CN110489631A - Stock market development method, apparatus, computer equipment and storage medium - Google Patents
Stock market development method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110489631A CN110489631A CN201910620463.0A CN201910620463A CN110489631A CN 110489631 A CN110489631 A CN 110489631A CN 201910620463 A CN201910620463 A CN 201910620463A CN 110489631 A CN110489631 A CN 110489631A
- Authority
- CN
- China
- Prior art keywords
- media event
- data
- stock market
- label
- return
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000001186 cumulative effect Effects 0.000 claims description 132
- 230000002159 abnormal effect Effects 0.000 claims description 125
- 230000001550 time effect Effects 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 27
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 claims description 4
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 230000018109 developmental process Effects 0.000 description 36
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 238000002372 labelling Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Abstract
This application involves big data technical field, in particular to a kind of stock market development method, apparatus, computer equipment and storage medium.The described method includes: receiving the media event data to be processed that target terminal is sent；Text identification is carried out to media event data to be processed and obtains the first text data, corresponding first label of media event to be processed is obtained according to the first text data；When there is the second label with the first tag match in presetting database, acquisition and the associated stock market's trend curve of the second label, the second label are obtained based on history media event data, with the label of stock market's trend curve associated storage in the preset database；Relevant prediction result is obtained according to stock market's trend curve, and prediction result is back to target terminal.Stock market development can carried out using this method, improving the efficiency of stock market development.
Description
Technical field
This application involves big data technical fields, set more particularly to a kind of stock market development method, apparatus, computer
Standby and storage medium.
Background technique
With the development of market economy, the status that securities market is occupied in modern society with financial investment is increasingly heavier
It wants.Quotations on the stock market also will receive various news impacts, such as international environment, national policy, economic situation and subtle
The personnel at place change etc., may all will affect quotations on the stock market, and cumulative abnormal rate of return (Cumulative Abnormal
Return, CAR), represent the change conditions of stock, it may be said that bright share price, can be significantly by event effect
Illustrate the subsequent trend of stock market.
However, currently to the prediction of cumulative abnormal rate of return, and the prediction to stock market's trend, it is all by periodically collecting
Marketing data predicts stock market's trend according to the feature of stock market's tendency curves, but the formation of stock market's tendency tendency chart needs
After wanting media event to occur, the stock market data for collecting the long period could be formed, cannot be timely right after media event generation
Stock market's trend is predicted that the efficiency of prediction is not high enough.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of news that can be improved stock market development efficiency
Event and stock market development method, apparatus, computer equipment and storage medium.
A kind of stock market development method, which comprises
Receive the media event data to be processed that target terminal is sent；
Text identification is carried out to the media event data to be processed and obtains the first text data, according to first text
Data obtain corresponding first label of the media event to be processed；
When there is the second label with the first tag match in presetting database, obtain associated with second label
Stock market's trend curve, wherein second label is to be obtained based on history media event data, and be associated with stock market's trend curve
The label of storage in the preset database；
Prediction result relevant to the media event to be processed is obtained according to stock market's trend curve, and will be described pre-
It surveys result and is back to the target terminal.
The stock market development method in one of the embodiments, further include:
Text identification is carried out to history media event data and obtains the second text data, is obtained according to second text data
To corresponding second label of the history media event；
Obtain the stock in the time adjacent segments of timing node and the timing node that the history media event occurs
City's avail data, and the cumulative abnormal rate of return in time adjacent segments is calculated according to the dividend yield data；
According to the cumulative abnormal rate of return in the time adjacent segments, stock market's trend curve is drawn；
Second label and stock market's trend curve are associated and stored into the presetting database.
It is described in one of the embodiments, that according to second text data to obtain the history media event corresponding
After second label, further includes:
It identifies the type of second label, obtains the corresponding stock market's trend float attribute of second tag types；
Corresponding cumulative abnormal rate of return computation model is determined according to stock market's trend float attribute；
It is described that the timing node time adjacent segments that the history media event occurs are calculated according to the dividend yield data
Interior daily cumulative abnormal rate of return, comprising:
The history media event is calculated according to the cumulative abnormal rate of return computation model and the dividend yield data
Daily cumulative abnormal rate of return cumulative abnormal rate of return in the timing node time adjacent segments of generation.
In one of the embodiments, after the acquisition history media event data, further includes:
Obtain the spacial influence force data in the history media event data；
The corresponding spatial influence grade of the history media event is obtained according to the spacial influence force data；
It determines the corresponding data influence range of the spatial influence grade, obtains third mark within the scope of the data influence
The history media event of label and second tag match；
The dividend yield data for obtaining the timing node time adjacent segments that history media event occurs, and according to described
Dividend yield data calculate cumulative transformation daily in the timing node time adjacent segments that the history media event occurs
Rate, comprising:
Obtain the dividend yield for the timing node time adjacent segments that the corresponding history media event of the third label occurs
Data, and the timing node phase that the corresponding history media event of the third label occurs is calculated according to the dividend yield data
The average value of daily cumulative abnormal rate of return in the adjacent period.
In one of the embodiments, after acquisition history media event data, further includes:
Obtain the time effects force data in the history media event data；
The corresponding time effects power grade of the history media event is obtained according to the time effects force data；
It determines the corresponding influence duration of the time effects power grade, preset number of days is obtained according to the influence duration.
It is described in one of the embodiments, to calculate what the history media event occurred according to the dividend yield data
Daily cumulative abnormal rate of return in timing node time adjacent segments, comprising:
Day is preset before cumulative abnormal rate of return daily in the intermediate node time adjacent segments is divided into the timing node
Cumulative abnormal rate of return daily in preset number of days after daily cumulative abnormal rate of return and the timing node in number；
First trend type is obtained according to cumulative abnormal rate of return daily in preset number of days before the timing node, according to
Cumulative abnormal rate of return daily in preset number of days obtains second trend type after the timing node；
Stock market's trend type is determined according to the first trend type and the second trend type；
It is described according to cumulative abnormal rate of return daily in the timing node time adjacent segments, it is bent to draw stock market's trend
Line, comprising:
Stock market's trend curve is drawn according to stock market's trend type.
A kind of stock market development device, described device include:
Receiving module, for receiving the media event data to be processed of target terminal transmission；
Text identification module obtains the first textual data for carrying out text identification to the media event data to be processed
According to obtaining corresponding first label of the media event to be processed according to first text data；
Obtain module, for when there is the second label with the first tag match in presetting database, obtain with it is described
The associated stock market's trend curve of second label, wherein second label be obtained based on history media event data, and with stock
The label of city's trend curve associated storage in the preset database；
Output module is tied for obtaining prediction relevant to the media event to be processed according to stock market's trend curve
Fruit, and the prediction result is back to the target terminal.
Described device in one of the embodiments, further include:
Second text identification module obtains the second text data for carrying out text identification to history media event data,
Corresponding second label of the history media event is obtained according to second text data；
Second obtains module, the timing node and the timing node occurred for obtaining the history media event
Time adjacent segments in dividend yield data, and calculate according to the dividend yield data accumulation in the time adjacent segments
Excess return；
Drafting module, for drawing stock market's trend curve according to the cumulative abnormal rate of return in the time adjacent segments；
Memory module is stored for second label and stock market's trend curve to be associated to the present count
According in library.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes the above method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above method is realized when row.
Above-mentioned stock market development method, apparatus, computer equipment and storage medium, server are receiving target terminal hair
After the media event data to be processed sent, text identification is carried out to media event data to be processed and obtains the first text data, the
One circumferential edge is the data of stock market's trend may to be influenced in media event data, and obtain according to the first text data to be processed
Corresponding first label of media event, the first label are then the critical data in media event data, by critical data therein
It is set as the first label.And when there is the second label with the first tag match in presetting database, obtain and the second label
Associated stock market's trend curve, wherein the second label be obtained based on history media event data, and with stock market's trend curve
The label of associated storage in the preset database；According to the matching relationship of label, by with the associated stock market's trend of the second label
Curve obtains prediction result relevant to media event to be processed, and prediction result is back to target terminal, can carry out
When stock market development, the corresponding stock market of history media event data of tag match is obtained by media event label to be processed
Trend curve makes stock market development according to stock market's trend curve, improves the efficiency of stock market development.
Detailed description of the invention
Fig. 1 is the application scenario diagram of stock market development method in one embodiment；
Fig. 2 is the flow diagram of stock market development method in one embodiment；
Fig. 3 be in one embodiment history media event data generate and with the step of stock market's trend curve associated storage
Flow diagram；
Fig. 4 is the structural block diagram of stock market development device in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Stock market development method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, mesh
Mark terminal 102 is communicated by network with server 104.Server 104 is receiving the to be processed new of the transmission of target terminal 102
After hearing event data, text identification is carried out to media event data to be processed and obtains the first text data, and according to the first text
Data obtain corresponding first label of media event to be processed, mark when existing in presetting database with the second of the first tag match
When label, obtain stock market's trend curve with the associated storage of the second tag match, as with the associated stock market's curve of the first label,
Wherein, the second label is obtained based on history media event data, and with stock market's trend curve associated storage in preset data
Label in library；Prediction result relevant to media event to be processed is obtained according to stock market's curve, and prediction result is back to
Target terminal 104.Wherein, target terminal 102 can be, but not limited to be various personal computers, laptop, smart phone,
Tablet computer and portable wearable device, server 104 can use the either multiple server compositions of independent server
Server cluster is realized.
In one embodiment, as shown in Fig. 2, providing a kind of stock market development method, it is applied to Fig. 1 in this way
In server 104 for be illustrated, comprising the following steps:
Step 202, the media event data to be processed that target terminal is sent are received.
Specifically, server receive target terminal send media event data to be processed, wherein target terminal send to
The opportunity for handling media event data can be for periodically, for example can be set as uploading for every 24 hours primary, or
Triggering property, for example when stock market's trend occurs abnormal, current media event is obtained, media event is sent to service by terminal
Device, in addition, the type for the media event data to be processed that target terminal is sent can be various possible influence company stock market's trend
Media event data, for example economic crisis, inflation or Top Management are left office, stockpiling of unsold product etc., form packet
Include but be not limited to text data, code data, web page interlinkage etc., according to the difference of media event form to be processed, server
Received content can also be different, for example when media event to be processed is web page interlinkage, server can receive target terminal
What is sent presses web page interlinkage, does not need other detailed datas.In addition, target terminal can be to possess access server
The permission of other media event data, target terminal can check other news after sending media event data to be processed
Event data.
Step 204, text identification is carried out to media event data to be processed and obtains the first text data, according to the first text
Data obtain corresponding first label of media event to be processed.
Specifically, after the media event data to be processed that server receives terminal upload, to media event to be processed
Data carry out text identification, obtain the first text data of media event data to be processed, the first text data after text identification
Content can indicate the event type of media event to be processed.Server passes through preset mark according to the first text data
Label algorithm obtains corresponding first label of the first text data, wherein the preset algorithm that labels can compose news for Euler diagram
Labeling algorithm etc. labels algorithm, and the process of labelling can analyze result to be processed according to the data characteristics of the first text data
Media event labels, for example when media event to be processed is that Top Management leaves office, the algorithm that labels can be to company
Senior executive departing event stamps first labels such as " coverage is only our company ", " it is shorter to continue event ", " high-rise staff redeployment ",
It will be seen that the event type and feature of media event to be processed by the first label.
Step 206, it when there is the second label with the first tag match in presetting database, obtaining and being closed with the second label
Stock market's trend curve of connection, wherein the second label is to be obtained based on history media event data, and be associated with stock market's trend curve
The label of storage in the preset database.
Specifically, the second label is server by obtaining history media event data, and according to history media event number
According to progress text identification and the default label that algorithm obtains, corresponding with history media event that labels, and according to history
The second label that media event data obtain is with the stock market's trend curve for the timing node that corresponding history media event occurs
Associated storage.Presetting database is for storing the second label.Server by corresponding first label of media event to be processed with
Corresponding second label of history media event is matched, and is detected corresponding with the presence or absence of history media event in presetting database
Second label, first tag match corresponding with media event to be processed, in order in the historical data search with it is to be processed
The matched history media event of media event.Wherein, tag match process can be searched whether in the second label exist with
The identical label of the tag types of first label, result matched in this way can find corresponding with the first label wait locate
Manage the identical history media event of media event type；Tag match similarity degree, i.e. fuzzy matching can also be preset, when
Exist when reaching preset value with the tag match similarity degree of the first label in second label, then exists and the first tag match
Second label, such as when the similarity degree of label reaches 80% or more, then be considered as same type label, the first label it is corresponding to
Processing media event history media event corresponding with the second label can also be considered as same type event.It is corresponding according to the second label
The available associated storage of history media event data stock market's trend curve, wherein dividend yield curve can be by going through
The dividend yield data calculating and plotting for the timing node that history media event occurs obtains.When server detect the presence of with it is to be processed
When corresponding second label of the history media event of corresponding first tag match of media event, acquisition is associated with the second label is deposited
Stock market's trend curve of storage.
Step 208, prediction result relevant to media event to be processed is obtained according to stock market's trend curve, and prediction is tied
Fruit is back to the target terminal.
Specifically, it gets in server with after stock market's trend curve of the second label associated storage, is become according to stock market
The trend of power curve is moved towards to obtain stock market's trend trend of media event to be processed, is moved towards to obtain stock market's trend according to stock market's trend
Prediction result, and stock market development result is back to target terminal, it is referred to for the user of target terminal.
In above-mentioned stock market development method, server is in the media event data to be processed for receiving target terminal transmission
Afterwards, text identification is carried out to media event data to be processed and obtains the first text data, and according to the first text data obtain to
Corresponding first label of media event being handled, when there is the second label with the first tag match in presetting database, being obtained
With the associated stock market's trend curve of the second label, wherein the second label be obtained based on history media event data, and with stock
The label of city's trend curve associated storage in the preset database；It is obtained according to stock market's curve relevant to media event to be processed
Prediction result, and prediction result is back to target terminal.News thing to be processed can be passed through when carrying out stock market development
Part label obtains the corresponding stock market's trend curve of history media event data of matching label, makes stock according to stock market's trend curve
City's trend prediction improves the efficiency of stock market development.
In one embodiment, being previously mentioned the second label is to be generated according to history media event data and become with stock market
Power curve associated storage, as shown in figure 3, history media event data generate and the step of with stock market's trend curve associated storage
May include:
Step 302, text identification is carried out to history media event data and obtains the second text data, according to the second textual data
According to obtaining corresponding second label of history media event.
Specifically, after server obtains history media event data, text identification, text are carried out to history news data
The second text data of history media event data is obtained after identification, the content of the second text data can substantially indicate that history is new
It is corresponding to obtain the second text data by the preset algorithm that labels according to the second text data for the event type of news event
Second label will be seen that the event type and feature of history media event by the second label.
Step 304, the stock in the time adjacent segments of timing node and timing node that history media event occurs is obtained
City's avail data, and the cumulative abnormal rate of return in time adjacent segments is calculated according to dividend yield data.
Specifically, it is new to obtain history after obtaining history media event data from history media event data for server
The timing node that news event occurs, and the timing node time adjacent segments that history media event occurs are obtained according to preset number of days
Dividend yield data, dividend yield data can be daily stock market's opening price in preset number of days, closing price, amount of increase index etc.
Then it is super to calculate daily accumulation according to dividend yield data daily before and after time of origin node time adjacent segments for avail data
Volume earning rate, wherein the daily cumulative abnormal rate of return numerical value being calculated can probably indicate stock market's trend by news thing
The influence degree of part, calculating for daily cumulative abnormal rate of return can be according to the closing price and media event generation on the day of stock market
The difference of the closing price on the same day is obtained than the closing price that the same day occurs for upper media event.Specific cumulative abnormal rate of return calculated
Journey can be with for example: server detects that preset number of days is 20 days, then obtain and go through after obtaining history media event data
The timing node that 20 days stock market's closing prices and history media event occur before and after the timing node that history media event occurs
Stock market's closing price, timing node front and back 20 days the stock market's closing prices and history news then occurred according to history media event
The stock market's closing price for the timing node that event occurs calculates 20 days before and after timing node cumulative abnormal rate of return.
Step 306, according to cumulative abnormal rate of return, stock market's trend curve is drawn.
Specifically, the cumulative premium of the timing node time adjacent segments of history media event generation is calculated in server
After earning rate, stock market's trend curve can be drawn according to the cumulative abnormal rate of return numerical value of time adjacent segments, pass through adjacent time
Stock market's trend curve of the cumulative abnormal rate of return numeric renderings of section can substantially indicate stock market's trend by history media event
Influence degree.
Step 308, the second label and stock market's trend curve are associated and are stored into presetting database.
Specifically, server is by the second label and according to the stock market of the corresponding history media event data drafting of the second label
Trend curve associated storage, stock market when by determining that corresponding second label of history media event and history media event occur
The incidence relation of trend curve determines the incidence relation of label Yu stock market's trend curve, facilitates the news to be processed of subsequent generation
When tag match in the label and incidence relation of event data, stock market's trend curve of relationship can be directly acquired, after saving
Continuous calculating operation improves the preset efficiency of stock market's trend.
In above-mentioned stock market development method, server is obtaining second to history media event data progress text identification
Text data obtains corresponding second label of history media event according to the second text data；History media event is obtained to occur
Timing node time adjacent segments dividend yield data, and according to dividend yield data calculate history media event occur when
Daily cumulative abnormal rate of return in intermediate node time adjacent segments；According to cumulative premium daily in timing node time adjacent segments
Earning rate draws stock market's trend curve；Second label and stock market's trend curve are associated storage.By determining history news
Event and stock market's trend curve incidence relation, facilitate in the label and incidence relation of media event data to be processed of subsequent generation
Tag match when, stock market's trend curve of relationship can be directly acquired, save subsequent calculating operation, improve stock market's trend
Preset efficiency.
In one embodiment, stock market development method is obtaining history media event correspondence according to the second text data
The second label after, can also include: the type for identifying the second label, it is floating to obtain the corresponding stock market's trend of the second tag types
Dynamic attribute；Corresponding cumulative abnormal rate of return computation model is determined according to stock market's trend float attribute；According to dividend yield data
Calculate cumulative abnormal rate of return daily in the timing node time adjacent segments that history media event occurs, comprising: according to accumulation
Excess return computation model and dividend yield data calculate every in the timing node time adjacent segments that history media event occurs
It cumulative abnormal rate of return cumulative abnormal rate of return.
Specifically, trend float attribute in stock market's can indicate the stability of the corresponding stock market's trend curve of history media event
By the influence degree size of stock market's deep bid index or stock market's index sector, when stock market's deep bid index or stock market's index sector can be very big
When the influence stock market trend curve of degree, corresponding stock market's trend float attribute is to be easier float type.Server is according to
After two text datas obtain corresponding second label of history media event, it can judge that correspondence is gone through according to the type of the second label
Trend float attribute in stock market's corresponding to history media event, specific judgment method can be according to the expression trend in the second label
The label of stability judges, for example, according in the second label " stock market data is unstable, when stock market's deep bid data variation variation compared with
The labels judgement such as greatly ", or the judgement of stability stock market of the corresponding same type media event data of type according to the second label
The float attribute of trend floats according to stock market's trend and belongs to after judgement obtains the corresponding stock market's trend float attribute of the second label
Property determines corresponding cumulative abnormal rate of return computation model.Wherein, when stock market's trend float attribute is to be easier float type, sentence
Stranded city's trend curve by stock market's deep bid index or stock market's index sector influence degree size, when stock market's trend curve is by big
When the influence degree of disk index is greater than predeterminable level value, the corresponding cumulative abnormal rate of return computation model of stock market's trend float attribute
It is corresponding in subsequent calculating for the computation model for removing stock market's deep bid index, it is big that stock market is removed from dividend yield data
Disk index, when adjacent according to the timing node of the dividend yield data calculating history media event generation of removal stock market's deep bid index
Between cumulative abnormal rate of return daily in section, prevent the drafting of deep bid exponential effect stock market, stock market trend curve and subsequent
Stock market development；Similarly, when stock market's trend curve is greater than predeterminable level value by the influence degree of index sector, stock market's trend
The corresponding cumulative abnormal rate of return computation model of float attribute is the computation model for removing stock market's index sector, corresponding subsequent
Calculating in, from dividend yield data remove stock market's index sector, according to removal stock market's index sector dividend yield data
Calculate cumulative abnormal rate of return daily in the timing node time adjacent segments that history media event occurs；In addition, when stock market becomes
When power curve is all larger than predeterminable level value by the influence degree of index sector and deep bid index, stock market's trend float attribute is corresponding
Cumulative abnormal rate of return computation model be the computation model for removing stock market's deep bid index and stock market's index sector, it is corresponding rear
In continuous calculating, stock market's deep bid index and stock market's index sector are removed from dividend yield data, according to removal stock market's deep bid
The dividend yield data of index and stock market's index sector calculate in the timing node time adjacent segments that history media event occurs
Daily cumulative abnormal rate of return.
In above-described embodiment, it is floating to determine that history media event corresponds to stock market's trend according to the corresponding label of history media event
Dynamic attribute when stock market's trend curve is easy to be interfered by other stock market datas, can remove other interference data, prevent it
He interfere data influence stock market trend curve drafting and subsequent stock market development.
In one embodiment, stock market development method can also include: after obtaining history media event data
Obtain the spacial influence force data in history media event data；It is corresponding that history media event is obtained according to spacial influence force data
Spatial influence grade；It determines the corresponding data influence range of spatial influence grade, obtains third within the scope of data influence
The history media event of label and the second tag match；Obtain the stock for the timing node time adjacent segments that history media event occurs
City's avail data, and calculated according to dividend yield data daily in the timing node time adjacent segments that history media event occurs
Cumulative abnormal rate of return, comprising: obtain the timing node time adjacent segments that the corresponding history media event of third label occurs
Dividend yield data, and the timing node phase that the corresponding history media event of third label occurs is calculated according to dividend yield data
The average value of daily cumulative abnormal rate of return in the adjacent period.
It specifically, can be according to history media event data acquisition after server obtains history media event data
Certain model in front and back can occur by analysis of history media event for spacial influence force data therein, spacial influence force data
Stock market's trend curve in enclosing obtains, for example when front and back occurs for history media event, a certain range of stock market's trend all exists
Same Long-term change trend illustrates that a certain range of stock market's trend is all influenced by history media event, then a certain range of
Stock market's trend curve is spacial influence force data, and then according to spacial influence force data, available history media event is corresponding
Spatial influence grade, spatial influence grade can indicate history media event to the coverage of stock market's trend, such as
When spatial influence grade is level-one, coverage can be the stock market of single company, when spatial influence grade is two
When grade, coverage can be the stock market of single industry, and when spatial influence grade is three-level, coverage be can be entirely
Stock market.After determining the corresponding data influence range of spatial influence grade, third label and the within the scope of data influence is obtained
The history media event of two tag match, for example when data influence range is single industry, then obtains in entire industry and own
Then history media event corresponding with the third label of the second tag match is gone through according to third labels all in industry are corresponding
History media event carries out subsequent calculating, that is, it is adjacent to obtain the timing node that the corresponding history media event of all third labels occurs
The dividend yield data of period, and according to dividend yield data calculate that the corresponding history media event of third label occurs when
The average value of daily cumulative abnormal rate of return in intermediate node time adjacent segments.
It is number according to more history news data corresponding with the third label of the second tag match in above-described embodiment
According to basis, when carrying out subsequent calculating, data reference is more, and obtained stock market's trend curve can be more accurate, and stock market's trend is pre-
Surveying also can be more accurate.
In one embodiment, stock market development method can also include: after obtaining history media event data
Obtain the time effects force data in history media event data；It is corresponding that history media event is obtained according to time effects force data
Time effects power grade；It determines the corresponding influence duration of time effects power grade, obtains preset number of days according to duration is influenced.
It specifically, can be according to history media event data acquisition after server obtains history media event data
Stock market in front and back can occur by analysis of history media event for time effects force data therein, time effects force data
Trend curve obtains, for example when front and back occurs for history media event, stock market's trend in a period of time all exists normal with stock market
Trend it is different anomaly trend variation, illustrate that stock market's trend in one section of event is all influenced by history media event, then this
Stock market's trend curve in the section time is time effects force data, and then according to time effects force data, available history is new
The corresponding time effects power grade of news event, time effects power grade can indicate influence of the history media event to stock market's trend
Duration, such as when time Hierarchy of Effects is 1 grade, the front and back 1 for the timing node that a length of history media event occurs when influencing
It；When time Hierarchy of Effects is 2 grades, the front and back for the timing node that a length of history media event occurs when influencing 7 days；At that time
Between Hierarchy of Effects when being 3 grades, the front and back 15 days etc. for the timing node that a length of history media event occurs when influencing, it is only for
For example, can also be by the thinner of time effects power ranking score.After obtaining time effects power grade, according to time effects power
Grade determines corresponding influence duration, then according to the default day influenced when duration determines subsequent calculating cumulative abnormal rate of return
Number, the front and back for the timing node that a length of history media event occurs when influencing 7 days, then preset number of days is history media event hair
The front and back of raw timing node 7 days calculates cumulative premium daily in 7 days before and after the timing node that history media event occurs and receives
Beneficial rate.
In above-described embodiment, is determined according to the time effects power grade of history media event and calculate cumulative abnormal rate of return
Number of days keeps data when subsequent calculating more accurate, and obtained stock market's trend curve can be more accurate, and stock market development also can be more
It is accurate to add.
In one embodiment, history media event is calculated according to dividend yield data in stock market development method to occur
Timing node time adjacent segments in daily cumulative abnormal rate of return, may include: will be every in timing node time adjacent segments
It cumulative abnormal rate of return is divided into pre- after cumulative abnormal rate of return and timing node daily in preset number of days before timing node
If daily cumulative abnormal rate of return in number of days；It is obtained according to cumulative abnormal rate of return daily in preset number of days before timing node
First trend type obtains second trend type according to cumulative abnormal rate of return daily in preset number of days after timing node；Root
Stock market's trend type is determined according to first trend type and second trend type；Tired out according to daily in timing node time adjacent segments
Product excess return, draws stock market's trend curve, comprising: draws stock market's trend curve according to stock market's trend type.
Specifically, cumulative abnormal rate of return daily in the timing node time adjacent segments being calculated is divided by server
Cumulative premium daily in preset number of days after cumulative abnormal rate of return and timing node daily in preset number of days before timing node
Then earning rate obtains first trend type according to cumulative abnormal rate of return daily in preset number of days before timing node, according to
Cumulative abnormal rate of return daily in preset number of days obtains second trend type after timing node, and specific trend type can be as
Shown in table 1:
Table 1:
| First trend type | Second trend type |
| Cumulative abnormal rate of return is persistently reduced | Cumulative abnormal rate of return is persistently reduced |
| Cumulative abnormal rate of return continues to increase | Cumulative abnormal rate of return continues to increase |
| Cumulative abnormal rate of return remains stable substantially | Cumulative abnormal rate of return remains stable substantially |
Stock market's trend type, determining stock market's trend type can be determined according to first trend type and second trend type
For one of 9 kinds of basic stock market trend types, basic stock market's trend type can be set reference numeral, such as No. 1 corresponding
It is that cumulative abnormal rate of return is persistently reduced before and after timing node, it is that cumulative abnormal rate of return continues before timing node that No. 2 corresponding
It reduces, cumulative abnormal rate of return continues to increase after timing node, after determining stock market's trend type, is drawn according to stock market's trend type
Stranding city trend curve.
In above-described embodiment, after cumulative abnormal rate of return and timing node daily in preset number of days before timing node
Daily cumulative abnormal rate of return determines stock market's trend type in preset number of days, and it is bent to draw stock market's trend according to stock market's trend type
Stock market's trend curve of line, drafting can be more accurate, and stock market development also can be more accurate.
In one embodiment, above-mentioned stock market development method, according to stock market's trend curve obtain with it is to be processed new
The relevant prediction result of news event, and after output, it can be according to the prediction result of output come the stock to media event to be processed
City's Long-term change trend, which makes incremental dissipated hysteretic energy in 20 days after reply, such as prediction result occur for media event, can all continue
It reduces, the closing price of corresponding stock market can also continue to reduce, then can be received in 20 days after media event generation according to stock market
Disk valence can continue to reduce to make counte-rplan, and it is pre- to provide high efficiency stock market trend in the stock market for company or individual in this way
Under the premise of survey, company is reduced or personal because of media event bring economic loss.
It should be understood that although each step in the flow chart of Fig. 2, Fig. 3 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2, Fig. 3 extremely
Few a part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
Moment executes completion, but can execute at different times, and the execution sequence in these sub-steps or stage is also not necessarily
It successively carries out, but in turn or can be handed over at least part of the sub-step or stage of other steps or other steps
Alternately execute.
In one embodiment, as shown in figure 4, providing a kind of stock market development device, comprising: receiving module 402,
Text identification module 404, obtain module 406, output module 408, in which:
Receiving module 402, for receiving the media event data to be processed of target terminal transmission.
Text identification module 404 obtains the first text data for carrying out text identification to media event data to be processed,
Corresponding first label of media event to be processed is obtained according to the first text data.
Module 406 is obtained, for when there is the second label with the first tag match in presetting database, obtaining and the
The associated stock market's trend curve of two labels, wherein the second label be obtained based on history media event data, and with stock market's trend
The label of curve associated storage in the preset database.
Output module 408, for obtaining prediction result relevant to media event to be processed according to stock market's trend curve, and
Prediction result is back to target terminal.
In one embodiment, device can also include:
Second text identification module obtains the second text data for carrying out text identification to history media event data,
Corresponding second label of history media event is obtained according to the second text data.
Second obtain module, for obtain history media event generation timing node and timing node it is adjacent when
Between dividend yield data in section, and calculate the cumulative abnormal rate of return in time adjacent segments according to dividend yield data.It is adjacent
Daily cumulative abnormal rate of return in period draws stock market's trend curve.
Drafting module, for drawing stock market's trend curve according to the cumulative abnormal rate of return in time adjacent segments.
Memory module is stored for the second label and stock market's trend curve to be associated into presetting database.
In one embodiment, device can also include:
Third obtains module, for identification the type of second label, obtains the corresponding stock market of the second tag types and becomes
Gesture float attribute.
Model determining module, for determining that corresponding cumulative abnormal rate of return calculates mould according to stock market's trend float attribute
Type.
Computing module, for calculating history media event according to cumulative abnormal rate of return computation model and dividend yield data
Daily cumulative abnormal rate of return cumulative abnormal rate of return in the timing node time adjacent segments of generation.
In one embodiment, device can also include:
4th obtains module, for obtaining the spacial influence force data in history media event data.
Class computing module, for obtaining corresponding spatial influence of history media event etc. according to spacial influence force data
Grade.
Range determination module obtains data influence model for determining the corresponding data influence range of spatial influence grade
Enclose the history media event of interior third label and the second tag match.
Second computing module, the timing node adjacent time occurred for obtaining the corresponding history media event of third label
The dividend yield data of section calculate the timing node that the corresponding history media event of third label occurs according to dividend yield data
The average value of daily cumulative abnormal rate of return in time adjacent segments.
In one embodiment, device can also include:
5th obtains module, for obtaining the time effects force data in history media event data.
Second class computing module, for obtaining the corresponding time effects of history media event according to time effects force data
Power grade.
Duration determining module obtains pre- for determining the corresponding influence duration of time effects power grade according to influence duration
If number of days.
In one embodiment, device can also include:
Segmentation module, before cumulative abnormal rate of return daily in timing node time adjacent segments is divided into timing node
Cumulative abnormal rate of return daily in preset number of days after daily cumulative abnormal rate of return and timing node in preset number of days.
Trend determining module, for obtaining first according to cumulative abnormal rate of return daily in preset number of days before timing node
Trend type obtains second trend type according to cumulative abnormal rate of return daily in preset number of days after timing node.
Stock market's trend determining module, for determining stock market's trend type according to first trend type and second trend type.
Drawing of Curve module, for drawing stock market's trend curve according to stock market's trend type.
Specific about stock market development device limits the limit that may refer to above for stock market development method
Fixed, details are not described herein.Modules in above-mentioned stock market development device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing history media event data.The network interface of the computer equipment is used for and external terminal
It is communicated by network connection.To realize a kind of stock market development method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, which performs the steps of when executing computer program receives the news to be processed that target terminal is sent
Event data；Text identification is carried out to media event data to be processed and obtains the first text data, is obtained according to the first text data
To corresponding first label of media event to be processed；When there is the second label with the first tag match in presetting database,
Obtain and the associated stock market's trend curve of the second label, wherein the second label be obtained based on history media event data, and with
The label of stock market's trend curve associated storage in the preset database；It is obtained and media event to be processed according to stock market's trend curve
Relevant prediction result, and prediction result is back to target terminal.
In one embodiment, it also performs the steps of when processor executes computer program to history media event number
The second text data is obtained according to text identification is carried out, corresponding second mark of history media event is obtained according to the second text data
Label；The dividend yield data in the time adjacent segments of timing node and timing node that history media event occurs are obtained, and
The cumulative abnormal rate of return in time adjacent segments is calculated according to dividend yield data；It is received according to the cumulative premium in time adjacent segments
Beneficial rate draws stock market's trend curve；Second label and stock market's trend curve are associated and stored into presetting database.
In one embodiment, that is realized when processor execution computer program obtains history according to the second text data
After corresponding second label of media event, it can also include: the type for identifying the second label, it is corresponding to obtain the second tag types
Stock market's trend float attribute；Corresponding cumulative abnormal rate of return computation model is determined according to stock market's trend float attribute；According to
Dividend yield data calculate cumulative abnormal rate of return daily in the timing node time adjacent segments that history media event occurs, packet
Include: it is adjacent to calculate the timing node that history media event occurs according to cumulative abnormal rate of return computation model and dividend yield data
Daily cumulative abnormal rate of return cumulative abnormal rate of return in period.
In one embodiment, when processor executes computer program the acquisition history media event data realized it
It afterwards, can also include: the spacial influence force data obtained in history media event data；It is gone through according to spacial influence force data
The corresponding spatial influence grade of history media event；It determines the corresponding data influence range of spatial influence grade, obtains data
The history media event of third label and the second tag match in coverage；Obtain the timing node that history media event occurs
The dividend yield data of time adjacent segments, and it is adjacent according to the timing node that dividend yield data calculate the generation of history media event
Daily cumulative abnormal rate of return in period, comprising: obtain the when segmentum intercalaris that the corresponding history media event of third label occurs
The dividend yield data of point time adjacent segments, and calculate the corresponding history media event of third label according to dividend yield data and send out
The average value of daily cumulative abnormal rate of return in raw timing node time adjacent segments.
In one embodiment, when processor executes computer program the acquisition history media event data realized it
It afterwards, can also include: the time effects force data obtained in history media event data；It is gone through according to time effects force data
The corresponding time effects power grade of history media event；The corresponding influence duration of time effects power grade is determined, according to influence duration
Obtain preset number of days.
In one embodiment, processor executes related according to dividend yield data calculating history when computer program
Daily cumulative abnormal rate of return may include: that timing node is adjacent in the timing node time adjacent segments that media event occurs
It is timely to be divided into cumulative abnormal rate of return daily in preset number of days before timing node for daily cumulative abnormal rate of return in period
Cumulative abnormal rate of return daily in preset number of days after intermediate node；According to cumulative premium daily in preset number of days before timing node
Earning rate obtains first trend type, obtains second according to cumulative abnormal rate of return daily in preset number of days after timing node and becomes
Gesture type；Stock market's trend type is determined according to first trend type and second trend type；According to timing node time adjacent segments
Interior daily cumulative abnormal rate of return draws stock market's trend curve, comprising: it is bent to draw stock market's trend according to stock market's trend type
Line.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor receives the media event data to be processed that target terminal is sent；Treat place
Reason media event data carry out text identification and obtain the first text data, obtain media event to be processed according to the first text data
Corresponding first label；When there is the second label with the first tag match in presetting database, obtaining and being closed with the second label
Stock market's trend curve of connection, wherein the second label is to be obtained based on history media event data, and be associated with stock market's trend curve
The label of storage in the preset database；Prediction result relevant to media event to be processed is obtained according to stock market's trend curve,
And prediction result is back to target terminal.
In one embodiment, it also performs the steps of when computer program is executed by processor to history media event
Data carry out text identification and obtain the second text data, obtain corresponding second mark of history media event according to the second text data
Label；The dividend yield data in the time adjacent segments of timing node and timing node that history media event occurs are obtained, and
The cumulative abnormal rate of return in time adjacent segments is calculated according to dividend yield data；It is received according to the cumulative premium in time adjacent segments
Beneficial rate draws stock market's trend curve；Second label and stock market's trend curve are associated and stored into presetting database.
In one embodiment, that is realized when computer program is executed by processor is gone through according to the second text data
After corresponding second label of history media event, it can also include: the type for identifying the second label, obtain the second tag types pair
The stock market's trend float attribute answered；Corresponding cumulative abnormal rate of return computation model is determined according to stock market's trend float attribute；Root
Cumulative abnormal rate of return daily in the timing node time adjacent segments that history media event occurs is calculated according to dividend yield data,
It include: to calculate the timing node phase that history media event occurs according to cumulative abnormal rate of return computation model and dividend yield data
Daily cumulative abnormal rate of return cumulative abnormal rate of return in the adjacent period.
In one embodiment, the acquisition history media event data realized when computer program is executed by processor it
It afterwards, can also include: the spacial influence force data obtained in history media event data；It is gone through according to spacial influence force data
The corresponding spatial influence grade of history media event；It determines the corresponding data influence range of spatial influence grade, obtains data
The history media event of third label and the second tag match in coverage；Obtain the timing node that history media event occurs
The dividend yield data of time adjacent segments, and it is adjacent according to the timing node that dividend yield data calculate the generation of history media event
Daily cumulative abnormal rate of return in period, comprising: obtain the when segmentum intercalaris that the corresponding history media event of third label occurs
The dividend yield data of point time adjacent segments, and calculate the corresponding history media event of third label according to dividend yield data and send out
The average value of daily cumulative abnormal rate of return in raw timing node time adjacent segments.
In one embodiment, the acquisition history media event data realized when computer program is executed by processor it
It afterwards, can also include: the time effects force data obtained in history media event data；It is gone through according to time effects force data
The corresponding time effects power grade of history media event；The corresponding influence duration of time effects power grade is determined, according to influence duration
Obtain preset number of days.
In one embodiment, related when computer program is executed by processor to be gone through according to the calculating of dividend yield data
Daily cumulative abnormal rate of return may include: by timing node phase in the timing node time adjacent segments that history media event occurs
In the adjacent period daily cumulative abnormal rate of return be divided into cumulative abnormal rate of return daily in preset number of days before timing node and
Cumulative abnormal rate of return daily in preset number of days after timing node；It is super according to accumulation daily in preset number of days before timing node
Volume earning rate obtains first trend type, obtains second according to cumulative abnormal rate of return daily in preset number of days after timing node
Trend type；Stock market's trend type is determined according to first trend type and second trend type；According to timing node adjacent time
Daily cumulative abnormal rate of return in section, draws stock market's trend curve, comprising: it is bent to draw stock market's trend according to stock market's trend type
Line.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of stock market development method, which comprises
Receive the media event data to be processed that target terminal is sent；
Text identification is carried out to the media event data to be processed and obtains the first text data, according to first text data
Obtain corresponding first label of the media event to be processed；
When there is the second label with the first tag match in presetting database, obtain and the associated stock market of the second label
Trend curve, wherein second label be obtained based on history media event data, and with stock market's trend curve associated storage
Label in the preset database；
Prediction result relevant to the media event to be processed is obtained according to stock market's trend curve, and the prediction is tied
Fruit is back to the target terminal.
2. the method according to claim 1, wherein the method also includes；
Text identification is carried out to history media event data and obtains the second text data, institute is obtained according to second text data
State corresponding second label of history media event；
The stock market obtained in the time adjacent segments of timing node and the timing node that the history media event occurs is received
Beneficial data, and calculate according to the dividend yield data cumulative abnormal rate of return in the time adjacent segments；
According to the cumulative abnormal rate of return in the time adjacent segments, stock market's trend curve is drawn；
Second label and stock market's trend curve are associated and stored into the presetting database.
3. according to the method described in claim 2, it is characterized in that, described obtain the history according to second text data
After corresponding second label of media event, further includes:
It identifies the type of second label, obtains the corresponding stock market's trend float attribute of second tag types；
Corresponding cumulative abnormal rate of return computation model is determined according to stock market's trend float attribute；
It is described to be calculated in the timing node time adjacent segments that the history media event occurs often according to the dividend yield data
It cumulative abnormal rate of return, comprising:
The history media event is calculated according to the cumulative abnormal rate of return computation model and the dividend yield data to occur
Timing node time adjacent segments in daily cumulative abnormal rate of return cumulative abnormal rate of return.
4. according to the method described in claim 2, it is characterized in that, after the acquisition history media event data, further includes:
Obtain the spacial influence force data in the history media event data；
The corresponding spatial influence grade of the history media event is obtained according to the spacial influence force data；
Determine the corresponding data influence range of the spatial influence grade, obtain within the scope of the data influence third label with
The history media event of second tag match；
The dividend yield data for obtaining the timing node time adjacent segments that history media event occurs, and according to the stock market
Avail data calculates cumulative abnormal rate of return daily in the timing node time adjacent segments that the history media event occurs, packet
It includes:
The dividend yield data for the timing node time adjacent segments that the corresponding history media event of the third label occurs are obtained,
And when adjacent according to the timing node that the dividend yield data calculate the corresponding history media event generation of the third label
Between cumulative abnormal rate of return daily in section average value.
5. according to the method described in claim 2, it is characterized in that, after obtaining history media event data, further includes:
Obtain the time effects force data in the history media event data；
The corresponding time effects power grade of the history media event is obtained according to the time effects force data；
It determines the corresponding influence duration of the time effects power grade, preset number of days is obtained according to the influence duration.
6. according to the method described in claim 2, it is characterized in that, described calculate the history according to the dividend yield data
Daily cumulative abnormal rate of return in the timing node time adjacent segments that media event occurs, comprising:
Cumulative abnormal rate of return daily in the timing node time adjacent segments is divided into preset number of days before the timing node
Cumulative abnormal rate of return daily in preset number of days after interior daily cumulative abnormal rate of return and the timing node；
First trend type is obtained according to cumulative abnormal rate of return daily in preset number of days before the timing node, according to described
Cumulative abnormal rate of return daily in preset number of days obtains second trend type after timing node；
Stock market's trend type is determined according to the first trend type and the second trend type；
It is described that stock market's trend curve is drawn according to cumulative abnormal rate of return daily in the timing node time adjacent segments, it wraps
It includes:
Stock market's trend curve is drawn according to stock market's trend type.
7. a kind of stock market development device, which is characterized in that described device includes:
Receiving module, for receiving the media event data to be processed of target terminal transmission；
Text identification module obtains the first text data, root for carrying out text identification to the media event data to be processed
Corresponding first label of the media event to be processed is obtained according to first text data；
Module is obtained, for obtaining and described second when there is the second label with the first tag match in presetting database
The associated stock market's trend curve of label, wherein second label is to be obtained based on history media event data, and become with stock market
The label of power curve associated storage in the preset database；
Output module, for obtaining prediction result relevant to the media event to be processed according to stock market's trend curve,
And the prediction result is back to the target terminal.
8. device according to claim 7, which is characterized in that described device includes:
Second text identification module obtains the second text data for carrying out text identification to history media event data, according to
Second text data obtains corresponding second label of the history media event；
Second obtains module, for obtaining the phase of timing node and the timing node that the history media event occurs
Time adjacent segments dividend yield data in the adjacent period, and calculated in the time adjacent segments according to the dividend yield data
Cumulative abnormal rate of return；
Drafting module, for drawing stock market's trend curve according to the cumulative abnormal rate of return in the time adjacent segments；
Memory module is stored for second label and stock market's trend curve to be associated to the presetting database
In.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910620463.0A CN110489631A (en) | 2019-07-10 | 2019-07-10 | Stock market development method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910620463.0A CN110489631A (en) | 2019-07-10 | 2019-07-10 | Stock market development method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110489631A true CN110489631A (en) | 2019-11-22 |
Family
ID=68546904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910620463.0A Pending CN110489631A (en) | 2019-07-10 | 2019-07-10 | Stock market development method, apparatus, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110489631A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222051A (en) * | 2020-01-16 | 2020-06-02 | 深圳市华海同创科技有限公司 | Training method and device of trend prediction model |
| CN114846460A (en) * | 2019-12-23 | 2022-08-02 | 艾玛迪斯简易股份公司 | System and method for optimizing the transmission of requests for updated content from external data sources |
| CN115577093A (en) * | 2022-05-26 | 2023-01-06 | 深圳格隆汇信息科技有限公司 | AI analysis method and system of financial information |
| CN116542238A (en) * | 2023-07-07 | 2023-08-04 | 和元达信息科技有限公司 | Event heat trend determining method and system based on small program |
| US11789932B2 (en) | 2019-12-23 | 2023-10-17 | Amadeus S.A.S. | System and method for optimizing transmission of requests for updated content from external data sources |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956770A (en) * | 2016-05-03 | 2016-09-21 | 中国科学院大学 | Stock market risk prediction platform and text excavation method thereof |
| KR20180066726A (en) * | 2016-12-09 | 2018-06-19 | 동국대학교 산학협력단 | Apparatus and method for estimating stock price |
| CN108985941A (en) * | 2018-07-18 | 2018-12-11 | 河海大学 | A kind of stock intelligent Forecasting of combination newsletter archive |
| CN109657851A (en) * | 2018-12-12 | 2019-04-19 | 哈尔滨工业大学（深圳） | Forecasting of Stock Prices method, apparatus, equipment and the storage medium of event driven |
| CN109670837A (en) * | 2018-11-30 | 2019-04-23 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
-
2019
- 2019-07-10 CN CN201910620463.0A patent/CN110489631A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956770A (en) * | 2016-05-03 | 2016-09-21 | 中国科学院大学 | Stock market risk prediction platform and text excavation method thereof |
| KR20180066726A (en) * | 2016-12-09 | 2018-06-19 | 동국대학교 산학협력단 | Apparatus and method for estimating stock price |
| CN108985941A (en) * | 2018-07-18 | 2018-12-11 | 河海大学 | A kind of stock intelligent Forecasting of combination newsletter archive |
| CN109670837A (en) * | 2018-11-30 | 2019-04-23 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
| CN109657851A (en) * | 2018-12-12 | 2019-04-19 | 哈尔滨工业大学（深圳） | Forecasting of Stock Prices method, apparatus, equipment and the storage medium of event driven |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114846460A (en) * | 2019-12-23 | 2022-08-02 | 艾玛迪斯简易股份公司 | System and method for optimizing the transmission of requests for updated content from external data sources |
| US11789932B2 (en) | 2019-12-23 | 2023-10-17 | Amadeus S.A.S. | System and method for optimizing transmission of requests for updated content from external data sources |
| CN111222051A (en) * | 2020-01-16 | 2020-06-02 | 深圳市华海同创科技有限公司 | Training method and device of trend prediction model |
| CN111222051B (en) * | 2020-01-16 | 2023-09-12 | 深圳市华海同创科技有限公司 | Training method and device for trend prediction model |
| CN115577093A (en) * | 2022-05-26 | 2023-01-06 | 深圳格隆汇信息科技有限公司 | AI analysis method and system of financial information |
| CN115577093B (en) * | 2022-05-26 | 2023-05-16 | 深圳格隆汇信息科技有限公司 | AI analysis method and system for financial information |
| CN116542238A (en) * | 2023-07-07 | 2023-08-04 | 和元达信息科技有限公司 | Event heat trend determining method and system based on small program |
| CN116542238B (en) * | 2023-07-07 | 2024-03-15 | 和元达信息科技有限公司 | Event heat trend determining method and system based on small program |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489631A (en) | Stock market development method, apparatus, computer equipment and storage medium | |
| Behmiri et al. | The role of outliers and oil price shocks on volatility of metal prices | |
| Segnon et al. | Modeling and forecasting the volatility of carbon dioxide emission allowance prices: A review and comparison of modern volatility models | |
| Lee et al. | Optimal hedging with a regime‐switching time‐varying correlation GARCH model | |
| Mahajan et al. | Mining financial news for major events and their impacts on the market | |
| CN104978356B (en) | A kind of recognition methods of synonym and device | |
| CN110119870A (en) | Macro risks method for early warning, device, computer equipment and storage medium | |
| CN109558421A (en) | Data processing method, system, device and storage medium based on caching | |
| CN106600463A (en) | Local shape similarity ultra short-period load prediction method and apparatus | |
| CN112818230B (en) | Content recommendation method, device, electronic equipment and storage medium | |
| Ozgur et al. | Detecting speculative bubbles in metal prices: Evidence from GSADF test and machine learning approaches | |
| Liu et al. | Forecasting the occurrence of extreme electricity prices using a multivariate logistic regression model | |
| CN110442713A (en) | Abstract generation method, apparatus, computer equipment and storage medium | |
| CN109767226A (en) | Suspicious transaction statistical views generation method and device based on big data | |
| CN110688846B (en) | Periodic word mining method, system, electronic equipment and readable storage medium | |
| CN110751317A (en) | Power load prediction system and prediction method | |
| CN114076841A (en) | Electricity stealing behavior identification method and system based on electricity utilization information data | |
| Altuzarra et al. | Is world trade slowing down? New evidence on trade-income elasticity | |
| Gurung et al. | AI-Based Customer Churn Prediction Model for Business Markets in the USA: Exploring the Use of AI and Machine Learning Technologies in Preventing Customer Churn | |
| Ahmed et al. | Enhancing stock portfolios for enterprise management and investment in energy industry | |
| CN111737308A (en) | Stock exchange point prediction method, system and storage medium based on minimum entropy score | |
| CN110097250A (en) | Product risks prediction technique, device, computer equipment and storage medium | |
| Chuang et al. | Backtesting VaR in consideration of the higher moments of the distribution for minimum-variance hedging portfolios | |
| CN110110885A (en) | Information forecasting method, device, computer equipment and storage medium | |
| CN115828901A (en) | Sensitive information identification method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |