CN109461067A - A kind of detection method of foreign exchange quotation abnormal data, apparatus and system - Google Patents
A kind of detection method of foreign exchange quotation abnormal data, apparatus and system Download PDFInfo
- Publication number
- CN109461067A CN109461067A CN201811061270.8A CN201811061270A CN109461067A CN 109461067 A CN109461067 A CN 109461067A CN 201811061270 A CN201811061270 A CN 201811061270A CN 109461067 A CN109461067 A CN 109461067A
- Authority
- CN
- China
- Prior art keywords
- data
- quotation
- quote
- quote data
- prediction
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 175
- 238000001514 detection method Methods 0.000 title claims abstract description 128
- 230000005856 abnormality Effects 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims description 108
- 230000015654 memory Effects 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 28
- 230000005540 biological transmission Effects 0.000 claims description 12
- 230000007787 long-term memory Effects 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000006403 short-term memory Effects 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000008676 import Effects 0.000 abstract description 15
- 238000010586 diagram Methods 0.000 description 27
- 230000008569 process Effects 0.000 description 25
- 230000006870 function Effects 0.000 description 17
- 238000004422 calculation algorithm Methods 0.000 description 12
- 230000006872 improvement Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 239000000047 product Substances 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002688 persistence Effects 0.000 description 3
- 230000000750 progressive effect Effects 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 229910021389 graphene Inorganic materials 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011017 operating method Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This specification provides a kind of detection method of foreign exchange quotation abnormal data, apparatus and system, carries out the prediction of quote data based on historical quotes data using data platform, determines prediction quote data.The prediction quote data and historical quotes data that quotation center can be sent according to data platform, whether abnormal detect the quote data that bank or financial institution send, realize the abnormality detection of foreign exchange quotation, it is ensured that the accuracy of foreign exchange quotation provides accurate basic data for import and export business.
Description
Technical field
This specification belongs to financial technology field more particularly to a kind of detection method of foreign exchange quotation abnormal data, device
And system.
Background technique
Cross-border transaction payment is related to import and export business, and import and export business usually requires to carry out the exchange of currency, and exchanges then
It is related to the foreign exchange quotation of each bank or financial institution for foreign exchange.
Ensure that the reasonability of foreign exchange quotation and correctness become the basic energy that each cross-border transaction payment system needs to have
Power may have the quote data of inaccuracy in the foreign exchange quotation of each bank or financial institution for foreign exchange.If occurring abnormal
Quote data, may will affect currency conversion as a result, influence cross-border transaction business.
Summary of the invention
This specification is designed to provide a kind of detection method of foreign exchange quotation abnormal data, apparatus and system, realizes outer
The abnormality detection of report valence, it is ensured that the accuracy of foreign exchange quotation.
First aspect this specification embodiment provides a kind of detection method of foreign exchange quotation abnormal data, comprising:
Receiving quotation data；
The quote data and the basis quote data in database are compared, determine whether the quote data is different
Often, the basis quote data include: historical quotes data, prediction quote data.
Further, in another embodiment of the method, whether the determination quote data is abnormal, comprising:
Judge in the quote data and the historical quotes data specify quote data between irrelevance whether
In first default fluctuation range, if not existing, it is determined that the quote data is abnormal quote data, the specified quote data
Corresponding quotation time, quotation time interval corresponding with the quote data was less than preset time threshold.
Further, in another embodiment of the method, the prediction quote data includes: to utilize autoregressive conditions
The quote data fluctuation range that heteroscedastic model determines；
Correspondingly, whether the determination quote data is abnormal, comprising:
Judge the difference between quote data closing price corresponding with specified time whether in the quote data wave
In dynamic range, if not existing, it is determined that the quote data is abnormal quote data.
Further, in another embodiment of the method, the prediction quote data includes: to be remembered using shot and long term
The real-time prediction quotation that network model determines；
Correspondingly, whether the determination quote data is abnormal, comprising:
Judge the quote data and it is described it is real-time prediction quotation between difference whether in the second default fluctuation range, if
Do not exist, it is determined that the quote data is abnormal quote data.
Further, in another embodiment of the method, the prediction quote data includes: to utilize Pauta criterion
Determining quotation range；
Correspondingly, whether the determination quote data is abnormal, comprising:
The quote data is judged whether in the quotation range, if not existing, it is determined that the quote data is abnormal
Quote data.
Further, in another embodiment of the method, the method also includes:
The solicited message of inquiry quote data is sent, includes: request quotation parameter in the solicited message；
After receiving the quote data, the quote data is matched with the quotation parameter, determines the quotation
Whether data meet the solicited message.
Further, in another embodiment of the method, the method also includes:
If it is determined that the quote data is normal, then the quote data is persisted in the database；
If it is determined that the quote data is abnormal quote data, then abnormal warning is carried out.
Second aspect, present description provides a kind of detection methods of foreign exchange quotation abnormal data, comprising:
Obtain historical quotes data；
According to the historical quotes data, prediction quote data is determined；
The prediction quote data is sent to quotation central platform, so that the quotation central platform is based on the prediction
Quote data carries out abnormality detection the quote data received.
Further, described according to the historical quotes data in another embodiment of the method, it determines to predict
Quote data, comprising:
Quote data fluctuation range is determined using autoregressive conditional different Variance model according to the historical quotes data,
Using the quote data fluctuation range as the prediction quote data.
Further, described according to the historical quotes data in another embodiment of the method, it determines to predict
Quote data, comprising:
According to the historical quotes data, using Pauta criterion, the quotation range of each currency type under different latitude is determined,
Using the quotation range as the prediction quote data.
Further, described according to the historical quotes data in another embodiment of the method, it determines to predict
Quote data, comprising:
Real-time price quotations data are obtained, the historical quotes data are updated, are based on the updated historical quotes data, benefit
With shot and long term memory network model, real-time prediction quotation is predicted, by the real-time prediction quotation as prediction quotation number
According to.
Further, in another embodiment of the method, the method also includes:
The abnormal quote data that the quotation central platform is sent is received, the abnormal offer of different quotation channels is counted
Breath, and be shown.
The third aspect, present description provides a kind of detection devices of foreign exchange quotation abnormal data, comprising:
Data reception module is used for receiving quotation data；
Anomaly data detection module is used for receiving quotation data；
The quote data and the basis quote data in database are compared, determine whether the quote data is different
Often, the basis quote data include: historical quotes data, data platform send determined based on historical quotes data it is pre-
Survey quote data.
Further, in another embodiment of described device, the anomaly data detection module is specifically used for:
Judge in the quote data and the historical quotes data specify quote data between irrelevance whether
In first default fluctuation range, if not existing, it is determined that the quote data is abnormal quote data, the specified quote data
Corresponding quotation time, quotation time interval corresponding with the quote data was less than preset time threshold.
Further, in another embodiment of described device, the prediction quote data includes: to utilize autoregressive conditions
The quote data fluctuation range that heteroscedastic model determines；
Correspondingly, the anomaly data detection module is specifically used for:
Judge the difference between quote data closing price corresponding with specified time whether in the quote data wave
In dynamic range, if not existing, it is determined that the quote data is abnormal quote data.
Further, in another embodiment of described device, the prediction quote data includes: to be remembered using shot and long term
The real-time prediction quotation that network model determines；
Correspondingly, the anomaly data detection module is specifically used for:
Judge the quote data and it is described it is real-time prediction quotation between difference whether in the second default fluctuation range, if
Do not exist, it is determined that the quote data is abnormal quote data.
Further, in another embodiment of described device, the prediction quote data includes: to utilize Pauta criterion
Determining quotation range；
Correspondingly, the anomaly data detection module is specifically used for:
The quote data is judged whether in the quotation range, if not existing, it is determined that the quote data is abnormal
Quote data.
Further, in another embodiment of described device, described device further include:
Request for quote module includes: request report for sending the solicited message of inquiry quote data, in the solicited message
Valence parameter；
Quote data correction verification module, after receiving the quote data, by the quote data and the quotation parameter
It is matched, determines whether the quote data meets the solicited message.
Further, in another embodiment of described device, described device further includes dealing of abnormal data module, is used
In:
If it is determined that the quote data is normal, then the quote data is persisted in the database；
If it is determined that the quote data is abnormal quote data, then abnormal warning is carried out.
Fourth aspect, present description provides a kind of processing equipments of the different quotation anomaly data detection of foreign exchange, comprising: at least
One processor and memory for storage processor executable instruction, the processor are realized when executing described instruction
State the detection method of the different quotation abnormal data of foreign exchange described in first aspect.
5th aspect, present description provides a kind of detection devices of foreign exchange quotation abnormal data, comprising:
Data acquisition module, for obtaining historical quotes data；
Quote data prediction module, for determining prediction quote data according to the historical quotes data；
Data transmission blocks, for the prediction quote data to be sent to quotation center, so that the quotation center is flat
Stylobate carries out abnormality detection the quote data received in the prediction quote data.
Further, in another embodiment of described device, the quote data prediction module is specifically used for:
Quote data fluctuation range is determined using autoregressive conditional different Variance model according to the historical quotes data,
Using the quote data fluctuation range as the prediction quote data.
Further, in another embodiment of described device, the quote data prediction module is specifically used for:
According to the historical quotes data, using Pauta criterion, the quotation range of each currency type under different latitude is determined,
Using the quotation range as the prediction quote data.
Further, in another embodiment of described device, the quote data prediction module is specifically used for:
Real-time price quotations data are obtained, the historical quotes data are updated, are based on the updated historical quotes data, benefit
With shot and long term memory network model, real-time prediction quotation is predicted, by the real-time prediction quotation as prediction quotation number
According to.
Further, in another embodiment of described device, described device further include:
Exception information display module, the abnormal quote data sent for receiving the quotation central platform, statistics are different
The abnormal quotation information of quotation channel, and be shown.
6th aspect, present description provides a kind of processing equipments of the different quotation anomaly data detection of foreign exchange, comprising: at least
One processor and memory for storage processor executable instruction, the processor are realized when executing described instruction
State the detection method of the different quotation abnormal data of foreign exchange described in second aspect.
7th aspect, present description provides a kind of detection systems of foreign exchange quotation abnormal data, comprising: data platform,
Exchanging platform, the data platform include device described in above-mentioned 5th aspect, and the exchanging platform includes the above-mentioned third aspect
The device.
Detection method, device, processing equipment, the system for the foreign exchange quotation abnormal data that this specification provides, utilize data
Platform carries out the prediction of quote data based on historical quotes data, determines prediction quote data.It quotation center can be according to number
The historical quotes data stored in the prediction quote data and database sent according to platform, detect bank or financial institution sends
Quote data it is whether abnormal, realize the abnormality detection of foreign exchange quotation, it is ensured that the accuracy of foreign exchange quotation mentions for import and export business
For accurate data basis.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the structural schematic diagram of the detection system of foreign exchange quotation abnormal data in this specification one embodiment；
Fig. 2 is the flow diagram of the detection method of foreign exchange quotation abnormal data in this specification one embodiment；
Fig. 3 is the flow diagram of detection of offering extremely in this specification one embodiment；
Fig. 4 is the detection method flow diagram that this specification has foreign exchange quotation abnormal data in one embodiment；
Fig. 5 is the flow diagram of quotation channel billboard generating process in this specification one embodiment；
Fig. 6 is the calculation processes schematic diagram that quote data is predicted in this specification one embodiment；
Fig. 7 is the abnormality detecting process schematic diagram of foreign exchange quotation in another embodiment of this specification；
Fig. 8 is the modular structure signal of the detection device one embodiment for the foreign exchange quotation abnormal data that this specification provides
Figure；
Fig. 9 is the structural schematic diagram of the detection device of foreign exchange quotation abnormal data in the another embodiment of this specification；
Figure 10 is the structural schematic diagram of the detection device of foreign exchange quotation abnormal data in the another embodiment of this specification；
Figure 11 is the structural schematic diagram of the detection device of foreign exchange quotation abnormal data in the another embodiment of this specification；
Figure 12 is the hardware configuration frame using a kind of server of foreign exchange quotation anomaly data detection of the embodiment of the present invention
Figure.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book embodiment is clearly and completely described the technical solution in this specification embodiment, it is clear that described
Embodiment be only this specification a part of the embodiment, instead of all the embodiments.The embodiment of base in this manual,
Every other embodiment obtained by those of ordinary skill in the art without making creative efforts, all should belong to
The range of this specification protection.
With the development of economy, import and export business is more and more, needs to carry out currency conversion in import and export business, currency is converted
The foreign exchange quotation that financial institution or bank are needed when changing carries out currency conversion according to foreign exchange quotation.
Fig. 1 is the structural schematic diagram of the detection system of foreign exchange quotation abnormal data in this specification one embodiment, such as Fig. 1
Shown, in this specification one embodiment, the detection system of foreign exchange quotation abnormal data may include data platform and exchange flat
Platform.Wherein, data platform can obtain the quotation number of different channels from the storage facility located at processing plant at quotation center respectively based on big data technology
According to obtaining sample data of the off-line data as prediction model from data warehouse, then run the algorithm for being deployed in algorithm platform
Model, the basis quote data after the corresponding statistical analysis of output.As shown in Figure 1, data platform may include algorithm platform, report
Table platform, off-line data platform, Real-time Data Center, algorithm platform can be used for calculating basis quote data；Report platform
Can to quotation center database in abnormal quote data statisticallyd analyze afterwards, construct corresponding billboard and show
The associated user of service operation；Off-line data platform can obtain the historical quotes data in quotation central database offline, real
When the available real-time price quotations data of data platform.
Exchanging platform may include redemption center and quotation center, and redemption center mainly carries exchange trading and accepts, open
It collects, exchanges the functions such as square position.Quotation center mainly carries query service, and price calculation publication, quotation access and quotation are abnormal
The functions such as detection.Quotation abnormality detection can be taken absolute value using the difference of the quote data and basis quote data received and be removed
With basis quote data, calculated result is compared with pre-set fluctuation threshold.According to different info quote business
Different fluctuation thresholds can be set, offers center in receiving quotation data procedures, system detection to fluctuation range is more than wave
Dynamic threshold value can then trigger the alarm such as short message, mail, and current received quote data is set to abnormal quotation.After receiving alarm,
The abnormal quotation of business intervention inquiry, if business judge this quotation be caused due to reasonable causes such as market big ups and downs it is misjudged
For abnormal quotation, this quotation can be promoted into again by the operation page normal.
In addition, the detection system of foreign exchange quotation abnormal data can also include that bank, financial institution etc. are able to carry out foreign exchange
The mechanism of quotation can also include that other mechanisms or equipment, this specification embodiment are not especially limited certainly.
The detection method of foreign exchange quotation abnormal data can be applied in client or server in this specification, client
Can be smart phone, tablet computer, intelligent wearable device (smartwatch, virtual reality glasses, virtual implementing helmet etc.),
The electronic equipments such as intelligent vehicle-carried equipment.Exchanging platform, data platform in Fig. 1 can also apply client or server or its
In his computer module, this specification embodiment is not especially limited.
A kind of detection method of foreign exchange quotation abnormal data is provided in this specification one embodiment, utilizes data platform
The prediction that quote data is carried out based on historical quotes data, determines prediction quote data, and quotation center can be flat according to data
Whether different the prediction quote data and historical quotes data that platform is sent detect the quote data that bank or financial institution send
Often.
Specifically, Fig. 2 is the process signal of the detection method of foreign exchange quotation abnormal data in this specification one embodiment
Figure, as shown in Fig. 2, the overall process of the detection method of the foreign exchange quotation abnormal data provided in this specification one embodiment can
To include:
Step 202, receiving quotation data.
Fig. 3 is the flow diagram of detection of offering extremely in this specification one embodiment, as shown in figure 3, specific
In implementation process, the mechanism hair of the i.e. foreign exchange quotation of foreign exchange rate can be issued from quotation center to bank or financial institution etc.
Send the solicited message of inquiry quote data, bank or financial institution according to the solicited message at quotation center return it is corresponding as a result,
Quotation center can receive the quote data that bank or financial institution return.
As shown in figure 3, quotation center can be by being arranged timed task to bank or gold in this specification one embodiment
Melt the solicited message of the transmissions such as mechanism inquiry quote data, i.e. inquiry exchange rate quotation in Fig. 3, exchange rate quotation can indicate foreign exchange
The foreign currency exchange sticker price of appointed bank.It may include request report in the solicited message for the inquiry quote data that quotation center is sent
Valence parameter, request quotation parameter can characterize the feature of the quote data of request inquiry, such as: the date of the exchange rate quotation of inquiry,
The type etc. of exchange rate quotation.Such as: quotation center can send request inquiry same day quotation in real time to bank or financial institution
Data.
In addition, quotation center receives after the solicited message for sending inquiry quote data in this specification one embodiment
After the quote data returned to bank or financial institution, legitimacy inspection can also be carried out to the quote data received, such as: can
To verify the quote data received and quotation parameter, judge whether received quote data meets asking for quotation center
Seek the quote data requested in information.Such as: quotation center sends the solicited message of request quote data to certain bank, and request obtains
The real-time price quotations data of today are taken, if the quote data that the bank returns is the quote data of yesterday, it is determined that current quotation
Data do not meet the solicited message at quotation center.
Step 204 compares the quote data and the basis quote data in database, determines the quotation number
Extremely whether according to, the basis quote data include: historical quotes data, prediction quote data.
Database can be set in quotation center, can store basis quote data in database, basis quote data can
To include: the historical quotes data of each bank or financial institution's transmission, and prediction quote data, prediction quote data can be with table
The quote data determined based on the training of historical quotes data is levied, such as predicts that quote data may include: the fluctuation of quote data
Zone of reasonableness etc. where range, the quote data of subsequent time, quote data.Predict that quote data can be by data platform root
It determines according to historical quotes data, certainly, can also be determined according to actual needs by quotation center based on historical quotes data.Quotation
After center receives the quote data that bank or financial institution send, the benchmark report that can will store in quote data and database
Valence mumber determines whether the current quote data received is abnormal according to comparing.
Such as: can judge number of offering by the quote data received compared with basis quote data carry out numerical values recited
Whether in allowed limits according to the difference with basis quote data；It can also be by the difference of quote data and basis quote data
It takes absolute value divided by basis quote data, calculated result is compared with pre-set threshold value；Or judge quote data
Whether in the range of basis quote data；Or be compared quote data with the mean value of basis quote data, according to
Actual needs can also use other control methods, and this specification embodiment is not especially limited.
In this specification one embodiment, if it is detected that current quote data is normal data, it can will offer
Data persistence is into the database at quotation center, one of basis quote data of abnormality detection as next quote data.
If it is detected that current quote data is abnormal quote data, abnormal warning can be carried out, such as pass through mail or short message side
Method is warned.After relevant business side receives exception warning, it can be inquired on the operation page that quotation center provides
Abnormal quote data judges whether the price fluctuation of abnormal quote data is reasonable, can promote into price again if rationally
Normally, it and can be persisted in the database at quotation center.Persistence can indicate data (object in such as memory) to protect
Being stored to can store quote data into database in the storage equipment of persistence (such as disk), may include permanent
It saves or keeps in database.
A kind of detection method of foreign exchange quotation abnormal data is provided in this specification one embodiment, utilizes data platform
Prediction quote data is determined in the prediction that quote data is carried out based on historical quotes data.It quotation center can be flat according to data
The historical quotes data stored in the prediction quote data and database that platform is sent detect the report that bank or financial institution send
Whether valence mumber evidence is abnormal, realizes the abnormality detection of foreign exchange quotation, it is ensured that the accuracy of foreign exchange quotation provides standard for import and export business
True data basis.
On the basis of the above embodiments, in this specification one embodiment, whether the determination quote data is different
Often, comprising:
Judge in the quote data and the historical quotes data specify quote data between irrelevance whether
In first default fluctuation range, if not existing, it is determined that the quote data is abnormal quote data, the specified quote data
Corresponding quotation time, quotation time interval corresponding with the quote data was less than preset time threshold.
In the specific implementation process, the historical quotes data offered in the database at center can carry out in real time at any time
It updates, after the quote data received every time is determined as arm's length quotation data, the quote data received can be persisted to
In data.Specified quote data can indicate updated newest quote data in database, or with the quotation that receives
The time of data immediate quote data, can be by being arranged suitable preset time threshold, the quotation for selecting and receiving
The time of data immediate quote data.It quotation center can be by the historical quotes in the quote data and database that receive
Specified quote data in data compares, and judges the deviation between the quote data received and specified quote data
Degree whether in the first default fluctuation range, if irrelevance not in the first default fluctuation range, can be with firm offer data
For abnormal quote data.Irrelevance can indicate the difference between the quote data received and specified quote data.First
Default fluctuation range can be configured according to actual needs, and this specification embodiment is not especially limited.
Such as: if current time is on September 3rd, 2018, the quote data of today is received, the quotation that can will be received
The quote data on the 2nd of September in 2018 stored in data, with database compares, judge the quote data received with
The irrelevance of the quote data on the 2nd of September in 2018 determines the quotation number being currently received whether in the first default fluctuation range
According to whether being abnormal quote data.If judging the deviation of the quote data being currently received and the quote data on the 2nd of September in 2018
Degree is not in the first default fluctuation range, it is determined that the quote data being currently received is abnormal quote data, can be carried out different
Often warning, is further verified by business side.
This specification embodiment carries out the quote data received based on the historical quotes data stored in database different
Often detection determines whether foreign exchange quotation is abnormal, it is ensured that the accuracy of foreign exchange quotation provides accurate number for import and export business
According to basis.
On the basis of the above embodiments, in this specification one embodiment, the prediction quote data includes: using certainly
Return the quote data fluctuation range that Conditional heterosedasticity model determines；
Correspondingly, whether the determination quote data is abnormal, comprising:
Judge the difference between quote data closing price corresponding with specified time whether in the quote data wave
In dynamic range, if not existing, it is determined that the quote data is abnormal quote data.
In the specific implementation process, data platform or quotation center can use autoregressive conditional different Variance model i.e.
Garch (generalized autoregressive conditional heteroskedasticity) model, predicts report
Valence mumber is according to fluctuation range.Garch model is properly termed as ARCH (the Autoregressive conditional of broad sense
Heteroskedasticity model, autoregressive conditional different Variance model) model, it can be understood as it is measured for finance data
The tailor-made regression model of body, removes and common regression model something in common, garch further build to the variance of error
Mould predicts the fluctuation range of quote data using the bound that garch model can predict quote data.Quotation center
After receiving quote data, it can be determined that the difference between the quote data received closing price corresponding with specified time is
It is no in the quote data fluctuation range that data platform is gone out based on garch model prediction, if not existing, can determine and to receive
Quote data is abnormal quote data.Wherein, specified time can based on the received quote data corresponding time combine it is practical
It needs to be configured, such as: can be by the closing price of the previous day of the quote data received, as specified time corresponding closing quotation
Valence.Closing price can indicate that the concluded price of last transaction or daylight trading terminate previous point at the end of transaction
The weighted average price of the exchange hand of All Activity in clock, specifically can be set according to actual needs, this specification embodiment
It is not especially limited.
Such as: current time is on September 3rd, 2018, after the quote data for receiving current time bank, can be calculated
The quote data of received current time and the previous day are the difference between the closing price on the 2nd of September in 2018, are judged calculated
Whether difference is in the quote data fluctuation range of data platform prediction, if not existing, it is determined that the quote data received is different
Normal quote data can carry out abnormal warning.
This specification embodiment is docked using data platform based on the quote data fluctuation range that garch model prediction goes out
Whether the quote data received carries out abnormality detection, the quote data being currently received can be determined in reasonable fluctuation range
It is interior, determine whether foreign exchange quotation is abnormal, it is ensured that the accuracy of foreign exchange quotation provides accurate data base for import and export business
Plinth.
On the basis of the above embodiments, in this specification one embodiment, the prediction quote data includes: to utilize length
The real-time prediction quotation that short-term memory network model determines；
Correspondingly, whether the determination quote data is abnormal, comprising:
Judge the quote data and it is described it is real-time prediction quotation between difference whether in the second default fluctuation range, if
Do not exist, it is determined that the quote data is abnormal quote data.
In the specific implementation process, data platform can use shot and long term memory network model i.e. LSTM (Long
Short-Term Memory) model determine in real time in real time prediction quotation, LSTM model is a kind of time recurrent neural net
Network can use LSTM model and predict the real-time of subsequent time based on historical quotes data or real-time price quotations data and pre- observes and predicts
Valence.Real-time prediction that quotation center can be reported according to data platform quotation detects the quote data received, can be with
Whether the difference between real-time prediction quotation that the calculating quote data received and LSTM are determined is preset second fluctuates model
In enclosing, if not existing, it can determine that the quote data received is abnormal quote data, abnormal warning can be carried out.Second is default
Fluctuation range can be configured in conjunction with actual quote situations, and the second default fluctuation range can be with the first default fluctuation range
It is identical, it also can be set according to actual needs as different ranges, this specification embodiment is not especially limited.
Such as: current time is 10 points of the morning of September in 2018 3 day, and quotation center sends asking for inquiry list price to certain bank
Information is sought, and receives the quote data of bank return.Real-time reception is sent to data platform in the database at quotation center
Determined based on LSTM model real-time prediction quotation, such as: LSTM model is based on Septembers in 2018 3rd got in real time
It is A that quote data before 10 points of noon, which predicts 10 points of the morning quotations on the 3rd of September in 2018,.The bank that can be will acquire returns
Quote data be compared with the quotation A of LSTM model prediction, judge bank return quote data quotation A between it is inclined
Difference, if not existing, can determine that the quote data received is abnormal quote data whether in the second prediction fluctuation range, can be with
Abnormal warning is carried out by mail or short message.
This specification embodiment goes out the real-time prediction quotation pair of subsequent time using data platform based on LSTM model prediction
The quote data received carries out abnormality detection, and can accurately judge whether the quote data received offers with real-time prediction
Deviation is excessive, identifies abnormal quote data, it is ensured that the accuracy of foreign exchange quotation provides accurate data for import and export business
Basis.
On the basis of the above embodiments, in this specification one embodiment, the prediction quote data includes: to utilize drawing
According to the quotation range determined up to criterion；
Correspondingly, described to compare the quote data and the basis quote data in database, determine the report
Whether valence mumber is according to abnormal, comprising:
The quote data is judged whether in the quotation range, if not existing, it is determined that the quote data is abnormal
Quote data.
In the specific implementation process, data platform or quotation center can also utilize Pauta criterion i.e. 3 σ criterion, press
Each currency type pair in the case where confidence interval 99% is precipitated according to the dimensions statistical such as local and overseas, currency type, time limit, offer type
The quotation range answered can be used as the basis quote data of monitoring quotation, auxiliary quotation prison as the zone of reasonableness of quote data
Control.It, can be quasi- by the quote data received and 3 σ after quotation center receives the quote data that bank or financial institution return
The quotation range then determined, which is compared, to be determined, whether the quote data being currently received is in quotation range, if not existing,
It can then determine that the quote data received is abnormal quote data, abnormal warning can be carried out by modes such as mails.
This specification embodiment, data platform can determine the reasonable of each currency type under different latitude using 3 σ criterion
Quotation range, quotation center are given the quotation range that 3 σ criterion are determined and are carried out abnormality detection to the quote data received, can
With quickly determine the quote data received whether reasonably quotation range in, identify abnormal quote data, for into
Export business provides accurate data basis.
It in the specific implementation process, can be with as shown in figure 3, quotation center is when carrying out the abnormality detection of quote data
Successively the abnormal data received is carried out abnormality detection using the method for above-described embodiment, when the quote data received is not inconsistent
When closing conditions all in above-described embodiment, it is determined as abnormal quote data, it is of course also possible to will not meet in above-described embodiment
At least one condition quote data as abnormal quote data.
The process that quote data abnormality detection is carried out in this specification one embodiment is specifically introduced below with reference to Fig. 3:
1, quotation center starts timed task.Timer, timing acquisition quote data can be set in quotation center, and carries out
Abnormality detection.
2, Xiang Yinhang or financial institution etc. inquire corresponding exchange rate quotation.
3, quotation center carries out legitimacy verifies to the quote data of return.Whether can detecte the quote data that receives
Meet the solicited message of inquiry quotation, can specifically refer to the record of above-described embodiment, details are not described herein again.
4, quotation center carries out fluctuation irrelevance verification based on the basis quote data that data platform synchronizes, if being more than
The fluctuation range of setting then carries out abnormal warning.The basis quote data memory quote data sent according to data platform
Abnormality detection, detection method may include:
1) whether the irrelevance of newest price is in the first default fluctuation the quote data and current database that receive
In range；
2) deviation of the closing price of the quote data and T-1 that receive day whether garch (1,1) model output quotation
Within the scope of data fluctuations；
3) whether the deviation of the real-time prediction quotation of the quote data and LSTM model output that receive is in the second default wave
In dynamic range；
4) whether the quote data received is inside the quotation range of 3 σ criterion model outputs.
If the quote data received by it is above-mentioned 1)~4) verification, database is persisted to, if do not passed through
This quotation is updated to abnormal quote data, and abnormal warning is carried out by mail or SMS alarm.
5, business intervenes after receiving alarm, and the abnormal quotation of inquiry, judges valence on the operation page that quotation center provides
Rationally whether lattice wave dynamic, promotes into price again if rationally normal.
This specification embodiment, the fluctuation range of the quote data using data platform using different model predictions out,
Basis quotes data, the quote datas returned to mechanisms such as banks such as range, prediction quotation in real time of offering carry out abnormality detection, can
Quickly and accurately to identify whether quote data is abnormal, it is ensured that the accuracy of foreign exchange quotation provides for import and export business
Accurate data basis.
Fig. 4 is the detection method flow diagram that this specification has foreign exchange quotation abnormal data in one embodiment, such as Fig. 4
Shown, on the basis of the above embodiments, in this specification one embodiment, the detection method of foreign exchange quotation abnormal data may be used also
To include:
Step 402 obtains historical quotes data.
In this specification one embodiment, historical quotes data can indicate the quote data before specified time, such as: can
To indicate the quote data before current time.It can use off-line data platform and obtain historical quotes data, such as: can pass through
Each bank in ODPS (Open Data Processing Service, the open data processing service) central database that will offer
The historical quotes data sent etc. different quotation mechanisms are synchronized in off-line data platform.In addition, in this specification embodiment,
Real-time quote data can also be obtained by Real-time Data Center, historical quotes data are updated.
Step 404, according to the historical quotes data, determine prediction quote data.
Using historical quotes data, prediction quote data can be determined by the methods of mathematical statistics, machine learning,
Prediction quote data can characterize the reasonable fluctuation range or reasonable value of quote data.Such as: machine learning can be passed through
Model, using historical quotes data, study predicts the quote data of specified time, as prediction quote data.
It is described according to the historical quotes data in this specification one embodiment, determine prediction quote data, it can be with
Include:
Quote data fluctuation range is determined using autoregressive conditional different Variance model according to the historical quotes data,
Using the quote data fluctuation range as the prediction quote data.
The specific introduction of autoregressive conditional different Variance model, that is, garch model, garch model can refer to above-described embodiment
Record, divided based on the historical quotes data before T days and T day in conjunction with financial time series stability bandwidth model garch (1,1)
Stability bandwidth, that is, quote data fluctuation range of analysis quotation in T+1 days, it can analysis predicts the upper and lower of T+1 days quote datas
Limit, the stability bandwidth of the quotation based on prediction examine the reasonability of the quotation obtained in T+1 days.Garch model can be determined
Quote data fluctuation range carries out abnormal quotation detection for quotation center and provides data basis as prediction quote data.garch
(1,1) in (1,1) can indicate model parameter, can also be other numerical value, can specifically be set according to actual needs
It sets, this specification embodiment is not especially limited.
In this specification one embodiment, prediction quote data can also be determined using following methods:
According to the historical quotes data, using Pauta criterion, the quotation range of each currency type under different latitude is determined,
Using the quotation range as the prediction quote data.
Pauta criterion i.e. 3 σ criterion, 3 σ criterion models can first assume that one group of detection data contains only random error, right
It carries out calculation processing and obtains standard deviation, by one section of certain determine the probability, it is believed that more than the error in this section, just not
Belong to random error but gross error, the data containing the error can be rejected.It, can be according to domestic using 3 σ criterion
Outside, the different dimensions such as currency type, time limit, offer type, statistical are precipitated in the case where confidence interval 99%, and each currency type is corresponding
Quotation range, can be used as the zone of reasonableness of quotation, as monitoring quotation prediction quote data, auxiliary quotation monitoring, be
Quotation center carries out abnormal quotation detection and provides data basis.Certainly, according to actual needs, 3 σ criterion statisticals can also be utilized
The quotation range in other confidence intervals is precipitated, as the quotation range of quote data, the setting of confidence interval can basis
Actual needs is selected, and this specification embodiment is not especially limited.
In this specification one embodiment, prediction quote data can also be determined using following methods:
Real-time price quotations data are obtained, the historical quotes data are updated, are based on the updated historical quotes data, benefit
With shot and long term memory network model, prediction quotation in real time is predicted in real time, by the real-time prediction quotation as described pre- in real time
Survey quote data.
In specific implementation process, Real-time Data Center can use, obtain the real-time price quotations data that quotation center receives,
Historical quotes data are updated based on real-time price quotations data, the real-time price quotations data that are got using LSTM models coupling and
Historical quotes data can predict the real-time prediction quotation at each moment, by the real-time prediction determined quotation as pre- in real time
Survey quote data.Model training can be carried out using historical quotes data, construct LSTM model, specific construction method can be with
It is configured according to actual needs, this specification embodiment is not especially limited.
Such as: current time is 10 points of the morning of September in 2018 3 day, and Real-time Data Center is available to be connect to quotation center
The real-time price quotations data received can predict 2018 on September 3, using LSTM model and the real-time price quotations data got
The real-time prediction predicted is offered as prediction quote data, is carried out for quotation center by 11 points of the morning of real-time prediction quotation
The reference data of abnormal quotation detection.
The prediction quote data is sent to quotation central platform by step 406, so that the quotation central platform is based on
The prediction quote data carries out abnormality detection the quote data received.
Data platform, which can synchronize calculated prediction quote data, is sent to quotation central platform i.e. quotation center,
As: each currency type that can be determined by the quote data fluctuation range determined using garch model, using 3 σ criterion models
Quotation range, the real-time prediction at each moment determined using LSTM model quotation are synchronized in the database at quotation center.Report
The historical quotes data stored in the prediction quote data and database that valence center can be sent according to data platform are to reception
Such as to each quotation channel: the quote data that mechanism, bank is sent carries out abnormality detection, and identifies abnormal quote data, abnormal
The specific method of detection can refer to the record of above-described embodiment, and details are not described herein again.
This specification embodiment analyzes fluctuation range, the rational quotation model of foreign exchange quotation according to historical quotes data
It encloses, predict that the prediction quote data such as quotation, the abnormality detection for carrying out quote data for quotation center provide data basis in real time,
Realize the abnormality detection of foreign exchange quotation, it is ensured that the accuracy of foreign exchange quotation.
It should be noted that the data platform in this specification embodiment, carries out quote data based on historical quotes data
Prediction, can be not limited to the above embodiments in model, other prediction models can also be selected according to actual needs, such as:
Recognition with Recurrent Neural Network model etc., this specification embodiment are not especially limited.
Fig. 5 is the flow diagram of quotation channel billboard generating process in this specification one embodiment, as shown in figure 5,
In this specification one embodiment, abnormal quote data or other offers that data platform can also go out recognition detection
Cease it is for statistical analysis, obtain it is different quotation channels abnormal quotation information, be shown by billboard, be supplied to service operation
Side.Specifically quotation exception information can be counted by the off-line data platform in data platform, it can be according to different dimensions
Carry out data cleansing and statistics such as: quotation channel, currency type dimension.The quotation exception information that off-line data platform obtains statistics
It is sent to report platform, report platform generates index billboard, shows relevant user.Abnormal quotation information can characterize with outside
The relevant data of report valence, such as: the corresponding abnormal quote data of different time, the corresponding abnormal quotation of each quotation channel of statistics
Rate, the corresponding availability of each quotation channel (such as: quote data is inquired in request, but is not returned the result), each quotation channel
Quotation frequency, the starting quote data of each channel and terminate quote data, each channel for same currency type quote data
Comparison etc..
This specification embodiment is counted abnormal quotation by different dimensions based on the means of mathematical statistics, and output is each
A quotation channel health degree billboard, digitization, fining show the quote situations of each quotation channel, and auxiliary activities is preferably controlled
Reason quotation channel.
Fig. 6 is the calculation processes schematic diagram that quote data is predicted in this specification one embodiment, as shown in fig. 6,
In this specification one embodiment, prediction quote data can be calculated using following methods:
1, off-line data platform cleans historical quotes data.Data cleansing can indicate to examine data again and school
The process tested, it is therefore intended that delete mistake existing for duplicate message, correction, and data consistency is provided, be data warehouse technology
A data handling procedure of ETL (Extract-Transform-Load).It can be from quotation center using off-line data module
Database in obtain historical quotes data.
2, algorithm platform obtains historical quotes information.
3, algorithm platform runs garch model, calculates quote data fluctuation range.
4, algorithm platform runs 3 σ criterion models, calculates the corresponding quotation range of each currency type.
5, calculated quote data fluctuation range, quotation range are synchronized to by quotation center based on number storehouse simultaneous techniques
Database in.
6, the LSTM model that algorithm platform is deployed in platform based on the training of historical quotes data.The specific training side of model
Method this specification embodiment is not especially limited, and can be selected according to actual needs.
7, Real-time Data Center cleans on-line pricing data in real time.
8, algorithm platform sends the request for obtaining real-time price quotations data to Real-time Data Center, obtains real-time price quotations data.
9, algorithm platform runs the real-time prediction quotation at trained LSTM model output lower a moment.
10, the real-time prediction determined quotation is synchronized in the database at quotation center.
Fig. 7 is the abnormality detecting process schematic diagram of foreign exchange quotation in another embodiment of this specification, as shown in fig. 7, this
The abnormality detection of foreign exchange quotation in specification can be by the algorithm platform in data platform according to off-line data platform, in real time number
The quote data got according to platform is determined to offer using prediction models such as garch model, 3 σ criterion models, LSTM models
The prediction quote datas such as data fluctuations range, quotation range, prediction quotation in real time, and prediction quote data is synchronized in quotation
The heart.The prediction quote data that quotation center synchronizes algorithm platform stores in the database, periodically to each quotation channel
The solicited message for sending inquiry quotation can use in database after receiving the quote data that each quotation channel is sent
The historical quotes data and prediction quote data of storage carry out abnormality detection the quote data received, what determination received
Whether quote data is abnormal.If detecting, abnormal quote data can carry out abnormal warning by modes such as mail or short messages, by
Business side is verified, it is ensured that the accuracy of abnormal quote data identification.If detecting, the quote data received is normal number
According to can then be persisted in database, the basic data as next quote data abnormality detection.
This specification embodiment, by prediction in advance, monitoring emergency and subsequent analysis in thing are fed back, and systematization is known
Not abnormal quote data, provides accurate data basis for foreign currency exchange.
Various embodiments are described in a progressive manner for the above method in this specification, identical between each embodiment
Similar part may refer to each other, and each embodiment focuses on the differences from other embodiments.Correlation
Place illustrates referring to the part of embodiment of the method.
Based on the detection method of foreign exchange quotation abnormal data described above, this specification one or more embodiment is also mentioned
For a kind of detection device of foreign exchange quotation abnormal data.The device may include having used side described in this specification embodiment
The system (including distributed system) of method, software (application), module, component, server, client etc. simultaneously combine necessary implementation
The device of hardware.Based on same innovation thinking, the device in one or more embodiments that this specification embodiment provides is as follows
Described in the embodiment in face.Since the implementation that device solves the problems, such as is similar to method, this specification embodiment is specific
The implementation of device may refer to the implementation of preceding method, and overlaps will not be repeated.It is used below, term " unit " or
The combination of the software and/or hardware of predetermined function may be implemented in " module ".Although device is preferably described in following embodiment
It is realized with software, but the realization of the combination of hardware or software and hardware is also that may and be contemplated.
Specifically, Fig. 8 is the module of the detection device one embodiment for the foreign exchange quotation abnormal data that this specification provides
Structural schematic diagram, as shown in figure 8, the detection device of the foreign exchange quotation abnormal data provided in this specification includes: data receiver
Module 81, anomaly data detection module 82, in which:
Data reception module 81 can be used for receiving quotation data；
Anomaly data detection module 82 can be used for receiving quotation data；
The quote data and the basis quote data in database are compared, determine whether the quote data is different
Often, the basis quote data include: historical quotes data, data platform send determined based on historical quotes data it is pre-
Survey quote data.
The detection device for the foreign exchange quotation abnormal data that this specification embodiment provides is based on history report using data platform
Valence mumber determines prediction quote data according to the prediction for carrying out quote data.Quotation center can send pre- according to data platform
It observes and predicts valence mumber accordingly and whether extremely historical quotes data, the quote data that detection bank or financial institution send, realizes foreign exchange
The abnormality detection of quotation, it is ensured that the accuracy of foreign exchange quotation provides accurate basic data for import and export business.
On the basis of the above embodiments, the anomaly data detection module is specifically used for:
Judge in the quote data and the historical quotes data specify quote data between irrelevance whether
In first default fluctuation range, if not existing, it is determined that the quote data is abnormal quote data, the specified quote data
Corresponding quotation time, quotation time interval corresponding with the quote data was less than preset time threshold.
The detection device for the foreign exchange quotation abnormal data that this specification embodiment provides, based on the history stored in database
Quote data carries out abnormality detection the quote data received, determines whether foreign exchange quotation is abnormal, it is ensured that foreign exchange quotation
Accuracy, provide accurate data basis for import and export business.
On the basis of the above embodiments, the prediction quote data includes: true using autoregressive conditional different Variance model
Fixed quote data fluctuation range；
Correspondingly, the anomaly data detection module is specifically used for:
Judge the difference between quote data closing price corresponding with specified time whether in the quote data wave
In dynamic range, if not existing, it is determined that the quote data is abnormal quote data.
The detection device for the foreign exchange quotation abnormal data that this specification embodiment provides is based on garch using data platform
The quote data fluctuation range that model prediction goes out carries out abnormality detection the quote data received, can determine currently to receive
The quote data arrived determines whether foreign exchange quotation is abnormal, it is ensured that the standard of foreign exchange quotation whether in reasonable fluctuation range
True property provides accurate data basis for import and export business.
On the basis of the above embodiments, the prediction quote data includes: to be determined using shot and long term memory network model
Real-time prediction quotation；
Correspondingly, the anomaly data detection module is specifically used for:
Judge the quote data and it is described it is real-time prediction quotation between difference whether in the second default fluctuation range, if
Do not exist, it is determined that the quote data is abnormal quote data.
This specification embodiment goes out the real-time prediction quotation pair of subsequent time using data platform based on LSTM model prediction
The quote data received carries out abnormality detection, and can accurately judge whether the quote data received offers with real-time prediction
Deviation is excessive, identifies abnormal quote data, it is ensured that the accuracy of foreign exchange quotation provides accurate data for import and export business
Basis.
On the basis of the above embodiments, the prediction quote data includes: the quotation model determined using Pauta criterion
It encloses；
Correspondingly, the anomaly data detection module is specifically used for:
The quote data is judged whether in the quotation range, if not existing, it is determined that the quote data is abnormal
Quote data.
This specification embodiment, data platform can determine the reasonable of each currency type under different latitude using 3 σ criterion
Quotation range, quotation center are given the quotation range that 3 σ criterion are determined and are carried out abnormality detection to the quote data received, can
With quickly determine the quote data received whether reasonably quotation range in, identify abnormal quote data, for into
Export business provides accurate data basis.
Fig. 9 is the structural schematic diagram of the detection device of foreign exchange quotation abnormal data in the another embodiment of this specification, such as Fig. 9
It is shown, on the basis of the above embodiments, described device further include:
Request for quote module 91 can be used for sending the solicited message of inquiry quote data, include: in the solicited message
Request quotation parameter；
Quote data correction verification module 92, after can be used for receiving the quote data, by the quote data and the report
Valence parameter is matched, and determines whether the quote data meets the solicited message.
This specification embodiment carries out legitimacy verifies to the quote data that bank returns, to determine the report currently returned
Valence mumber provides accurate data basis according to whether solicited message is met for the abnormality detection of subsequent bids data.
On the basis of the above embodiments, described device further includes dealing of abnormal data module, is used for:
If it is determined that the quote data is normal, then the quote data is persisted in the database；
If it is determined that the quote data is abnormal quote data, then abnormal warning is carried out.
The detection device for the foreign exchange quotation abnormal data that this specification embodiment provides, is determining abnormal quote data
Afterwards, it carries out abnormal warning and improves the accuracy of the abnormality detection result of quote data so that related personnel verifies.
It should be noted that device described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
This specification embodiment also provides a kind of processing equipment of different quotation anomaly data detection of foreign exchange, comprising: at least one
A processor and memory for storage processor executable instruction, the processor are realized above-mentioned when executing described instruction
The detection method of the foreign exchange quotation abnormal data of embodiment, such as:
Receiving quotation data；
The quote data and the basis quote data in database are compared, determine whether the quote data is different
Often, the basis quote data include: historical quotes data, data platform send determined based on historical quotes data it is pre-
Survey quote data.
It should be noted that processing equipment described above can also include other implement according to the description of embodiment of the method
Mode.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
Figure 10 is the structural schematic diagram of the detection device of foreign exchange quotation abnormal data in the another embodiment of this specification, is such as schemed
Shown in 10, the detection device of the foreign exchange quotation abnormal data provided in this specification includes: data acquisition module 101, quotation number
It is predicted that module 102, data transmission blocks 103, in which:
Data acquisition module 101 can be used for obtaining historical quotes data；
Quote data prediction module 102 can be used for determining prediction quote data according to the historical quotes data；
Data transmission blocks 103 can be used for the prediction quote data being sent to quotation center, for the quotation
Central platform carries out abnormality detection the quote data received based on the prediction quote data.
This specification is implemented, and using historical quotes data, predicts the predictions such as fluctuation range, the quotation range of quote data
Quote data carries out anomaly data detection for subsequent bids center and provides accurate data basis.
On the basis of the above embodiments, the quote data prediction module is specifically used for:
Quote data fluctuation range is determined using autoregressive conditional different Variance model according to the historical quotes data,
Using the quote data fluctuation range as the prediction quote data.
This specification is implemented, and the reasonable quotation fluctuation range of quote data, method letter are gone out using garch model prediction
It is single, reference data is provided for quotation center.
On the basis of the above embodiments, the quote data prediction module is specifically used for:
According to the historical quotes data, using Pauta criterion, the quotation range of each currency type under different latitude is determined,
Using the quotation range as the prediction quote data.
This specification is implemented, and using 3 σ criterion models, predicts the rational quotation range of quote data, method is simple, is
Quotation center provides reference data.
On the basis of the above embodiments, the quote data prediction module is specifically used for:
Real-time price quotations data are obtained, the historical quotes data are updated, are based on the updated historical quotes data, benefit
With shot and long term memory network model, real-time prediction quotation is predicted, by the real-time prediction quotation as prediction quotation number
According to.
This specification is implemented, and using LSTM model, predicts real-time price quotations data, provides reference number for quotation center
According to.
Figure 11 is the structural schematic diagram of the detection device of foreign exchange quotation abnormal data in the another embodiment of this specification, is such as schemed
Shown in 11, on the basis of the above embodiments, described device further include:
Exception information display module 111, the abnormal quote data sent for receiving the quotation central platform, statistics is not
With the abnormal quotation information of quotation channel, and it is shown.
This specification is implemented, and is counted to abnormal quotation by different dimensions based on the means of mathematical statistics, output is each
Quotation channel health degree billboard, digitization, fining show the quote situations of each quotation channel, and auxiliary activities is preferably administered
Quotation channel.
It should be noted that device described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
This specification embodiment also provides a kind of processing equipment of different quotation anomaly data detection of foreign exchange, comprising: at least one
A processor and memory for storage processor executable instruction, the processor are realized above-mentioned when executing described instruction
The detection method of the foreign exchange quotation abnormal data of embodiment, such as:
Obtain historical quotes data；
According to the historical quotes data, prediction quote data is determined；
The prediction quote data is sent to quotation central platform, so that the quotation central platform is based on the prediction
Quote data carries out abnormality detection the quote data received.
The storage medium may include the physical unit for storing information, usually by after information digitalization again with benefit
The media of the modes such as electricity consumption, magnetic or optics are stored.It may include: that letter is stored in the way of electric energy that the storage medium, which has,
The device of breath such as, various memory, such as RAM, ROM；The device of information is stored in the way of magnetic energy such as, hard disk, floppy disk, magnetic
Band, core memory, magnetic bubble memory, USB flash disk；Using optical mode storage information device such as, CD or DVD.Certainly, there are also it
Readable storage medium storing program for executing of his mode, such as quantum memory, graphene memory etc..
It should be noted that processing equipment described above can also include other implement according to the description of embodiment of the method
Mode.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
Embodiment of the method provided by this specification embodiment can mobile terminal, terminal, server or
It is executed in similar arithmetic unit.For running on the server, Figure 12 is the outer report of one kind using the embodiment of the present invention
The hardware block diagram of the server of valence anomaly data detection.As shown in figure 12, server 10 may include one or more (figures
In only show one) (processor 100 can include but is not limited to Micro-processor MCV or programmable logic device to processor 100
The processing unit of FPGA etc.), memory 200 for storing data and the transmission module 300 for communication function.This neighbour
Domain those of ordinary skill is appreciated that structure shown in Figure 12 is only to illustrate, and does not cause to the structure of above-mentioned electronic device
It limits.It for example, server 10 may also include the more or less component than shown in Figure 12, such as can also include others
Hardware is handled, such as database or multi-level buffer, GPU, or with the configuration different from shown in Figure 12.
Memory 200 can be used for storing the software program and module of application software, outside in this specification embodiment
Corresponding program instruction/the module of the detection method of report valence abnormal data, processor 100 are stored in memory 200 by operation
Interior software program and module, thereby executing various function application and data processing.Memory 200 may include that high speed is random
Memory may also include nonvolatile memory, such as one or more magnetic storage device, flash memory or other are non-volatile
Property solid-state memory.In some instances, memory 200 can further comprise the storage remotely located relative to processor 100
Device, these remote memories can pass through network connection to terminal 10.The example of above-mentioned network is including but not limited to mutual
Networking, intranet, local area network, mobile radio communication and combinations thereof.
Transmission module 300 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of terminal 10 provide.In an example, transmission module 300 includes that a network is suitable
Orchestration (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to
Internet is communicated.In an example, transmission module 300 can be radio frequency (Radio Frequency, RF) module,
For wirelessly being communicated with internet.
This specification also provides a kind of detection system of foreign exchange quotation abnormal data, and the system can be individual foreign exchange
The detection system of quotation abnormal data, can also apply in a variety of Data Analysis Services systems.On the system may include
State the detection device of any one foreign exchange quotation abnormal data in embodiment.The system can be individual server,
May include used this specification one or more the methods or one or more embodiment device server cluster,
System (including distributed system), software (application), practical operation device, logic gates device, quantum computer etc. are simultaneously tied
Close the necessary terminal installation for implementing hardware.The detection system of the foreign exchange quotation abnormal data may include at least one processing
Device and the memory for storing computer executable instructions, the processor realized when executing described instruction it is above-mentioned any one or
The step of method described in the multiple embodiments of person.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
Method or apparatus described in above-described embodiment that this specification provides can realize that business is patrolled by computer program
It collects and records on a storage medium, the storage medium can be read and be executed with computer, realize this specification embodiment institute
The effect of description scheme.
The detection method or device for the above-mentioned foreign exchange quotation abnormal data that this specification embodiment provides can be in computers
In corresponding program instruction executed by processor to realize, such as realized using the c++ language of windows operating system at the end PC,
Linux system is realized or other are for example realized using android, iOS system programming language in intelligent terminal, Yi Jiji
Realized in the processing logic of quantum computer etc..
It should be noted that specification device described above, computer storage medium, system are implemented according to correlation technique
The description of example can also include other embodiments, and concrete implementation mode is referred to the description of corresponding method embodiment,
It does not repeat one by one herein.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for hardware+
For program class embodiment, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to side
The part of method embodiment illustrates.
This specification embodiment is not limited to meet industry communication standard, standard computer data processing sum number
According to situation described in storage rule or this specification one or more embodiment.The right way of conduct is made in certain professional standards or use by oneself
In formula or the practice processes of embodiment description embodiment modified slightly also may be implemented above-described embodiment it is identical, it is equivalent or
The implementation result being anticipated that after close or deformation.Using these modifications or deformed data acquisition, storage, judgement, processing side
The embodiment of the acquisitions such as formula still may belong within the scope of the optional embodiment of this specification embodiment.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method process can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, vehicle-mounted human-computer interaction device, cellular phone, camera phone, smart phone, individual
Digital assistants, media player, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or
The combination of any equipment in these equipment of person.
Although this specification one or more embodiment provides the method operating procedure as described in embodiment or flow chart,
It but may include more or less operating procedure based on conventional or without creativeness means.The step of being enumerated in embodiment
Sequence is only one of numerous step execution sequence mode, does not represent and unique executes sequence.Device in practice or
When end product executes, can be executed according to embodiment or the execution of method shown in the drawings sequence or parallel (such as it is parallel
The environment of processor or multiple threads, even distributed data processing environment).The terms "include", "comprise" or its
Any other variant is intended to non-exclusive inclusion so that include the process, methods of a series of elements, product or
Equipment not only includes those elements, but also including other elements that are not explicitly listed, or further include for this process,
Method, product or the intrinsic element of equipment.In the absence of more restrictions, being not precluded is including the element
There is also other identical or equivalent elements in process, method, product or equipment.The first, the second equal words are used to indicate name
Claim, and does not indicate any particular order.
For convenience of description, it is divided into various modules when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each module can be realized in the same or multiple software and or hardware when specification one or more, it can also be with
The module for realizing same function is realized by the combination of multiple submodule or subelement etc..Installation practice described above is only
It is only illustrative, for example, in addition the division of the unit, only a kind of logical function partition can have in actual implementation
Division mode, such as multiple units or components can be combined or can be integrated into another system or some features can be with
Ignore, or does not execute.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be logical
Some interfaces are crossed, the indirect coupling or communication connection of device or unit can be electrical property, mechanical or other forms.
The present invention be referring to according to the method for the embodiment of the present invention, the process of device (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage, graphene stores or other
Magnetic storage device or any other non-transmission medium, can be used for storage can be accessed by a computing device information.According to herein
In define, computer-readable medium does not include temporary computer readable media (transitory media), such as the data of modulation
Signal and carrier wave.
It will be understood by those skilled in the art that this specification one or more embodiment can provide as method, system or calculating
Machine program product.Therefore, this specification one or more embodiment can be used complete hardware embodiment, complete software embodiment or
The form of embodiment combining software and hardware aspects.Moreover, this specification one or more embodiment can be used at one or
It is multiple wherein include computer usable program code computer-usable storage medium (including but not limited to magnetic disk storage,
CD-ROM, optical memory etc.) on the form of computer program product implemented.
This specification one or more embodiment can computer executable instructions it is general on
It hereinafter describes, such as program module.Generally, program module includes executing particular task or realization particular abstract data type
Routine, programs, objects, component, data structure etc..This this specification one can also be practiced in a distributed computing environment
Or multiple embodiments, in these distributed computing environments, by being held by the connected remote processing devices of communication network
Row task.In a distributed computing environment, program module can be located at the local and remote computer including storage equipment
In storage medium.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ",
The description of " specific example " or " some examples " etc. means specific features described in conjunction with this embodiment or example, structure, material
Or feature is contained at least one embodiment or example of this specification.In the present specification, to the signal of above-mentioned term
Property statement be necessarily directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
The foregoing is merely the embodiments of this specification one or more embodiment, are not limited to book explanation
Book one or more embodiment.To those skilled in the art, this specification one or more embodiment can have various
Change and variation.All any modification, equivalent replacement, improvement and so within the spirit and principle of this specification, should all wrap
It is contained within scope of the claims.
Claims (27)
1. a kind of detection method of foreign exchange quotation abnormal data, comprising:
Receiving quotation data；
The quote data and the basis quote data in database are compared, determine whether the quote data is abnormal,
The basis quote data include: historical quotes data, prediction quote data.
2. the method as described in claim 1, whether the determination quote data is abnormal, comprising:
Judge the irrelevance between the quote data specified in the quote data and the historical quotes data whether first
In default fluctuation range, if not existing, it is determined that the quote data is abnormal quote data, and the specified quote data is corresponding
Quotation time quotation time interval corresponding with the quote data be less than preset time threshold.
3. the method as described in claim 1, the prediction quote data includes: to be determined using autoregressive conditional different Variance model
Quote data fluctuation range；
Correspondingly, whether the determination quote data is abnormal, comprising:
Judge the difference between quote data closing price corresponding with specified time whether in quote data fluctuation model
In enclosing, if not existing, it is determined that the quote data is abnormal quote data.
4. the method as described in claim 1, the prediction quote data includes: to be determined using shot and long term memory network model
Prediction quotation in real time；
Correspondingly, whether the determination quote data is abnormal, comprising:
The difference between the quote data and the real-time prediction quotation is judged whether in the second default fluctuation range, if not
, it is determined that the quote data is abnormal quote data.
5. the method as described in claim 1, the prediction quote data includes: the quotation model determined using Pauta criterion
It encloses；
Correspondingly, whether the determination quote data is abnormal, comprising:
The quote data is judged whether in the quotation range, if not existing, it is determined that the quote data is abnormal quotation
Data.
6. the method as described in claim 1, the method also includes:
The solicited message of inquiry quote data is sent, includes: request quotation parameter in the solicited message；
After receiving the quote data, the quote data is matched with the quotation parameter, determines the quote data
Whether the solicited message is met.
7. the method as described in claim 1, the method also includes:
If it is determined that the quote data is normal, then the quote data is persisted in the database；
If it is determined that the quote data is abnormal quote data, then abnormal warning is carried out.
8. a kind of detection method of foreign exchange quotation abnormal data, comprising:
Obtain historical quotes data；
According to the historical quotes data, prediction quote data is determined；
The prediction quote data is sent to quotation central platform, so that the quotation central platform is offered based on the prediction
Data carry out abnormality detection the quote data received.
9. method according to claim 8, described according to the historical quotes data, prediction quote data is determined, comprising:
Quote data fluctuation range is determined using autoregressive conditional different Variance model according to the historical quotes data, by institute
Quote data fluctuation range is stated as the prediction quote data.
10. method according to claim 8, described according to the historical quotes data, prediction quote data, packet are determined
It includes:
According to the historical quotes data, using Pauta criterion, the quotation range of each currency type under different latitude is determined, by institute
Quotation range is stated as the prediction quote data.
11. method according to claim 8, described according to the historical quotes data, prediction quote data, packet are determined
It includes:
Real-time price quotations data are obtained, the historical quotes data are updated, the updated historical quotes data is based on, utilizes length
Short-term memory network model predicts prediction quotation in real time, regard the real-time prediction quotation as the prediction quote data.
12. method according to claim 8, the method also includes:
The abnormal quote data that the quotation central platform is sent is received, the abnormal quotation information of different quotation channels is counted, and
It is shown.
13. a kind of detection device of foreign exchange quotation abnormal data, comprising:
Data reception module is used for receiving quotation data；
Anomaly data detection module is used for receiving quotation data；
The quote data and the basis quote data in database are compared, determine whether the quote data is abnormal,
The basis quote data include: the prediction of historical quotes data, data platform transmission determined based on historical quotes data
Quote data.
14. device as claimed in claim 13, the anomaly data detection module is specifically used for:
Judge the irrelevance between the quote data specified in the quote data and the historical quotes data whether first
In default fluctuation range, if not existing, it is determined that the quote data is abnormal quote data, and the specified quote data is corresponding
Quotation time quotation time interval corresponding with the quote data be less than preset time threshold.
15. device as claimed in claim 13, the prediction quote data includes: true using autoregressive conditional different Variance model
Fixed quote data fluctuation range；
Correspondingly, the anomaly data detection module is specifically used for:
Judge the difference between quote data closing price corresponding with specified time whether in quote data fluctuation model
In enclosing, if not existing, it is determined that the quote data is abnormal quote data.
16. device as claimed in claim 13, the prediction quote data includes: to be determined using shot and long term memory network model
Real-time prediction quotation；
Correspondingly, the anomaly data detection module is specifically used for:
The difference between the quote data and the real-time prediction quotation is judged whether in the second default fluctuation range, if not
, it is determined that the quote data is abnormal quote data.
17. device as claimed in claim 13, the prediction quote data includes: the quotation model determined using Pauta criterion
It encloses；
Correspondingly, the anomaly data detection module is specifically used for:
The quote data is judged whether in the quotation range, if not existing, it is determined that the quote data is abnormal quotation
Data.
18. device as claimed in claim 13, described device further include:
Request for quote module includes: request quotation ginseng for sending the solicited message of inquiry quote data, in the solicited message
Number；
Quote data correction verification module carries out the quote data and the quotation parameter after receiving the quote data
Matching, determines whether the quote data meets the solicited message.
19. device as claimed in claim 13, described device further includes dealing of abnormal data module, is used for:
If it is determined that the quote data is normal, then the quote data is persisted in the database；
If it is determined that the quote data is abnormal quote data, then abnormal warning is carried out.
20. a kind of processing equipment of the different quotation anomaly data detection of foreign exchange, comprising: at least one processor and at storage
The memory of device executable instruction is managed, the processor realizes the described in any item sides of claim 1-7 when executing described instruction
Method.
21. a kind of detection device of foreign exchange quotation abnormal data, comprising:
Data acquisition module, for obtaining historical quotes data；
Quote data prediction module, for determining prediction quote data according to the historical quotes data；
Data transmission blocks, for the prediction quote data to be sent to quotation center, for the quotation central platform base
The quote data received is carried out abnormality detection in the prediction quote data.
22. device as claimed in claim 21, the quote data prediction module is specifically used for:
Quote data fluctuation range is determined using autoregressive conditional different Variance model according to the historical quotes data, by institute
Quote data fluctuation range is stated as the prediction quote data.
23. device as claimed in claim 21, the quote data prediction module is specifically used for:
According to the historical quotes data, using Pauta criterion, the quotation range of each currency type under different latitude is determined, by institute
Quotation range is stated as the prediction quote data.
24. device as claimed in claim 21, the quote data prediction module is specifically used for:
Real-time price quotations data are obtained, the historical quotes data are updated, the updated historical quotes data is based on, utilizes length
Short-term memory network model predicts prediction quotation in real time, regard the real-time prediction quotation as the prediction quote data.
25. device as claimed in claim 21, described device further include:
Exception information display module, the abnormal quote data sent for receiving the quotation central platform, counts different quotations
The abnormal quotation information of channel, and be shown.
26. a kind of processing equipment of the different quotation anomaly data detection of foreign exchange, comprising: at least one processor and at storage
The memory of device executable instruction is managed, the processor realizes the described in any item sides of claim 8-12 when executing described instruction
Method.
27. a kind of detection system of foreign exchange quotation abnormal data, comprising: data platform, exchanging platform, the data platform include
The described in any item devices of the claims 21-25, the exchanging platform include described in the claims any one of 13-19
Device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811061270.8A CN109461067A (en) | 2018-09-12 | 2018-09-12 | A kind of detection method of foreign exchange quotation abnormal data, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811061270.8A CN109461067A (en) | 2018-09-12 | 2018-09-12 | A kind of detection method of foreign exchange quotation abnormal data, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109461067A true CN109461067A (en) | 2019-03-12 |
Family
ID=65606565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811061270.8A Pending CN109461067A (en) | 2018-09-12 | 2018-09-12 | A kind of detection method of foreign exchange quotation abnormal data, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109461067A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428333A (en) * | 2019-08-01 | 2019-11-08 | 上海爱富爱克斯网络科技发展有限责任公司 | For the Data Detection and analysis method of financial intermediary MT4 foreign exchange transaction software |
| CN110807024A (en) * | 2019-10-12 | 2020-02-18 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN112258246A (en) * | 2020-11-12 | 2021-01-22 | 北京筑龙信息技术有限责任公司 | Abnormal offer identification method and device for material, electronic equipment and storage medium |
| CN112734465A (en) * | 2020-12-31 | 2021-04-30 | 宁夏华泰家俱制造有限公司 | Household decoration project quotation generation system and generation method thereof |
| CN113313591A (en) * | 2021-05-26 | 2021-08-27 | 中国银行股份有限公司 | Data abnormity warning method and device |
| CN114677186A (en) * | 2022-05-27 | 2022-06-28 | 太平金融科技服务(上海)有限公司深圳分公司 | Offer calculation method and device for financial product, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890803A (en) * | 2011-07-21 | 2013-01-23 | 阿里巴巴集团控股有限公司 | Method and device for determining abnormal transaction process of electronic commodity |
| CN104181883A (en) * | 2014-08-08 | 2014-12-03 | 青岛高校信息产业有限公司 | Method for processing abnormal data of real-time data acquisition system in real time |
| CN105825284A (en) * | 2016-04-24 | 2016-08-03 | 上海久茂国际物流有限公司 | Airborne logistics self-service space booking system |
| CN107392759A (en) * | 2016-11-25 | 2017-11-24 | 深圳福迈斯科技有限公司 | A kind of disaster recovery method and device of foreign exchange Feed systems |
| CN108399248A (en) * | 2018-03-02 | 2018-08-14 | 郑州云海信息技术有限公司 | A kind of time series data prediction technique, device and equipment |
-
2018
- 2018-09-12 CN CN201811061270.8A patent/CN109461067A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890803A (en) * | 2011-07-21 | 2013-01-23 | 阿里巴巴集团控股有限公司 | Method and device for determining abnormal transaction process of electronic commodity |
| CN104181883A (en) * | 2014-08-08 | 2014-12-03 | 青岛高校信息产业有限公司 | Method for processing abnormal data of real-time data acquisition system in real time |
| CN105825284A (en) * | 2016-04-24 | 2016-08-03 | 上海久茂国际物流有限公司 | Airborne logistics self-service space booking system |
| CN107392759A (en) * | 2016-11-25 | 2017-11-24 | 深圳福迈斯科技有限公司 | A kind of disaster recovery method and device of foreign exchange Feed systems |
| CN108399248A (en) * | 2018-03-02 | 2018-08-14 | 郑州云海信息技术有限公司 | A kind of time series data prediction technique, device and equipment |
Non-Patent Citations (3)
| Title |
|---|
| 孙克雷: "《基于动态数据驱动的煤矿瓦斯灾害预测技术研究》", 31 March 2017 * |
| 谢建豪: "住房价格波动影响因素分析与调控研究", 《中国博士学位论文全文数据库 经济与管理科学辑》 * |
| 陈静等: "美元／欧元汇率的组合模型区间预测", 《科技和产业》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428333A (en) * | 2019-08-01 | 2019-11-08 | 上海爱富爱克斯网络科技发展有限责任公司 | For the Data Detection and analysis method of financial intermediary MT4 foreign exchange transaction software |
| CN110807024A (en) * | 2019-10-12 | 2020-02-18 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN110807024B (en) * | 2019-10-12 | 2022-04-19 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN112258246A (en) * | 2020-11-12 | 2021-01-22 | 北京筑龙信息技术有限责任公司 | Abnormal offer identification method and device for material, electronic equipment and storage medium |
| CN112258246B (en) * | 2020-11-12 | 2024-01-05 | 北京筑龙信息技术有限责任公司 | Abnormal quotation identification method and device for materials, electronic equipment and storage medium |
| CN112734465A (en) * | 2020-12-31 | 2021-04-30 | 宁夏华泰家俱制造有限公司 | Household decoration project quotation generation system and generation method thereof |
| CN113313591A (en) * | 2021-05-26 | 2021-08-27 | 中国银行股份有限公司 | Data abnormity warning method and device |
| CN114677186A (en) * | 2022-05-27 | 2022-06-28 | 太平金融科技服务(上海)有限公司深圳分公司 | Offer calculation method and device for financial product, computer equipment and storage medium |
| CN114677186B (en) * | 2022-05-27 | 2023-03-07 | 太平金融科技服务(上海)有限公司深圳分公司 | Offer calculation method and device for financial product, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461067A (en) | A kind of detection method of foreign exchange quotation abnormal data, apparatus and system | |
| CN107608862B (en) | Monitoring alarm method, monitoring alarm device and computer readable storage medium | |
| US20170286845A1 (en) | Automatic extraction of user mobility behaviors and interaction preferences using spatio-temporal data | |
| Bormetti et al. | Modelling systemic price cojumps with Hawkes factor models | |
| Chen et al. | Multi-step-ahead crude oil price forecasting using a hybrid grey wave model | |
| CN109887272B (en) | Traffic pedestrian flow prediction method and device | |
| CN110322349A (en) | A kind of processing method of data, device and equipment | |
| CN110046633A (en) | A kind of data quality checking method and device | |
| CN110033130A (en) | The monitoring method and device of abnormal traffic | |
| CN109274597A (en) | A kind of control method, device and the equipment of business special line | |
| CN110471821A (en) | Abnormal alteration detection method, server and computer readable storage medium | |
| CN109523190A (en) | A kind of management method of electric energy meter, managing device and terminal | |
| CN109240848A (en) | A kind of data object tag generation method and device | |
| CN110188793B (en) | Data anomaly analysis method and device | |
| CN110390198A (en) | Risk method for inspecting, device and the electronic equipment of a kind of pair of small routine | |
| CN110009359A (en) | Training method, update method and the device of unsupervised risk prevention system model | |
| CN113342939B (en) | Data quality monitoring method and device and related equipment | |
| CN109613351A (en) | A kind of method for diagnosing faults of transformer, equipment and system | |
| CN110351136A (en) | A kind of Fault Locating Method and device | |
| CN109344061A (en) | A kind of method for detecting abnormality of interface, device, equipment and system | |
| CN109064104A (en) | Material equipment management method, system and terminal device | |
| JP2023026399A (en) | System, computer-implemented method, and computer program (associating disturbance events to accidents or tickets) | |
| CN109409923A (en) | Distribution method, computer readable storage medium and the terminal device of sales region | |
| CN110222905A (en) | A kind of method and device for predicting flow of the people | |
| CN110264213A (en) | A kind of processing method of information, device and equipment |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201010 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201010 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: Greater Cayman, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |