CN113254787B - Event analysis method, device, computer equipment and storage medium - Google Patents
Event analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113254787B CN113254787B CN202110694645.XA CN202110694645A CN113254787B CN 113254787 B CN113254787 B CN 113254787B CN 202110694645 A CN202110694645 A CN 202110694645A CN 113254787 B CN113254787 B CN 113254787B
- Authority
- CN
- China
- Prior art keywords
- event
- heat
- value
- analyzed
- curve
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application is applicable to the technical field of artificial intelligence, and provides an event analysis method, an event analysis device, computer equipment and a storage medium, wherein the event analysis method comprises the following steps: acquiring event news which is matched with an event to be analyzed and is within a preset time length; determining event heat and an event heat curve according to event news; determining a detection date according to the event heat curve, and determining value fluctuation of different target objects in the detection date respectively; determining an event influence value of the event to be analyzed on the target object according to the value fluctuation; if the event impact value of any target object is larger than the impact threshold value, determining that the event to be analyzed has a significant impact on the value of the target object. According to the method and the device, the event influence value of the event to be analyzed on different target objects can be effectively calculated according to the determined value fluctuation, whether the event to be analyzed has obvious influence on the value of different target objects or different types of target objects can be accurately judged based on the event influence value, and the analysis efficiency of the event analysis is improved.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence, and in particular, to an event analysis method, an event analysis device, a computer device, and a storage medium.
Background
The event analysis method is a demonstration research method and is applied to the financial field at the earliest. Event analysis methods are typically analysis methods for quantitatively measuring the extent to which an event, such as company dynamics, affects the value of a company. The basic idea of the event analysis method is to analyze the impact of a particular event on the value of a company by means of financial market data.
The existing event analysis method only can predict the influence of the event to be analyzed on one or the same class of articles, and cannot accurately predict the value influence of the event to be analyzed on different articles and different classes of articles, so that the analysis efficiency of the event analysis is reduced.
Disclosure of Invention
In view of this, the embodiments of the present application provide an event analysis method, apparatus, computer device, and storage medium, so as to solve the problem in the prior art that the influence of the event to be analyzed on different articles and different types of articles cannot be accurately predicted.
A first aspect of an embodiment of the present application provides an event analysis method, including:
responding to the received event description information for inquiring the event to be analyzed, and acquiring event news which is matched with the event description information and is within a preset time length;
determining the event heat of the event to be analyzed under different dates according to the number of the event news, and generating an event heat curve corresponding to the event to be analyzed;
determining a detection date according to a date corresponding to a peak point in the event heat curve and a preset date determining rule, and determining value fluctuation of different target objects in the detection date respectively;
determining event influence values of the events to be analyzed on different target objects according to the value fluctuation, wherein the event influence values are used for representing the influence degree of the events to be analyzed on the value of the target objects;
and if the event influence value of any target object is larger than the influence threshold value, determining that the event to be analyzed has a significant influence on the value of the target object.
Further, the determining the detection date according to the date corresponding to the peak point in the event heat curve and the preset date determining rule includes:
calculating an average value of heat peak points in a first preset time interval in the event heat curve to obtain a heat average value, and constructing a heat average value curve according to the heat average value;
filtering the event heat curve according to the heat mean curve to obtain a first candidate peak point set;
acquiring peak points in the event heat curve and the heat mean curve, and constructing a second candidate peak point set according to the acquired peak points;
acquiring an intersection set between the first candidate peak point set and the second candidate peak point set to obtain a backtracking date, and respectively calculating the sum of the backtracking date and different second preset time intervals to obtain the detection date.
Further, the filtering processing is performed on the event heat curve according to the heat mean curve to obtain a first candidate peak point set, including:
determining a heat difference curve between the event heat curve and the heat mean curve;
and filtering the event heat curve according to the heat difference curve to obtain the first candidate peak point set.
Further, the determining the event heat of the event to be analyzed under different dates according to the number of the event news includes:
respectively acquiring the occurrence date of the event news, and respectively determining the total news amount under different dates according to the acquired occurrence date;
and for each date, respectively inquiring the total news quantity of the current day, and calculating the quotient between the total news quantity corresponding to the total news quantity of the current day to obtain the event heat of the event to be analyzed under different dates.
Further, the determining the value fluctuation of different target objects within the detection date respectively includes:
and respectively calculating the expansion values of the target object in different detection dates, and calculating the average expansion of the target object in the detection dates according to the expansion values to obtain the value expansion.
Further, according to the value fluctuation, a calculation formula adopted for determining event influence values of the event to be analyzed on different target objects is as follows:
wherein AR is the target objectThe rise value in the detection date, m is the total number of the detection dates, test is the event impact value, AR_SD is the standard deviation of the rise value,is the value rise.
Further, the news recall of the event to be analyzed to obtain event news includes:
extracting event characteristics of the event to be analyzed from the event description information, and determining event labels of the event to be analyzed according to the event characteristics;
and inputting the event tag and the news in the preset time into a pre-trained recall model for recall, so as to obtain the event news.
A second aspect of an embodiment of the present application provides an event analysis apparatus, including:
the system comprises an event news acquisition unit, a search unit and a search unit, wherein the event news acquisition unit is used for responding to the received event description information for inquiring an event to be analyzed and acquiring event news which is matched with the event description information and is within a preset time length;
the event heat determining unit is used for determining the event heat of the event to be analyzed under different dates according to the number of the event news and generating an event heat curve corresponding to the event to be analyzed;
a value fluctuation calculation unit, configured to determine a detection date according to a date corresponding to a peak point in the event heat curve and a preset date determination rule, and determine value fluctuation of different target objects in the detection date respectively;
the event influence determining unit is used for determining event influence values of the event to be analyzed on different target objects according to the value fluctuation, wherein the event influence values are used for representing the influence degree of the event to be analyzed on the value of the target objects; and if the event influence value of any target object is larger than the influence threshold value, determining that the event to be analyzed has a significant influence on the value of the target object.
A third aspect of the embodiments of the present application provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the computer device, the processor implementing the steps of the event analysis method provided by the first aspect when the computer program is executed.
A fourth aspect of the embodiments provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the event analysis method provided by the first aspect.
According to the event analysis method, the event analysis device, the computer equipment and the storage medium, news related to the event to be analyzed is analyzed to obtain the detection date for detecting the target objects, and therefore the influence degree of the event to be analyzed on the value of the target objects is determined by analyzing the value fluctuation of each target object in the detection date. The method can be used for simultaneously predicting the influence degree of the event to be analyzed on the values of a plurality of target objects. In addition, the influence degree of the event to be analyzed on the values of the target objects is predicted at the same time, and compared with the fact that the influence degree of the value of one or the same class of target objects can only be predicted at one time in the related technology, the data analysis efficiency is higher, namely, the data analysis efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required for the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an implementation of an event analysis method provided in an embodiment of the present application;
FIG. 2 is a flow chart illustrating an implementation of a method for event analysis according to another embodiment of the present application;
fig. 3 is a block diagram of an event analysis device according to an embodiment of the present application;
fig. 4 is a block diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The event analysis method according to the embodiment of the present application may be executed by a control device or a terminal (hereinafter referred to as a "mobile terminal").
Referring to fig. 1, fig. 1 shows a flowchart of an implementation of an event analysis method provided in an embodiment of the present application, where the event analysis method is applied to any computer device, and the computer device may be a server, a mobile phone, a tablet or a wearable intelligent device, and the event analysis method includes:
step S10, responding to the received event description information for inquiring the event to be analyzed, and acquiring event news which is matched with the event description information and is within a preset time length;
wherein, the event to be analyzed is usually an event to be analyzed. In practice, the event to be analyzed may be an event that has already occurred, or may be an event that has not yet occurred. The event description information is generally information for describing an event to be analyzed. The implementation forms of the event description information may include, but are not limited to: text, speech, pictures, etc. The predetermined time period may be a predetermined time period. As an example, the above-mentioned preset time period may be 1 month, 1 year, 10 years, or the like. The event news is generally news information that matches the event description information. In practice, the event news described above is typically related to the event to be analyzed.
In this embodiment, the execution body may receive the event description information input by the user, and then acquire the event news matching the event description information from a target server, such as a search server providing a search service.
Optionally, in this step, the acquiring the event news matching with the event description information and within a preset time length may include:
and extracting event characteristics of the event to be analyzed from the event description information, and determining event labels of the event to be analyzed according to the event characteristics.
The event characteristics are used for representing event content of the event to be analyzed, and in the step, event labels of the event to be analyzed are determined by matching the event characteristics of the event to be analyzed with a prestored label lookup table, wherein corresponding relations between different event characteristics and corresponding event labels are stored in the prestored label lookup table.
And then inputting the event tag and the news in the preset time into a pre-trained recall model for recall, so as to obtain the event news.
The recall model is used for respectively extracting event labels of news in the preset time, outputting news which is the same as the event labels of the events to be analyzed, and obtaining the event news. The recall model is typically used to extract news including event tags from all news entered.
Step S20, determining the event heat of the event to be analyzed under different dates according to the number of event news, and generating an event heat curve corresponding to the event to be analyzed;
optionally, in this step, the determining, according to the number of event news, the event hotness of the event to be analyzed under different dates includes:
respectively acquiring the occurrence date of the event news, and respectively determining the total news amount under different dates according to the acquired occurrence date;
for each date, respectively inquiring the total news quantity of the day, and calculating the quotient between the total news quantity of the corresponding day and the total news quantity of the day to obtain the event heat of the event to be analyzed under different dates;
for example, for a date A1 within a preset time length, the total number of event news with the occurrence date being the date A1 is B1, and the total number of news on the day of the date A1 is C1, calculating a quotient between B1 and C1 to obtain an event heat of the event to be analyzed within the date A1, and it can be understood that the calculation of the corresponding event heat can be performed in the above manner for other dates within the preset time length, which is not described herein.
Specifically, in the step, a curve is drawn by taking dates in a preset time length as abscissa and event heat corresponding to different dates as a coordinate table, so as to obtain an event heat curve corresponding to the event to be analyzed, wherein the event heat curve is used for representing the relationship between the event to be analyzed and the corresponding event heat under different dates.
Step S30, determining a detection date according to a date corresponding to a peak point in the event heat curve and a preset date determining rule, and determining value fluctuation of different target objects in the detection date respectively;
the method comprises the steps that a target object is any object with value, such as a stock, a bond or any commodity, the peak point in the event heat curve is a coordinate point corresponding to a wave peak in the curve, and a plurality of different peak points can exist in the same event heat curve.
Specifically, in this step, the date corresponding to the peak point in the event heat curve is a trace-back date, and the preset date determination rule may be set according to the requirement, for example, the preset date determination rule may be set to set the time ranges within 7 days, 9 days and 19 days to the detection date, respectively, that is, when the trace-back date is 1 month 15 days, the detection date corresponding to the trace-back date is 1 month 12 to 1 month 18 days, 1 month 11 to 1 month 19 days and 1 month 6 to 1 month 24 days.
Optionally, in this step, the determining the value fluctuation of the different target objects within the detection date includes:
respectively calculating the expansion values of the target object in different detection dates, and calculating the average expansion of the target object in the detection dates according to the expansion values to obtain the value expansion;
wherein the expansion value is the interval profit value of the target object in the corresponding detection date, in the step, the expansion value F1, the expansion value F2 and the expansion value F3 are obtained by respectively calculating the expansion values of different target objects in different detection dates and calculating the average expansion of the same target object in different detection dates, for example, when the detection date is the detection date E1, the detection date E2 and the detection date E3, the expansion value of the target object D1 in the detection date E1, the detection date E2 and the detection date E3 is calculated respectively, and the average value among the expansion value F1, the expansion value F2 and the expansion value F3 is calculated to obtain the value expansion corresponding to the target object D1.
Step S40, determining event influence values of the events to be analyzed on different target objects according to the value fluctuation;
the event influence value is used for representing the influence degree of the event to be analyzed on the value of the target object, and in the step, according to the value fluctuation, a calculation formula adopted by the event influence value of the event to be analyzed on different target objects is determined as follows:
wherein AR is an expansion value of the target article within the detection date, m is a total number of the detection dates, test is the event impact value, AR_SD is a standard deviation of the expansion value,is the value rise.
Step S50, if the event influence value of any target object is larger than an influence threshold value, determining that the event to be analyzed has a significant influence on the value of the target object;
when the event influence value is larger, the influence degree of the event to be analyzed on the value of the target object is judged to be larger, namely, when the event to be analyzed occurs, the value fluctuation of the target object is larger, and when the event influence value is smaller, the influence degree of the event to be analyzed on the value of the target object is judged to be smaller, namely, when the event to be analyzed occurs, the event to be analyzed does not have a significant influence on the value of the target object, and the value fluctuation of the target object is not influenced by the event to be analyzed.
Specifically, the influence threshold may be set according to requirements, where the influence threshold is used to determine whether an event to be analyzed has a significant influence on the value of the target object corresponding to the event influence value.
In this embodiment, the news related to the event to be analyzed is analyzed to obtain the detection date for detecting the target object, so that the influence degree of the event to be analyzed on the value of the target object is determined by analyzing the value fluctuation of each target object in the detection date. The method can be used for simultaneously predicting the influence degree of the event to be analyzed on the values of a plurality of target objects. In addition, the influence degree of the event to be analyzed on the values of the target objects is predicted at the same time, and compared with the fact that the influence degree of the value of one or the same class of target objects can only be predicted at one time in the related technology, the data analysis efficiency is higher, namely, the data analysis efficiency is improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating an implementation of an event analysis method according to another embodiment of the present application. With respect to the embodiment of fig. 1, the event analysis method provided in this embodiment is used to further refine step S30 in the embodiment of fig. 1, and includes:
step S31, calculating an average value of heat peak points in a first preset time interval in the event heat curve to obtain a heat average value, and constructing a heat average value curve according to the heat average value;
the first preset time interval may be set according to requirements, and in this embodiment, the first preset time interval is set to 7 days, in this step, an average value of peak points of the heat of the event to be analyzed in 7 days is calculated through the event heat curve, so as to obtain the heat average value, and the heat average value curve is constructed according to the calculated heat average value, where the heat average value curve is used to represent a corresponding relationship between different 7-day interval times and heat average values of the event to be analyzed.
Specifically, in this step, a calculation formula adopted for calculating an average value of heat peak points in a first preset time interval in the event heat curve is as follows:
MA7 i ＝heat i-3 +…+heat i +…+heat i+3
MA7 i is the mean value of the heat corresponding to the event to be analyzed on the i day, heat i Is the event heat value corresponding to the event to be analyzed on the i day.
Step S32, filtering the event heat curve according to the heat mean curve to obtain a first candidate peak point set;
the filtering processing is performed on an event heat curve according to a heat mean curve to achieve an effect of peak point screening on the event heat curve, and specifically, in the step, the filtering processing is performed on the event heat curve according to the heat mean curve to obtain a first candidate peak point set, including:
determining a heat difference curve between the event heat curve and the heat mean curve, wherein the heat difference of the event heat curve and the heat mean curve on the same date is calculated respectively, and a curve is constructed according to the relation between the calculated heat difference and the corresponding date to obtain the heat difference curve;
and filtering the event heat curve according to the heat difference curve to obtain the first candidate peak point set, wherein the heat difference curve is compared with the event heat curve, if the heat value in the event heat curve is smaller than the heat value in the heat difference curve on the same date, deleting the coordinate point corresponding to the heat value in the event heat curve to achieve the filtering effect of the event heat curve, and setting the rest coordinate points in the event heat curve after the filtering process as the first candidate peak point set.
Step S33, obtaining peak points in the event heat curve and the heat mean curve, and constructing a second candidate peak point set according to the obtained peak points;
specifically, in this step, the constructing a second candidate peak point set according to the obtained peak points includes:
constructing a peak point neighborhood according to the peak point in the heat mean curve and a third preset time interval, wherein the third preset time interval can be set according to requirements, and the third preset time interval is set to 3 days in this embodiment, that is, in this step, the peak point in the heat mean curve is taken as a neighborhood center, and a region corresponding to 3 adjacent days is obtained, so as to obtain the peak point neighborhood, for example, when the date corresponding to the peak point in the heat mean curve is a date g, a region formed between the dates g-3 to g+3 in the heat mean curve and the corresponding heat value is set as the peak point neighborhood;
acquiring an intersection between a peak point in the event heat curve and the neighborhood of the peak point to obtain the second candidate peak point set, wherein if the peak point in any event heat curve is in the neighborhood of the peak point, the peak point in the event heat curve is extracted, and the second candidate peak point set is constructed according to the peak point in the extracted event heat curve.
Step S34, acquiring an intersection set between the first candidate peak point set and the second candidate peak point set to obtain a backtracking date, and respectively calculating the sum of the backtracking date and different second preset time intervals to obtain the detection date;
the backtracking date is used for representing an event fermentation peak date predicted by the event to be analyzed within a preset time, the second preset time interval and the number of intervals can be set according to requirements, in the step, the second preset time interval is set to be 5n, n is a preset natural number, and preferably, the second preset time interval in the embodiment comprises 5, 10, 15, 20, 25 and …;
for example, when the backtracking date is 1 month and 1 day, the second preset time interval includes 5, 10 and 15, the date of detection includes 1 month 1 day to 1 month 6 days, 1 month 1 day to 1 month 11 days, 1 month 1 day to 1 month 16 days.
In this embodiment, the average value of the heat peak points in the first preset time interval in the event heat curve is calculated to obtain the heat average value, and the heat average value curve is constructed according to the heat average value, so that the accuracy of filtering processing on the event heat curve is effectively improved, the effect of peak point screening on the event heat curve is achieved by filtering processing on the event heat curve according to the heat average value curve, the backtracking date can be accurately obtained by acquiring the intersection between the first candidate peak point set and the second candidate peak point set, the detection date corresponding to the event to be analyzed can be accurately calculated based on the backtracking date, and the accuracy of value fluctuation calculation corresponding to the target object is improved based on the detection date.
In all embodiments of the present application, the event impact value of the event to be analyzed on the target item is determined based on the value fluctuation, and in particular, the event impact value of the event to be analyzed on the target item is determined from the value fluctuation. Uploading the event impact value of the event to be analyzed on the target object to the blockchain can ensure the safety and the fairness and transparency to the user. The user equipment can download the event influence value of the event to be analyzed on the target object from the blockchain so as to check whether the event influence value of the event to be analyzed on the target object is tampered or not. The blockchain referred to in this example is a novel mode of application for computer technology such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Referring to fig. 3, fig. 3 is a block diagram illustrating an event analysis apparatus 100 according to an embodiment of the present application. The event analysis apparatus 100 in this embodiment includes units for executing the steps in the embodiments corresponding to fig. 1 and 2. Refer specifically to fig. 1 and fig. 2, and the related descriptions in the embodiments corresponding to fig. 1 and fig. 2. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 3, the event analysis apparatus 100 includes: an event news acquisition unit 10, an event heat determination unit 11, a value rise calculation unit 12, and an event influence determination unit 13, wherein:
and the event news acquisition unit 10 is used for responding to the received event description information for inquiring the event to be analyzed and acquiring event news matched with the event description information within a preset time length.
Wherein the event news acquisition unit 10 is further configured to: extracting event characteristics of the event to be analyzed from the event description information, and determining event labels of the event to be analyzed according to the event characteristics;
and inputting the event tag and the news in the preset time into a pre-trained recall model for recall, so as to obtain the event news.
An event heat determining unit 11, configured to determine, according to the number of event news, event heat of the event to be analyzed on different dates, and generate an event heat curve corresponding to the event to be analyzed.
The event heat determination unit 11 is further configured to: the determining the event heat of the event to be analyzed under different dates according to the number of the event news comprises the following steps:
respectively acquiring the occurrence date of the event news, and respectively determining the total news amount under different dates according to the acquired occurrence date;
and for each date, respectively inquiring the total news quantity of the current day, and calculating the quotient between the total news quantity corresponding to the total news quantity of the current day to obtain the event heat of the event to be analyzed under different dates.
A value rise calculation unit 12 for determining a detection date according to a date corresponding to a peak point in the event heat curve and a preset date determination rule, and determining value rises of different target articles within the detection dates, respectively.
Wherein the value rise calculation unit 12 is further configured to: calculating an average value of heat peak points in a first preset time interval in the event heat curve to obtain a heat average value, and constructing a heat average value curve according to the heat average value;
filtering the event heat curve according to the heat mean curve to obtain a first candidate peak point set;
acquiring peak points in the event heat curve and the heat mean curve, and constructing a second candidate peak point set according to the acquired peak points;
acquiring an intersection set between the first candidate peak point set and the second candidate peak point set to obtain a backtracking date, and respectively calculating the sum of the backtracking date and different second preset time intervals to obtain the detection date.
Optionally, the value rise calculation unit 12 is further configured to: determining a heat difference curve between the event heat curve and the heat mean curve;
and filtering the event heat curve according to the heat difference curve to obtain the first candidate peak point set.
Further, the value rise calculation unit 12 is also configured to: constructing a peak point neighborhood according to the peak point in the heat mean value curve and a third preset time interval;
and acquiring an intersection set between a peak point in the event heat curve and the neighborhood of the peak point to obtain the second candidate peak point set.
Further, the value rise calculation unit 12 is also configured to: and respectively calculating the expansion values of the target object in different detection dates, and calculating the average expansion of the target object in the detection dates according to the expansion values to obtain the value expansion.
An event influence determining unit 13, configured to determine event influence values of the event to be analyzed on different target objects according to the value fluctuation, where the event influence values are used to characterize the influence degree of the event to be analyzed on the value of the target object; and if the event influence value of any target object is larger than the influence threshold value, determining that the event to be analyzed has a significant influence on the value of the target object.
According to the value fluctuation, a calculation formula adopted for determining event influence values of the events to be analyzed on different target objects is as follows:
wherein AR is an expansion value of the target article within the detection date, m is a total number of the detection dates, test is the event impact value, AR_SD is a standard deviation of the expansion value,is the value rise.
In this embodiment, the news related to the event to be analyzed is analyzed to obtain the detection date for detecting the target object, so that the influence degree of the event to be analyzed on the value of the target object is determined by analyzing the value fluctuation of each target object in the detection date. The method can be used for simultaneously predicting the influence degree of the event to be analyzed on the values of a plurality of target objects. In addition, the influence degree of the event to be analyzed on the values of the target objects is predicted at the same time, and compared with the fact that the influence degree of the value of one or the same class of target objects can only be predicted at one time in the related technology, the data analysis efficiency is higher, namely, the data analysis efficiency is improved.
Fig. 4 is a block diagram of a computer device 2 according to another embodiment of the present application. As shown in fig. 4, the computer device 2 of this embodiment includes: a processor 20, a memory 21 and a computer program 22, such as a program of an event analysis method, stored in said memory 21 and executable on said processor 20. The steps of the various embodiments of the event analysis method described above, such as S10 to S50 shown in fig. 1 or S31 to S34 shown in fig. 2, are implemented when the processor 20 executes the computer program 23. Alternatively, the processor 20 may implement the functions of each unit in the embodiment corresponding to fig. 3, for example, the functions of the units 10 to 13 shown in fig. 3, when executing the computer program 22, and the detailed description of the embodiment corresponding to fig. 3 will be referred to herein, which is omitted.
Illustratively, the computer program 22 may be partitioned into one or more units that are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more elements may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used to describe the execution of the computer program 22 in the computer device 2. For example, the computer program 22 may be divided into an event news acquisition unit 10, an event heat determination unit 11, a value rise calculation unit 12, and an event impact determination unit 13, each of which functions specifically as described above.
The computer device may include, but is not limited to, a processor 20, a memory 21. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the computer device 2 and is not meant to be limiting as the computer device 2 may include more or fewer components than shown, or may combine certain components, or different components, e.g., the computer device may also include input and output devices, network access devices, buses, etc.
The processor 20 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. The memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the computer device 2. Further, the memory 21 may also include both an internal storage unit and an external storage device of the computer device 2. The memory 21 is used for storing the computer program and other programs and data required by the computer device. The memory 21 may also be used for temporarily storing data that has been output or is to be output.
Embodiments of the present application also provide a computer readable storage medium storing a computer program, which when executed by a processor, may implement the steps in the above-described method embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. A method of event analysis, comprising:
responding to the received event description information for inquiring the event to be analyzed, and acquiring event news which is matched with the event description information and is within a preset time length;
determining the event heat of the event to be analyzed under different dates according to the number of the event news, and generating an event heat curve corresponding to the event to be analyzed;
determining a detection date according to a date corresponding to a peak point in the event heat curve and a preset date determining rule, and determining value fluctuation of different target objects in the detection date respectively;
determining event influence values of the events to be analyzed on different target objects according to the value fluctuation, wherein the event influence values are used for representing the influence degree of the events to be analyzed on the value of the target objects;
if the event influence value of any one of the target objects is larger than an influence threshold value, determining that the event to be analyzed has a significant influence on the value of the target object;
wherein, the determining the detection date according to the date corresponding to the peak point in the event heat curve and the preset date determining rule includes:
calculating an average value of heat peak points in a first preset time interval in the event heat curve to obtain a heat average value, and constructing a heat average value curve according to the heat average value;
filtering the event heat curve according to the heat mean curve to obtain a first candidate peak point set, wherein the filtering comprises the following steps: determining a heat difference curve between the event heat curve and the heat mean curve; filtering the event heat curve according to the heat difference curve to obtain the first candidate peak point set;
acquiring peak points in the event heat curve and the heat mean curve, and constructing a second candidate peak point set according to the acquired peak points;
acquiring an intersection set between the first candidate peak point set and the second candidate peak point set to obtain a backtracking date, and respectively calculating the sum of the backtracking date and different second preset time intervals to obtain the detection date.
2. The event analysis method according to claim 1, wherein determining the event hotness of the event to be analyzed at different dates according to the number of event news comprises:
respectively acquiring the occurrence date of the event news, and respectively determining the total news amount under different dates according to the acquired occurrence date;
and for each date, respectively inquiring the total news quantity of the current day, and calculating the quotient between the total news quantity corresponding to the total news quantity of the current day to obtain the event heat of the event to be analyzed under different dates.
3. The event analysis method according to claim 1, wherein said determining the value fluctuation of the different target items within the detection dates, respectively, comprises:
and respectively calculating the expansion values of the target object in different detection dates, and calculating the average expansion of the target object in the detection dates according to the expansion values to obtain the value expansion.
4. The method of claim 1, wherein the calculation formula adopted for determining the event impact values of the event to be analyzed on different target objects according to the value fluctuation is:
wherein AR is an expansion value of the target object within the detection date, m is a total number of the detection dates, test is the event impact value,is the standard deviation of the amplitude value, < >>Is the value rise.
5. The event analysis method according to claim 1, wherein the acquiring the event news matching the event description information for a preset time length includes:
extracting event characteristics of the event to be analyzed from the event description information, and determining event labels of the event to be analyzed according to the event characteristics;
and inputting the event tag and the news in the preset time into a pre-trained recall model for recall, so as to obtain the event news.
6. An event analysis apparatus, comprising:
the system comprises an event news acquisition unit, a search unit and a search unit, wherein the event news acquisition unit is used for responding to the received event description information for inquiring an event to be analyzed and acquiring event news which is matched with the event description information and is within a preset time length;
the event heat determining unit is used for determining the event heat of the event to be analyzed under different dates according to the number of the event news and generating an event heat curve corresponding to the event to be analyzed;
a value fluctuation calculation unit, configured to determine a detection date according to a date corresponding to a peak point in the event heat curve and a preset date determination rule, and determine value fluctuation of different target objects in the detection date respectively;
the event influence determining unit is used for determining event influence values of the event to be analyzed on different target objects according to the value fluctuation, wherein the event influence values are used for representing the influence degree of the event to be analyzed on the value of the target objects; if the event influence value of any one of the target objects is larger than an influence threshold value, determining that the event to be analyzed has a significant influence on the value of the target object;
wherein, the determining the detection date according to the date corresponding to the peak point in the event heat curve and the preset date determining rule includes:
calculating an average value of heat peak points in a first preset time interval in the event heat curve to obtain a heat average value, and constructing a heat average value curve according to the heat average value;
filtering the event heat curve according to the heat mean curve to obtain a first candidate peak point set, wherein the filtering comprises the following steps: determining a heat difference curve between the event heat curve and the heat mean curve; filtering the event heat curve according to the heat difference curve to obtain the first candidate peak point set;
acquiring peak points in the event heat curve and the heat mean curve, and constructing a second candidate peak point set according to the acquired peak points;
acquiring an intersection set between the first candidate peak point set and the second candidate peak point set to obtain a backtracking date, and respectively calculating the sum of the backtracking date and different second preset time intervals to obtain the detection date.
7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110694645.XA CN113254787B (en) | 2021-06-22 | 2021-06-22 | Event analysis method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110694645.XA CN113254787B (en) | 2021-06-22 | 2021-06-22 | Event analysis method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113254787A CN113254787A (en) | 2021-08-13 |
| CN113254787B true CN113254787B (en) | 2023-07-21 |
Family
ID=77189231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110694645.XA Active CN113254787B (en) | 2021-06-22 | 2021-06-22 | Event analysis method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113254787B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956874A (en) * | 2023-07-17 | 2023-10-27 | 广东南方智媒科技有限公司 | Event context generation method based on news data, terminal equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344316A (en) * | 2018-08-14 | 2019-02-15 | 优视科技（中国）有限公司 | News temperature calculates method and device |
| CN110929198A (en) * | 2019-12-05 | 2020-03-27 | 中国银行股份有限公司 | Hot event display method and device |
| CN111461775A (en) * | 2020-03-30 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Method and device for determining influence of event on traffic |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100287146A1 (en) * | 2009-05-11 | 2010-11-11 | Dean Skelton | System and method for change analytics based forecast and query optimization and impact identification in a variance-based forecasting system with visualization |
-
2021
- 2021-06-22 CN CN202110694645.XA patent/CN113254787B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344316A (en) * | 2018-08-14 | 2019-02-15 | 优视科技（中国）有限公司 | News temperature calculates method and device |
| CN110929198A (en) * | 2019-12-05 | 2020-03-27 | 中国银行股份有限公司 | Hot event display method and device |
| CN111461775A (en) * | 2020-03-30 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Method and device for determining influence of event on traffic |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113254787A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101708444B1 (en) | Method for evaluating relation between keyword and asset value and Apparatus thereof | |
| CN111401609A (en) | Prediction method and prediction device for traffic flow time series | |
| CN111814910B (en) | Abnormality detection method, abnormality detection device, electronic device, and storage medium | |
| CN112529663B (en) | Commodity recommendation method, commodity recommendation device, terminal equipment and storage medium | |
| EP3608802A1 (en) | Model variable candidate generation device and method | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN113254787B (en) | Event analysis method, device, computer equipment and storage medium | |
| CN118396786A (en) | Contract document auditing method and device, electronic equipment and computer readable storage medium | |
| JP7170689B2 (en) | Output device, output method and output program | |
| CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN111275071B (en) | Prediction model training method, prediction device and electronic equipment | |
| CN113282837B (en) | Event analysis method, device, computer equipment and storage medium | |
| CN111639213A (en) | Abnormal behavior identification method and device | |
| CN112328779B (en) | Training sample construction method, device, terminal equipment and storage medium | |
| CN114418743A (en) | Account information detection method, device, equipment, storage medium and program product | |
| Caferoglu et al. | Measuring Technology Diffusion for the Case of RFID Technology: A Comparison between tf-lag-idf and Topic Modeling | |
| CN113901817A (en) | Document classification method and device, computer equipment and storage medium | |
| CN113434660A (en) | Product recommendation method, device, equipment and storage medium based on multi-domain classification | |
| CN113849618A (en) | Strategy determination method and device based on knowledge graph, electronic equipment and medium | |
| CN113656649A (en) | Generation and storage algorithm and system for label portrait data | |
| CN111382343A (en) | Label system generation method and device | |
| CN116775623A (en) | Quality inspection method and device for label data in user portrait, terminal equipment and medium | |
| CN112396445B (en) | Method and device for identifying user identity information | |
| KR20170057179A (en) | Method for evaluating relation between keyword and asset value and Apparatus thereof | |
| CN117541885A (en) | Sample data processing method, device, storage medium and system |
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 |