CN116151975A - Transaction abnormity warning method and device - Google Patents

Transaction abnormity warning method and device Download PDF

Info

Publication number
CN116151975A
CN116151975A CN202211555652.2A CN202211555652A CN116151975A CN 116151975 A CN116151975 A CN 116151975A CN 202211555652 A CN202211555652 A CN 202211555652A CN 116151975 A CN116151975 A CN 116151975A
Authority
CN
China
Prior art keywords
data
target
asset
future
model
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
Application number
CN202211555652.2A
Other languages
Chinese (zh)
Inventor
洪欢江
叶昱堂
江之深
丘威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202211555652.2A priority Critical patent/CN116151975A/en
Publication of CN116151975A publication Critical patent/CN116151975A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The invention provides a transaction abnormity warning method and a device, in particular to the financial field, wherein the method comprises the following steps: acquiring future data of the target asset before the change of a plurality of future time points based on the asset data association influence model, the current target data of the target asset, the current association data and the current interest rate of the associated asset, which are commonly corresponding to the target asset and the associated asset; acquiring future data of the target asset after the change at a plurality of future time points based on the interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate; and judging whether the target asset has transaction abnormality or not based on the pre-change future data and the post-change future data corresponding to the future time point, and if so, carrying out transaction abnormality warning. The invention can improve the accuracy of the transaction abnormality alarm, thereby improving the efficiency of the transaction abnormality alarm.

Description

Transaction abnormity warning method and device
Technical Field
The invention relates to the technical field of transaction processing, in particular to the financial field, and particularly relates to a transaction abnormity warning method and device.
Background
In related transactions, if the fluctuation range of the asset data is too large, coordination and overall arrangement of related transaction processing are not facilitated, so that smooth proceeding of the transaction is not facilitated, and loss of a transaction party is possibly caused, so that corresponding transaction abnormality is caused by the too large fluctuation range of the asset data. For such abnormal transaction alarms, it is often necessary to predict the fluctuation of the target asset data, so that the abnormal transaction alarms are performed based on the fluctuation of the target asset data.
In the prior art, the method for alarming trade abnormality mainly analyzes the target asset by related staff, so as to predict the fluctuation condition of the target asset and further carry out the trade abnormality alarming. However, in the above manner, the working experience of the staff is relied on, and the dependence of the analysis information on the fluctuation condition of the asset data may not be strong, so that the situation that false alarms are performed when no abnormality exists or no alarms exist when the abnormality exists is more, and thus the accuracy of transaction abnormality alarms is lower.
In summary, in the prior art, the accuracy of the transaction abnormality alarm is low, so that the efficiency of the transaction abnormality alarm is low.
Disclosure of Invention
The invention aims to provide a transaction abnormity warning method, which aims to solve the problem that the accuracy of transaction abnormity warning is low in the prior art, so that the efficiency of the transaction abnormity warning is low. Another object of the present invention is to provide a transaction abnormality warning apparatus. It is a further object of the invention to provide a computer device. It is a further object of the invention to provide a readable medium.
To achieve the above object, an aspect of the present invention discloses a transaction abnormality warning method, which includes:
Acquiring future data of the target asset before the change at a plurality of future time points based on an asset data association influence model, current target data of the target asset, current association data of the associated asset and current interest rate, which are commonly corresponding to the target asset and the associated asset corresponding to the target asset;
obtaining future data of the target asset after the change of a plurality of future time points based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate;
and judging whether the target asset has transaction abnormality or not based on the future data before the change and the future data after the change corresponding to the future time points, and if so, carrying out transaction abnormality warning.
Optionally, the method further comprises:
before the asset data association influence model, the current target data of the target asset, the current association data of the associated asset and the current interest rate which are commonly corresponding to the target asset and the associated asset corresponding to the target asset are obtained, the initial target model of the target asset and the initial association model of the associated asset corresponding to the target asset are constructed based on a preset data power function;
Obtaining a target model in an asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate and the initial target model;
and obtaining a correlation model in the asset data correlation influence model based on the target historical data information, the correlation historical data information, the historical interest rate and the initial correlation model.
Optionally, the constructing an initial target model of the target asset and an initial association model of the associated asset corresponding to the target asset based on a preset data power function includes:
based on a plurality of data power functions, respectively constructing a first data item which corresponds to the influence of the target asset on the target asset data, a second data item which corresponds to the influence of the associated asset on the target asset data, a third data item which corresponds to the influence of the associated asset and the target asset on the target asset data, a fourth data item which corresponds to the influence of the associated asset on the associated asset data, a fifth data item which corresponds to the influence of the target asset on the associated asset data, and a sixth data item which corresponds to the influence of the associated asset and the target asset on the associated asset data;
Constructing the initial target model based on a preset first data variable data item, a time difference data item, the first data item, a second data item and a third data item;
and constructing the initial association model based on a preset second data variable data item, the time difference data item, a fourth data item, a fifth data item and a sixth data item.
Optionally, the obtaining a target model in the asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate and the initial target model includes:
based on historical target data of a plurality of historical time points in the target historical data information, obtaining historical target data change amounts corresponding to the historical time points;
substituting historical target data of a plurality of historical time points in the target historical data information, historical target data variation, historical associated data of a plurality of historical time points in the associated historical data information, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial target model to obtain a plurality of pending target models;
And solving a plurality of undetermined target models, determining a first term coefficient of the corresponding first data item, a second term coefficient of the second data item and a third term coefficient of a third data item, and obtaining the target model based on the first term coefficient, the second term coefficient, the third term coefficient and an initial target model.
Optionally, the obtaining an association model in the asset data association influence model based on the target historical data information, the association historical data information, the historical interest rate and the initial association model includes:
based on the history associated data of a plurality of history time points in the associated history data information, obtaining a history associated data change amount corresponding to the history time points;
substituting historical target data of a plurality of historical time points in the target historical data information, historical associated data of a plurality of historical time points in the associated historical data information, historical associated data variation, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial associated model to obtain a plurality of undetermined associated models;
and solving a plurality of undetermined association models, determining a fourth term coefficient of the fourth data item, a fifth term coefficient of the fifth data item and a sixth term coefficient of a sixth data item, and obtaining the association model based on the fourth term coefficient, the fifth term coefficient, the sixth term coefficient and an initial association model.
Optionally, the method further comprises:
before deriving pre-change future data of a target asset at a plurality of future time points based on a target asset and asset data associated influence model that corresponds in common with associated assets corresponding to the target asset, current target data of the target asset, current associated data of the associated asset, and current interest rate,
and judging whether the asset data association influence model is applicable or not based on the verification target data of a plurality of verification time points of the target asset, the verification associated data of a plurality of verification time points of the associated asset, the corresponding verification interest rate and the verification time difference of the corresponding adjacent verification time points, and if not, carrying out model applicability warning.
Optionally, the determining whether the asset data association influence model is applicable based on the verification target data of the multiple verification time points of the target asset, the verification associated data of the multiple verification time points of the associated asset, the corresponding verification interest rate, and the verification time difference of the corresponding adjacent verification time points includes:
inputting the corresponding verification time difference, the verification interest rate, the verification target data corresponding to the earliest verification time point and the verification associated data into a target model and an associated model in the asset data associated influence model to perform cross iteration operation, so as to obtain test output data of a plurality of verification time points of the target asset;
Determining error rates corresponding to a plurality of verification time points based on the corresponding verification target data and test output data;
and judging whether the verification time point with the corresponding error rate being greater than or equal to a preset error rate threshold value does not exist, and if not, carrying out model applicability warning.
Optionally, the obtaining future data of the target asset before the change at a plurality of future time points based on the target asset and the asset data association influence model corresponding to the associated asset corresponding to the target asset, the current target data of the target asset, the current associated data of the associated asset and the current interest rate includes:
and inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain future data of the target asset before the change of a plurality of future time points.
Optionally, the obtaining future data of the target asset after the future time points of the future time points are changed based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate includes:
Obtaining the interest rate after expected change based on the interest rate change range and the current interest rate;
and inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain post-change future data of the target asset at a plurality of future time points.
Optionally, the determining whether the target asset has a transaction abnormality based on the future data before the change and the future data after the change corresponding to the future time points includes:
obtaining a target data change amplitude corresponding to the future time point based on the corresponding pre-change future data and post-change future data;
and judging whether the future time point with the corresponding target data change amplitude larger than or equal to a preset data change amplitude threshold exists, and if so, carrying out transaction abnormality warning.
Optionally, the determining whether the target asset has a transaction abnormality based on the future data before the change and the future data after the change corresponding to the future time points includes:
obtaining a target data change amplitude corresponding to the future time point based on the corresponding pre-change future data and post-change future data;
Obtaining a target data change rate corresponding to the future time point based on the target data change amplitude and the future data before change or the future data after change;
and judging whether the future time point with the corresponding target data change rate larger than or equal to a preset data change rate threshold exists, and if so, carrying out transaction abnormality warning.
To achieve the above object, another aspect of the present invention discloses a transaction abnormality warning apparatus, the apparatus comprising:
the first prediction module is used for obtaining future data of the target asset before the change of a plurality of future time points based on an asset data association influence model, current target data of the target asset, current association data of the associated asset and current interest rate, which are commonly corresponding to the target asset and the associated asset corresponding to the target asset;
the second prediction module is used for obtaining future data of the target asset after the change of a plurality of future time points based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate;
and the abnormality alarming module is used for judging whether the target asset has transaction abnormality or not based on the future data before the change and the future data after the change corresponding to a plurality of future time points, and if so, carrying out transaction abnormality alarming.
The invention also discloses a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the method as described above when executing said program.
The invention also discloses a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as described above.
According to the transaction abnormality alarming method and device, the future data of the target asset before the change of a plurality of future time points is obtained by associating the influence model, the current target data of the target asset, the current association data of the association asset and the current interest rate based on the target asset and the asset data which are commonly corresponding to the association asset corresponding to the target asset, the model which is related to the influence characteristics of the corresponding data between the target asset and the association asset can be used, the corresponding actual current data and the interest rate are used as input for operation processing, the future data of the target asset under the current interest rate is accurately and rapidly predicted, and therefore the accuracy of the overall transaction abnormality alarming is improved; the future data of the target asset after the change of a plurality of future time points is obtained by associating the influence model, the current target data, the current associated data and the current interest rate based on the expected interest rate change range, the asset data, the expected interest rate and the predicted interest rate change range, and the model related to the corresponding data influence characteristics between the target asset and the associated asset can be used for carrying out operation processing by taking the corresponding actual current data, the interest rate and the predicted interest rate change range as inputs, so that the future data of the target asset after the interest rate change can be accurately and rapidly predicted, and the accuracy of the overall transaction abnormal alarm is improved; and judging whether the target asset has transaction abnormality or not based on the pre-change future data and the post-change future data corresponding to the future time points, and if so, carrying out transaction abnormality warning, wherein the pre-change future data and the post-change future data of the target asset at the same time of reflecting the relative fluctuation condition can be comprehensively used as the basis, so that the accuracy of the transaction abnormality warning is improved.
The transaction abnormity warning method and device provided by the invention can realize automatic execution in the forms of programs, functions, algorithms, software or application and the like, thereby greatly reducing the dependence on the working experience of staff, and can fully consider the influence of the related asset and the corresponding interest rate related to the target asset on the target asset data, so that the analyzed basis information has stronger correlation with the fluctuation condition of the asset data. Specifically, the fluctuation of the interest rate is closely related to the fluctuation of the target asset data, the fluctuation of the target asset data is further influenced by the corresponding associated asset condition, the determined future data before the fluctuation is the predicted future data of the target asset under the condition that the interest rate is not changed, and the future data before the fluctuation is closely related to the own condition of the target asset, the associated asset condition and the interest rate; the determined future data after change is the future data of the predicted target asset under the condition that the interest rate is changed (which is consistent with the actual condition, and the interest rate is changed frequently in the actual condition), and the future data after change is closely related to the self condition of the target asset, the condition of the related asset and the interest rate, so that the influence of the interest rate change on the fluctuation condition of the target asset data can be intuitively and accurately represented by integrating the future data before change and the future data after change, and the influence of the condition of the related asset on the fluctuation condition of the target asset data can be intuitively and accurately represented by integrating the future data before change and the future data after change by adopting the corresponding related asset information as the basis, thereby conforming to the related economic rules. Therefore, the transaction abnormality warning method and device provided by the invention can greatly improve the accuracy of predicting the fluctuation condition of the target asset data, thereby greatly improving the accuracy of the transaction abnormality warning based on the fluctuation condition of the target asset data.
In summary, the transaction abnormality warning method and device provided by the invention can improve the accuracy of the transaction abnormality warning, thereby improving the efficiency of the transaction abnormality warning.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a transaction anomaly alerting method according to an embodiment of the present invention;
FIG. 2 shows a schematic diagram of an alternative step of obtaining a target model according to an embodiment of the present invention;
FIG. 3 shows a schematic diagram of an alternative step of obtaining a correlation model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram showing an alternative step of determining whether a transaction anomaly exists in a target asset according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating an alternative step of determining whether a transaction anomaly exists in a target asset according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of a transaction anomaly alerting device according to an embodiment of the present invention;
fig. 7 shows a schematic diagram of a computer device suitable for use in implementing embodiments of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first," "second," … …, and the like, as used herein, do not denote a particular order or sequence, nor are they intended to be limiting of the invention, but rather are merely used to distinguish one element or operation from another in the same technical terms.
As used herein, the terms "comprising," "including," "having," "containing," and the like are intended to be inclusive and mean an inclusion, but not limited to.
As used herein, "and/or" includes any or all combinations of such things.
It should be noted that, in the technical scheme of the invention, the acquisition, storage, use, processing and the like of the data all conform to the relevant regulations of national laws and regulations.
It should be noted that, the transaction abnormality warning method and device disclosed in the present application may be used in the technical field of transaction processing, and may also be used in any field other than the technical field of transaction processing, and the application field of the transaction abnormality warning method and device disclosed in the present application is not limited.
The embodiment of the invention discloses a transaction abnormity warning method, which specifically comprises the following steps as shown in fig. 1:
s101: and obtaining future data of the target asset before the change of a plurality of future time points based on the target asset and the asset data association influence model which corresponds to the associated asset corresponding to the target asset together, the current target data of the target asset, the current associated data of the associated asset and the current interest rate.
S102: future data of the target asset after the change at a plurality of future time points is obtained based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate.
S103: and judging whether the target asset has transaction abnormality or not based on the future data before the change and the future data after the change corresponding to the future time points, and if so, carrying out transaction abnormality warning.
For example, after determining that the target asset has a transaction abnormality, the corresponding transaction abnormality prompting information may be further sent to the asset holder corresponding to the target asset (for example, a terminal of the asset holder corresponding to the target asset), and the asset holder is recommended to replace the corresponding target asset and then participate in the transaction again (for example, the corresponding asset replacement recommendation information is sent together). The method may further include, after determining that the target asset has a transaction abnormality, obtaining a data difference value for each future time point based on the pre-change future data and the post-change future data corresponding to the plurality of future time points (for example, taking an absolute value of a difference value between the pre-change future data and the post-change future data for the future time point as the data difference value), taking a future time point with a data difference value smaller than a preset data difference value threshold as a time point to be transacted, and performing transaction processing based on the target asset in a transaction time period between the time point to be transacted and a next future time point and/or a transaction time period between the time point to be transacted and a previous future time point. Preferably, after determining that the target asset has transaction abnormality, a data difference value of each future time point may be obtained based on the pre-change future data and the post-change future data corresponding to a plurality of future time points (for example, an absolute value of a difference value between the pre-change future data and the post-change future data of the future time points is taken as the data difference value), the data difference value is divided by the corresponding pre-change future data or post-change future data to obtain a data difference coefficient, and then a future time point with the data difference coefficient smaller than a preset data difference coefficient threshold is taken as a time point to be transacted, and transaction processing may be performed based on the target asset in a transaction time period between the time point to be transacted and a next future time point and/or a transaction time period between the time point to be transacted and a previous future time point. The specific processing manner of the related data and information specifically related to the transaction processing may be determined by those skilled in the art according to practical situations, and the embodiment of the present invention is not limited thereto. Further, after determining that the target asset has a transaction abnormality, the related target asset information about the target asset and the related transaction object asset information about the transaction object asset that is the transaction object of the target asset may be further transmitted to a corresponding worker (specifically, may be transmitted to a worker terminal of the worker who specifically handles the abnormal transaction) who specifically handles the abnormal transaction, so that the worker performs the transaction processing. It should be noted that, the specific content and type of the related measures after determining that the target asset has a transaction abnormality may be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Illustratively, the associated asset may be, but is not limited to, an asset having an association relationship with the target asset that has a significant financial interaction relationship, or interaction relationship. For example, if the target asset is a hybrid fund a and the hybrid fund a is established with a determination that a portion of its profit requires investment for engaging in bond B, then there is at least an association relationship such as an interaction relationship, and an action relationship between the hybrid fund a and bond B, then bond B is the associated asset of hybrid fund a. For another example, if the target asset is a mobile phone C, the mobile phone C needs to be manufactured by using a certain silicon wafer D, and therefore, at least an interaction relationship, an action relationship, and the like exist between the mobile phone C and the silicon wafer D, and therefore, the silicon wafer D is the related asset of the mobile phone C. It should be noted that, regarding the nature and determination of the associated assets, those skilled in the art may determine the nature and determination of the associated assets according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Illustratively, the data in the embodiment of the invention can be, but is not limited to, related value, transaction number in a preset time period of all the similar assets or related heat coefficient of the whole similar assets, and the like, and the value is preferred. In particular, it may be, but is not limited to, a unit value or a total value of an asset, etc. The value may be further taken as a corresponding unit price or total price, etc. It should be noted that, for the specific nature of the data, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the invention is not limited thereto.
For example, the transaction anomaly alarm may be, but not limited to, sending alarm information such as "xxx asset data fluctuates greatly, is not suitable for transaction based on the xxx asset data, has transaction anomalies, and requests timely verification processing" to the corresponding transaction party, manager or staff. It should be noted that, for the specific implementation manner of the transaction abnormality warning, those skilled in the art may determine the specific implementation manner according to the actual situation, and the foregoing description is merely exemplary, and the present invention is not limited thereto.
Illustratively, an asset data association influence model corresponds to a target asset and an associated asset, the target asset corresponding to a current target data, the associated asset corresponding to a current associated data, the target asset corresponding to a pre-change future data and a post-change future data at a future point in time. It should be noted that the above description is only an example and not a limitation, and the corresponding relation can be determined by a person skilled in the art according to the actual situation. According to the transaction abnormality alarming method and device, the future data of the target asset before the change of a plurality of future time points is obtained by associating the influence model, the current target data of the target asset, the current association data of the association asset and the current interest rate based on the target asset and the asset data which are commonly corresponding to the association asset corresponding to the target asset, the model which is related to the influence characteristics of the corresponding data between the target asset and the association asset can be used, the corresponding actual current data and the interest rate are used as input for operation processing, the future data of the target asset under the current interest rate is accurately and rapidly predicted, and therefore the accuracy of the overall transaction abnormality alarming is improved; the future data of the target asset after the change of a plurality of future time points is obtained by associating the influence model, the current target data, the current associated data and the current interest rate based on the expected interest rate change range, the asset data, the expected interest rate and the predicted interest rate change range, and the model related to the corresponding data influence characteristics between the target asset and the associated asset can be used for carrying out operation processing by taking the corresponding actual current data, the interest rate and the predicted interest rate change range as inputs, so that the future data of the target asset after the interest rate change can be accurately and rapidly predicted, and the accuracy of the overall transaction abnormal alarm is improved; and judging whether the target asset has transaction abnormality or not based on the pre-change future data and the post-change future data corresponding to the future time points, and if so, carrying out transaction abnormality warning, wherein the pre-change future data and the post-change future data of the target asset at the same time of reflecting the relative fluctuation condition can be comprehensively used as the basis, so that the accuracy of the transaction abnormality warning is improved. The transaction abnormity warning method and device provided by the invention can realize automatic execution in the forms of programs, functions, algorithms, software or application and the like, thereby greatly reducing the dependence on the working experience of staff, and can fully consider the influence of the related asset and the corresponding interest rate related to the target asset on the target asset data, so that the analyzed basis information has stronger correlation with the fluctuation condition of the asset data. Specifically, the fluctuation of the interest rate is closely related to the fluctuation of the target asset data, the fluctuation of the target asset data is further influenced by the corresponding associated asset condition, the determined future data before the fluctuation is the predicted future data of the target asset under the condition that the interest rate is not changed, and the future data before the fluctuation is closely related to the own condition of the target asset, the associated asset condition and the interest rate; the determined future data after change is the future data of the predicted target asset under the condition that the interest rate is changed (which is consistent with the actual condition, and the interest rate is changed frequently in the actual condition), and the future data after change is closely related to the self condition of the target asset, the condition of the related asset and the interest rate, so that the influence of the interest rate change on the fluctuation condition of the target asset data can be intuitively and accurately represented by integrating the future data before change and the future data after change, and the influence of the condition of the related asset on the fluctuation condition of the target asset data can be intuitively and accurately represented by integrating the future data before change and the future data after change by adopting the corresponding related asset information as the basis, thereby conforming to the related economic rules. Therefore, the transaction abnormality warning method and device provided by the invention can greatly improve the accuracy of predicting the fluctuation condition of the target asset data, thereby greatly improving the accuracy of the transaction abnormality warning based on the fluctuation condition of the target asset data.
In summary, the transaction abnormality warning method and device provided by the invention can improve the accuracy of the transaction abnormality warning, thereby improving the efficiency of the transaction abnormality warning.
In an alternative embodiment, further comprising:
before the asset data association influence model, the current target data of the target asset, the current association data of the associated asset and the current interest rate which are commonly corresponding to the target asset and the associated asset corresponding to the target asset are obtained, the initial target model of the target asset and the initial association model of the associated asset corresponding to the target asset are constructed based on a preset data power function;
obtaining a target model in an asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate and the initial target model;
and obtaining a correlation model in the asset data correlation influence model based on the target historical data information, the correlation historical data information, the historical interest rate and the initial correlation model.
Illustratively, a target asset corresponds to an initial target model and a target model, and an associated asset corresponds to an initial associated model and an associated model. It should be noted that the above description is only an example and not a limitation, and the corresponding relation can be determined by a person skilled in the art according to the actual situation.
The initial target model, the initial association model and the association model may be implemented by corresponding equations or be a neural network model, etc. specifically, but not limited to, the initial target model, the initial association model and the association model are preferably implemented by corresponding equations. It should be noted that, the specific forms of the initial target model, the initial association model and the association model may be determined by those skilled in the art according to the actual situation, and the foregoing description is merely exemplary, and the present invention is not limited thereto.
Through the steps, the target model for representing the influence characteristics of the related assets and the corresponding interest rates on the target asset data and the associated model for representing the influence characteristics of the target assets and the corresponding interest rates on the related asset data can be respectively constructed comprehensively based on the target historical data of the actual target assets, the associated historical data of the related assets and the corresponding historical interest rates, so that the matching degree of the corresponding data influence characteristics between the asset data associated influence model and the target assets and the related assets is higher and more comprehensive, future data before and future data after the change of the target assets are accurately determined later, and the accuracy of the integral transaction abnormal alarm is improved.
In an optional embodiment, the constructing an initial target model of the target asset and an initial association model of the associated asset corresponding to the target asset based on the preset data power function includes:
based on a plurality of data power functions, respectively constructing a first data item which corresponds to the influence of the target asset on the target asset data, a second data item which corresponds to the influence of the associated asset on the target asset data, a third data item which corresponds to the influence of the associated asset and the target asset on the target asset data, a fourth data item which corresponds to the influence of the associated asset on the associated asset data, a fifth data item which corresponds to the influence of the target asset on the associated asset data, and a sixth data item which corresponds to the influence of the associated asset and the target asset on the associated asset data;
constructing the initial target model based on a preset first data variable data item, a time difference data item, the first data item, a second data item and a third data item;
and constructing the initial association model based on a preset second data variable data item, the time difference data item, a fourth data item, a fifth data item and a sixth data item.
For example, when the corresponding object model and the associated model are implemented by the corresponding equation, the corresponding data item may be, but is not limited to, the equation item. Wherein the nature of the object model and the correlation model may be understood as, but not limited to, sub-models of the corresponding asset data correlation influence model, and the related data items may be understood as components of the relevant execution logic of the corresponding sub-models, etc. In the model, the corresponding execution logic may naturally be embodied as a corresponding function or equation, etc. It should be noted that the specific structure, properties, etc. of the model can be determined by those skilled in the art according to practical situations, and the above description is only for example, and the invention is not limited thereto.
Illustratively, the data power function may be determined by one skilled in the art according to actual circumstances, and embodiments of the present invention are not limited in this regard. For example, the data power function may include, but is not limited to, a data power function such as f (x) =x 2 Polynomial functions of +x, etc., such as f (x) =e 0.01x Exponential function such as f (x) =ln (x), trigonometric function such as f (x) =sin (x), and trigonometric function such as f (x) =2 0.1x sin(x)+x 2 Etc., and the like. Preferably, the data power function may be f (x) =x.
The method includes the steps of respectively constructing a first data item, a second data item, a third data item, a fourth data item, a fifth data item, a sixth data item, a functional formula of the third data item (typically, a functional sub-on right of a function equivalent) and a corresponding item coefficient variable of the corresponding data power function, and respectively obtaining a corresponding first data item, a second data item, a third data item, a fourth data item, a fifth data item and a sixth data item, wherein the functional formula of the first data item is the target asset data X, the functional formula of the second data item is the associated asset data Y, the functional formula of the third data item is the associated asset data Y, the functional formula of the fourth data item is the associated asset data Y, and the functional formula of the fourth data item is the target asset data Y.
For example, the first data item may be represented as, but is not limited to, arf 1 (X) wherein r represents a interest rate variable, a represents a term coefficient of the first data term, f 1 (X) represents a functional formula of the first data item; the second data item may be represented as, but is not limited to bg 1 (Y) wherein b represents the term coefficient of the second data term, g 1 (Y) represents a functional of the second data item; the third data item may be represented as, but is not limited to, alpha h 1 (XY), where α represents the term coefficient of the third data term, h 1 (XY) a functional formula representing a third data item; the fourth data item may be represented as, but is not limited to, a crf 2 (Y) wherein r represents a interest rate variable, c represents a term coefficient of the fourth data term, f 2 (Y) a functional formula representing a fourth data item; the fifth data item may be represented as, but is not limited to dg 2 (X) wherein d represents the term coefficient of the fifth data term, g 2 (X) represents a functional formula of a fifth data item; the sixth data item may be represented as, but is not limited to, βh 2 (XY), wherein β represents the term coefficient of the sixth data term, h 2 (XY) represents the functional of the sixth data item.
The specific logic of the functional formulas of the first data item, the second data item, the third data item, the fourth data item, the fifth data item and the sixth data item may be identical (for example, the logic of the specific logic is f (x) =x), or may be different from each other.
It should be noted that, for the specific implementation manner of respectively constructing the first data item corresponding to the influence of the target asset itself on the target asset data, the second data item corresponding to the influence of the associated asset on the target asset data, the third data item corresponding to the influence of the associated asset and the target asset on the target asset data, the fourth data item corresponding to the influence of the associated asset itself on the associated asset data, the fifth data item corresponding to the influence of the target asset on the associated asset data, and the sixth data item corresponding to the influence of the associated asset and the target asset on the associated asset data based on the multiple data power functions, the foregoing description is only for example and not limiting.
For example, the time difference data item may be, but is not limited to, a corresponding time difference variable, where the time dimension of the value needs to be the same as the time dimension of the interest rate, for example, if the time difference variable takes the value of 1 day, the interest rate needs to be a corresponding daily interest rate; if the time difference variable is 1 year, the interest rate is annual. Preferably, the time difference variable is 1 day, and the corresponding interest rate is a daily interest rate. It should be noted that, the specific arrangement and properties of the time difference data item can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Illustratively, the first data variable amount data item and the second data variable amount data item may be, but are not limited to, corresponding data variable amount variables. It should be noted that, the specific arrangement and properties of the first data variable amount data item and the second data variable amount data item may be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
The initial target model is constructed based on a preset first data variable quantity data item, a time difference data item, the first data item, a second data item and a third data item, and may be, but not limited to, performing an operation configuration such as addition, subtraction, multiplication and division between the first data item, the second data item and the third data item to obtain first sub-logic information, performing an operation configuration such as multiplication and division between the first sub-logic information and the time difference data item to form first main logic information, and finally setting the first main logic information on one side of an equal sign and setting the first data variable quantity data item on the other side of the equal sign to construct the initial target model. The following illustrates a representation of the execution logic of an exemplary initial object model:
dX＝(arf 1 (X)-bg 1 (Y)+αh 1 (XY))dt
Wherein dX represents a first data change amount data item, dt represents a time difference data item, arf 1 (X) represents the first data item bg 1 (Y) represents a second data item, αh 1 (XY) represents the third data item, (arf) 1 (X)-bg 1 (Y)+αh 1 (XY)) represents the first sub-logic information, (arf) 1 (X)-bg 1 (Y)+αh 1 (XY)) dt represents the first master logic information.
It should be noted that, for the specific implementation manner of constructing the initial target model based on the preset first data variable data item, time difference data item, the first data item, the second data item and the third data item, the foregoing description is only exemplary and not limiting, and may be determined by those skilled in the art according to actual situations.
The initial association model is constructed based on a preset second data variable amount data item, the time difference data item, a fourth data item, a fifth data item and a sixth data item, and may be, but not limited to, performing an operation configuration such as addition, subtraction, multiplication and division between the fourth data item, the fifth data item and the sixth data item to obtain second sub-logic information, performing an operation configuration such as multiplication and division between the second sub-logic information and the time difference data item to form second main logic information, and finally setting the second main logic information on one side of an equal sign and setting the second data variable amount data item on the other side of the equal sign to construct the initial association model. The following illustrates a representation of the execution logic of an exemplary initial correlation model:
dY＝(crf 2 (Y)-dg 2 (X)+βh 2 (XY))dt
Wherein dY represents a second data variation data item, dt represents a time difference data item, crf 2 (Y) represents the fourth data item, dg 2 (X) represents a fifth data item, βh 2 (XY) represents the sixth data item, (crf) 2 (Y)-dg 2 (X)+βh 2 (XY)) represents the second sub-logic information, (crf) 2 (Y)-dg 2 (X)+βh 2 (XY)) dt represents the second main logic information.
It should be noted that, for the specific implementation manner of constructing the initial association model based on the preset second data variable amount data item, the time difference data item, the fourth data item, the fifth data item and the sixth data item, the foregoing description is merely exemplary and is not limited thereto, and may be determined by those skilled in the art according to actual situations.
Through the steps, the initial target model can be further deeply related to the influence of the condition of the target asset on the data of the initial target model, the influence of the related asset on the data of the target asset, the influence of the combined action of the target asset and the related asset on the data of the target asset, and the mutual coordination relation and the cooperation characteristic among the influences, so that the initial target model is more accurately and comprehensively consistent with the data fluctuation influence condition of the target asset; the initial association model can be further deeply associated to the influence of the self condition of the associated asset on the self data, the influence of the target asset on the associated asset data and the influence of the combined action of the target asset and the associated asset on the associated asset data, and the mutual coordination relation and the cooperation characteristic between the influence, so that the initial association model is more accurately and comprehensively consistent with the data fluctuation influence condition of the associated asset. And fluctuations in the target asset data are affected by the associated asset data, while fluctuations in the associated asset data affect the associated asset data. Therefore, the step can further enable the matching degree of the corresponding data influence characteristics between the asset data association influence model and the target asset and the associated asset which are determined later to be higher and more comprehensive, and accordingly the accuracy of the overall transaction abnormity warning is improved.
In an alternative embodiment, as shown in fig. 2, the obtaining a target model in the asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate and the initial target model includes the following steps:
s201: and obtaining the historical target data change quantity corresponding to the historical time points based on the historical target data of a plurality of historical time points in the target historical data information.
S202: substituting historical target data of a plurality of historical time points in the target historical data information, historical target data change amounts, historical associated data of a plurality of historical time points in the associated historical data information, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial target model to obtain a plurality of pending target models.
S203: and solving a plurality of undetermined target models, determining a first term coefficient of the corresponding first data item, a second term coefficient of the second data item and a third term coefficient of a third data item, and obtaining the target model based on the first term coefficient, the second term coefficient, the third term coefficient and an initial target model.
For example, the time difference between adjacent historical time points may be fixed (i.e., the historical time points may be represented as an arithmetic series after being sequentially arranged), or may be not fixed. If the time difference between adjacent historical time points is fixed, there are the following examples: if the historical time point A, the historical time point B, the historical time point C and the historical time point D exist, the time difference between the historical time point B and the historical time point A, the time difference between the historical time point C and the historical time point B and the time difference between the historical time point D and the historical time point C are the same.
For example, the plurality of historical time points corresponding to the target historical data information are preferably the same as the plurality of historical time points corresponding to the associated historical data information, for example, the plurality of historical time points corresponding to the target historical data information include a time point a, a time point b and a time point c, and the plurality of historical time points corresponding to the associated historical data information also include a time point a, a time point b and a time point c.
For example, the step S201 may be, but is not limited to, subtracting, for each historical time point, the historical target data of the current time point from the historical target data of the next historical time point of the current historical time point, to obtain the historical target data variation corresponding to the current historical time point. For example, if there is a historical time point A (corresponding historical target data is x 1 ) Historical time point B (corresponding historical target data is x 2 ) And a history time point C (corresponding history target data is x 3 ) The change amount of the historical target data corresponding to the historical time point A is x 2 -x 1 The change amount of the historical target data corresponding to the historical time point B is x 3 -x 2 If there is no next history time point after the history time point, the history time point is not required to correspond to one history target data change amount (the history target data corresponding to the history time point is not required to participate in the corresponding solving operation). It should be noted that, for the specific implementation of step S201, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Illustratively, a pending objective model corresponds to a historical objective data for a time point, a historical correlation data for a time point, a historical objective data variance for a time point, and a historical time difference for a time point (i.e., a time difference between a next historical time point for a current historical time point and a current historical time point), and, in aggregate, a pending objective model corresponds to a historical time point. It should be noted that the above description is only an example and not a limitation, and the corresponding relation can be determined by a person skilled in the art according to the actual situation.
Illustratively, the step S202 may be, but is not limited to, substituting the historical target data and the historical interest rate into a first data item in the initial target model, substituting the historical target data variable into a first data variable data item in the initial target model, substituting the historical associated data into a second data item in the initial target model, substituting the historical associated data and the historical target data into a third data item in the initial target model, and substituting the historical time difference into a time difference data item in the initial target model, so as to obtain the pending target model (at this time, the value of the corresponding item coefficient variable is still uncertain, that is, the corresponding item coefficient variable is a variable to be solved). It should be noted that, for the specific implementation of step S202, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
For example, in the step S203, a plurality of pending target models may be, but not limited to, first grouped to obtain a plurality of pending target model groups, where the number of pending target models in a pending target model group is the number (typically 3 in the embodiment of the present invention) of variables (term coefficient variables) to be solved in one pending target model, and there may or may not be an intersection between a plurality of pending target model groups. Then, performing an equation solving operation on each of the pending target model groups (when relevant logic of the model can be represented as an equation), using an euler method, a lagrangian method, other equation solving methods, and the like, to obtain a first term coefficient to be processed, a second term coefficient to be processed, and a third term coefficient to be processed, which correspond to each of the pending target model groups (one to be processed first term coefficient, to be processed second term coefficient, and to be processed third term coefficient to be corresponding to one of the pending target model groups), then taking an average value of a plurality of the first term coefficients to be processed as the first term coefficient, taking an average value of a plurality of the second term coefficients to be processed as the second term coefficient, and taking an average value of a plurality of the third term coefficients to be processed as the third term coefficient, and finally substituting the first term coefficient, the second term coefficient, and the third term coefficient into the initial target model to obtain the target model. It should be noted that, for the specific implementation of step S203, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Preferably, in the plurality of history time points, if there is a loss of the history target data or the history associated data at some history time points, the data repair and data cleaning methods such as spline interpolation may be used to repair the history target data or the history associated data that is lost at the history time points, so that the history time points that originally lost the corresponding data can also correspond to one history target data and one history associated data. Further preferably, if the time difference between the plurality of history time points is fixed, the history target data or history associated data corresponding to the missing history time points may be determined by the following formula:
Figure BDA0003983201090000171
where i denotes the number of the history time point at which no history target data deficiency has occurred and no history associated data deficiency has occurred relative to the last time of the current history time point (history time point corresponding to the missing data), k denotes the number of the history time point at which no history target data deficiency has occurred and no history associated data deficiency has occurred next to the current history time point (history time point corresponding to the missing data), j denotes the difference of the number of the current history time point minus the number of the history time point at which no history target data deficiency has occurred last and no history associated data deficiency has occurred, x i+j Historical target data/historical associated data, x, representing a current historical point in time i History target data/history associated data indicating a history time point at which no history target data deficiency has occurred and no history associated data deficiency has occurred with respect to a current history time point (history time point corresponding to the missing data), x k Historical target data/historical associated data representing a next historical time point at which no historical target data deficiency has occurred and no historical associated data deficiency has occurred relative to a current historical time point (a historical time point corresponding to the missing data). When the historical target data corresponding to the missing historical time points are determined, other substituted data are all other historical target data, and when the historical associated data corresponding to the missing historical time points are determined, other substituted data are all other historical associated data.
It should be noted that, the repair method of the missing data at the historical time point can be determined by a person skilled in the art according to the actual situation, and the above description is only for example, and the present invention is not limited thereto.
According to the method, the initial target model can be processed to obtain the plurality of pending target models by taking actual historical information of a plurality of historical time points as parameter basis, so that the corresponding first term coefficient, second term coefficient and third term coefficient can be accurately determined by comprehensively solving the plurality of pending target models, the accuracy of the determined target model is improved, the operation accuracy of the asset data association influence model is further improved, and the accuracy of integral transaction abnormal alarming is further improved.
In an alternative embodiment, as shown in fig. 3, the obtaining the association model in the asset data association influence model based on the target historical data information, the association historical data information, the historical interest rate and the initial association model includes the following steps:
s301: and obtaining the change quantity of the history associated data corresponding to the history time point based on the history associated data of a plurality of history time points in the associated history data information.
S302: substituting historical target data of a plurality of historical time points in the target historical data information, historical associated data of a plurality of historical time points in the associated historical data information, historical associated data change amounts, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial associated model to obtain a plurality of undetermined associated models.
S303: and solving a plurality of undetermined association models, determining a fourth term coefficient of the fourth data item, a fifth term coefficient of the fifth data item and a sixth term coefficient of a sixth data item, and obtaining the association model based on the fourth term coefficient, the fifth term coefficient, the sixth term coefficient and an initial association model.
For example, the step S301 may be, but is not limited to, subtracting, for each historical time point, the historical associated data of the current time point from the historical associated data of the next historical time point of the current historical time point to obtain the historical associated data variation corresponding to the current historical time point. For example, if there is a history time point A (the corresponding history associated data is y 1 ) Historical time point B (corresponding historical associated data is y 2 ) And a history time point C (corresponding history associated data is y 3 ) The change amount of the history associated data corresponding to the history time point A is y 2 -y 1 The change amount of the history associated data corresponding to the history time point B is y 3 -y 2 If there is no next history time point after the history time point, the history time point is not required to be corresponding to one history related data change amount (the history related data corresponding to the history time point is not required to be involved in the corresponding solving operation). It should be noted that, for the specific implementation of step S301, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Illustratively, a pending association model corresponds to a historical target data for a time point, a historical association data change amount for a time point, and a historical time difference (i.e., a time difference between a next historical time point at a current historical time point and a current historical time point) for a time point, and in combination, a pending association model corresponds to a historical time point. It should be noted that the above description is only an example and not a limitation, and the corresponding relation can be determined by a person skilled in the art according to the actual situation.
Illustratively, the step S302 may be, but is not limited to, substituting the historical association data and the historical interest rate into a fourth data item in the initial association model, substituting the historical association data variable into a second data variable data item in the initial association model, substituting the historical target data into a fifth data item in the initial association model, substituting the historical association data and the historical target data into a third data item in the initial association model, and substituting the historical time difference into a time difference data item in the initial association model, so as to obtain the pending association model (at this time, the value of the corresponding item coefficient variable is still uncertain, that is, the corresponding item coefficient variable is a variable to be solved). It should be noted that, for the specific implementation of step S302, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
The step S303 may be, but is not limited to, first grouping a plurality of to-be-determined correlation models to obtain a plurality of to-be-determined correlation model groups, where the number of to-be-determined correlation models in one to-be-determined correlation model group is the number (generally 3 in the embodiment of the present invention) of variables (term coefficient variables) to be solved in one to-be-determined correlation model, and there may or may not be an intersection between the plurality of to-be-determined correlation model groups. Then, performing an equation solving operation on each of the pending association model groups (when relevant logic of the model can be represented as an equation), using, for example, an euler method, a lagrangian method, and other equation solving methods, to obtain a fourth term coefficient to be processed, a fifth term coefficient to be processed, and a sixth term coefficient to be processed, which correspond to each of the pending association model groups (one of the pending association model groups corresponds to one of the fourth term coefficient to be processed, the fifth term coefficient to be processed, and the sixth term coefficient to be processed), and then substituting an average value of the fourth term coefficients to be processed as the fourth term coefficient, an average value of the fifth term coefficients to be processed as the fifth term coefficient, and an average value of the sixth term coefficients to be processed as the sixth term coefficient, and finally substituting the fourth term coefficient, the fifth term coefficient, and the sixth term coefficient to the initial association model to obtain the association model. It should be noted that, for the specific implementation of step S303, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
According to the method, the initial association model can be processed to obtain a plurality of to-be-qualitatively associated models by taking actual historical information of a plurality of historical time points as parameter basis, so that the corresponding fourth term coefficient, fifth term coefficient and sixth term coefficient can be accurately determined by comprehensively solving the plurality of to-be-qualitatively associated models, the accuracy of the determined related models is improved, the operation accuracy of the asset data association influence model is further improved, and the accuracy of integral transaction abnormal alarming is further improved.
In an alternative embodiment, further comprising:
before deriving pre-change future data of a target asset at a plurality of future time points based on a target asset and asset data associated influence model that corresponds in common with associated assets corresponding to the target asset, current target data of the target asset, current associated data of the associated asset, and current interest rate,
and judging whether the asset data association influence model is applicable or not based on the verification target data of a plurality of verification time points of the target asset, the verification associated data of a plurality of verification time points of the associated asset, the corresponding verification interest rate and the verification time difference of the corresponding adjacent verification time points, and if not, carrying out model applicability warning.
Illustratively, the verification time point and the history time point are similar, and are both time points that have elapsed with respect to the current time, but the verification time point is generally different from the history time point.
The time difference between adjacent checking time points is fixed (i.e. the checking time points can be expressed as an arithmetic series after being sequentially arranged), and in common practice, the time differences corresponding to different adjacent checking time point groups are the same. For example, if there are the check time point a, the check time point b, the check time point c, and the check time point d, the time difference between the check time point b and the check time point a, the time difference between the check time point c and the check time point b, and the time difference between the check time point d and the check time point c are the same.
Illustratively, a verification time point corresponds to a verification target data and a verification-associated data. It should be noted that the above description is only an example and not a limitation, and the corresponding relation can be determined by a person skilled in the art according to the actual situation.
The verification time difference of the verification time point may be, but is not limited to, a time difference between a next verification time point of the current verification time point and the current verification time point.
For example, the historical target data, the verification target data, the historical association data, the verification association data and the like can be obtained or analyzed from related asset information. It should be noted that, regarding the relevant sources of the historical data, those skilled in the art can determine the sources according to the actual situation, and the above description is only for example, and the invention is not limited thereto.
Illustratively, the alerting of the applicability of the model may send alerting information such as "the accuracy of the target model and/or the associated model in the model does not meet the corresponding service requirement, please reset" to the relevant staff. It should be noted that, for the specific implementation manner of the model applicability alarm, those skilled in the art can determine the model applicability alarm according to the actual situation, and the above description is only for example, and the invention is not limited thereto.
Preferably, when the asset data association influence model is judged to be not applicable, the data dynamic function can be reselected to construct a corresponding initial target model and an initial association model, so that operations such as solving operation and the like are performed to retrieve the target model and the association model, and further the re-modeling of the asset data association influence model is realized. Thus, the method is beneficial to further improving the operation accuracy of the asset data association influence model, and further improving the accuracy of the integral transaction abnormal alarm.
Through the steps, the accuracy of the asset data association influence model can be checked by using the actual related data, so that the model can be found in time without participating in subsequent operation when the applicability of the model is poor, the accuracy of the asset data association influence model participating in the production operation subsequently can be favorably met to meet the corresponding requirement and be suitable, and the accuracy of the whole transaction abnormal alarm can be indirectly improved.
In an optional implementation manner, the determining whether the asset data association influence model is applicable based on the verification target data of the multiple verification time points of the target asset, the verification association data of the multiple verification time points of the associated asset, the corresponding verification interest rate and the verification time difference of the corresponding adjacent verification time points includes:
inputting the corresponding verification time difference, the verification interest rate, the verification target data corresponding to the earliest verification time point and the verification associated data into a target model and an associated model in the asset data associated influence model to perform cross iteration operation, so as to obtain test output data of a plurality of verification time points of the target asset;
Determining error rates corresponding to a plurality of verification time points based on the corresponding verification target data and test output data;
and judging whether the verification time point with the corresponding error rate being greater than or equal to a preset error rate threshold value does not exist, and if not, carrying out model applicability warning.
Exemplary, the inputting the corresponding verification target data and the verification association data corresponding to the verification time difference, the verification interest rate and the earliest verification time point into the target model and the association model in the asset data association influence model to perform a cross iteration operation, so as to obtain test output data of a plurality of verification time points of the target asset may be, but not limited to:
taking the verification target data corresponding to the earliest verification time point as current target data to be verified, and taking the verification associated data corresponding to the earliest verification time point as current associated data to be verified;
setting the value of a time difference data item in the target model and the value of a time difference data item in the associated model as the verification time difference, and setting the value of a interest rate variable in a first data item in the target model and the value of a interest rate variable in a fourth data item in the associated model as the verification interest rate;
Taking the earliest checking time point as the current checking time point;
repeating the first cross iteration step until the number of times of executing the first cross iteration step reaches a value obtained by subtracting 1 from the number of the verification time points; wherein the first cross iteration step includes:
correspondingly inputting the current target data to be checked into a first data item and a third data item of the target model, correspondingly inputting the current associated data to be checked into a second data item and a third data item of the target model, and carrying out operation to obtain the output target data to be checked corresponding to the next checking time point of the current checking time point;
correspondingly inputting the current to-be-verified associated data into a fourth data item and a sixth data item of the associated model, correspondingly inputting the current to-be-verified target data into a fifth data item and a sixth data item of the associated model, and carrying out operation to obtain the output to-be-verified associated data corresponding to a next verification time point of a current verification time point;
taking the output target data to be verified corresponding to the next verification time point of the current verification time point as current target data to be verified, and taking the output associated data to be verified corresponding to the next verification time point of the current verification time point as current associated data to be verified;
Taking the next checking time point of the current checking time point as the updated current checking time point;
and after repeatedly executing the first cross iteration step, taking the target data to be verified at a plurality of verification time points as the test output data.
Further, the step of inputting the corresponding verification target data and verification association data corresponding to the verification time difference, the verification interest rate and the earliest verification time point into a target model and an association model in the asset data association influence model to perform cross iteration operation, so as to obtain test output data of a plurality of verification time points of the target asset, which is exemplified by the following steps:
the known verification time points comprise a verification time point A, a verification time point B, a verification time point C and a verification time point D, wherein the verification time point A is the earliest verification time point, the verification target data corresponding to the verification time point A is a (which is also the target data to be verified corresponding to the verification time point A), and the verification associated data is b (which is also the associated data to be verified corresponding to the verification time point A); at this time, the value of the time difference data item in the target model and the value of the time difference data item in the associated model are determined to be the verification time difference q corresponding to the verification time point A, the verification time point B, the verification time point C and the verification time point D, and the value of the interest rate variable in the first data item in the target model and the value of the interest rate variable in the fourth data item in the associated model are set to be the corresponding verification interest rate p.
Substituting the target data a to be verified and the associated data b to be verified corresponding to the verification time point A into a target model for operation to obtain target data c to be verified corresponding to the verification time point B, and substituting the target data a to be verified and the associated data b to be verified corresponding to the verification time point A into an associated model for operation to obtain associated data d to be verified corresponding to the verification time point B;
substituting the target data c to be checked corresponding to the checking time point B and the associated data d to be checked into a target model for operation to obtain target data e to be checked corresponding to the checking time point C, and substituting the target data c to be checked corresponding to the checking time point B and the associated data d to be checked into an associated model for operation to obtain associated data f to be checked corresponding to the checking time point C;
substituting the target data e to be checked corresponding to the checking time point C and the associated data f to be checked into a target model for operation to obtain target data g to be checked corresponding to the checking time point D, and substituting the target data e to be checked corresponding to the checking time point C and the associated data f to be checked into an associated model for operation to obtain associated data h to be checked corresponding to the checking time point D;
in this way, the test output data includes the target data to be verified corresponding to the verification time point A, the target data to be verified corresponding to the verification time point B, the target data to be verified corresponding to the verification time point C, and the target data to be verified corresponding to the verification time point D.
Further, the inputting the current target data to be verified into the first data item and the third data item of the target model correspondingly, inputting the current associated data to be verified into the second data item and the third data item of the target model correspondingly, performing operation to obtain the output target data to be verified corresponding to the next verification time point of the current verification time point, which may be inputting the current target data to be verified into the first data item and the third data item of the target model correspondingly, performing operation to the current associated data to be verified into the second data item and the third data item of the target model correspondingly, obtaining a target verification fluctuation range, and superposing the target verification wave amplitude on the current target data to be verified to obtain the output associated data to be verified corresponding to the next verification time point of the current verification time point.
Correspondingly, the corresponding input of the current to-be-verified association data into the fourth data item and the sixth data item of the association model, the corresponding input of the current to-be-verified target data into the fifth data item and the sixth data item of the association model, and the operation are performed to obtain the output to-be-verified association data corresponding to the next verification time point of the current verification time point, which may be the corresponding input of the current to-be-verified association data into the fourth data item and the sixth data item of the association model, and the corresponding input of the current to-be-verified target data into the fifth data item and the sixth data item of the association model, so as to obtain an association verification fluctuation amplitude, and the overlapping of the association verification wave amplitude with the current to-be-verified association data, so as to obtain the output to-be-verified association data corresponding to the next verification time point of the current verification time point.
It should be noted that, for the specific implementation manner of inputting the corresponding verification target data and the verification association data corresponding to the verification time difference, the verification interest rate and the earliest verification time point into the target model and the association model in the asset data association influence model to perform the cross iterative operation, to obtain the test output data of the plurality of verification time points of the target asset, the foregoing description is only exemplary and not limiting.
The determining, based on the corresponding calibration target data and test output data, the error rates corresponding to the multiple calibration time points may be, but not limited to, dividing the absolute value of the difference between the calibration target data and the test output data corresponding to each calibration time point by the corresponding calibration target data or test output data, so as to obtain the corresponding error rates. Wherein one check time point corresponds to one error rate. It should be noted that, for the specific implementation manner of determining the error rates corresponding to the plurality of verification time points based on the corresponding verification target data and test output data, those skilled in the art may determine the error rates according to the actual situation, and the foregoing description is merely exemplary, and the present invention is not limited thereto.
The preset error rate threshold may be determined by one skilled in the art according to practical situations, and the embodiment of the present invention is not limited thereto, and the preset error rate threshold may be, for example, but not limited to, 5%.
Through the steps, the accuracy of the target model and the associated model in the asset data associated model can be deeply and finely checked, and the accuracy of the accuracy check is greatly improved, so that the accuracy of the asset data associated influence model which is subsequently participated in production operation is more favorably suitable for meeting the corresponding requirement, and the accuracy of the overall transaction abnormal alarm can be further indirectly improved.
In an optional embodiment, the obtaining future data of the target asset before the change at a plurality of future time points based on the target asset and the asset data association influence model, the current target data of the target asset, the current association data of the associated asset and the current interest rate, which are commonly corresponding to the associated asset corresponding to the target asset, includes:
and inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain future data of the target asset before the change of a plurality of future time points.
Preferably, the target model may be replaced by a trained target power neural network model, and the association model may be replaced by a trained association power neural network model, and correspondingly, before the formal use, the historical target data, the historical association data and the corresponding historical interest rate at a plurality of corresponding historical time points may be respectively used as input samples of the target power neural network model, the historical target data variation corresponding to the input samples of the target power neural network model may be used as input samples of the target power neural network model, and the input samples and the output samples of the target power neural network model may be used to train the target power neural network model. Correspondingly, the historical target data, the historical associated data and the corresponding historical interest rates at a plurality of corresponding historical time points can be respectively used as input samples of the associated power neural network model, the historical associated data change amounts corresponding to the input samples of the associated power neural network model are used as output samples of the associated power neural network model, and the input samples and the output samples of the associated power neural network model are used for training the associated power neural network model.
Illustratively, one future point in time corresponds to one pre-change future data, and one target asset corresponds to a plurality of pre-change future data for a plurality of future points in time.
Illustratively, the predicted time difference may be determined by those skilled in the art according to practical situations, and the embodiment of the present invention is not limited thereto, for example, the predicted time difference may be, but is not limited to, 1 day. The dimension of the predicted time difference needs to correspond to the dimension of the current interest rate, for example, if the predicted time difference is 1 day, the current interest rate needs to be the current daily interest rate.
By way of example, the number of future points in time may be determined by one skilled in the art based on actual circumstances, and embodiments of the present invention are not limited in this regard. For example, the number of the plurality of future points in time may be, but is not limited to 365, 366, 10 or 30, etc.
For example, the time difference between adjacent future time points may be fixed (i.e., the future time points may be sequentially arranged to be represented in the form of an arithmetic progression, which is colloquially the same for different sets of adjacent future time points). For example, if there are a future time point a, a future time point b, a future time point c, and a future time point d, the time difference between the future time point b and the future time point a, the time difference between the future time point c and the future time point b, and the time difference between the future time point d and the future time point c are the same.
Exemplary, the inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into the target model and the associated model in the asset data associated influence model to perform a cross iteration operation, so as to obtain future data of the target asset before the change at a plurality of future time points may be, but not limited to:
setting the value of a time difference data item in the target model and the value of a time difference data item in an associated model as the prediction time difference, and setting the value of a interest rate variable in a first data item in the target model and the value of a interest rate variable in a fourth data item in the associated model as the current interest rate;
superposing the current time with the predicted time difference to obtain the earliest future time point;
correspondingly inputting the current target data into a first data item and a third data item of the target model, correspondingly inputting the current associated data into a second data item and a third data item of the target model, performing operation to obtain a target prediction fluctuation range, superposing the current target data on the target prediction fluctuation range to obtain future data before fluctuation corresponding to the earliest future time point, and taking the future data before fluctuation corresponding to the earliest future time point as the future data before current fluctuation;
Correspondingly inputting the current association data into a fourth data item and a sixth data item of the association model, correspondingly inputting the current target data into a fifth data item and a sixth data item of the association model, performing operation to obtain association prediction fluctuation amplitude, superposing the current association data on the association prediction fluctuation amplitude to obtain pre-change future association data corresponding to the earliest future time point, and taking the pre-change future association data corresponding to the earliest future time point as current pre-change future association data;
taking the earliest future time point as a current future time point;
repeating the second cross iteration step until the number of times of executing the second cross iteration step reaches a value obtained by subtracting 1 from the preset number of the future time points; wherein the second cross-iterating step includes:
correspondingly inputting the current future data before change into a first data item and a third data item of the target model, correspondingly inputting the current future associated data before change into a second data item and a third data item of the target model, carrying out operation to obtain a current target prediction fluctuation range, and superposing the current future data before change on the current target prediction fluctuation range to obtain output future data before change corresponding to a next future time point of a current future time point;
Correspondingly inputting the current pre-change future associated data into a fourth data item and a sixth data item of the associated model, correspondingly inputting the current pre-change future data into a fifth data item and a sixth data item of the associated model, performing operation to obtain a current associated prediction fluctuation range, and superposing the current pre-change future associated data on the current associated prediction fluctuation range to obtain output pre-change future associated data corresponding to a next future time point of a current future time point; wherein a next future time point of the current future time point is obtained by superimposing the predicted time difference for the current future time point;
taking the output pre-change future data corresponding to the next future time point of the current future time point as current pre-change future data, and taking the output pre-change future associated data corresponding to the next future time point of the current future time point as current pre-change future associated data;
taking the next future time point of the current future time point as the updated current future time point;
after repeating the second cross-iteration step, pre-change future data of the target asset at a plurality of future time points is obtained.
Further, the step of inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into a target model and an associated model in the asset data associated influence model to perform a cross iteration operation, so as to obtain future data of the target asset before the change at a plurality of future time points, which is exemplified as follows:
knowing that the future time points include a future time point a, a future time point b, a future time point c and a future time point t, the future time point a being the earliest future time point (the current time can be determined by adding the predicted time difference), wherein the value of the time difference data item in the target model and the value of the time difference data item in the associated model are determined as the predicted time difference q corresponding to the future time point a, the future time point b, the future time point c and the future time point t, and the value of the interest rate variable in the first data item in the target model and the value of the interest rate variable in the fourth data item in the associated model are set to the corresponding current interest rate p;
and the future data before the change (the predicted data corresponding to the target asset) corresponding to the future time point A is obtained by the initial calculation and the future associated data before the change (the predicted data corresponding to the associated asset) is b;
Substituting the pre-change future data a and the pre-change future associated data b corresponding to the future time point A into a target model for operation to obtain the pre-change future data c corresponding to the future time point B, substituting the pre-change future data a and the pre-change future associated data b corresponding to the future time point A into an associated model for operation to obtain the pre-change future associated data d corresponding to the future time point B;
substituting the pre-change future data c and the pre-change future associated data d corresponding to the future time point B into a target model for operation to obtain pre-change future data e corresponding to the future time point C, substituting the pre-change future data c and the pre-change future associated data d corresponding to the future time point B into an associated model for operation to obtain pre-change future associated data f corresponding to the future time point C;
substituting the future data e and the future associated data f corresponding to the future time point C into a target model for operation to obtain the future data g corresponding to the future time point D, and substituting the future data e and the future associated data f corresponding to the future time point C into an associated model for operation to obtain the future associated data h corresponding to the future time point D;
In the above example, the description of superimposing the corresponding predicted fluctuation magnitudes is omitted.
In this way, the pre-change future data at the plurality of future time points includes the pre-change future data a corresponding to the future time point a, the pre-change future data c corresponding to the future time point b, the pre-change future data e corresponding to the future time point c, and the pre-change future data g corresponding to the future time point t.
It should be noted that, for inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into the target model and the associated model in the asset data associated influence model, a specific implementation manner of obtaining future data of the target asset before the change at a plurality of future time points may be determined by a person skilled in the art according to actual situations, and the above description is merely illustrative and not limiting.
Through the steps, the preset prediction time difference, the current target data, the current associated data and the current interest rate can be fully used as input, the asset data associated influence model is used for carrying out operation processing in a more detailed and deep mode, the influence of the associated asset is better combined in the operation process by means of the cross iteration mode, and therefore the accuracy of future data before prediction change is greatly improved, and the accuracy of integral transaction abnormal alarming is greatly improved.
In an alternative embodiment, the deriving future data of the target asset after the change at the plurality of future time points based on the expected interest rate change magnitude, the asset data association influence model, the current target data, the current association data, and the current interest rate includes:
obtaining the interest rate after expected change based on the interest rate change range and the current interest rate;
and inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain post-change future data of the target asset at a plurality of future time points.
Illustratively, the obtaining the interest rate after the expected change based on the interest rate change range and the current interest rate may be, but is not limited to, overlapping the interest rate change range with the current interest rate, to obtain the interest rate after the expected change. The interest rate variation range may be, but not limited to, 0.0001, 0.0002, -0.0001 or-0.0002, and the specific range may be determined by those skilled in the art according to practical situations. The method for obtaining the desired interest rate after the change based on the interest rate change width and the current interest rate may be, but not limited to, a method for superimposing the interest rate change width on the current interest rate to obtain a specific implementation of the desired interest rate after the change and a specific value of the interest rate change width, and may be determined by a person skilled in the art according to the actual situation.
Exemplary, the inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into the target model and the associated model in the asset data associated influence model performs a cross iterative operation, so as to obtain post-change future data of the target asset at a plurality of future time points, which may be but not limited to:
setting the value of a time difference data item in the target model and the value of a time difference data item in an associated model as the prediction time difference, and setting the value of a interest rate variable in a first data item in the target model and the value of a interest rate variable in a fourth data item in the associated model as the post-change interest rate;
superposing the current time with the predicted time difference to obtain the earliest future time point;
correspondingly inputting the current target data into a first data item and a third data item of the target model, correspondingly inputting the current associated data into a second data item and a third data item of the target model, performing operation to obtain a post-change target prediction fluctuation range, superposing the current target data on the post-change target prediction fluctuation range to obtain post-change future data corresponding to the earliest future time point, and taking the post-change future data corresponding to the earliest future time point as the current post-change future data;
Correspondingly inputting the current association data into a fourth data item and a sixth data item of the association model, correspondingly inputting the current target data into a fifth data item and a sixth data item of the association model, performing operation to obtain an association prediction fluctuation range after fluctuation, superposing the current association data on the association prediction fluctuation range after fluctuation to obtain future association data after fluctuation corresponding to the earliest future time point, and taking the future association data after fluctuation corresponding to the earliest future time point as future association data after current fluctuation;
taking the earliest future time point as a current future time point;
repeatedly executing a third cross iteration step until the times of executing the third cross iteration step reach a value obtained by subtracting 1 from the preset number of the future time points; wherein the third cross iteration step includes:
correspondingly inputting the current post-change future data into a first data item and a third data item of the target model, correspondingly inputting the current post-change future associated data into a second data item and a third data item of the target model, performing operation to obtain a current post-change target prediction fluctuation range, and superposing the current post-change future data on the current post-change target prediction fluctuation range to obtain output post-change future data corresponding to a next future time point of a current future time point;
Correspondingly inputting the current post-change future associated data into a fourth data item and a sixth data item of the associated model, correspondingly inputting the current post-change future data into a fifth data item and a sixth data item of the associated model, performing operation to obtain a current post-change associated prediction fluctuation range, and superposing the current post-change associated data with the current post-change associated prediction fluctuation range to obtain output post-change future associated data corresponding to a next future time point of a current future time point; wherein a next future time point of the current future time point is obtained by superimposing the predicted time difference for the current future time point;
taking the output future data after the change corresponding to the next future time point of the current future time point as the current future data after the change, and taking the output future associated data after the change corresponding to the next future time point of the current future time point as the current future associated data after the change;
taking the next future time point of the current future time point as the updated current future time point;
after repeating the third cross-iteration step, post-change future data of the target asset at a plurality of future time points is obtained.
Further, the step of inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into a target model and an associated model in the asset data associated influence model to perform a cross iteration operation, so as to obtain post-change future data of the target asset at a plurality of future time points, which is exemplified as follows:
knowing that the future time points include a future time point a, a future time point b, a future time point c and a future time point t, the future time point a being the earliest future time point (the current time can be determined by adding the predicted time difference), wherein the value of the time difference data item in the target model and the value of the time difference data item in the associated model are determined as the predicted time difference q corresponding to the future time point a, the future time point b, the future time point c and the future time point t, and the value of the interest rate variable in the first data item in the target model and the value of the interest rate variable in the fourth data item in the associated model are set as the corresponding post-change interest rate p;
and the future data (the predicted data corresponding to the target asset) after the change corresponding to the future time point A is obtained by the initial calculation is a, and the future associated data (the predicted data corresponding to the associated asset) after the change is b;
Substituting the post-change future data a and the post-change future associated data b corresponding to the future time point A into a target model for operation to obtain post-change future data c corresponding to the future time point B, substituting the post-change future data a and the post-change future associated data b corresponding to the future time point A into an associated model for operation to obtain post-change future associated data d corresponding to the future time point B;
substituting the post-change future data c and the post-change future associated data d corresponding to the future time point B into a target model for operation to obtain post-change future data e corresponding to the future time point C, substituting the post-change future data c and the post-change future associated data d corresponding to the future time point B into an associated model for operation to obtain post-change future associated data f corresponding to the future time point C;
substituting the post-change future data e and the post-change future associated data f corresponding to the future time point C into a target model for operation to obtain post-change future data g corresponding to the future time point D, substituting the post-change future data e and the post-change future associated data f corresponding to the future time point C into an associated model for operation to obtain post-change future associated data h corresponding to the future time point D;
In the above example, the description of superimposing the corresponding predicted fluctuation magnitudes is omitted.
In this way, the post-change future data of the plurality of future time points includes the post-change future data a corresponding to the future time point a, the post-change future data c corresponding to the future time point b, the post-change future data e corresponding to the future time point c, and the post-change future data g corresponding to the future time point t.
It should be noted that, for inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into the target model and the associated model in the asset data associated influence model, a specific implementation manner of obtaining the post-change future data of the target asset at a plurality of future time points may be determined by a person skilled in the art according to actual situations, and the above description is merely illustrative and not limiting.
Through the steps, the preset prediction time difference, the current target data, the current associated data and the interest rate after change are fully taken as inputs, the asset data associated influence model is used for carrying out operation processing in a more detailed and deep mode, the influence of the associated asset is better combined in the operation process by means of the cross iteration mode, and therefore the accuracy of future data after prediction and change is greatly improved, and the accuracy of integral transaction abnormal alarming is further greatly improved.
In an alternative embodiment, as shown in fig. 4, the determining whether the transaction abnormality exists in the target asset based on the future data before the change and the future data after the change corresponding to the future time points includes the following steps:
s401: and obtaining the change amplitude of the target data corresponding to the future time point based on the corresponding future data before the change and the future data after the change.
S402: and judging whether the future time point with the corresponding target data change amplitude larger than or equal to a preset data change amplitude threshold exists, and if so, carrying out transaction abnormality warning.
For example, the step S401 may be, but is not limited to, setting an absolute value of a difference between the post-change future data and the pre-change future data as the corresponding target data change amplitude. Wherein a future point in time corresponds to a pre-change future data, a post-change future data, and a target data change magnitude. It should be noted that, for the specific implementation of step S401, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
The data change amplitude threshold may be determined by one skilled in the art according to practical situations, and embodiments of the present invention are not limited thereto. For example, the data change amplitude threshold may be, but is not limited to, 100, 500, 1000, 5000, 10000, etc.,
Preferably, the process of continuously obtaining the new interest rate after the change based on the interest rate after the change and the expected interest rate change range can be repeated, so that new future data after the change at a plurality of future time points are determined by using the new interest rate after the change, and whether the target asset has transaction abnormality is judged based on the new future data after the change and corresponding future data before the change or the last future data after the change, so as to further improve the comprehensiveness of transaction abnormality warning.
Through the steps, the condition that the target asset data is fluctuated due to the influence of interest rate fluctuation and related assets at different future times can be determined based on the corresponding data variation accurately, and therefore the accuracy of transaction abnormality warning is improved.
In an alternative embodiment, as shown in fig. 5, the determining whether the transaction abnormality exists in the target asset based on the future data before the change and the future data after the change corresponding to the future time points includes the following steps:
s501: and obtaining the change amplitude of the target data corresponding to the future time point based on the corresponding future data before the change and the future data after the change.
S502: and obtaining the target data change rate corresponding to the future time point based on the target data change amplitude and the future data before change or the future data after change.
S503: and judging whether the future time point with the corresponding target data change rate larger than or equal to a preset data change rate threshold exists, and if so, carrying out transaction abnormality warning.
For example, for the specific implementation of step S501, reference may be made to the description of step S401 in the embodiment of the present invention, which is not repeated here.
Illustratively, the step S502 may be, but is not limited to, dividing the target data change range by the future data before the change or the future data after the change to obtain the target data change rate corresponding to the future time point. Wherein a future point in time corresponds to a target rate of change of data. It should be noted that, for the specific implementation of step S502, it can be determined by those skilled in the art according to the actual situation, and the above description is merely exemplary, and the present invention is not limited thereto.
Illustratively, the data rate threshold may be determined by one skilled in the art based on actual conditions, and embodiments of the present invention are not limited in this regard. For example, the data rate of change threshold may be, but is not limited to, 5%, 4%, 6%, etc.
Through the steps, the condition that the target asset data is fluctuated due to the influence of interest rate fluctuation and related assets at different future times can be determined based on the corresponding data change rate more precisely, and therefore the accuracy of transaction abnormality warning is improved.
Based on the same principle, the embodiment of the invention discloses a transaction abnormality warning device 600, as shown in fig. 6, the transaction abnormality warning device 600 includes:
a first prediction module 601, configured to obtain future data of a target asset before a plurality of future time points, based on a target asset and asset data association influence model that corresponds to the associated asset that corresponds to the target asset together, current target data of the target asset, current associated data of the associated asset, and a current interest rate;
a second prediction module 602, configured to obtain future data of the target asset after the future time points are changed based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate;
and the abnormality alarming module 603 is configured to determine whether the target asset has a transaction abnormality based on the future data before the change and the future data after the change corresponding to the future time points, and if so, perform a transaction abnormality alarm.
In an alternative embodiment, the method further comprises a model building module for:
before the asset data association influence model, the current target data of the target asset, the current association data of the associated asset and the current interest rate which are commonly corresponding to the target asset and the associated asset corresponding to the target asset are obtained, the initial target model of the target asset and the initial association model of the associated asset corresponding to the target asset are constructed based on a preset data power function;
obtaining a target model in an asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate and the initial target model;
and obtaining a correlation model in the asset data correlation influence model based on the target historical data information, the correlation historical data information, the historical interest rate and the initial correlation model.
In an alternative embodiment, the model building module is configured to:
based on a plurality of data power functions, respectively constructing a first data item which corresponds to the influence of the target asset on the target asset data, a second data item which corresponds to the influence of the associated asset on the target asset data, a third data item which corresponds to the influence of the associated asset and the target asset on the target asset data, a fourth data item which corresponds to the influence of the associated asset on the associated asset data, a fifth data item which corresponds to the influence of the target asset on the associated asset data, and a sixth data item which corresponds to the influence of the associated asset and the target asset on the associated asset data;
Constructing the initial target model based on a preset first data variable data item, a time difference data item, the first data item, a second data item and a third data item;
and constructing the initial association model based on a preset second data variable data item, the time difference data item, a fourth data item, a fifth data item and a sixth data item.
In an alternative embodiment, the model building module is configured to:
based on historical target data of a plurality of historical time points in the target historical data information, obtaining historical target data change amounts corresponding to the historical time points;
substituting historical target data of a plurality of historical time points in the target historical data information, historical target data variation, historical associated data of a plurality of historical time points in the associated historical data information, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial target model to obtain a plurality of pending target models;
and solving a plurality of undetermined target models, determining a first term coefficient of the corresponding first data item, a second term coefficient of the second data item and a third term coefficient of a third data item, and obtaining the target model based on the first term coefficient, the second term coefficient, the third term coefficient and an initial target model.
In an alternative embodiment, the model building module is configured to:
based on the history associated data of a plurality of history time points in the associated history data information, obtaining a history associated data change amount corresponding to the history time points;
substituting historical target data of a plurality of historical time points in the target historical data information, historical associated data of a plurality of historical time points in the associated historical data information, historical associated data variation, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial associated model to obtain a plurality of undetermined associated models;
and solving a plurality of undetermined association models, determining a fourth term coefficient of the fourth data item, a fifth term coefficient of the fifth data item and a sixth term coefficient of a sixth data item, and obtaining the association model based on the fourth term coefficient, the fifth term coefficient, the sixth term coefficient and an initial association model.
In an alternative embodiment, the method further comprises a model checking module for:
before deriving pre-change future data of a target asset at a plurality of future time points based on a target asset and asset data associated influence model that corresponds in common with associated assets corresponding to the target asset, current target data of the target asset, current associated data of the associated asset, and current interest rate,
And judging whether the asset data association influence model is applicable or not based on the verification target data of a plurality of verification time points of the target asset, the verification associated data of a plurality of verification time points of the associated asset, the corresponding verification interest rate and the verification time difference of the corresponding adjacent verification time points, and if not, carrying out model applicability warning.
In an alternative embodiment, the model checking module is configured to:
inputting the corresponding verification time difference, the verification interest rate, the verification target data corresponding to the earliest verification time point and the verification associated data into a target model and an associated model in the asset data associated influence model to perform cross iteration operation, so as to obtain test output data of a plurality of verification time points of the target asset;
determining error rates corresponding to a plurality of verification time points based on the corresponding verification target data and test output data;
and judging whether the verification time point with the corresponding error rate being greater than or equal to a preset error rate threshold value does not exist, and if not, carrying out model applicability warning.
In an alternative embodiment, the first prediction module 601 is configured to:
And inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain future data of the target asset before the change of a plurality of future time points.
In an alternative embodiment, the second prediction module 602 is configured to:
obtaining the interest rate after expected change based on the interest rate change range and the current interest rate;
and inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain post-change future data of the target asset at a plurality of future time points.
In an alternative embodiment, the anomaly alarm module 603 is configured to:
obtaining a target data change amplitude corresponding to the future time point based on the corresponding pre-change future data and post-change future data;
and judging whether the future time point with the corresponding target data change amplitude larger than or equal to a preset data change amplitude threshold exists, and if so, carrying out transaction abnormality warning.
In an alternative embodiment, the anomaly alarm module 603 is configured to:
obtaining a target data change amplitude corresponding to the future time point based on the corresponding pre-change future data and post-change future data;
obtaining a target data change rate corresponding to the future time point based on the target data change amplitude and the future data before change or the future data after change;
and judging whether the future time point with the corresponding target data change rate larger than or equal to a preset data change rate threshold exists, and if so, carrying out transaction abnormality warning.
Since the principle of the transaction abnormality warning device 600 for solving the problem is similar to that of the above method, the implementation of the transaction abnormality warning device 600 can be referred to the implementation of the above method, and will not be repeated here.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
In a typical example the computer apparatus comprises in particular a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the method as described above when said program is executed.
Referring now to FIG. 7, there is illustrated a schematic diagram of a computer device 700 suitable for use in implementing embodiments of the present application.
As shown in fig. 7, the computer apparatus 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the system 700 are also stored. The CPU701, ROM702, and RAM703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a liquid crystal feedback device (LCD), and the like, and a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as needed, so that a computer program read therefrom is mounted as needed as the storage section 708.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the record "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (14)

1. A transaction anomaly alerting method, comprising:
acquiring future data of the target asset before the change at a plurality of future time points based on an asset data association influence model, current target data of the target asset, current association data of the associated asset and current interest rate, which are commonly corresponding to the target asset and the associated asset corresponding to the target asset;
obtaining future data of the target asset after the change of a plurality of future time points based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate;
and judging whether the target asset has transaction abnormality or not based on the future data before the change and the future data after the change corresponding to the future time points, and if so, carrying out transaction abnormality warning.
2. The method as recited in claim 1, further comprising:
before the asset data association influence model, the current target data of the target asset, the current association data of the associated asset and the current interest rate which are commonly corresponding to the target asset and the associated asset corresponding to the target asset are obtained, the initial target model of the target asset and the initial association model of the associated asset corresponding to the target asset are constructed based on a preset data power function;
Obtaining a target model in an asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate and the initial target model;
and obtaining a correlation model in the asset data correlation influence model based on the target historical data information, the correlation historical data information, the historical interest rate and the initial correlation model.
3. The method of claim 2, wherein constructing an initial target model of the target asset and an initial association model of the associated asset corresponding to the target asset based on the preset data dynamic function comprises:
based on a plurality of data power functions, respectively constructing a first data item which corresponds to the influence of the target asset on the target asset data, a second data item which corresponds to the influence of the associated asset on the target asset data, a third data item which corresponds to the influence of the associated asset and the target asset on the target asset data, a fourth data item which corresponds to the influence of the associated asset on the associated asset data, a fifth data item which corresponds to the influence of the target asset on the associated asset data, and a sixth data item which corresponds to the influence of the associated asset and the target asset on the associated asset data;
Constructing the initial target model based on a preset first data variable data item, a time difference data item, the first data item, a second data item and a third data item;
and constructing the initial association model based on a preset second data variable data item, the time difference data item, a fourth data item, a fifth data item and a sixth data item.
4. The method of claim 3, wherein the deriving a target model of the asset data association influence model based on the target historical data information of the target asset, the associated historical data information of the associated asset, the corresponding historical interest rate, and the initial target model comprises:
based on historical target data of a plurality of historical time points in the target historical data information, obtaining historical target data change amounts corresponding to the historical time points;
substituting historical target data of a plurality of historical time points in the target historical data information, historical target data variation, historical associated data of a plurality of historical time points in the associated historical data information, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial target model to obtain a plurality of pending target models;
And solving a plurality of undetermined target models, determining a first term coefficient of the corresponding first data item, a second term coefficient of the second data item and a third term coefficient of a third data item, and obtaining the target model based on the first term coefficient, the second term coefficient, the third term coefficient and an initial target model.
5. The method of claim 3, wherein the deriving an association model of the asset data association influence model based on the target historical data information, association historical data information, historical interest rates, and an initial association model comprises:
based on the history associated data of a plurality of history time points in the associated history data information, obtaining a history associated data change amount corresponding to the history time points;
substituting historical target data of a plurality of historical time points in the target historical data information, historical associated data of a plurality of historical time points in the associated historical data information, historical associated data variation, the historical interest rate and the historical time difference corresponding to the adjacent historical time points into the initial associated model to obtain a plurality of undetermined associated models;
And solving a plurality of undetermined association models, determining a fourth term coefficient of the fourth data item, a fifth term coefficient of the fifth data item and a sixth term coefficient of a sixth data item, and obtaining the association model based on the fourth term coefficient, the fifth term coefficient, the sixth term coefficient and an initial association model.
6. The method as recited in claim 1, further comprising:
before deriving pre-change future data of a target asset at a plurality of future time points based on a target asset and asset data associated influence model that corresponds in common with associated assets corresponding to the target asset, current target data of the target asset, current associated data of the associated asset, and current interest rate,
and judging whether the asset data association influence model is applicable or not based on the verification target data of a plurality of verification time points of the target asset, the verification associated data of a plurality of verification time points of the associated asset, the corresponding verification interest rate and the verification time difference of the corresponding adjacent verification time points, and if not, carrying out model applicability warning.
7. The method of claim 6, wherein the determining whether the asset data association influence model is applicable based on the verification target data for the plurality of verification time points of the target asset, the verification association data for the plurality of verification time points of the associated asset, the corresponding verification interest rate, and the verification time differences for the adjacent verification time points comprises:
Inputting the corresponding verification time difference, the verification interest rate, the verification target data corresponding to the earliest verification time point and the verification associated data into a target model and an associated model in the asset data associated influence model to perform cross iteration operation, so as to obtain test output data of a plurality of verification time points of the target asset;
determining error rates corresponding to a plurality of verification time points based on the corresponding verification target data and test output data;
and judging whether the verification time point with the corresponding error rate being greater than or equal to a preset error rate threshold value does not exist, and if not, carrying out model applicability warning.
8. The method of claim 1, wherein the obtaining future data of the target asset before the change at the plurality of future time points based on the target asset and the asset data association influence model, the current target data of the target asset, the current association data of the associated asset, and the current interest rate that collectively correspond to the associated asset corresponding to the target asset comprises:
and inputting the preset prediction time difference, the current target data, the current associated data and the current interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain future data of the target asset before the change of a plurality of future time points.
9. The method of claim 8, wherein the deriving post-change future data for the target asset at a plurality of the future points in time based on the expected interest rate variation magnitude, the asset data association influence model, current target data, current association data, and current interest rate comprises:
obtaining the interest rate after expected change based on the interest rate change range and the current interest rate;
and inputting the predicted time difference, the current target data, the current associated data and the expected post-change interest rate into a target model and an associated model in the asset data associated influence model to perform cross iterative operation, so as to obtain post-change future data of the target asset at a plurality of future time points.
10. The method of claim 1, wherein determining whether the target asset has a transaction anomaly based on pre-change future data and post-change future data corresponding to a plurality of the future points in time comprises:
obtaining a target data change amplitude corresponding to the future time point based on the corresponding pre-change future data and post-change future data;
and judging whether the future time point with the corresponding target data change amplitude larger than or equal to a preset data change amplitude threshold exists, and if so, carrying out transaction abnormality warning.
11. The method of claim 1, wherein determining whether the target asset has a transaction anomaly based on pre-change future data and post-change future data corresponding to a plurality of the future points in time comprises:
obtaining a target data change amplitude corresponding to the future time point based on the corresponding pre-change future data and post-change future data;
obtaining a target data change rate corresponding to the future time point based on the target data change amplitude and the future data before change or the future data after change;
and judging whether the future time point with the corresponding target data change rate larger than or equal to a preset data change rate threshold exists, and if so, carrying out transaction abnormality warning.
12. A transaction anomaly warning device, comprising:
the first prediction module is used for obtaining future data of the target asset before the change of a plurality of future time points based on an asset data association influence model, current target data of the target asset, current association data of the associated asset and current interest rate, which are commonly corresponding to the target asset and the associated asset corresponding to the target asset;
The second prediction module is used for obtaining future data of the target asset after the change of a plurality of future time points based on the expected interest rate change range, the asset data association influence model, the current target data, the current association data and the current interest rate;
and the abnormality alarming module is used for judging whether the target asset has transaction abnormality or not based on the future data before the change and the future data after the change corresponding to a plurality of future time points, and if so, carrying out transaction abnormality alarming.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-11 when the program is executed by the processor.
14. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1-11.
CN202211555652.2A 2022-12-06 2022-12-06 Transaction abnormity warning method and device Pending CN116151975A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211555652.2A CN116151975A (en) 2022-12-06 2022-12-06 Transaction abnormity warning method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211555652.2A CN116151975A (en) 2022-12-06 2022-12-06 Transaction abnormity warning method and device

Publications (1)

Publication Number Publication Date
CN116151975A true CN116151975A (en) 2023-05-23

Family

ID=86339811

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211555652.2A Pending CN116151975A (en) 2022-12-06 2022-12-06 Transaction abnormity warning method and device

Country Status (1)

Country Link
CN (1) CN116151975A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117172925B (en) * 2023-11-03 2024-02-20 建信金融科技有限责任公司 Transaction processing method, device, equipment and medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117172925B (en) * 2023-11-03 2024-02-20 建信金融科技有限责任公司 Transaction processing method, device, equipment and medium

Similar Documents

Publication Publication Date Title
US11086762B2 (en) Methods and systems for predicting estimation of project factors in software development
CN111143102A (en) Abnormal data detection method and device, storage medium and electronic equipment
US10738599B2 (en) System and tool with increased forecast accuracy to configure well settings in mature oil fields
CN110633194B (en) Performance evaluation method of hardware resources in specific environment
Kirchen et al. Metrics for the evaluation of data quality of signal data in industrial processes
CN113570396A (en) Time series data abnormity detection method, device, equipment and storage medium
CN110766184A (en) Order quantity prediction method and device
CN116151975A (en) Transaction abnormity warning method and device
Swei Forecasting infidelity: Why current methods for predicting costs miss the mark
Amiri et al. Multi-objective economic-statistical design of MEWMA control chart
CN115115190A (en) Quality monitoring method based on working condition, related device and program medium product
US20150073956A1 (en) Model risk rating
US20150073957A1 (en) Extended range model risk rating
US20130332225A1 (en) Risk-profile generation device
Celano et al. Control charts monitoring product's loss to society
CN115062687A (en) Enterprise credit monitoring method, device, equipment and storage medium
Saito et al. Robustness of non-homogeneous gamma process-based software reliability models
RU162895U1 (en) AUTOMATED RISK ASSESSMENT DEVICE
Biller et al. Propagation of input uncertainty in manufacturing process flow simulations
EP4075211B1 (en) Prediction method and system for multivariate time series data in manufacturing systems
Marei et al. Modeling and Predicting the Egyptian Pound's Exchange Rate Per the American Dollar on a Short-Term Scale by Using ARIMA–Probability Distributions
US9117172B2 (en) Optimisation of resource management using perfect knowledge bias
Bogdanova et al. Forecast Accuracy Evaluation of the Enterprise’s Industrial Safety Integral Risk.
Skatkov et al. Effectiveness analysis of the kulback’s information measure in the technological objects monitoring
Goroshko et al. Harmonizing Social and Production Indicators in the Way to Technological Sovereignty

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