CN108596765A - A kind of Electronic Finance resource recommendation method and device - Google Patents
A kind of Electronic Finance resource recommendation method and device Download PDFInfo
- Publication number
- CN108596765A CN108596765A CN201810399403.6A CN201810399403A CN108596765A CN 108596765 A CN108596765 A CN 108596765A CN 201810399403 A CN201810399403 A CN 201810399403A CN 108596765 A CN108596765 A CN 108596765A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- development
- sourcing
- wave time
- electronic finance
- 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
Classifications
-
- 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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
This application provides a kind of Electronic Finance resource recommendation methods and device, this method to include：History media data based on target industry determines the development wave time sequence of characterization target industry development fluctuation；The ups and downs wave time sequence for characterizing Electronic Finance resource ups and downs fluctuation is determined based on the historical trading data of the Electronic Finance resource for each Electronic Finance resource of target industry；Based on the correlation analysis between development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource as a result, determining destination financial e-sourcing；Trend prediction model is built for determining destination financial e-sourcing, the historical trading data of history media data and destination financial e-sourcing based on destination financial e-sourcing said target industry is trained trend prediction model；The development trend of destination financial e-sourcing is predicted using the trend prediction model for completing training, and destination financial e-sourcing is recommended according to prediction result.
Description
Technical field
This application involves data analysis technique fields, in particular to a kind of Electronic Finance resource recommendation method and dress
It sets.
Background technology
Securities market is the basis of national economic development Capital Flow, and the evolutionary process of security price is by many economical
Body and economic factor participate in co-determination jointly, cause the model of volatility complex, it is difficult to effectively predicted,
Cause the accuracy of the recommendation to stock low in turn.The method currently recommended stock is concentrated mainly on two classes, respectively
Online stock based on stock comment recommends method and the Stock Price Forecasting based on mathematical analysis.Online stock based on stock comment is recommended
Method cannot meet the needs of user individual stock recommendation, for example, user is interested just for some industry stock, it is only uncommon
Hope the stock of purchase the sector, the online stock based on stock comment recommends method that cannot meet the needs of this user at this time, and adopts
The method that stock recommendation is carried out with the Stock Price Forecasting based on mathematical analysis is more complicated, is not easy to user and understands and masters, answers
It is larger with difficulty.
Invention content
In view of this, the application's is designed to provide a kind of Electronic Finance resource recommendation method and device, for solving
The low problem of the Electronic Finance resource accuracy recommended in the prior art.
In a first aspect, the embodiment of the present application provides a kind of Electronic Finance resource recommendation method, this method includes：
History media data based on target industry determines the development wave time for characterizing the target industry development fluctuation
Sequence；
For each Electronic Finance resource of the target industry, based on the historical trading data of the Electronic Finance resource, really
Surely the ups and downs wave time sequence of Electronic Finance resource ups and downs fluctuation is characterized；
Based on related between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Property analysis result, determines destination financial e-sourcing；
Trend prediction model is built for determining destination financial e-sourcing, and based on belonging to destination financial e-sourcing
The history media data of target industry and the historical trading data of destination financial e-sourcing carry out trend prediction model
Training；
The development trend of destination financial e-sourcing is predicted using the trend prediction model for completing training, and according to
Prediction result recommends destination financial e-sourcing.
Optionally, the history media data based on target industry determines the development for characterizing the target industry development fluctuation
Wave time sequence, including：
History media data based on target industry determines and characterizes the target industry in the first default historical time section
Develop the development wave time sequence of fluctuation；
For each Electronic Finance resource of the target industry, based on the historical trading data of the Electronic Finance resource, really
Surely the ups and downs wave time sequence of Electronic Finance resource ups and downs fluctuation is characterized, including：
For each Electronic Finance resource of the target industry, based on the historical trading data of the Electronic Finance resource, really
Surely the Electronic Finance resource ups and downs wave time that ups and downs are fluctuated in at least one second default historical time section respectively is characterized
Sequence；
Based on related between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Property analysis result, determines destination financial e-sourcing, including：
Based on related between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Property analysis result, is determined as destination financial e-sourcing by the Electronic Finance resource for meeting following condition：
The Electronic Finance resource is when ups and downs wave time sequence is with development fluctuation in corresponding second preset time period
Between correlation between sequence meet default correlated condition, and
Second preset time period of correspondence compares the corresponding first default historical time section of the development wave time sequence
Lag.
Optionally, when being fluctuated with the following method to the ups and downs of the development wave time sequence and each Electronic Finance resource
Between sequence carry out correlation analysis：
It is default each second for the Electronic Finance resource for each Electronic Finance resource in the target industry
Ups and downs wave time sequence in historical time section determines the ups and downs wave time sequence and the development wave time sequence respectively
Between related coefficient；
Wherein, at least one second default historical time section compares the described first default historical time section lag, or
Person
Precedence relationship between at least one second default historical time section and the first default historical time section
Including lag, and it is one or more as follows：It is in advance or identical.
Optionally, the history media data based on target industry determines the development for characterizing the target industry development fluctuation
Wave time sequence, including：
The history media data of the target industry is parsed using pre-set text analytical algorithm；
Positive and negative tendency emotional semantic classification is carried out to the vocabulary that parsing obtains, obtains characterizing the vocabulary favourable being just inclined to and characterization
The empty profit vocabulary of negative tendency；
Vocabulary favourable and empty profit vocabulary quantity in each default unit interval are counted；
The polarity of each default unit interval is determined according to statistical result；Wherein, vocabulary number favourable in the unit interval is preset
Amount is more than empty profit vocabulary quantity, then it is just, to preset advantage vocabulary quantity in the unit interval and be less than empty profit vocabulary quantity to correspond to polarity,
It is negative then to correspond to polarity, presets favourable vocabulary quantity in the unit interval and is equal to empty profit vocabulary quantity, then corresponds to during polarity is；And
It is default that the default unit interval corresponding polarity sequence of continuous preset quantity is determined as the continuous preset quantity
Unit interval corresponding development wave time sequence.
Optionally, trend prediction model is built for determining destination financial e-sourcing, including：
Development fluctuation characteristic vector is determined based on the development wave time sequence；And
Transaction feature vector is determined based on the historical trading data of destination financial e-sourcing；
Using development fluctuation characteristic vector and transaction feature vector as independent variable, by destination financial e-sourcing
Ups and downs trend builds the trend prediction model of destination financial e-sourcing as dependent variable；
Wherein, it is corresponding to compare the development fluctuation characteristic vector for the exchange hour sequence of the transaction feature vector characterization
Develop wave time sequence lag, and hysteresis compares the described first default historical time with corresponding second preset time period
The hysteresis of section is identical.
Optionally, the development trend of destination financial e-sourcing is carried out using the trend prediction model for completing training pre-
It surveys, and destination financial e-sourcing is recommended according to prediction result, including：
The development trend of each destination financial e-sourcing is predicted using the trend prediction model for completing training, is obtained
The rise probabilistic forecasting result of each destination financial e-sourcing；
According to obtained rise probabilistic forecasting as a result, the preceding preset quantity destination financial electricity descending to rise probability
Child resource is recommended.
Second aspect, the embodiment of the present application provide a kind of Electronic Finance resource recommendation device, which includes：
First determining module is used for the history media data based on target industry, determines and characterizes the target industry development
The development wave time sequence of fluctuation；
Second determining module is based on the Electronic Finance resource for each Electronic Finance resource for the target industry
Historical trading data, determine characterize the Electronic Finance resource ups and downs fluctuation ups and downs wave time sequence；
Third determining module, when being fluctuated for the ups and downs based on the development wave time sequence and each Electronic Finance resource
Between correlation analysis between sequence as a result, determining destination financial e-sourcing；
Training module, for building trend prediction model for determining destination financial e-sourcing, and based on target gold
Melt the history media data of e-sourcing said target industry and the historical trading data of destination financial e-sourcing, to becoming
Gesture prediction model is trained；
Recommending module, for using complete the trend prediction model of training to the development trend of destination financial e-sourcing into
Row prediction, and destination financial e-sourcing is recommended according to prediction result.
Optionally, first determining module is specifically used for：
History media data based on target industry determines and characterizes the target industry in the first default historical time section
Develop the development wave time sequence of fluctuation；
Second determining module is specifically used for：
For each Electronic Finance resource of the target industry, based on the historical trading data of the Electronic Finance resource, really
Surely the Electronic Finance resource ups and downs wave time that ups and downs are fluctuated in at least one second default historical time section respectively is characterized
Sequence；
The third determining module is specifically used for：
Based on related between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Property analysis result, is determined as destination financial e-sourcing by the Electronic Finance resource for meeting following condition：
The Electronic Finance resource is when ups and downs wave time sequence is with development fluctuation in corresponding second preset time period
Between correlation between sequence meet default correlated condition, and
Second preset time period of correspondence compares the corresponding first default historical time section of the development wave time sequence
Lag.
The third aspect, the embodiment of the present application provide a kind of computer equipment and include memory, processor and be stored in institute
The computer program that can be run on memory and on the processor is stated, the processor executes real when the computer program
The step of existing above method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer-readable storage
The step of being stored with computer program on medium, the above method executed when the computer program is run by processor.
Electronic Finance resource recommendation method provided by the embodiments of the present application is determined according to the history media data of target industry
Develop wave time sequence, according to the historical trading data of each Electronic Finance resource of target industry, determines each Electronic Finance money
The ups and downs wave time sequence in source, further to the ups and downs wave time sequence of development wave time sequence and each Electronic Finance resource
Row carry out correlation analysis, determine destination financial e-sourcing, and trend prediction model is built for each destination financial e-sourcing,
According to the history media data of destination financial e-sourcing said target industry and the historical trading of destination financial e-sourcing
Data are trained trend prediction model, and then predict the development trend of destination financial e-sourcing, and according to pre-
Result is surveyed to recommend destination financial e-sourcing.The application establishes trend prediction according to the data obtained from target industry
Model recommends the Electronic Finance resource of the target industry, on the one hand establishes the target industry of trend prediction model consideration
Various factors, improve the accuracy of the Electronic Finance resource of recommendation, on the other hand, for only to a certain particular row
When the interested user of industry recommends Electronic Finance resource, the Electronic Finance resource of recommendation is easier to be easily accepted by a user, and improves use
The satisfaction at family.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Description of the drawings
It, below will be to needed in the embodiment attached in order to illustrate more clearly of the technical solution of the embodiment of the present application
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of flow diagram of Electronic Finance resource recommendation method provided by the embodiments of the present application；
Fig. 2 is a kind of the first structural schematic diagram of Electronic Finance resource recommendation device provided by the embodiments of the present application；
Fig. 3 is a kind of second of structural schematic diagram of Electronic Finance resource recommendation device provided by the embodiments of the present application；
Fig. 4 is a kind of structural schematic diagram of computer equipment 400 provided by the embodiments of the present application.
Specific implementation mode
To keep the purpose, technical scheme and advantage of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, technical solutions in the embodiments of the present application are clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
Applying the component of example can be arranged and designed with a variety of different configurations.Therefore, below to the application's for providing in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, institute that those skilled in the art are obtained without making creative work
There is other embodiment, shall fall in the protection scope of this application.
The embodiment of the present application provides a kind of Electronic Finance resource recommendation method, as shown in Figure 1, this method includes following step
Suddenly：
S101, the history media data based on target industry determine the development wave for characterizing the target industry development fluctuation
Dynamic time series；
Here, target industry is generally pre-set industry, for example, the communications industry, transportation industry, internet industry etc.
Deng；History media data can be from default platform obtain, default platform can be today's tops, Netease's news, Sina News,
Sina weibo etc., history media data may include industry financial and economic news, the comment of industry stock, industry public opinion news, industry
Policy news etc.；Develop the correspondence between wave time sequence characterization time and polarity.
In the history media data based on target industry, when determining the development fluctuation for characterizing the target industry development fluctuation
Between sequence when, be generally based on the history media data of target industry, determine and characterize the target industry in the first default history
The development wave time sequence of development fluctuation in period.Wherein, the first default historical time section can be 1 day, it is several days continuous,
1 week, 1 month, 1 season etc., the application not limit this.
History media data based on target industry determines the development wave time for characterizing the target industry development fluctuation
Sequence specifically includes following steps：
The history media data of the target industry is parsed using pre-set text analytical algorithm；
Positive and negative tendency emotional semantic classification is carried out to the vocabulary that parsing obtains, obtains characterizing the vocabulary favourable being just inclined to and characterization
The empty profit vocabulary of negative tendency；
Vocabulary favourable and empty profit vocabulary quantity in each default unit interval are counted；
The polarity of each default unit interval is determined according to statistical result；Wherein, vocabulary number favourable in the unit interval is preset
Amount is more than empty profit vocabulary quantity, then it is just, to preset advantage vocabulary quantity in the unit interval and be less than empty profit vocabulary quantity to correspond to polarity,
It is negative then to correspond to polarity, presets favourable vocabulary quantity in the unit interval and is equal to empty profit vocabulary quantity, then corresponds to during polarity is；And
It is default that the default unit interval corresponding polarity sequence of continuous preset quantity is determined as the continuous preset quantity
Unit interval corresponding development wave time sequence.
Here, text resolution algorithm can be jieba kits etc., using text resolution algorithm to history media data into
The process of row parsing, the prior art have detailed introduction, are no longer excessively illustrated herein；The vocabulary favourable being just inclined to is general
To generate the vocabulary favourable of positive influences to Electronic Finance resource, the empty profit vocabulary for bearing tendency generally produces Electronic Finance resource
The empty profit vocabulary of raw negative effect, vocabulary favourable can be rise, favourable, super expected, tolerance and wrap, promotes development, necessary branch
Support etc., empty profit vocabulary can be drop, empty profit, diving, increasing supervision, income tax, rectification etc.；The default unit interval is generally one
A working day.
In specific implementation, in the first default historical time section for obtaining target industry each default unit interval history
After media data, for the unit interval is each preset in the first default historical time section, counts vocabulary and empty profit vocabulary favourable and exist
The number occurred in the history media data of the default unit interval, according to the number of statistics to vocabulary favourable and empty profit vocabulary into
Row assignment, obtains vocabulary vector sum empty profit vocabulary vector favourable, and vocabulary vector favourable includes the value of each vocabulary favourable, empty profit word
The vector that converges includes the value of each empty profit vocabulary, calculates separately vocabulary vector intermediate value favourable and value average value TbullishAnd empty profit
Vocabulary vector intermediate value and value average value TberarishIf TbullishMore than Tberarish, then the period corresponding polarity is just
(e.g., 1), if TbullishLess than Tberarish, then the period corresponding polarity is negative (e.g., -1), if TbullishEqual to Tberarish,
During then the period corresponding polarity is (e.g., 0), select continuous preset quantity default single from the first default historical time section
Position time corresponding polarity sequence is ultimately determined to development wave time sequence.
It being illustrated by taking the communications industry as an example, the first preset time period includes 5 working days, for the every workday,
The communications industry is got after workaday a large amount of financial and economic news, the policy news etc., statistics goes up, is favourable, is expected etc.
The number that the empty profits such as vocabulary favourable and drop, empty profit, diving vocabulary occurs in each news, for example, on any one working day
In, rise appears in 7 news, and advantage appears in 4 news, it is contemplated that appears in 4 news, drop appears in 10
In news, empty profit appears in 7 news, and diving appears in 1 news, then the empty profit vocabulary vector obtained is [7,4,4]
Empty profit vocabulary vector is [10,7,1], calculates the T being worth to that is averaged of empty profit vocabulary vectorbullishBe 5, calculate empty profit vocabulary to
The T being worth to that is averaged of amountbullishIt is 6, the TbullishLess than Tberarish, for this, any one workaday polarity number is then
It is -1, the polarity calculation of every workday is identical as above-mentioned example, is no longer introduced one by one.It may finally obtain first
The polarity of preset time period corresponding every workday.
S102, for each Electronic Finance resource of the target industry, the historical trading number based on the Electronic Finance resource
According to the determining ups and downs wave time sequence for characterizing Electronic Finance resource ups and downs fluctuation；
Here, each Electronic Finance resource of target industry generally belongs to stock, security, fund of the target industry etc.,
Historical trading data can be stock certificate data, and stock certificate data generally comprises the closing price of stock, highest price, lowest price, transaction
Amount, turnover rate etc.；Correspondence between ups and downs wave time sequence characterization time and ups and downs trend.
It is determined based on the historical trading data of the Electronic Finance resource in each Electronic Finance resource for target industry
When characterizing the ups and downs wave time sequence of Electronic Finance resource ups and downs fluctuation, generally be directed to each Electronic Finance of target industry
Resource is determined and is characterized the Electronic Finance resource respectively at least one the based on the historical trading data of the Electronic Finance resource
The ups and downs wave time sequence that ups and downs are fluctuated in two default historical time sections.Wherein, the second default historical time section can be 1
It, several days continuous, 1 week, 1 month, 1 season etc., the application not limits this.
Second default historical time section can lag behind the first historical time section, can also be ahead of the first historical time
Section, can also be identical as the first historical time section.For example, the first historical time section is April 6 18 on April -18 years 2, lag
The second default historical time section be April 13 18 on April -18 years 9, the second advanced default historical time section is 18 years 3
Month No. 26 on March 30th, 1, identical second default historical time section are April 6 18 on April -18 years 2, and first default goes through
The time number of days that history period and the second default historical period include is generally identical, then, two default historical time sections can be with
There are the parts of overlapping：Advanced historical time section, historical time section start time point or end time point are compared another
The correspondence time point of a historical time section is advanced；The historical time section of lag, historical time section start time point or end
Time point compares the correspondence time point lag of another historical time section.It in practical applications, can be determines according to actual conditions.
In specific implementation, the historical trading data of acquisition can be the number of at least one second default historical time section
According to each second default historical time section includes that (this unit preset time can be gone through multiple unit preset times with first
Unit preset time in the history period is identical), for each unit preset time in each second default historical time section,
According to the historical trading data of the unit preset time, the ups and downs trend of Electronic Finance resource is determined, by continuous preset quantity
Default unit interval corresponding ups and downs trend sequence is determined as ups and downs wave time sequence.
For example, the second default historical time section includes 5 working days, the every workday is corresponding with the receipts of Electronic Finance resource
Disk valence, trading volume, highest price etc. compare work at present day and previous workaday closing price, if the closing quotation of work at present day
Valence is higher than the 5% of previous workaday closing price, then the ups and downs trend of work at present day is generally 5%, if work at present day
Closing price be less than previous workaday closing price 5%, then the ups and downs trend of work at present day be generally -5%, if current work
The closing price for making day is equal to previous workaday closing price, then the ups and downs trend of work at present day is 0, and each second default goes through
The computational methods for the ups and downs trend that each of history period works are identical as above-mentioned example, do not introduce one by one, finally obtain characterization
The ups and downs wave time sequence of correspondence between time and ups and downs trend.
S103, based between development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Correlation analysis is as a result, determine destination financial e-sourcing；
Here, destination financial e-sourcing is generally screened from the Electronic Finance resource of target industry.
Phase between the ups and downs wave time sequence based on the development wave time sequence with each Electronic Finance resource
Closing property analysis result when determining destination financial e-sourcing, is generally based on the development wave time sequence and each finance electricity
Correlation analysis between the ups and downs wave time sequence of child resource is as a result, the Electronic Finance resource for meeting following condition is determined
For destination financial e-sourcing：
The Electronic Finance resource is when ups and downs wave time sequence is with development fluctuation in corresponding second preset time period
Between correlation between sequence meet default correlated condition, and
Second preset time period of correspondence compares the corresponding first default historical time section of the development wave time sequence
Lag.
Correlation analysis is being carried out to development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
When, phase is carried out to the ups and downs wave time sequence of the development wave time sequence and each Electronic Finance resource with the following method
The analysis of closing property：
It is pre- each second for the Electronic Finance resource for each Electronic Finance resource in each Electronic Finance resource
If ups and downs wave time sequence in historical time section, the ups and downs wave time sequence and the development wave time sequence are determined respectively
Related coefficient between row；Here, the second default historical time section compare the first default historical time section can lag, in advance,
Or it is identical.
Here, default correlated condition can be Electronic Finance resource ups and downs wave time in corresponding second preset time period
Correlation between sequence and development wave time sequence is more than the relevance threshold of setting, and the application not limits this.
In specific implementation, the development wave time sequence P for obtaining target industry is the first default historical time section, needle
To each Electronic Finance resource in target industry, the ups and downs wave time sequence sets S of the multiple second default historical time sections is obtained,
S collection includes multiple sequences, and the time lead for the first preset number ups and downs wave time sequence that S is concentrated is in the first default history
Period, the time lag of the second preset number ups and downs wave time sequence is in the first default historical time section, a ups and downs
The time of wave time sequence is identical as the first default historical time section, and each rise is calculated separately by related coefficient calculation formula
Fall wave time sequence and develop the correlation between wave time sequence, by the maximum absolute value of correlation, and second is default
Historical time section lags behind the corresponding Electronic Finance resource of the first default historical time section and is determined as destination financial e-sourcing.Its
In, correlation calculations formula can refer to following formula.
Correlation r calculation formula are as follows：
Wherein, r is the correlation developed between wave time sequence and ups and downs wave time sequence, xiWhen being fluctuated for development
Between i-th of polarity number in sequence, yiFor i-th of ups and downs Trend value in ups and downs wave time sequence, N is development wave time
The number of sequence or ups and downs wave time sequence intermediate value, generally positive integer.
It is illustrated by taking the correlation between an Electronic Finance resource of target industry and target industry as an example, target line
The corresponding first default historical time section of P sequences of industry is the 6th day to the 10th day in time series, when with the first default history
Between the corresponding second historical time sections of the identical S0 of section be time series in the 6th day to the 10th day, advanced first default history
The corresponding second default historical time section of S1, S2, S3 of period can be the 5th day to the 9th day in time series, the
4 days to the 8th day, the 3rd day to the 7th day, S4, S5, S6 corresponding second of the first default historical time section of lag, which is preset, to be gone through
The history period can be the 7th day to the 11st day, the 8th day to the 12nd day, the 9th day to the 13rd day in time series, calculate separately P
Correlation between sequence and S0, S1, S2, S3, S4, S5, S6 obtains r0, advanced 1 day r1, advanced 2 days r2,3 days advanced
R3, lag 1 day r4, lag 2 days r5, lag 3 days r6, the correlation of maximum absolute value is therefrom selected, if absolute value
Maximum correlation lags 2 days, at this point it is possible to determine that the Electronic Finance resource is destination financial e-sourcing, if absolute value is most
Advanced 2 days of big correlation is r0, then such Electronic Finance resource is rejected.
S104 is built trend prediction model for determining destination financial e-sourcing, and is provided based on destination financial electronics
The history media data of source said target industry and the historical trading data of destination financial e-sourcing, to trend prediction mould
Type is trained；
Here, the trend prediction model of structure can be Logic Regression Models, neural network model etc., the application to this not
Give limitation.
When building trend prediction model for determining destination financial e-sourcing, include the following steps：
Development fluctuation characteristic vector is determined based on the development wave time sequence；And
Transaction feature vector is determined based on the historical trading data of destination financial e-sourcing；
Using development fluctuation characteristic vector and transaction feature vector as independent variable, by destination financial e-sourcing
Ups and downs trend builds the trend prediction model of destination financial e-sourcing as dependent variable；
Wherein, it is corresponding to compare the development fluctuation characteristic vector for the exchange hour sequence of the transaction feature vector characterization
Develop wave time sequence lag, and hysteresis compares the described first default historical time with corresponding second preset time period
The hysteresis of section is identical.
In specific implementation, for each destination financial e-sourcing, by development fluctuation characteristic vector and transaction feature
Vector is used as independent variable, and using the ups and downs trend of destination financial e-sourcing as dependent variable, at least two preset models of structure are simultaneously
It is trained, using the prediction result of at least two preset models as independent variable, by the ups and downs trend of destination financial e-sourcing
As dependent variable, builds Fusion Model and be trained.Wherein, preset model includes Logic Regression Models, neural network model
Deng.
Fusion treatment is carried out to preset model, trend prediction model is finally obtained, can obtain preferably predicting goodness, is increased
The accuracy for adding Electronic Finance resource trends to predict.Model Fusion has following two methods：
Method one：Model accumulates (Model stacking), votes the prediction result of each preset model, is taken using minority
From most principles, usually the prediction result of several preset models being weighted and is averaging, weights are directly proportional to model prediction goodness,
It is inversely proportional with the uncertainty of model.
Method two：Model integrated (Model ensemble), using the prediction result of each preset model as output valve, instruction
Practice a new grader, then, is tied using the prediction result of trained grader as the final prediction of trend prediction model
Fruit.
When building at least two preset models and being trained, it is based on history media data, determines development fluctuation characteristic
Value in vector is based on historical trading data, the value of the value and ups and downs trend in transaction feature vector is determined, for each pre-
If model, the value in value and transaction feature vector in fluctuation characteristic vector will be developed as the value of independent variable, risen corresponding
Value of the value as dependent variable for falling trend, is trained the preset model, obtains at least two preset models for completing training.
If two preset models are respectively logistic regression prediction model and neural network prediction model, by determining development
The value of the value of fluctuation characteristic vector and the value of transaction feature vector as independent variable, using the value of ups and downs trend as dependent variable
Value, input logic regressive prediction model and neural network prediction model are trained respectively, obtain the logistic regression for completing training
Prediction model and neural network prediction model.Had using the process prior art that logistic regression prediction model is trained detailed
Introduction, no longer excessively illustrated, the principle of logistic regression prediction model is as follows：
Multivariate linear model is：H (x)=a0+a1x1+a2x2+…+anxn
Wherein, h (x) is the dependent variable of multivariate linear model, a0、a1、……anFor the weight of independent variable, x1、x2、……xn
For the independent variable of multivariate linear model.
Classified to article using multivariate linear model, presets threshold values, it is then that all dependent variable h (x) are big
It is divided into one kind in the sample of threshold values, others are divided into another kind of.But this mode has a problem that, since the value of h (x) is to appoint
Size of anticipating, the selection of threshold values is that a difficult thing is normalized it for the ease of the selection of threshold values.
If threshold values is：T, then
Wherein, ha(x) it is to utilize multivariate linear model prediction result；
Assuming that：
a0=a0- t, aTX=a0+a1x1+…+anxn
Using S types (sigmoid) function pair herein, it is normalized.
If at this point, estimate parameter using square smallest error function, since the function after normalization is non-convex function, therefore
And its minimum value cannot be found using gradient descent method.But estimate model parameter using the method for Maximum-likelihood estimation.
Due to being two classification, it can be assumed that：
P (y=1 | xi)=ha(xi), p (y=0 | xi)=1-ha(xi)
Wherein, P (y=1 | xi) it is the probability that prediction result is 1；
ha(xi) be
So likelihood function is：
Wherein, h (xi) be
M is positive integer；
Log-likelihood function L (a)：
To L (a) maximizings, the estimated value of a is obtained.
When preset model is neural network model, for multiple neural network models, following training operation is executed respectively,
Wherein, multiple neural networks have the different neural network numbers of plies：
The value in value and transaction feature vector in fluctuation characteristic vector will be developed as the value of independent variable, risen corresponding
Value of the value as dependent variable for falling trend, is trained Current Situation of Neural Network model, and it is accurate for weighing model prediction to obtain
The index value of the pre-set level of property；
Using the highest neural network model of index value as finally determining neural network prediction model
The number of plies of neural network could be provided as most 10 layers, since one layer, often increase by one layer of correspondence, one nerve net
Network model will develop the value in value and transaction feature vector in fluctuation characteristic vector as the value of independent variable, by ups and downs trend
Value of the value as dependent variable, input above-mentioned neural network model respectively and be trained, obtain each neural network model parameter, with
And the index value of model prediction accuracy is weighed, e.g., which can be that Andrei Kolmogorov-Si meter Nuo Fu is examined
Area (Area under below (Kolmogorov-Smirnov test, KS) check value, recipient's operating characteristic curve
Curve of receiver operating characteristic curve, AUC) index value.It in practical applications, can be with
Obtain KS check values and AUC index values simultaneously.
The accuracy of the bigger characterization model prediction of index value is higher, therefore, by the corresponding neural network of highest index value
Model is as finally determining neural network prediction model, and e.g., when the neural network number of plies is 9, corresponding index value is maximum, the god
It is final neural network prediction model through 9 corresponding neural network model of the network number of plies.Wherein, highest index value can be
KS check values, can also be AUC index values, and the application not limits this.
Continue the example in step S103, is said for a same destination financial e-sourcing for target industry
It is bright, if the corresponding related coefficient of destination financial e-sourcing be lag 2 days, when building at least two preset models and into
When row Model Fusion, the exchange hour sequence of transaction feature vector characterization compares the corresponding development of the development fluctuation characteristic vector
Wave time sequence lags 2 days.Different hysteresises may be corresponding with for different destination financial e-sourcings, specific real
Shi Zhong, the hysteresis of current goal Electronic Finance resource of should being subject to are calculated, and detailed process can refer to above-mentioned example, this Shen
Do not illustrated one by one for each destination financial e-sourcing please.
For example, being illustrated by taking a destination financial e-sourcing as an example, two preset models are respectively that logistic regression is pre-
Model and neural network prediction model are surveyed, by the corresponding value and second for developing fluctuation characteristic vector of the first default historical time section
(hysteresis for e.g., lagging the first default historical time section is that the value of 2) corresponding transaction feature vector is made to default historical time section
For the value of independent variable, using the value of the ups and downs trend of the second default historical time section as the value of dependent variable, difference input logic returns
Prediction model is returned to obtain the first prediction result, the neural network prediction model that input finally determines obtains the second prediction result.
Further, using the first prediction result and the second prediction result as the value of independent variable, by the second historical time section
Value of the value of ups and downs trend as dependent variable, the Fusion Model for inputting structure are trained, and finally obtain trend prediction model, with
Just user predicts the up-trend of Electronic Finance resource using the trend prediction model.
S105, using complete training trend prediction model the development trend of destination financial e-sourcing is predicted,
And destination financial e-sourcing is recommended according to prediction result.
The development trend of destination financial e-sourcing is predicted using the trend prediction model for completing training, and root
It is predicted that when result recommends destination financial e-sourcing, include the following steps：
The development trend of each destination financial e-sourcing is predicted using the trend prediction model for completing training, is obtained
The rise probabilistic forecasting result of each destination financial e-sourcing；
According to obtained rise probabilistic forecasting as a result, the preceding preset quantity destination financial electricity descending to rise probability
Child resource is recommended.
In specific implementation, for each destination financial e-sourcing in target industry, it is based on the destination financial electronics
The development wave time sequence of resource determines the value in development fluctuation characteristic vector, the history based on the destination financial e-sourcing
Transaction data determines the value in transaction feature vector, will develop the value in value and transaction feature vector in fluctuation characteristic vector and makees
For the value of independent variable, it is input in the corresponding trend prediction model of destination financial e-sourcing, obtains the destination financial electronics
The rise probability of resource can will be greater than the corresponding destination financial e-sourcing of rise probability of setting probability threshold value as recommendation
Rise probability can also be ranked up by object according to descending sequence, and preceding preset quantity destination financial electronics is provided
Source is as recommended.
The embodiment of the present application provides a kind of Electronic Finance resource recommendation device, as shown in Fig. 2, the device includes：
First determining module 21 is used for the history media data based on target industry, determines and characterizes the target industry hair
Open up the development wave time sequence of fluctuation；
Second determining module 22 is provided for each Electronic Finance resource for the target industry based on the Electronic Finance
The historical trading data in source determines the ups and downs wave time sequence for characterizing Electronic Finance resource ups and downs fluctuation；
Third determining module 23 is fluctuated for the ups and downs based on the development wave time sequence and each Electronic Finance resource
Correlation analysis between time series is as a result, determine destination financial e-sourcing；
Training module 24 for building trend prediction model for determining destination financial e-sourcing, and is based on target
The history media data of Electronic Finance resource said target industry and the historical trading data of destination financial e-sourcing, it is right
Trend prediction model is trained；
Recommending module 25, for using development trend of the trend prediction model to destination financial e-sourcing for completing training
It is predicted, and destination financial e-sourcing is recommended according to prediction result.
Optionally, first determining module 21 is specifically used for：
History media data based on target industry determines and characterizes the target industry in the first default historical time section
Develop the development wave time sequence of fluctuation；
Second determining module 22 is specifically used for：
For each Electronic Finance resource of the target industry, based on the historical trading data of the Electronic Finance resource, really
Surely the Electronic Finance resource ups and downs wave time that ups and downs are fluctuated in at least one second default historical time section respectively is characterized
Sequence；
The third determining module 23 is specifically used for：
Based on related between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Property analysis result, is determined as destination financial e-sourcing by the Electronic Finance resource for meeting following condition：
The Electronic Finance resource is when ups and downs wave time sequence is with development fluctuation in corresponding second preset time period
Between correlation between sequence meet default correlated condition, and
Second preset time period of correspondence compares the corresponding first default historical time section of the development wave time sequence
Lag.
Optionally, the first determining module 21 is specifically used for：
The history media data of the target industry is parsed using pre-set text analytical algorithm；
Positive and negative tendency emotional semantic classification is carried out to the vocabulary that parsing obtains, obtains characterizing the vocabulary favourable being just inclined to and characterization
The empty profit vocabulary of negative tendency；
Vocabulary favourable and empty profit vocabulary quantity in each default unit interval are counted；
The polarity of each default unit interval is determined according to statistical result；Wherein, vocabulary number favourable in the unit interval is preset
Amount is more than empty profit vocabulary quantity, then it is otherwise negative just to correspond to polarity to be；And
It is default that the default unit interval corresponding polarity sequence of continuous preset quantity is determined as the continuous preset quantity
Unit interval corresponding development wave time sequence.
Optionally, the training module 24 is specifically used for：
Development fluctuation characteristic vector is determined based on the development wave time sequence；And
Transaction feature vector is determined based on the historical trading data of destination financial e-sourcing；
Using development fluctuation characteristic vector and transaction feature vector as independent variable, by destination financial e-sourcing
Ups and downs trend builds the trend prediction model of destination financial e-sourcing as dependent variable；
Wherein, it is corresponding to compare the development fluctuation characteristic vector for the exchange hour sequence of the transaction feature vector characterization
Develop wave time sequence lag, and hysteresis compares the described first default historical time with corresponding second preset time period
The hysteresis of section is identical.
Optionally, recommending module 25 is specifically used for：
The development trend of each destination financial e-sourcing is predicted using the trend prediction model for completing training, is obtained
The rise probabilistic forecasting result of each destination financial e-sourcing；
According to obtained rise probabilistic forecasting as a result, the preceding preset quantity destination financial electricity descending to rise probability
Child resource is recommended.
The embodiment of the present application provides a kind of Electronic Finance resource recommendation device, as shown in figure 3, in the device and Fig. 2
Device is compared, and further includes analysis module 26, and analysis module 26 is used for：
It is default each second for the Electronic Finance resource for each Electronic Finance resource in the target industry
Ups and downs wave time sequence in historical time section determines the ups and downs wave time sequence and the development wave time sequence respectively
Between related coefficient；
Wherein, at least one second default historical time section compares the described first default historical time section lag, or
Person
Precedence relationship between at least one second default historical time section and the first default historical time section
Including lag, and it is one or more as follows：It is in advance or identical.
Corresponding to the Electronic Finance resource recommendation method in Fig. 1, the embodiment of the present application also provides a kind of computer equipments
400, as shown in figure 4, the equipment includes memory 401, processor 402 and is stored on the memory 401 and can be in the processing
The computer program run on device 402, wherein above-mentioned processor 402 realizes above-mentioned finance electricity when executing above computer program
Child resource recommends method.
Specifically, above-mentioned memory 401 and processor 402 can be general memory and processor, do not do have here
Body limits, and when the computer program of 402 run memory 401 of processor storage, is able to carry out above-mentioned Electronic Finance resource and pushes away
It method is recommended, solves that the Electronic Finance resource accuracy recommended in the prior art is low, the application from target industry according to obtaining
Data establish trend prediction model, recommend the Electronic Finance resource of the target industry, on the one hand establish trend prediction mould
The various factors for the target industry that type considers, improve the accuracy of the Electronic Finance resource of recommendation, on the other hand, in needle
When to only recommending Electronic Finance resource to the interested user of a certain specific industry, the Electronic Finance resource of recommendation be easier by with
Family receives, and improves the satisfaction of user.
Corresponding to the Electronic Finance resource recommendation method in Fig. 1, the embodiment of the present application also provides a kind of computer-readable
Storage medium is stored with computer program on the computer readable storage medium, which holds when being run by processor
The step of row above-mentioned Electronic Finance resource recommendation method.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, be able to carry out above-mentioned Electronic Finance resource recommendation method, solve and recommend in the prior art
Electronic Finance resource accuracy is low, and the application establishes trend prediction model according to the data obtained from target industry, to the target
The Electronic Finance resource of industry is recommended, on the one hand establish trend prediction model consideration target industry a variety of influences because
Element improves the accuracy of the Electronic Finance resource of recommendation, on the other hand, for only to the interested use of a certain specific industry
When Electronic Finance resource is recommended at family, the Electronic Finance resource of recommendation is easier to be easily accepted by a user, and improves the satisfaction of user.
In embodiment provided herein, it should be understood that disclosed system and method, it can be by others side
Formula is realized.System embodiment described above is only schematical, for example, the division of the unit, only one kind are patrolled
Volume function divides, formula that in actual implementation, there may be another division manner, in another example, multiple units or component can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, system or unit
It connects, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the present application can be integrated in a processing unit, also may be used
It, can also be during two or more units be integrated in one unit to be that each unit physically exists alone.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer read/write memory medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of step.
And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic disc or CD.
It should be noted that：Similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent attached drawing in a attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally it should be noted that：Embodiment described above, the only specific implementation mode of the application, to illustrate the application
Technical solution, rather than its limitations, the protection domain of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, it will be understood by those of ordinary skill in the art that：Any one skilled in the art
In the technical scope that the application discloses, it can still modify to the technical solution recorded in previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution.The protection in the application should all be covered
Within the scope of.Therefore, the protection domain of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of Electronic Finance resource recommendation method, which is characterized in that this method includes：
History media data based on target industry determines the development wave time sequence for characterizing the target industry development fluctuation
Row；
Table is determined based on the historical trading data of the Electronic Finance resource for each Electronic Finance resource of the target industry
Levy the ups and downs wave time sequence of Electronic Finance resource ups and downs fluctuation；
Based on the correlation point between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Analysis is as a result, determine destination financial e-sourcing；
Trend prediction model is built for determining destination financial e-sourcing, and is based on destination financial e-sourcing said target
The history media data of industry and the historical trading data of destination financial e-sourcing, are trained trend prediction model；
The development trend of destination financial e-sourcing is predicted using the trend prediction model for completing training, and according to prediction
As a result destination financial e-sourcing is recommended.
2. the method as described in claim 1, which is characterized in that the history media data based on target industry determines characterization institute
The development wave time sequence of target industry development fluctuation is stated, including：
History media data based on target industry determines that characterize the target industry develops in the first default historical time section
The development wave time sequence of fluctuation；
Table is determined based on the historical trading data of the Electronic Finance resource for each Electronic Finance resource of the target industry
The ups and downs wave time sequence of Electronic Finance resource ups and downs fluctuation is levied, including：
Table is determined based on the historical trading data of the Electronic Finance resource for each Electronic Finance resource of the target industry
Levy the Electronic Finance resource ups and downs wave time sequence that ups and downs are fluctuated in at least one second default historical time section respectively；
Based on the correlation point between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Analysis as a result, determine destination financial e-sourcing, including：
Based on the correlation point between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Analysis by the Electronic Finance resource for meeting following condition as a result, be determined as destination financial e-sourcing：
The Electronic Finance resource ups and downs wave time sequence and development wave time sequence in corresponding second preset time period
Correlation between row meets default correlated condition, and
Second preset time period of correspondence compares the corresponding first default historical time section lag of the development wave time sequence.
3. method as claimed in claim 2, which is characterized in that with the following method to the development wave time sequence and respectively
The ups and downs wave time sequence of Electronic Finance resource carries out correlation analysis：
For each Electronic Finance resource in the target industry, for the Electronic Finance resource in each second default history
Ups and downs wave time sequence in period determines between the ups and downs wave time sequence and the development wave time sequence respectively
Related coefficient；
Wherein, at least one second default historical time section compares the described first default historical time section lag, or
Precedence relationship between at least one second default historical time section and the first default historical time section includes
Lag, and it is following one or more：It is in advance or identical.
4. method as described in any one of claims 1-3, which is characterized in that the history media data based on target industry, really
Surely the development wave time sequence of the target industry development fluctuation is characterized, including：
The history media data of the target industry is parsed using pre-set text analytical algorithm；
Positive and negative tendency emotional semantic classification is carried out to the vocabulary that parsing obtains, obtains characterizing the vocabulary favourable being just inclined to and characterization is born and inclines
To empty profit vocabulary；
Vocabulary favourable and empty profit vocabulary quantity in each default unit interval are counted；
The polarity of each default unit interval is determined according to statistical result；Wherein, it is big to preset vocabulary quantity favourable in the unit interval
In empty profit vocabulary quantity, then it is just, to preset advantage vocabulary quantity in the unit interval and be less than empty profit vocabulary quantity to correspond to polarity, then right
It is negative to answer polarity, presets favourable vocabulary quantity in the unit interval and is equal to empty profit vocabulary quantity, then corresponds to during polarity is；And
The default unit interval corresponding polarity sequence of continuous preset quantity is determined as the default unit of the continuous preset quantity
Time corresponding development wave time sequence.
5. method as claimed in claim 2, which is characterized in that build trend prediction for determining destination financial e-sourcing
Model, including：
Development fluctuation characteristic vector is determined based on the development wave time sequence；And
Transaction feature vector is determined based on the historical trading data of destination financial e-sourcing；
Using development fluctuation characteristic vector and transaction feature vector as independent variable, by the ups and downs of destination financial e-sourcing
Trend builds the trend prediction model of destination financial e-sourcing as dependent variable；
Wherein, the exchange hour sequence of the transaction feature vector characterization compares the corresponding development of the development fluctuation characteristic vector
Wave time sequence lags, and hysteresis compares the described first default historical time section with corresponding second preset time period
Hysteresis is identical.
6. method as described in any one of claims 1-3, which is characterized in that using the trend prediction model of completion training to mesh
The development trend that e-sourcing is melted in standard gold is predicted, and is recommended destination financial e-sourcing according to prediction result, packet
It includes：
The development trend of each destination financial e-sourcing is predicted using the trend prediction model for completing training, obtains each mesh
The rise probabilistic forecasting result of e-sourcing is melted in standard gold；
According to obtained rise probabilistic forecasting as a result, the preceding preset quantity destination financial electronics money descending to rise probability
Recommended in source.
7. a kind of Electronic Finance resource recommendation device, which is characterized in that the device includes：
First determining module is used for the history media data based on target industry, determines and characterizes the target industry development fluctuation
Development wave time sequence；
Second determining module, for each Electronic Finance resource for the target industry, based on going through for the Electronic Finance resource
History transaction data determines the ups and downs wave time sequence for characterizing Electronic Finance resource ups and downs fluctuation；
Third determining module, for the ups and downs wave time sequence based on development the wave time sequence and each Electronic Finance resource
Correlation analysis between row is as a result, determine destination financial e-sourcing；
Training module, for building trend prediction model for determining destination financial e-sourcing, and based on destination financial electricity
The history media data of child resource said target industry and the historical trading data of destination financial e-sourcing, it is pre- to trend
Model is surveyed to be trained；
Recommending module, it is pre- for being carried out to the development trend of destination financial e-sourcing using the trend prediction model for completing training
It surveys, and destination financial e-sourcing is recommended according to prediction result.
8. device as claimed in claim 7, which is characterized in that first determining module is specifically used for：
History media data based on target industry determines that characterize the target industry develops in the first default historical time section
The development wave time sequence of fluctuation；
Second determining module is specifically used for：
Table is determined based on the historical trading data of the Electronic Finance resource for each Electronic Finance resource of the target industry
Levy the Electronic Finance resource ups and downs wave time sequence that ups and downs are fluctuated in at least one second default historical time section respectively；
The third determining module is specifically used for：
Based on the correlation point between the development wave time sequence and the ups and downs wave time sequence of each Electronic Finance resource
Analysis by the Electronic Finance resource for meeting following condition as a result, be determined as destination financial e-sourcing：
The Electronic Finance resource ups and downs wave time sequence and development wave time sequence in corresponding second preset time period
Correlation between row meets default correlated condition, and
Second preset time period of correspondence compares the corresponding first default historical time section lag of the development wave time sequence.
9. a kind of computer equipment includes memory, processor and is stored on the memory and can transport on the processor
Capable computer program, which is characterized in that the processor realizes the claims 1 to 6 when executing the computer program
The step of any one of them method.
10. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
The step of being, 1 to 6 any one of them method of the claims executed when the computer program is run by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810399403.6A CN108596765A (en) | 2018-04-28 | 2018-04-28 | A kind of Electronic Finance resource recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810399403.6A CN108596765A (en) | 2018-04-28 | 2018-04-28 | A kind of Electronic Finance resource recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596765A true CN108596765A (en) | 2018-09-28 |
Family
ID=63610781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810399403.6A Pending CN108596765A (en) | 2018-04-28 | 2018-04-28 | A kind of Electronic Finance resource recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596765A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443374A (en) * | 2019-08-14 | 2019-11-12 | 腾讯科技（深圳）有限公司 | A kind of resource information processing method, device and equipment |
| CN111210353A (en) * | 2020-01-08 | 2020-05-29 | 高盈量化云科技（深圳）有限公司 | Intelligent triggering and informing method |
| CN112749005A (en) * | 2020-07-10 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Resource data processing method and device, computer equipment and storage medium |
| CN114820191A (en) * | 2022-05-10 | 2022-07-29 | 中科柏诚科技（北京）股份有限公司 | Artificial intelligent stock system application method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226554A (en) * | 2012-12-14 | 2013-07-31 | 西藏同信证券有限责任公司 | Automatic stock matching and classifying method and system based on news data |
| CN106022522A (en) * | 2016-05-20 | 2016-10-12 | 南京大学 | Method and system for predicting stocks based on big data published by internet |
| US20170018033A1 (en) * | 2015-07-15 | 2017-01-19 | Foundation Of Soongsil University Industry Cooperation | Stock fluctuatiion prediction method and server |
-
2018
- 2018-04-28 CN CN201810399403.6A patent/CN108596765A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226554A (en) * | 2012-12-14 | 2013-07-31 | 西藏同信证券有限责任公司 | Automatic stock matching and classifying method and system based on news data |
| US20170018033A1 (en) * | 2015-07-15 | 2017-01-19 | Foundation Of Soongsil University Industry Cooperation | Stock fluctuatiion prediction method and server |
| CN106022522A (en) * | 2016-05-20 | 2016-10-12 | 南京大学 | Method and system for predicting stocks based on big data published by internet |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443374A (en) * | 2019-08-14 | 2019-11-12 | 腾讯科技（深圳）有限公司 | A kind of resource information processing method, device and equipment |
| CN111210353A (en) * | 2020-01-08 | 2020-05-29 | 高盈量化云科技（深圳）有限公司 | Intelligent triggering and informing method |
| CN112749005A (en) * | 2020-07-10 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Resource data processing method and device, computer equipment and storage medium |
| CN112749005B (en) * | 2020-07-10 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Resource data processing method, device, computer equipment and storage medium |
| CN114820191A (en) * | 2022-05-10 | 2022-07-29 | 中科柏诚科技（北京）股份有限公司 | Artificial intelligent stock system application method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485562B (en) | Commodity information recommendation method and system based on user historical behaviors | |
| Pitchipoo et al. | Fuzzy hybrid decision model for supplier evaluation and selection | |
| Chatterjee et al. | Supplier selection in Telecom supply chain management: a Fuzzy-Rasch based COPRAS-G method | |
| CN108596765A (en) | A kind of Electronic Finance resource recommendation method and device | |
| CN111340244B (en) | Prediction method, training method, device, server and medium | |
| CN110647696B (en) | Business object sorting method and device | |
| CN109766454A (en) | A kind of investor's classification method, device, equipment and medium | |
| CN108596393A (en) | A kind of training method and device of Electronic Finance resources model | |
| CN111797320B (en) | Data processing method, device, equipment and storage medium | |
| CN112966189B (en) | Fund product recommendation system | |
| CN106408325A (en) | User consumption behavior prediction analysis method based on user payment information and system | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN107590737A (en) | Personal credit scores and credit line measuring method | |
| CN102163304A (en) | Method and system for collaborative networking with optimized inter-domain information quality assessment | |
| CN107679987A (en) | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium | |
| CN111695084A (en) | Model generation method, credit score generation method, device, equipment and storage medium | |
| CN111859946B (en) | Method and apparatus for ordering comments and machine-readable storage medium | |
| KR102018838B1 (en) | Method for providing bigdata weighted moving average based bidding information analysis service for online bidding participation | |
| CN111667307A (en) | Method and device for predicting financial product sales volume | |
| CN111292188A (en) | Intelligent integrated return test system for pairing transaction | |
| CN107305662A (en) | Recognize the method and device of violation account | |
| CN116188039A (en) | Intelligent recommendation method and system for suppliers | |
| CN109598623A (en) | A kind of financial product future profits data predication method, apparatus and system | |
| CN115439180A (en) | Target object determination method and device, electronic equipment and storage medium | |
| CN109460778A (en) | Active evaluation method, apparatus, 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 101-8, 1st floor, building 31, area 1, 188 South Fourth Ring Road West, Fengtai District, Beijing Applicant after: Guoxin Youyi Data Co., Ltd Address before: 100070, No. 188, building 31, headquarters square, South Fourth Ring Road West, Fengtai District, Beijing Applicant before: SIC YOUE DATA Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |