CN114418450A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN114418450A CN114418450A CN202210116202.7A CN202210116202A CN114418450A CN 114418450 A CN114418450 A CN 114418450A CN 202210116202 A CN202210116202 A CN 202210116202A CN 114418450 A CN114418450 A CN 114418450A
- Authority
- CN
- China
- Prior art keywords
- stationarity
- unit
- variable
- prediction unit
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data processing method and a data processing device, which can respectively obtain data value sequences of a target prediction unit in a plurality of continuous historical time periods; respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period; storing the data value sequence of the target prediction unit passing through the stability check and the index value sequence of the macro economic index into a stability variable table, storing the data value sequence of the target prediction unit not passing through the stability check and the index value sequence of the macro economic index into a non-stability variable table, respectively screening a stability variable group and a non-stability variable group from the two variable tables, respectively determining the prediction index value of each macro economic index in the two variable groups in a predefined future time period, and inputting the prediction index value into a data prediction model to obtain the data value of the target prediction unit output by the model in the future time period. The invention can realize effective prediction of the data value of the target prediction unit in the future time period.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a data processing method and apparatus.
Background
In the operation management of the bank, the net profit before preparation can be used for representing the operation level of the bank, and the bank needs to predict the data value of the net profit before preparation in the future period (such as the next year) so as to carry out reasonable operation planning.
Specifically, the data prediction of net profit before preparation relates to various financial indexes, such as financial indexes of interest assets, liabilities and debts, offspecks and profits. In the prior art, various financial indexes can be regarded as a prediction unit respectively, and a data prediction model corresponding to the prediction unit is used for predicting data values of the prediction unit.
However, the prior art cannot effectively predict the data value of the prediction unit.
Disclosure of Invention
In view of the above problems, the present invention provides a data processing method and apparatus for overcoming the above problems or at least partially solving the above problems, and the technical solution is as follows:
a method of data processing, comprising:
respectively obtaining data value sequences of a target prediction unit in a plurality of continuous historical periods;
respectively carrying out stationarity check on the data value sequences of the target prediction unit in each historical time period, storing the data value sequences of the target prediction unit passing stationarity check into a stationarity variable table, and storing the data value sequences of the target prediction unit not passing stationarity check into a non-stationarity variable table;
respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period;
respectively carrying out stationarity check on an index value sequence of each macro-economic index in each historical time period, storing the index value sequences of the macro-economic indexes passing stationarity check into the stationarity variable table, and storing the index value sequences of the macro-economic indexes not passing stationarity check into the non-stationarity variable table;
respectively screening a stationarity variable group and a non-stationarity variable group from the stationarity variable table and the non-stationarity variable table according to a predefined variable combination screening rule; the stationary variable set and the non-stationary variable set each comprise at least one of the macro economic indicators;
respectively determining the predicted index values of each macro economic index in the stationary variable group and the non-stationary variable group in a predefined future time period;
and inputting the prediction index value of each macro economic index in the stationarity variable group and the non-stationarity variable group into a data prediction model matched with the target prediction unit, and obtaining the data value of the target prediction unit in the future time period output by the data prediction model.
Optionally, the historical period comprises the last day of each quarter in two adjacent years.
Optionally, the data prediction model is a moving average autoregressive model ARIMAX; the selecting a stationarity variable group and a non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively according to a predefined variable combination selecting rule comprises:
and screening the stationarity variable group and the non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively by using the screening rule of the ARIMAX on the variable groups.
Optionally, the stationarity checking includes: at least one of an expanded diky-fowler ADF test and a KPSS test; the method further comprises the following steps:
determining the data value sequence of the target prediction unit passing the ADF test and/or the KPSS test as the data value sequence of the target prediction unit passing the stationarity check;
determining the index value sequence of the macro-economic indicator passing the ADF inspection and/or the KPSS inspection as the index value sequence of the macro-economic indicator passing stationarity check.
Optionally, the method further includes:
respectively determining each prediction unit needing data value prediction in the net profit model before preparation as the target prediction unit, and executing the step of respectively obtaining data value sequences of the target prediction units in a plurality of continuous historical time periods so as to determine the data value of each prediction unit in the future time period;
and predicting the net profit before preparation in the future time period based on the net profit before preparation model and the data value of each prediction unit in the future time period.
A data processing apparatus comprising: the device comprises a first obtaining unit, a first checking unit, a first storage unit, a second obtaining unit, a second checking unit, a third storage unit, a fourth storage unit, a first screening unit, a first determining unit, a first input unit and a third obtaining unit; wherein:
the first obtaining unit is used for respectively obtaining data value sequences of the target prediction unit in a plurality of continuous historical periods;
the first checking unit is used for respectively carrying out stationarity checking on the data value sequences of the target prediction unit in each historical time interval;
the first storage unit is used for storing the data value sequences of the target prediction unit which pass through stationarity check into a stationarity variable table;
the second storage unit is used for storing the data value sequences of the target prediction unit which do not pass stationarity check into a non-stationarity variable table;
the second obtaining unit is used for respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period;
the second checking unit is used for respectively performing stationarity checking on the index value sequence of each macro economic index in each historical time period;
the third saving unit is configured to save the index value sequences of the macro economic indicators that pass stationarity check into the stationarity variable table;
the fourth saving unit is configured to save the index value sequences of the macro economic indicators that do not pass stationarity check into the non-stationarity variable table;
the first screening unit is used for screening a stationarity variable group and a non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively according to a predefined variable combination screening rule; the stationary variable set and the non-stationary variable set each comprise at least one of the macro economic indicators;
the first determining unit is used for respectively determining the predicted index values of each macro economic index in the stationary variable group and the non-stationary variable group in a predefined future time period;
the first input unit is used for inputting the prediction index value of each macroscopic economic index in the stationarity variable group and the non-stationarity variable group into a data prediction model matched with the target prediction unit;
the third obtaining unit is configured to obtain a data value of the target prediction unit output by the data prediction model in the future time period.
Optionally, the historical period comprises the last day of each quarter in two adjacent years.
Optionally, the data prediction model is a moving average autoregressive model ARIMAX;
the first screening unit is used for screening the stationarity variable group and the non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively by using the screening rule of the ARIMAX on the variable group.
Optionally, the stationarity checking includes: at least one of an expanded diky-fowler ADF test and a KPSS test; the device further comprises: a second determination unit and a third determination unit;
the second determining unit is configured to determine the data value sequence of the target prediction unit that passes the ADF check and/or the KPSS check as the data value sequence of the target prediction unit that passes the stationarity check;
the third determining unit is configured to determine the index value sequence of the macro economic indicator passing through the ADF inspection and/or the KPSS inspection as the index value sequence of the macro economic indicator passing through stationarity check.
Optionally, the apparatus further comprises: a triggering unit and a prediction unit;
the triggering unit is used for respectively determining each prediction unit needing data value prediction in a net profit model before preparation as the target prediction unit and triggering the first obtaining unit to determine the data value of each prediction unit in the future time period;
and the prediction unit is used for predicting the net profit before preparation in the future time period based on the net profit before preparation model and the data value of each prediction unit in the future time period.
The data processing method and the data processing device can respectively obtain data value sequences of the target prediction unit in a plurality of continuous historical time periods; respectively carrying out stability verification on the data value sequences of the target prediction units in each historical time period, storing the data value sequences of the target prediction units passing the stability verification into a stability variable table, and storing the data value sequences of the target prediction units not passing the stability verification into a non-stability variable table; respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period; respectively carrying out stability verification on the index value sequences of each macro-economic index in each historical time period, storing the index value sequences of the macro-economic indexes passing the stability verification into a stability variable table, and storing the index value sequences of the macro-economic indexes not passing the stability verification into a non-stability variable table; respectively screening a stationarity variable group and a non-stationarity variable group from a stationarity variable table and a non-stationarity variable table according to a predefined variable combination screening rule; the stationarity variable group and the non-stationarity variable group both comprise at least one macroscopic economic index; respectively determining the prediction index values of each macroscopic economic index in the stationary variable group and the non-stationary variable group in a predefined future time period; and inputting the prediction index values of the macroscopic economic indexes in the stationary variable group and the non-stationary variable group into a data prediction model matched with the target prediction unit to obtain the data value of the target prediction unit output by the data prediction model in the future time period. The invention can realize effective prediction of the data value of the target prediction unit in the future time period.
The foregoing description is only an overview of the technical solutions of the present invention, and the following detailed description of the present invention is provided to enable the technical means of the present invention to be more clearly understood, and to enable the above and other objects, features, and advantages of the present invention to be more clearly understood.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart illustrating a first data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a second data processing method provided by the embodiment of the invention;
fig. 3 is a schematic structural diagram illustrating a data processing apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, the present embodiment proposes a first data processing method, which may include the steps of:
s101, respectively obtaining data value sequences of a target prediction unit in a plurality of continuous history periods;
the target prediction unit can be a certain prediction unit, namely a certain financial index in a plurality of financial indexes related to the net profit before preparation, such as unit fixed property loan.
Wherein the historical period may be a certain period or periods in the past.
Optionally, the historical period comprises the last day of each quarter in two adjacent years. For example, the first historical period may include 31 days 3/2020, 30 days 6/2020, 30 days 9/2020, 31 days 12/2020, 31 days 3/2021, 30 days 6/2021, 30 days 9/2021, and 31 days 12/2021.
Optionally, the historical period may also include the last day of each quarter of the adjacent three years; alternatively, the historical period may also include the last day of five consecutive quarters. It should be noted that the specific time period included in the historical time period may be determined by a skilled person according to actual situations, and the present invention is not limited to this.
The plurality of history periods may be time-continuous periods. For example, the second history period temporally continuous with the first history period may be 31/2018/3/2018, 30/2018/6/30/2018, 30/2018/9/12/31/2018/3/31/2019, 30/2019/6/2019/9/30/2019/12/31/2019.
The data value sequence may be a sequence formed by arranging data values of the target prediction unit in the historical time period according to a time sequence. For example, when the data values of the target prediction unit on the days in the first history period are 5.7, 5.8, 5.5, 5.6, 5.8, 5.9, 5.7 and 5.5, respectively, the data value sequence of the target prediction unit in the first history period is {5.7, 5.8, 5.5, 5.6, 5.8, 5.9, 5.7, 5.5 }. It will be appreciated that the sequence of data values may be a time sequence of data values for the target prediction unit over the history period.
Optionally, the invention can firstly derive the total financial statement in the target historical period from the system operation platform in the enterprise. The data values of all financial indexes within the corresponding date can be included in the full-amount financial statement. Then, the data values of the target prediction unit in a plurality of historical time periods can be matched and searched from the full-amount financial statement, and the data values are exported and stored into the corresponding data storage space.
S102, performing stationarity check on data value sequences of the target prediction unit in each historical time period respectively;
specifically, after the data value sequences of the target prediction unit in each historical time period are obtained, the stability of the data value sequences of the target prediction unit in each historical time period can be checked respectively. For example, after obtaining the data value sequences of the target prediction unit in the first history period and the second history period, the stationarity check may be performed on the data value sequence in the first history period in advance, and then the stationarity check may be performed on the data value sequence in the second history period.
It should be noted that the present invention is not limited to the specific stability verification method, such as ADF verification, KPSS verification, and PP verification.
It will be appreciated that the present invention may enable automatic, batch verification of sequences of data values for a target prediction unit over historical time periods.
S103, storing the data value sequences of the target prediction units passing through the stability verification into a stability variable table;
the stationarity variable table may be a data table for storing a data value sequence of the target prediction unit with stationarity and an index value sequence of the macro economic indicator with stationarity.
Specifically, after the stationarity of the data value sequence of the target prediction unit in a certain historical time period is checked, whether the data value sequence of the target prediction unit in the historical time period passes the stationarity or not, that is, whether the data value sequence has the stationarity or not can be determined.
It should be noted that, if the data value sequence of the target prediction unit in a certain historical time period passes through stationarity check, it can be stated that the data value sequence of the target prediction unit in the historical time period has stationarity; if the data value sequence of the target prediction unit in a certain historical period does not pass stationarity check, it can be shown that the data value sequence of the target prediction unit in the historical period does not have stationarity.
Specifically, after the data value sequence of the target prediction unit in a certain historical time period is determined to have stationarity, the data value sequence of the target prediction unit in the historical time period is inserted into the stationarity variable table.
Specifically, after all the data value sequences with stationarity are determined, all the data value sequences with stationarity are inserted into the stationarity variable table.
S104, storing all data value sequences of the target prediction units which do not pass through stationarity check into a non-stationarity variable table;
the non-stationarity variable table may be a data table that stores a data value sequence of the target prediction unit that does not have stationarity and an index value sequence of the macro economic indicator that does not have stationarity.
Specifically, the present invention may insert the data value sequence of the target prediction unit in a certain history period into the non-stationarity variable table after the data value sequence of the target prediction unit in the history period has no stationarity.
Specifically, after all data value sequences without stationarity are determined, all data value sequences without stationarity are inserted into the non-stationarity variable table.
S105, acquiring index value sequences of a plurality of macro economic indexes in each historical time period respectively;
the macro economic indicator may be an indicator representing a macro economic operation condition, and may describe an approximate outline of macro economic change, such as a GDP.
The plurality of macro economic indicators may be macro economic indicators specified by workers such as economic experts and technicians according to actual situations, which is not limited in the present invention.
The index value sequence may be a sequence in which index values of a certain macro-economic index in a historical period are arranged according to a time sequence. For example, when the index values of a certain macro economic indicator in the first history period are 6.7, 6.8, 6.5, 6.6, 6.8, 6.9, 6.7 and 6.5, respectively, the index value sequence of the macro economic indicator in the first history period is {6.7, 6.8, 6.5, 6.6, 6.8, 6.9, 6.7, 6.5 }. It is understood that the index value sequence may be a time sequence of data values of a macro economic index in a history period.
Specifically, the method can respectively obtain the index value sequence of each macroscopic economic index in each historical time period. For example, for a first macro economic indicator and a second macro economic indicator, a first history period and a second history period, the present invention may obtain an index value sequence of the first macro economic indicator in the first history period, an index value sequence of the first macro economic indicator in the second history period, an index value sequence of the second macro economic indicator in the first history period, and an index value sequence of the second macro economic indicator in the second history period.
Specifically, the index values of all the macroscopic factor indexes in the target historical period can be derived in advance from the data storage space of the enterprise recording the historical data of the macroscopic factor indexes. At this time, the present invention may also perform data processing on the derived index value of the macroscopic factor index to obtain processed values in various forms (such as geometric, circular, differential, lag, advance, etc.), and use the processed values as the index values of the corresponding macroscopic factor index in the corresponding history period.
Specifically, the present invention can find out the index values of all the macroscopic factor indexes in the plurality of historical periods from the index values of all the macroscopic factor indexes in the target historical period, so as to obtain the index value sequence of each macroscopic economic index in the plurality of historical periods.
S106, respectively carrying out stability verification on the index value sequences of the macro economic indexes in the historical time periods;
it should be noted that the specific verification method adopted by the present invention for performing stationarity check on the index value sequence and the data value sequence may be the same or different.
Specifically, after an index value sequence of a certain macro economic index in a certain historical period is obtained, stability verification is performed on the index value sequence of the macro economic index in the historical period.
It can be understood that the invention can realize automatic and batch inspection of the index value sequence of each macroscopic economic index in each historical period.
S107, storing all index value sequences of macro economic indexes passing stability verification into a stability variable table;
specifically, after stability check is performed on an index value sequence of a macro economic index in a certain historical time period, whether the index value sequence of the macro economic index in the historical time period passes the stability check or not, namely whether the index value sequence has stability or not, can be determined.
It can be understood that if the index value sequence of a certain macro economic index in a certain historical period passes through stability verification, the macro economic index can be proved to have stability; if the index value sequence of the macro economic index in the historical time interval does not pass stability check, the macro economic index can be proved to have no stability.
Specifically, when the stability of the index value sequence of a certain macro-economic index in a certain historical period is determined, the index value sequence of the macro-economic index in the historical period is inserted into the stability variable table.
Specifically, after all the index value sequences with stationarity are determined, all the index value sequences with stationarity are inserted into the stationarity variable table.
Alternatively, the arrangement form of the index value sequence of the macro economic indicator and the data value sequence of the target prediction unit stored in the stationarity variable table may be as shown in table 1 below.
TABLE 1 smoothness variable scale
Wherein, the data value sequence with stationarity of the target prediction unit y1 in a history period and the index value sequence with stationarity of the macro economic indicators x1, x2 and x3 in the corresponding history period are stored in table 1.
Specifically, the date in table 1 may be a date, and all dates under the date, that is, the last day in each quarter in two consecutive years (2020 and 2021), may constitute a corresponding history period, that is, the first history period; y1 in table 1 may be a target prediction unit, each data value under y1 column may be a data value of y1 at a corresponding date, and a data value sequence of y1 in the first history period may be formed after the data values are arranged in chronological order; the x1, the x2 and the x3 can be macro economic indicators, the indicator values under each column of the macro economic indicators can be indicator values at corresponding dates, and the indicator values can form an indicator value sequence of the macro economic indicators in the first history period after being arranged according to the time sequence, for example, the indicator values under each column of the x1 can be indicator values of the x1 at corresponding dates, and the indicator value sequence of the x1 in the first history period can be formed after being arranged according to the time sequence.
S108, storing all index value sequences of macro economic indexes which do not pass stability verification into a non-stability variable table;
specifically, the method can insert the index value sequence of the macro economic index in the historical period into the non-stationarity variable table when the index value sequence of the macro economic index in the historical period is determined to have no stationarity.
Specifically, after all the index value sequences without stationarity are determined, all the index value sequences without stationarity can be inserted into the non-stationarity variable table.
Alternatively, the arrangement form of the index value sequence of the macro economic indicator and the data value sequence of the target prediction unit stored in the non-stationarity variable table may be as shown in table 2 below.
TABLE 2 non-stationarity VARIABLE METER
Wherein, stored in table 2 are the data value sequences of the target prediction unit y1 having no stationarity in a history period, and the index value sequences of the macro economic indicators x4, x5 and x6 having no stationarity in the corresponding history period. For the understanding of table 2, reference may be made to table 1 above, and the description thereof will not be repeated.
S109, respectively screening a stationarity variable group and a non-stationarity variable group from a stationarity variable table and a non-stationarity variable table according to a predefined variable combination screening rule; the stationarity variable group and the non-stationarity variable group both comprise at least one macroscopic economic index;
wherein, the stationarity variable group and the non-stationarity variable group can be formed by at least one macroscopic economic index. For example, the stationary variable set may be { x1, x2} and the non-stationary variable set may be { x4, x5, x6 }.
Specifically, after all data value sequences with stationarity of the target prediction unit are inserted into the stationarity variable table and all data value sequences without stationarity are inserted into the non-stationarity variable table, all index value sequences with stationarity of each macro economic index are inserted into the stationarity variable and all index value sequences without stationarity are inserted into the non-stationarity variable table, variable screening is respectively carried out on the stationarity variable table and the non-stationarity variable according to a predefined variable combination screening rule, a stationarity variable group is screened from the stationarity variable table, and a non-stationarity variable group is screened from the non-stationarity variable table.
Specifically, in the screening process, the variable combinations can be sorted from top to bottom according to three dimensions including variable coefficients, a model R side and variable significance, two models are selected from the variable combinations, the generalization ability of the two models is compared, one model is determined to be an optimal model, and the other model is determined to be an alternative model.
Specifically, the method can screen the stationarity variable group and the non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively according to the ARIMAX modeling method.
Optionally, the stationarity variable group selected from the stationarity variable table and the non-stationarity variable group selected from the non-stationarity variables may be both stored in the variable combination table of the target prediction unit.
S110, respectively determining the prediction index values of each macro economic index in a stationarity variable group and a non-stationarity variable group in a predefined future time period;
wherein the future period may be a period in which a prediction of a data value of the target prediction unit is required. For example, the future period may include the last day of each quarter in the next year, and when the historical periods include 2020.3.31, 2020.6.30, 2020.9.30, 2020.12.31, 2021.3.31, 2021.6.30, 2021.9.30, and 2021.12.31, the future period may include 2022.3.31, 2022.6.30, 2022.9.30, and 2022.12.31.
Specifically, the method and the device predict the index value of each macro economic index in the screened stationarity variable group and non-stationarity variable group in the future time period respectively, and determine the predicted index value in the future time period. For example, for the macro-economic indicator x1 in the selected stationarity variable group, the method can determine the indicator value x1 in the future time period, namely the predicted indicator value.
Optionally, the present invention may predefine the prediction index value of each macro-economic index in the future time period for different macro-economic scenarios that may occur in the future time period. The method can determine different macro-economic scenes which may appear in the future period through the macro-economic scene generator, wherein the different macro-economic scenes may comprise a benchmark economic scene, a light economic scene, a moderate economic scene and a heavy economic scene. Specifically, the present invention may predict and define the prediction index value of each macro-economic index under different macro-economic situations that may occur in the future time period, respectively, to determine the data value of the target prediction unit under different macro-economic situations that may occur in the future time period.
S111, inputting the prediction index values of the macro economic indexes in the stationary variable group and the non-stationary variable group into a data prediction model matched with a target prediction unit;
it should be noted that, in the data prediction model provided in this embodiment, the data value of the target prediction unit in the future time period may be a dependent variable thereof, and the prediction index value of each macro economic indicator in the stationary variable group and the non-stationary variable group in the future time period may be an independent variable thereof. The data prediction model can determine the data value of the target prediction unit in the future time period based on the prediction index value of each macro economic index in the stationary variable group and the non-stationary variable group in the future time period.
Specifically, after the prediction index values of the macro economic indexes in the stationarity variable group and the non-stationarity variable group are determined, the prediction index values of the macro economic indexes in the stationarity variable group and the non-stationarity variable group can be input into the corresponding data prediction models.
Optionally, in another data processing method provided in this embodiment, the data prediction model is a moving average autoregressive model ARIMAX; in this case, the step S110 may be:
and screening a stationarity variable group and a non-stationarity variable group from a stationarity variable table and a non-stationarity variable table respectively by using a screening rule of ARIMAX on the variable groups.
And S112, obtaining the data value of the target prediction unit output by the data prediction model in the future time period.
Specifically, the data prediction model may output the data value of the target prediction unit in the future time period after obtaining the prediction index value of each macro economic index in the stationary variable group and the non-stationary variable group.
It should be noted that the present invention can realize effective prediction of the data value of the target prediction unit in the future time period through the steps shown in fig. 1.
The data processing method provided by the embodiment can respectively obtain data value sequences of the target prediction unit in a plurality of continuous historical time periods; respectively carrying out stability verification on the data value sequences of the target prediction units in each historical time period, storing the data value sequences of the target prediction units passing the stability verification into a stability variable table, and storing the data value sequences of the target prediction units not passing the stability verification into a non-stability variable table; respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period; respectively carrying out stability verification on the index value sequences of each macro-economic index in each historical time period, storing the index value sequences of the macro-economic indexes passing the stability verification into a stability variable table, and storing the index value sequences of the macro-economic indexes not passing the stability verification into a non-stability variable table; respectively screening a stationarity variable group and a non-stationarity variable group from a stationarity variable table and a non-stationarity variable table according to a predefined variable combination screening rule; the stationarity variable group and the non-stationarity variable group both comprise at least one macroscopic economic index; respectively determining the prediction index values of each macroscopic economic index in the stationary variable group and the non-stationary variable group in a predefined future time period; and inputting the prediction index values of the macroscopic economic indexes in the stationary variable group and the non-stationary variable group into a data prediction model matched with the target prediction unit to obtain the data value of the target prediction unit output by the data prediction model in the future time period. The invention can realize effective prediction of the data value of the target prediction unit in the future time period.
Based on fig. 1, the present embodiment proposes a second data processing method as shown in fig. 2. In the method, the stationarity check includes: at least one of an expanded diky-fowler ADF test and a KPSS test; the method may further comprise the steps of:
s201, determining the data value sequence of the target prediction unit which passes the ADF test and/or the KPSS test as the data value sequence of the target prediction unit which passes the stationarity test;
specifically, the method can adopt two stationarity check modes of ADF check and KPSS check to perform stationarity check on a data value sequence of a target prediction unit in a certain historical time period. If the data value sequence passes through one of the two stationarity check modes, the data value sequence can be proved to pass through stationarity check, and the data value sequence is proved to have stationarity.
S202, determining the index value sequence of the macro economic index passing ADF inspection and/or KPSS inspection as the index value sequence of the macro economic index passing stationarity check;
similarly, when the stability of the index value sequence of the macro economic index in a certain historical period is checked, as long as the index value sequence passes through one of the ADF check mode and the KPSS check mode, the index value sequence can be proved to pass through the stability check, and the index value sequence has stability.
Optionally, in the third data processing method provided in this embodiment, the method may further include the following steps:
s203, determining the data value sequence of the target prediction unit which does not pass the ADF test and the KPSS test as the data value sequence of the target prediction unit which does not pass the stationarity test;
it should be noted that, if a certain data value sequence fails to pass all the smoothness check modes specified, such as the ADF check and the KPSS check, it can be said that the data value sequence fails to pass the smoothness check, and it is said that the data value sequence does not have the smoothness check.
S204, determining the index value sequence of the macro economic index which does not pass the ADF inspection and the KPSS inspection as the index value sequence of the macro economic index which does not pass the stationarity check;
it should be noted that, if a certain index value sequence fails to pass all the stationarity check modes adopted by the specification, it may be said that the index value sequence fails to pass the stationarity check, and it is said that the index value sequence does not have the stationarity check.
Specifically, the stability verification is carried out on the index value sequence and the data value sequence by adopting two stability verification modes of ADF verification and KPSS verification, so that the accuracy of the stability verification can be improved, and the accuracy of the subsequent data value prediction of the target prediction unit is improved.
The data processing method provided by the embodiment adopts two stationarity check modes of ADF check and KPSS check to perform stationarity check on the index value sequence and the data value sequence, so that the accuracy of stationarity check can be improved, and the accuracy of subsequent data value prediction of the target prediction unit is improved.
Based on fig. 1, the present embodiment proposes a fourth data processing method. The method may further comprise:
s301, determining each prediction unit needing data value prediction in the net profit model before preparation as a target prediction unit, and executing the step of obtaining data value sequences of the target prediction units in a plurality of continuous historical time periods so as to determine the data value of each prediction unit in a future time period;
specifically, the present invention may determine each prediction unit involved in the prediction of net profit before preparation in advance, then determine each prediction unit as the target prediction unit, and execute steps S101 to S112 to predict the data value of each prediction unit in the future time period. For example, for the first prediction unit and the second prediction unit, the present invention may determine the first prediction unit as the target prediction unit, perform steps S101 to S112, predict the data value of the first prediction unit in the future period, determine the second prediction unit as the target prediction unit, perform steps S101 to S112, and predict the data value of the second prediction unit in the future period.
S302, predicting the net profit before preparation in the future time period based on the net profit before preparation model and the data values of the prediction units in the future time period.
Specifically, after the data value of each prediction unit in the future time period is obtained, the net profit before the preparation in the future time period can be predicted based on the net profit before the preparation model and the data value of each prediction unit in the future time period.
The data processing method provided by the embodiment can effectively realize the prediction of the net profit before the preparation in the future time period.
It should be noted that the existing pre-preparation net profit model optimization and prediction process may include establishment of a financial index statistical model and data prediction for a commercial bank. However, the net profit model before preparation relates to a large number of models and is closely related to the financial policy, so that the business bank assets, liabilities, profits and extras are covered comprehensively, and the net profit model before preparation is rebuilt regularly around the updating of the financial policy in the future, so that the subsequent workload is large. When the data value of a certain prediction unit is predicted, a worker needs to try to calculate a balance table according to the seasons of the current line, and a series of steps are executed manually, wherein the steps comprise sorting historical data of the prediction unit, performing stability inspection on the historical data of the prediction unit one by one, screening variables from a variable list according to stability inspection results, and completing scene prediction of a single prediction unit by means of a data analysis tool subsequently; if the financial accounting policy is adjusted once, the manual operation needs to be performed repeatedly, and the number of the prediction units related to the net profit model before preparation can be divided into 36, so that the prediction workload of the net profit before preparation is extremely large, and the working period is long. Based on fig. 1, in the fifth data processing method proposed in this embodiment, the prediction of the net profit before preparation may include prediction of net interest income, non-interest income and non-interest expenditure, wherein the basis of the prediction of the net interest income is the corresponding interest bearing assets and the corresponding amount of interest bearing debt. To ensure that a complete balance sheet and profit-and-loss sheet is generated in the corporate capital pressure test and to support the prediction of risk weighted assets, the prediction of net profit before preparation may include:
(1) forecasting the assets and liabilities item: including an interest asset, a non-interest asset, an interest liability, a non-interest liability;
(2) predicting the profit and loss items: including net interest income predicted based on the interest assets, interest liabilities, and non-interest income, non-interest expenditure, etc.
(3) Off-table credit assets: including out-of-list credit commitments.
(4) And calculating the net profit before preparation on the basis of the assets and liabilities, the profit and loss and the out-of-form.
Specifically, through research by the inventor of the technical scheme, a set of comprehensive metering and expert judgment methodology can be constructed according to a pre-preparation net profit model, the fact that the number of related financial data exceeds 30 is ensured (according to the central limit theorem), and a prediction unit is designed according to the importance and proportion of finance (analysis of financial data is the basis for determining the prediction unit related to the pre-preparation net profit and is also the basis for primarily judging a prediction mode). And selecting a modeling method according to the historical data of the prediction unit, respectively comparing the advantages and disadvantages of different modeling methods, selecting an ARIMAX method as the modeling method, and confirming the standards and methods of data inspection and model evaluation in the model. And a macroscopic factor (i.e. macroscopic economic index) list is selected by fully combining the service scenes. And sequentially confirming the macroscopic factor combinations corresponding to the prediction units according to the performance of the macroscopic factor combinations. And obtaining the scene variable of the future macroscopic factor by using the macroscopic scene generator. And splicing the variable combination and the macroscopic factor situation to realize different situation predictions of net profit model results before preparation.
In the fifth data processing method, data collection may be performed in advance.
Specifically, the invention collects the full financial statements within the modeling date range according to the modeling start date and end date. In the following table 3, the first column is a prediction unit, the second-level subject of the financial statement corresponding to the first column is counted according to the relationship between the date and the subject, and the scale value of the prediction unit in each report period in the modeling date range is counted. Taking a unit fixed property loan as an example, the secondary subjects of the corresponding financial statements are 1217, 1417, 1517.
TABLE 3
| Prediction unit | Secondary subject code | Name of second degree subject |
| Unit fixed property loan | 1217 | Unit fixed property loan |
| Unit fixed property loan | 1417 | Fixed property loan of overdue unit |
| Unit fixed property loan | 1517 | Non-accrual unit fixed property loan |
Then, the invention can derive the historical data of the macroscopic factor from the system operation platform, and process various forms of the macroscopic variable, including various forms of equal ratio, ring ratio, difference, lag, advance and the like. (batch download and match data for the above macro factors and prediction units).
The method can also rely on a data warehouse of a bank enterprise to obtain financial data and macroscopic factor data according to business rules, import two tables of financial data and forecasting unit and subject relationship, divide all forecasting units into four categories of assets, liabilities, owner rights and interests and the outside of the tables, read the forecasting units and the subject relationship tables, respectively poll and access, match the relationship between the financial data and the forecasting units one by one to obtain historical values of the forecasting units, and arrange the historical data of the forecasting units after polling is finished. The invention can process the variable conversion of the prediction unit and generate variables of the prediction unit in various forms such as same ratio, ring ratio, difference and the like besides the scale.
Then, the invention can simultaneously test the stationarity of the fixed property loan of the prediction unit, and the specific test method can comprise ADF unit root test and KPSS test; establishing a model combination of a stationarity prediction unit and a stationarity macroscopic factor; establishing a model combination of an instability prediction unit and an instability macroscopic factor; screening out a model of a prediction unit by using an ARIMAX model in an SAS tool according to a preset automatic screening rule; introducing future expected macro variables, wherein the future prediction range is from the third quarter of 2022 to the second quarter of 2023, and the designed scenes comprise three basic, light, moderate and severe scenes and four scenes; inputting the value of the variable X and the model parameter into the model to obtain a prediction result of the prediction unit; according to the classification of the prediction unit, the following results are obtained:
the net profit before provisioning is interest income (interest assets) earning rate) -interest expenditure (interest liabilities earning rate) + non-interest income (commission + out-of-balance credit commitment rate) -non-interest expenditure (profit-loss class expenditure).
It should be noted that, the invention can automatically screen variable combinations according to preset threshold values, can also construct a prediction unit and a meeting and accounting purpose relation component, can flexibly realize data processing of the prediction unit, can flexibly adjust according to financial and accounting criteria at any time, improves working efficiency and saves human resources.
The data processing method provided by the embodiment can effectively improve the working efficiency of predicting the net profit before the preparation and save the consumption of manpower resources.
Corresponding to the method shown in fig. 1, the present embodiment proposes a data processing apparatus as shown in fig. 3. The apparatus may include: a first obtaining unit 101, a first verifying unit 102, a first holding unit 103, a second holding unit 104, a second obtaining unit 105, a second verifying unit 106, a third holding unit 107, a fourth holding unit 108, a first filtering unit 109, a first determining unit 110, a first input unit 111, and a third obtaining unit 112; wherein:
a first obtaining unit 101 for respectively obtaining data value sequences of the target prediction unit in a plurality of consecutive history periods;
the first checking unit 102 is used for respectively performing stationarity checking on data value sequences of the target prediction unit in each historical time period;
the first saving unit 103 is used for saving the data value sequences of the target prediction units which pass through the stationarity check into a stationarity variable table;
the second storage unit 104 is used for storing the data value sequences of the target prediction units which do not pass stationarity check into the non-stationarity variable table;
a second obtaining unit 105, configured to obtain index value sequences of a plurality of macro economic indicators in each history period;
the second checking unit 106 is used for respectively performing stationarity checking on the index value sequences of each macro economic index in each historical time period;
a third saving unit 107, configured to save all the index value sequences of the macro economic indicators that pass through stationarity check into a stationarity variable table;
a fourth storing unit 108, configured to store all the index value sequences of the macro economic indicators that do not pass stability verification into the non-stability variable table;
the first screening unit 109 is configured to screen a stationarity variable group and a non-stationarity variable group from a stationarity variable table and a non-stationarity variable table respectively according to a predefined variable combination screening rule; the stationarity variable group and the non-stationarity variable group both comprise at least one macroscopic economic index;
the first determining unit 110 is configured to determine prediction index values of macro economic indicators in a predefined future time period in a stationary variable group and a non-stationary variable group respectively;
the first input unit 111 is used for inputting the prediction index values of the macro economic indexes in the stationarity variable group and the non-stationarity variable group into a data prediction model matched with the target prediction unit;
a third obtaining unit 112, configured to obtain a data value of the target prediction unit output by the data prediction model in a future time period.
It should be noted that specific processing procedures of the first obtaining unit 101, the first verifying unit 102, the first saving unit 103, the second saving unit 104, the second obtaining unit 105, the second verifying unit 106, the third saving unit 107, the fourth saving unit 108, the first screening unit 109, the first determining unit 110, the first input unit 111, and the third obtaining unit 112 and technical effects brought by the specific processing procedures can refer to steps S101, S102, S103, S104, S105, S106, S107, S108, S109, S110, S111, and S112 in fig. 1, respectively, and details are not repeated here.
The data processing apparatus proposed in this embodiment can obtain data value sequences of the target prediction unit in a plurality of consecutive history periods, respectively; respectively carrying out stability verification on the data value sequences of the target prediction units in each historical time period, storing the data value sequences of the target prediction units passing the stability verification into a stability variable table, and storing the data value sequences of the target prediction units not passing the stability verification into a non-stability variable table; respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period; respectively carrying out stability verification on the index value sequences of each macro-economic index in each historical time period, storing the index value sequences of the macro-economic indexes passing the stability verification into a stability variable table, and storing the index value sequences of the macro-economic indexes not passing the stability verification into a non-stability variable table; respectively screening a stationarity variable group and a non-stationarity variable group from a stationarity variable table and a non-stationarity variable table according to a predefined variable combination screening rule; the stationarity variable group and the non-stationarity variable group both comprise at least one macroscopic economic index; respectively determining the prediction index values of each macroscopic economic index in the stationary variable group and the non-stationary variable group in a predefined future time period; and inputting the prediction index values of the macroscopic economic indexes in the stationary variable group and the non-stationary variable group into a data prediction model matched with the target prediction unit to obtain the data value of the target prediction unit output by the data prediction model in the future time period. The invention can realize effective prediction of the data value of the target prediction unit in the future time period.
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 phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A data processing method, comprising:
respectively obtaining data value sequences of a target prediction unit in a plurality of continuous historical periods;
respectively carrying out stationarity check on the data value sequences of the target prediction unit in each historical time period, storing the data value sequences of the target prediction unit passing stationarity check into a stationarity variable table, and storing the data value sequences of the target prediction unit not passing stationarity check into a non-stationarity variable table;
respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period;
respectively carrying out stationarity check on an index value sequence of each macro-economic index in each historical time period, storing the index value sequences of the macro-economic indexes passing stationarity check into the stationarity variable table, and storing the index value sequences of the macro-economic indexes not passing stationarity check into the non-stationarity variable table;
respectively screening a stationarity variable group and a non-stationarity variable group from the stationarity variable table and the non-stationarity variable table according to a predefined variable combination screening rule; the stationary variable set and the non-stationary variable set each comprise at least one of the macro economic indicators;
respectively determining the predicted index values of each macro economic index in the stationary variable group and the non-stationary variable group in a predefined future time period;
and inputting the prediction index value of each macro economic index in the stationarity variable group and the non-stationarity variable group into a data prediction model matched with the target prediction unit, and obtaining the data value of the target prediction unit in the future time period output by the data prediction model.
2. The data processing method of claim 1, wherein the historical period comprises a last day in each quarter of two adjacent years.
3. The data processing method of claim 1, wherein the data prediction model is a moving average autoregressive model, ARIMAX; the selecting a stationarity variable group and a non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively according to a predefined variable combination selecting rule comprises:
and screening the stationarity variable group and the non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively by using the screening rule of the ARIMAX on the variable groups.
4. The data processing method of claim 1, wherein the stationarity check comprises: at least one of an expanded diky-fowler ADF test and a KPSS test; the method further comprises the following steps:
determining the data value sequence of the target prediction unit passing the ADF test and/or the KPSS test as the data value sequence of the target prediction unit passing the stationarity check;
determining the index value sequence of the macro-economic indicator passing the ADF inspection and/or the KPSS inspection as the index value sequence of the macro-economic indicator passing stationarity check.
5. The data processing method of any of claims 1 to 4, wherein the method further comprises:
respectively determining each prediction unit needing data value prediction in the net profit model before preparation as the target prediction unit, and executing the step of respectively obtaining data value sequences of the target prediction units in a plurality of continuous historical time periods so as to determine the data value of each prediction unit in the future time period;
and predicting the net profit before preparation in the future time period based on the net profit before preparation model and the data value of each prediction unit in the future time period.
6. A data processing apparatus, comprising: the device comprises a first obtaining unit, a first checking unit, a first storage unit, a second obtaining unit, a second checking unit, a third storage unit, a fourth storage unit, a first screening unit, a first determining unit, a first input unit and a third obtaining unit; wherein:
the first obtaining unit is used for respectively obtaining data value sequences of the target prediction unit in a plurality of continuous historical periods;
the first checking unit is used for respectively carrying out stationarity checking on the data value sequences of the target prediction unit in each historical time interval;
the first storage unit is used for storing the data value sequences of the target prediction unit which pass through stationarity check into a stationarity variable table;
the second storage unit is used for storing the data value sequences of the target prediction unit which do not pass stationarity check into a non-stationarity variable table;
the second obtaining unit is used for respectively obtaining index value sequences of a plurality of macro economic indexes in each historical time period;
the second checking unit is used for respectively performing stationarity checking on the index value sequence of each macro economic index in each historical time period;
the third saving unit is configured to save the index value sequences of the macro economic indicators that pass stationarity check into the stationarity variable table;
the fourth saving unit is configured to save the index value sequences of the macro economic indicators that do not pass stationarity check into the non-stationarity variable table;
the first screening unit is used for screening a stationarity variable group and a non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively according to a predefined variable combination screening rule; the stationary variable set and the non-stationary variable set each comprise at least one of the macro economic indicators;
the first determining unit is used for respectively determining the predicted index values of each macro economic index in the stationary variable group and the non-stationary variable group in a predefined future time period;
the first input unit is used for inputting the prediction index value of each macroscopic economic index in the stationarity variable group and the non-stationarity variable group into a data prediction model matched with the target prediction unit;
the third obtaining unit is configured to obtain a data value of the target prediction unit output by the data prediction model in the future time period.
7. The data processing apparatus of claim 6, wherein the historical period comprises a last day in quarters of two adjacent years.
8. The data processing apparatus according to claim 6, wherein the data prediction model is a moving average autoregressive model ARIMAX;
the first screening unit is used for screening the stationarity variable group and the non-stationarity variable group from the stationarity variable table and the non-stationarity variable table respectively by using the screening rule of the ARIMAX on the variable group.
9. The data processing apparatus of claim 6, wherein the stationarity check comprises: at least one of an expanded diky-fowler ADF test and a KPSS test; the device further comprises: a second determination unit and a third determination unit;
the second determining unit is configured to determine the data value sequence of the target prediction unit that passes the ADF check and/or the KPSS check as the data value sequence of the target prediction unit that passes the stationarity check;
the third determining unit is configured to determine the index value sequence of the macro economic indicator passing through the ADF inspection and/or the KPSS inspection as the index value sequence of the macro economic indicator passing through stationarity check.
10. A data processing apparatus according to any one of claims 6 to 9, characterized in that the apparatus further comprises: a triggering unit and a prediction unit;
the triggering unit is used for respectively determining each prediction unit needing data value prediction in a net profit model before preparation as the target prediction unit and triggering the first obtaining unit to determine the data value of each prediction unit in the future time period;
and the prediction unit is used for predicting the net profit before preparation in the future time period based on the net profit before preparation model and the data value of each prediction unit in the future time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210116202.7A CN114418450A (en) | 2022-02-07 | 2022-02-07 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210116202.7A CN114418450A (en) | 2022-02-07 | 2022-02-07 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114418450A true CN114418450A (en) | 2022-04-29 |
Family
ID=81278813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210116202.7A Pending CN114418450A (en) | 2022-02-07 | 2022-02-07 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114418450A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115097376A (en) * | 2022-08-24 | 2022-09-23 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Processing method and device for check data of metering equipment and computer equipment |
-
2022
- 2022-02-07 CN CN202210116202.7A patent/CN114418450A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115097376A (en) * | 2022-08-24 | 2022-09-23 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Processing method and device for check data of metering equipment and computer equipment |
| CN115097376B (en) * | 2022-08-24 | 2022-11-01 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Processing method and device for check data of metering equipment and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| WO2003096237A2 (en) | Electronic data processing system and method of using an electronic data processing system for automatically determining a risk indicator value | |
| CN104766144A (en) | Order forecasting method and system | |
| CN116205355B (en) | Power load prediction method, device and storage medium | |
| CN109711424B (en) | Behavior rule acquisition method, device and equipment based on decision tree | |
| Marcelo et al. | An alternative approach to project selection: the infrastructure prioritization framework | |
| Marcelo et al. | Prioritizing infrastructure investment: a framework for government decision making | |
| CN106295351B (en) | A kind of Risk Identification Method and device | |
| CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
| CN114118691A (en) | Scheduling scheme processing method, device, equipment and medium based on traffic | |
| CN111415027A (en) | Method and device for constructing component prediction model | |
| CN114418450A (en) | Data processing method and device | |
| CN110544052A (en) | method and device for displaying relationship network diagram | |
| CN114004691A (en) | Line scoring method, device, equipment and storage medium based on fusion algorithm | |
| CN116977091A (en) | Method and device for determining individual investment portfolio, electronic equipment and readable storage medium | |
| CN111091410B (en) | Node embedding and user behavior characteristic combined net point sales prediction method | |
| CN113379211A (en) | Block chain-based logistics information platform default risk management and control system and method | |
| CN112418600A (en) | Enterprise policy scoring method and system based on index set | |
| Iwasaki et al. | A search model with subjective judgments: Auditing of incorrect tax declarations | |
| CN112308404B (en) | Project risk management method and device, electronic equipment and storage medium | |
| EP3646259A1 (en) | A computer implemented appraisal system and method thereof | |
| Rego et al. | A decision support system for municipal budget plan decisions | |
| CN116596661A (en) | Credit data-based enterprise credit assessment method, device, equipment and medium | |
| CN114398757A (en) | Power transformation overhaul efficiency optimization method based on big data analysis | |
| CN116993160A (en) | Charging pile management risk assessment method and device, storage medium and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |