increment and the historical data increment average value.
Specifically, data increment =2 k (INC (n) + INC (n-1))/incremental mean of historical data.
Where k is the incremental slope.
S22, obtaining a weight value corresponding to each preset index;
specifically, the weight value corresponding to each preset index is preset, and technicians can determine the weight value according to a specific application scenario.
The weight value corresponding to each preset index may be the same or different, for example, the weight value of praise is 0.3, and the weight value of comment is 0.5.
S23, calculating to obtain the information increasing length according to the data increasing length of the issued information under different preset indexes and the weight value corresponding to each preset index.
Optionally, on the basis of this embodiment, the sum of products of data increasing lengths under different preset indexes and weight values of corresponding preset indexes is used as the information increasing length.
Specifically, the news increase length = the sum of products of data increase lengths under different preset indexes and weighted values of corresponding preset indexes.
In this embodiment, a method for calculating the data increment length is provided, and then the data increment length may be calculated by using the method in this embodiment, and then the information increment length may be calculated by using the data increment length.
Optionally, on the basis of the previous embodiment, before step S33, the method may further include:
1) Acquiring the increment of each article published by the account in each preset fixed period within a preset historical time period;
specifically, the fixed period may be half an hour, and in this step, the account number, such as the north-river daily newspaper, is acquired, and the increment of each published article in each half hour in a preset historical event period, such as 6 days of 2018.2.10-15, may be a reading increment, a forwarding increment, a comment increment, and/or a praise increment. The increase in the five and half hours after the release of an article can be taken at this time.
2) Determining the average index increment of the account in different fixed time periods according to the increment of each article in each preset fixed period;
specifically, the different fixed time periods may be every half hour of 24 hours a day as one fixed time period.
After the increase amount of each article in each preset fixed period is obtained, because the publication time of the article is known, the time of the article in each preset fixed period can be determined, and the time is corresponding to each half hour in 24 hours in a day and is used as the increase amount of the half hour.
If an article published at 12.00 noon at 2018.2.10, an increase of 500 at 12.30, the increase is put into an increase in the period corresponding to 12.30.
In 24 hours of a day, after the increment of each half hour is determined, dividing the sum of all the increments in the half hour by the number of articles with the increment in the half hour, namely the index average increment of the account in the half hour. Wherein the average increase in reading, average increase in forwarding, average increase in comments, and average increase in likes need to be calculated separately.
3) Acquiring the average increase of the index of the account in each fixed time period from the average increase of the index of the account in the historical time period;
4) And taking the obtained average increment of the index as the average value of the historical data increment.
And because the preset time period is determined, finding the preset time period from the fixed time period, and taking the found index average increment of the period as the index average increment in the historical time period.
Optionally, on the basis of this embodiment, if the historical data increment average value of the account publishing the published information under the preset index is not obtained, the method further includes:
1) Acquiring a historical data increment mean value of the preset index of a similar account belonging to the same type as the account within the historical preset time period;
2) And taking the historical data increment mean value corresponding to the similar account as the historical data increment mean value corresponding to the account.
Specifically, for example, the historical preset time period is two night points in the north river daily report, but the north river daily report generally publishes articles in the daytime and does not publishes articles in the evening, and then there is no historical data increment mean value at two night points, and at this time, an account number similar to the north river daily report, for example, the historical data increment mean value of the people daily report at two night points, can be used as the historical data increment mean value of the north river daily report.
In this embodiment, a method for determining the historical data increment average is provided, and the data increment length may be calculated by using the historical data increment average.
In addition, in the embodiment, the single issued information increment is compared with the average message increment, the possibility that the issued information is about to become popular is predicted, the account number average message condition of the issued information is considered, the influence of different time periods on the message is considered, and the value of each stage of the issued information fermentation is considered.
Optionally, on the basis of the above embodiment of the method for predicting a hot spot event, another embodiment of the present invention provides a device for predicting a hot spot event, and with reference to fig. 4, the method may include:
the data acquisition module 101 is configured to acquire information data of a plurality of published information within a preset time period;
the data calculation module 102 is configured to calculate, for each piece of published information, an information increase length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information;
the sorting output module 103 is configured to sort the multiple pieces of published information and output a sorting result according to the length increase of the information corresponding to each piece of published information.
In this embodiment, information data of a plurality of pieces of published information in a preset time period is acquired, for each piece of published information, an information increase length of each piece of published information in the preset time period is calculated according to the information data, and the plurality of pieces of published information are sorted and a sorting result is output according to the information increase length corresponding to each piece of published information. The method and the device can obtain the sequencing result of the published information, the sequencing result with a smaller serial number can possibly become a hot event, the hot event can be obtained by screening, and the human input in the manual screening process is reduced.
It should be noted that, for the working process of each module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of an embodiment of the device for predicting the previous hot spot event, the data calculation module includes:
the first calculation submodule is used for calculating the data increment length of each issued information under different preset indexes in the preset time period according to the information data;
the obtaining submodule is used for obtaining a weight value corresponding to each preset index;
and the second calculation submodule is used for calculating the information increasing length according to the data increasing length of the published information under different preset indexes and the weight value corresponding to each preset index.
Further, the sum of products of data increasing lengths under different preset indexes and weighted values of corresponding preset indexes is used as the information increasing length.
Further, the first computation submodule includes:
the first data acquisition unit is used for acquiring the data increment of each piece of published information under a preset index according to the information data;
the first calculation unit is used for calculating the increment slope of the issued information under a preset index according to the data increment;
the second data acquisition unit is used for acquiring the historical data increment mean value of the account issuing the issued information under the preset index; the historical data increment mean value is an increment mean value in a historical time period corresponding to the preset time period;
and the second calculation unit is used for calculating the data increment length according to the increment slope, the data increment and the historical data increment average value.
In this embodiment, a method for calculating the data increment length is provided, and then the data increment length may be calculated by using the method in this embodiment, and then the information increment length may be calculated by using the data increment length.
It should be noted that, for the working processes of each module, sub-module, and unit in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of the embodiment of the previous prediction apparatus, the method further includes:
the third data acquisition unit is used for acquiring the increment of each article published by the account in each preset fixed period within a preset historical time period;
the first determining unit is used for determining the average index increase of the account in different fixed time periods according to the increase of each article in each preset fixed period;
a fourth data obtaining unit, configured to obtain an average index increase amount in the historical time period from an average index increase amount of the account in each fixed time period;
and the second determining unit is used for taking the average increment of the acquired indexes as the historical data increment average value.
Optionally, if the historical data increment mean value of the account publishing the published information under the preset index is not obtained, the method further includes:
a fifth data obtaining unit, configured to obtain a historical data increment average value of the preset index in the historical preset time period for a similar account belonging to the same type as the account;
and the third determining unit is used for taking the historical data increment mean value corresponding to the similar account number as the historical data increment mean value corresponding to the account number.
In this embodiment, a method for determining the historical data increment average is provided, and the data increment length may be calculated by using the historical data increment average.
In addition, in the embodiment, the single issued information increment is compared with the average message increment, the possibility that the issued information is about to become popular is predicted, the account number average message condition of the issued information is considered, the influence of different time periods on the message is considered, and the value of each stage of the issued information fermentation is considered.
It should be noted that, for the working processes of each module, sub-module, and unit in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, an embodiment of the present invention further provides a device for predicting a hot spot event, where the device for predicting a hot spot event includes a processor and a memory, the data obtaining module, the data calculating module, the sorting output module, and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to one or more than one, and hot events are screened by adjusting kernel parameters. The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a storage medium, on which a program is stored, where the program, when executed by a processor, implements the method for predicting the hot event.
The embodiment of the invention provides a processor, which is used for running a program, wherein the method for predicting the hot event is executed when the program runs.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps:
a method for predicting a hotspot event comprises the following steps:
acquiring information data of a plurality of published information in a preset time period;
for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information;
and sequencing the plurality of pieces of published information according to the information length increase corresponding to each piece of published information and outputting a sequencing result.
Further, for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data, and the method comprises the following steps:
for each piece of published information, calculating the data increasing length of the published information under different preset indexes in the preset time period according to the information data;
acquiring a weight value corresponding to each preset index;
and calculating to obtain the information increasing length according to the data increasing length of the issued information under different preset indexes and the weight value corresponding to each preset index.
Further, the sum of products of data increasing lengths under different preset indexes and weighted values of corresponding preset indexes is used as the information increasing length.
Further, for each piece of published information, calculating the data increment length of the published information under different preset indexes in the preset time period according to the information data, and the method comprises the following steps:
for each piece of published information, acquiring data increment of the published information under a preset index according to the information data;
according to the data increment, calculating the increment slope of the issued information under a preset index;
acquiring a historical data increment mean value of the account publishing the published information under the preset index; the historical data increment mean value is an increment mean value in a historical time period corresponding to the preset time period;
and calculating to obtain the data increment length according to the increment slope, the data increment and the historical data increment average value.
Further, before obtaining the historical data increment mean value of the account publishing the published information under the preset index, the method further includes:
acquiring the increment of each article published by the account in each preset fixed period within a preset historical time period;
determining the average index increment of the account in different fixed time periods according to the increment of each article in each preset fixed period;
acquiring the average increase of the index of the account in each fixed time period from the average increase of the index of the account in the historical time period;
and taking the obtained average increment of the index as the average value of the historical data increment.
Further, if the historical data increment mean value of the account publishing the published information under the preset index is not obtained, the method further comprises the following steps:
acquiring a historical data increment mean value of the preset index of a similar account belonging to the same type as the account within the historical preset time period;
and taking the historical data increment mean value corresponding to the similar account number as the historical data increment mean value corresponding to the account number.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
a method for predicting a hotspot event comprises the following steps:
acquiring information data of a plurality of published information in a preset time period;
for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information;
and sequencing the plurality of pieces of published information according to the information length increase corresponding to each piece of published information and outputting a sequencing result.
Further, for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data, and the method comprises the following steps:
for each piece of published information, calculating the data increasing length of the published information under different preset indexes in the preset time period according to the information data;
acquiring a weight value corresponding to each preset index;
and calculating to obtain the information increasing length according to the data increasing length of the issued information under different preset indexes and the weight value corresponding to each preset index.
Further, the sum of products of data increasing lengths under different preset indexes and weighted values of corresponding preset indexes is used as the information increasing length.
Further, for each piece of published information, calculating the data increment length of the published information under different preset indexes in the preset time period according to the information data, and the method comprises the following steps:
for each piece of published information, acquiring data increment of the published information under a preset index according to the information data;
according to the data increment, calculating an increment slope of the issued information under a preset index;
acquiring a historical data increment mean value of the account publishing the published information under the preset index; the historical data increment mean value is an increment mean value in a historical time period corresponding to the preset time period;
and calculating to obtain the data increment length according to the increment slope, the data increment and the historical data increment average value.
Further, before obtaining the historical data increment mean value of the account publishing the published information under the preset index, the method further comprises the following steps:
acquiring the increment of each article published by the account in each preset fixed period within a preset historical time period;
determining the average index increase of the account in different fixed time periods according to the increase of each article in each preset fixed period;
acquiring the average increase of the index in the historical time period from the average increase of the index of the account in each fixed time period;
and taking the obtained average increment of the index as the average value of the historical data increment.
Further, if the historical data increment mean value of the account publishing the published information under the preset index is not obtained, the method further comprises the following steps:
acquiring a historical data increment mean value of the preset index of a similar account belonging to the same type as the account within the historical preset time period;
and taking the historical data increment mean value corresponding to the similar account number as the historical data increment mean value corresponding to the account number.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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 phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. A method for predicting a hotspot event is characterized by comprising the following steps:
acquiring information data of a plurality of published information in a preset time period;
for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information; for each piece of published information, calculating the information increment length of each piece of published information in the preset time period according to the information data, wherein the method comprises the following steps: for each piece of published information, calculating data increasing length of the published information under different preset indexes in the preset time period according to the information data, acquiring a weight value corresponding to each preset index, and calculating to obtain the information increasing length according to the data increasing length of the published information under the different preset indexes and the weight value corresponding to each preset index; the data increment length is related to an increment slope, a data increment and a historical data increment mean value;
and sequencing the plurality of pieces of published information according to the information length increase corresponding to each piece of published information and outputting a sequencing result.
2. The prediction method according to claim 1, wherein the sum of products of data increment lengths in different preset indicators and weight values of corresponding preset indicators is used as the information increment length.
3. The prediction method according to claim 1, wherein for each piece of published information, calculating, according to the information data, a data increment length of the published information under different preset indexes in the preset time period comprises:
for each piece of published information, acquiring data increment of the published information under a preset index according to the information data;
according to the data increment, calculating the increment slope of the issued information under a preset index;
acquiring a historical data increment mean value of the account publishing the published information under the preset index; the historical data increment mean value is an increment mean value in a historical time period corresponding to the preset time period;
and calculating to obtain the data increment length according to the increment slope, the data increment and the historical data increment average value.
4. The prediction method according to claim 3, wherein before obtaining the historical data increment average value of the account publishing the published information under the preset index, the method further comprises:
acquiring the growth amount of each article published by the account in each preset fixed period within a preset historical time period;
determining the average index increment of the account in different fixed time periods according to the increment of each article in each preset fixed period;
acquiring the average increase of the index of the account in each fixed time period from the average increase of the index of the account in the historical time period;
and taking the obtained average increment of the index as the average value of the historical data increment.
5. The prediction method according to claim 3, wherein if the historical data increment average value of the account publishing the published information under the preset index is not obtained, the method further comprises:
acquiring a historical data increment mean value of the preset index of a similar account belonging to the same type as the account within the historical preset time period;
and taking the historical data increment mean value corresponding to the similar account number as the historical data increment mean value corresponding to the account number.
6. An apparatus for predicting a hotspot event, comprising:
the data acquisition module is used for acquiring information data of a plurality of published information in a preset time period;
the data calculation module is used for calculating the information increment length of each piece of published information in the preset time period according to the information data; wherein the information growth degree characterizes the popularity of the published information; the data calculation module includes: the first calculation submodule is used for calculating the data increment length of the issued information under different preset indexes in the preset time period according to the information data for each issued information; the obtaining submodule is used for obtaining a weight value corresponding to each preset index; the second calculation submodule is used for calculating the information increasing length according to the data increasing length of the published information under different preset indexes and the weight value corresponding to each preset index; the data increment length is related to an increment slope, a data increment and a historical data increment mean value;
and the sequencing output module is used for sequencing the plurality of issued information according to the information length increment corresponding to each issued information and outputting a sequencing result.
7. A storage medium characterized by comprising a stored program, wherein the program executes the prediction method of a hotspot event according to any one of claims 1 to 5.
8. A processor configured to execute a program, wherein the program executes the method for predicting a hotspot event according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811268032.4A CN111104627B (en) | 2018-10-29 | 2018-10-29 | Hot event prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811268032.4A CN111104627B (en) | 2018-10-29 | 2018-10-29 | Hot event prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111104627A CN111104627A (en) | 2020-05-05 |
| CN111104627B true CN111104627B (en) | 2023-04-07 |
Family
ID=70420196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811268032.4A Active CN111104627B (en) | 2018-10-29 | 2018-10-29 | Hot event prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111104627B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004348680A (en) * | 2003-05-26 | 2004-12-09 | Fujitsu Ltd | Composite event notification system and composite event notification program |
| CN103136280A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术（上海）有限公司 | System and method of automatically searching hot point video |
| CN106971348A (en) * | 2016-01-14 | 2017-07-21 | 阿里巴巴集团控股有限公司 | A kind of data predication method and device based on time series |
| CN107798027A (en) * | 2016-09-06 | 2018-03-13 | 腾讯科技（深圳）有限公司 | A kind of heatrate Forecasting Methodology, information recommendation method and device |
| CN107943905A (en) * | 2017-11-17 | 2018-04-20 | 北京锐安科技有限公司 | A kind of much-talked-about topic analysis method and system |
| CN108090089A (en) * | 2016-11-23 | 2018-05-29 | 北京国双科技有限公司 | Detect the methods, devices and systems of hot spot data in website |
-
2018
- 2018-10-29 CN CN201811268032.4A patent/CN111104627B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004348680A (en) * | 2003-05-26 | 2004-12-09 | Fujitsu Ltd | Composite event notification system and composite event notification program |
| CN103136280A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术（上海）有限公司 | System and method of automatically searching hot point video |
| CN106971348A (en) * | 2016-01-14 | 2017-07-21 | 阿里巴巴集团控股有限公司 | A kind of data predication method and device based on time series |
| CN107798027A (en) * | 2016-09-06 | 2018-03-13 | 腾讯科技（深圳）有限公司 | A kind of heatrate Forecasting Methodology, information recommendation method and device |
| CN108090089A (en) * | 2016-11-23 | 2018-05-29 | 北京国双科技有限公司 | Detect the methods, devices and systems of hot spot data in website |
| CN107943905A (en) * | 2017-11-17 | 2018-04-20 | 北京锐安科技有限公司 | A kind of much-talked-about topic analysis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111104627A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105099729A (en) | User ID (Identification) recognition method and device | |
| EP2601623A2 (en) | Returning estimated value of search keywords of entire account | |
| CN109257398A (en) | A kind of method for pushing and equipment of business object | |
| CN111159341A (en) | Information recommendation method and device based on user investment and financing preference | |
| CN110929965A (en) | Project risk assessment method and device | |
| CN106651417B (en) | Advertisement delivery information analysis method and device | |
| CN105022807A (en) | Information recommendation method and apparatus | |
| CN107451204B (en) | Data query method, device and equipment | |
| CN110971544B (en) | Data transmission method and device | |
| CN111104627B (en) | Hot event prediction method and device | |
| CN110457182A (en) | A kind of load balancing cluster example operating index monitoring system | |
| CN112149011A (en) | Method and device for updating popularity ranking list, server and computer storage medium | |
| CN110851758B (en) | Webpage visitor quantity counting method and device | |
| CN108984572B (en) | Website information pushing method and device | |
| CN105335537A (en) | Estimation method and system of network media information exposure in video album | |
| CN114968028A (en) | Method, apparatus, and medium for dynamically changing menu layout based on user behavior analysis | |
| CN109597743B (en) | Page circling method, click rate statistical method and related equipment | |
| CN109947713B (en) | Log monitoring method and device | |
| CN106204125A (en) | A kind of pricing method and device | |
| CN108241643B (en) | Index data analysis method and device for keywords | |
| CN107516114B (en) | Time sequence processing method and device | |
| CN107463581B (en) | Application download amount acquisition method and device and terminal equipment | |
| CN113657635B (en) | Method for predicting loss of communication user and electronic equipment | |
| CN111898013A (en) | Website monitoring method and device | |
| CN106021425A (en) | Hot news mining 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 |