CN110648045A - Risk assessment method, electronic device and computer-readable storage medium - Google Patents
Risk assessment method, electronic device and computer-readable storage medium Download PDFInfo
- Publication number
- CN110648045A CN110648045A CN201910752041.9A CN201910752041A CN110648045A CN 110648045 A CN110648045 A CN 110648045A CN 201910752041 A CN201910752041 A CN 201910752041A CN 110648045 A CN110648045 A CN 110648045A
- Authority
- CN
- China
- Prior art keywords
- preset
- index
- evaluated
- target
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012502 risk assessment Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to data processing and discloses a risk assessment method, which comprises the following steps: acquiring a historical value of a characteristic index of a target to be evaluated in a first preset time; analyzing the index type corresponding to the characteristic index, selecting a corresponding prediction rule to predict the predicted value of the characteristic index in second preset time, and calculating the predicted value of the target to be evaluated in the second preset time; and calculating the deviation degree of the predicted value and the planned value of the target to be evaluated, and inquiring and determining the corresponding risk level of the target to be evaluated according to the deviation degree. The invention also discloses an electronic device and a computer readable storage medium. By using the method and the device, the efficiency and the accuracy of risk condition evaluation of the target to be evaluated can be improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a risk assessment method, an electronic device, and a computer-readable storage medium.
Background
With the continuous development of market economy, the competition of enterprises is more and more intense, and the market risk is more and more difficult to control. For example, financial enterprises have a large number of new businesses, and how to evaluate the risk condition of each new business in the future is very important for the daily operation management of the financial enterprises.
At present, the risk assessment work of enterprises on the operation condition is usually carried out manually, and a unified quantitative standard does not exist, so that the accuracy of the obtained assessment result is difficult to guarantee, and therefore, how to improve the efficiency and the accuracy of the enterprise operation risk assessment becomes a problem to be solved urgently.
Disclosure of Invention
In view of the above, the present invention provides a risk assessment method, an electronic device and a computer-readable storage medium, which mainly aims to improve the efficiency and accuracy of risk assessment of a target to be assessed.
In order to achieve the above object, the present invention provides a risk assessment method, suitable for an electronic device, the method comprising:
an acquisition step: acquiring a historical value of a characteristic index of a target to be evaluated in a first preset time, a planned value of the target to be evaluated in a second preset time, preset classification rules, prediction rules corresponding to all preset index types and preset matching rules corresponding to all preset risk levels;
analyzing the index types corresponding to the characteristic indexes according to preset classification rules, predicting the predicted values of the characteristic indexes within second preset time according to the prediction rules corresponding to the preset index types, and calculating the predicted values of the target to be evaluated within the second preset time;
calculating the deviation degree of the predicted value and the planned value according to the planned value and the predicted value of the target to be evaluated within a second preset time, and inquiring the preset risk level matched with the target to be evaluated according to the preset matching rule corresponding to each preset risk level and the deviation degree; and
and determining, namely taking the inquired preset risk level matched with the target to be evaluated as the corresponding risk level of the target to be evaluated.
Preferably, the index types include a first index, a second index, a third index and a fourth index, and the classifying the preset indexes according to preset classification rules includes:
generating historical time sequence data of the characteristic indexes according to historical values of the characteristic indexes within first preset time;
when the historical time sequence data of the characteristic indexes meet a preset first classification condition, determining the characteristic indexes as first class indexes;
when the historical time sequence data of the characteristic indexes meet a preset second classification condition, determining the characteristic indexes as second class indexes;
when the historical time sequence data of the characteristic indexes meet a preset third classification condition, determining the characteristic indexes as third class indexes; and
and when the historical time sequence data of the characteristic indexes meet a preset fourth classification condition, determining the characteristic indexes to be fourth-class indexes.
Preferably, the predicting the predicted value of the feature indicator in the second preset time according to the prediction rule corresponding to each preset indicator type includes:
when the characteristic index is a first-class index, predicting a predicted value of the characteristic index within second preset time by using a preset first prediction rule corresponding to the first-class index;
when the characteristic index is a second-class index, predicting the predicted value of the preset index in a second preset time by using a preset second prediction rule corresponding to the second-class index;
when the characteristic index is a third type index, predicting the predicted value of the characteristic index in second preset time by using a preset third prediction rule corresponding to the third type index; and
and when the characteristic index is a fourth type index, predicting the predicted value of the characteristic index in second preset time by using a preset fourth prediction rule corresponding to the fourth type index.
Preferably, the preset risk levels include a first risk level, a second risk level and a third risk level;
the first risk level matching rule comprises: judging whether the deviation degree meets a preset first matching condition, if so, determining that the target to be evaluated is matched with a first risk level;
the matching rules of the second risk level include: judging whether the deviation degree meets a preset second matching condition, if so, determining that the second risk level of the target to be evaluated is matched; and
the matching rules of the third risk level include: and judging whether the deviation degree meets a preset third matching condition, if so, determining that the target to be evaluated is matched with a third risk level.
Preferably, after the determining step, the method further comprises:
early warning step: and generating early warning information corresponding to the risk grade based on the risk grade corresponding to the target to be evaluated, and feeding back the early warning information to a preset terminal.
In addition, to achieve the above object, the present invention also provides an electronic device, including: the risk assessment system comprises a memory and a processor, wherein a risk assessment program which can run on the processor is stored in the memory, and when the risk assessment program is executed by the processor, any step in the risk assessment method can be realized.
In addition, to achieve the above object, the present invention further provides a computer-readable storage medium, which includes a risk assessment program, and when the risk assessment program is executed by a processor, the risk assessment program can implement any of the steps in the risk assessment method as described above.
The risk assessment method, the electronic device and the computer readable storage medium provided by the invention classify the characteristic indexes of the target to be assessed, and respectively predict the predicted value of each characteristic index by a prediction method corresponding to the index type in short time so as to obtain the predicted value of the target to be assessed; and automatically determining the risk level corresponding to the target to be evaluated by matching the deviation degree of the predicted value and the planned value of the target to be evaluated with each preset risk level. Compared with the prior art, on one hand, the method realizes automation of risk assessment, reduces consumption of human resources, and improves assessment efficiency, on the other hand, due to the fact that different prediction methods are adopted for different types of characteristic indexes, accuracy of prediction of the target to be assessed is improved, and a unified preset matching rule is combined to serve as an assessment standard, and therefore accuracy of assessment results is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an embodiment of a risk assessment method according to the present invention;
FIG. 2 is a diagram of an electronic device according to an embodiment of the invention;
FIG. 3 is a block diagram of the risk assessment routine of FIG. 2.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a risk assessment method. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
Referring to fig. 1, fig. 1 is a flowchart of a risk assessment method according to an embodiment of the present invention.
In this embodiment, the method includes: step S1-step S4.
Step S1, obtaining a historical value of a characteristic index of a target to be evaluated within a first preset time, a planned value of the target to be evaluated within a second preset time, a preset classification rule, a prediction rule corresponding to each preset index type, and a preset matching rule corresponding to each preset risk level.
In this embodiment, the target to be evaluated is the value of a new business of a certain company. Taking an insurance company as an example, NBEV (New Business Embedded Value, Value created by a certain dangerous New sale Business) is a measure for better evaluating New Business Value, and the NBEV comprehensively reflects various factors influencing the New Business Value, so the NBEV is taken as a target to be evaluated. When the target to be evaluated is NBEV, the characteristic indicators of the target to be evaluated include: monthly labor, risk category activity, event uniform and uniform pieces FYP (First Year Premium).
The characteristic indexes corresponding to the targets to be evaluated, the plan values of the targets to be evaluated within the second preset time, the preset classification rules, the prediction rules corresponding to the types of the preset indexes and the preset matching rules corresponding to the preset risk levels are all preset and stored in a specified storage path.
Step S2, analyzing the index types corresponding to the feature indexes according to preset classification rules, predicting the predicted values of the feature indexes within a second preset time according to the prediction rules corresponding to the preset index types, and calculating the predicted values of the target to be evaluated within the second preset time.
The index types include: the first type index, the second type index, the third type index and the fourth type index.
The preset classification rule includes: a1-a 5.
a1, generating historical time series data of the characteristic index according to the historical value of the characteristic index in a first preset time.
For example, the first preset time is from 2012 to 2018 to 12 months. In the process of generating the historical time series data, in order to ensure the integrity of the time series data, missing values and abnormal values of the historical time series data are also required to be filled, and the missing values and the abnormal values are generally supplemented according to a mean () of a preset time window (for example, within 6 months before and after).
a2, when the historical time sequence data of the characteristic index meets the preset first classification condition, determining the characteristic index as a first class index.
The first classification condition includes: the historical time series data of the characteristic index satisfies the stability assumption. And calculating data capable of measuring the stability of the time sequence data. For example, the standard deviation, the covariance, the coefficient of variation, etc. when the standard deviation, the covariance, and the coefficient of variation are all within the corresponding preset intervals, the time series data is considered to satisfy the stability assumption.
a3, when the historical time sequence data of the characteristic indexes meet a preset second classification condition, determining the characteristic indexes as second-class indexes;
the second classification condition includes: the historical time sequence data of the characteristic indexes do not meet the stability hypothesis, and the historical time sequence data of the N sub-characteristic indexes corresponding to the characteristic indexes meet the stability hypothesis, wherein N is larger than or equal to 2 and is a natural number. Manpower y working in the month1This characteristic index is, for example, N-4 and y-y1+y2+y3+y4Wherein, y1Does not satisfy the stability assumption, but y, y2、y3、y4The historical timing data of (a) all satisfy the stability assumption.
In other embodiments, the second classification condition includes: the historical time sequence data of the characteristic index does not meet the stability hypothesis, the historical time sequence data of the weight corresponding to the N-1 sub-characteristic indexes of the characteristic index meets the stability hypothesis, and the historical time sequence data of the 1 sub-characteristic index of the characteristic index meets the stability hypothesis. Likewise, the manpower y is in the month1This characteristic index is given as an example, y1、y2、y3、y4The weight ratio at y is respectively omega1、ω2、ω3、ω4And ω is1+ω2+ω3+ω41, wherein ω1、ω2、ω3Satisfies the stability assumption, and y1、y2、y3Any one of the characteristic indexes meets the stability hypothesis.
a4, when the historical time sequence data of the characteristic index meets the preset third classification condition, determining the characteristic index as a third class index.
The third classification condition includes: the historical time series data of the characteristic index has large fluctuation and periodicity. Whether the fluctuation rate is within a preset interval or not is judged by calculating the fluctuation rate or GARCH (1, 1) of historical time sequence data, and the data have obvious periodicity. Among them, the obvious periodicity can be exemplified by: for example, four months of 1, 4, 7, 10 of 12 months of the year have poor performance, four months of 2, 5, 8, 11 have relatively good performance, and four months of 3, 6, 9, 12 have good performance.
a5, when the historical time sequence data of the characteristic index meets the preset fourth classification condition, determining the characteristic index as a fourth type index.
The fourth classification condition includes: the historical time sequence data of the characteristic index does not meet the preset stability hypothesis, but the rolling mean value and the standard deviation in the historical time sequence data of the characteristic index within the preset time interval meet the preset adjustment triggering condition. The trigger conditions include: the absolute value of the ratio of the rolling mean to the standard deviation over a preset time interval (e.g., 12 months prior to the current data point, which may be adjusted according to the data period) is greater than a preset threshold (e.g., 2).
The predicting the predicted value of the characteristic index within the second preset time according to the prediction rule corresponding to each preset index type includes: b1-b 4.
b1, when the characteristic index is the first type index, predicting the predicted value of the characteristic index in a second preset time by using a preset first prediction rule corresponding to the first type index.
The first prediction rule includes: obtaining a plurality of alternative models corresponding to each first-class index and parameters corresponding to the alternative models by adopting an auto-arima model based on historical time sequence data of each first-class index, and respectively selecting the alternative model corresponding to the minimum AICC value as a prediction model corresponding to each first-class index according to the AICC value in the parameters; and inputting the historical time sequence data of the first-class indexes into a corresponding prediction model to obtain the predicted value of each first-class index in second preset time.
In order to ensure the accuracy of model prediction, data of the characteristic indexes in the past 2 months are retested by using the determined prediction model, the deviation of the prediction model is calculated according to the predicted values and the actual values of the characteristic indexes in the past two months, whether the deviation of the model is within a preset range (for example, 10%) is judged, if yes, the model is determined to be the final prediction model, and the final model is used for prediction.
It should be noted that, for the case that the model deviation exceeds the preset range (for example, 10%), the d-order difference operation is performed on the historical time series data of the current characteristic index to obtain a stationary time series, and the autocorrelation coefficient ACF and the partial autocorrelation coefficient PACF of the stationary time series are respectively obtained, and the optimal level p and the optimal order q are obtained by analyzing the autocorrelation chart and the partial autocorrelation chart; based on the determined d, q, p, a model ARIMA (p, d, q) is generated and a model check is performed on the resulting model.
b2, when the characteristic index is the second-class index, predicting the predicted value of the preset index in a second preset time by using a preset second prediction rule corresponding to the second-class index.
The second prediction rule includes:
firstly, determining N sub-characteristic indexes corresponding to the second-class indexes and an operation relation between the N sub-characteristic indexes and the second-class indexes. For example: the index y is defined by1、y2、y3、y4The calculation relationship is as follows: y is1＝y-y2-y3-y4。
And then, respectively acquiring historical time series data corresponding to the N sub-characteristic indexes, and respectively predicting the predicted values of the N sub-characteristic indexes in second preset time by using the first prediction rule. Predicting y, y separately1、y3And y4The prediction value and the prediction method are the same as the first prediction rule, and are not described herein again.
And finally, calculating the predicted value of the second type of index in second preset time based on the operation relation and the predicted values of the N sub-characteristic indexes. Wherein:
y1 prediction＝yPrediction-y2 prediction-y3 prediction-y4 prediction。
In another embodiment, the second prediction rule includes:
firstly, determining N sub-characteristic indexes corresponding to the second-class indexes and an operation relation between the N sub-characteristic indexes and the second-class indexes. For example: the index y is defined by1、y2、y3、y4The calculation relationship is as follows: y is1＝y-y2-y3-y4。
Then, historical time series data of the weight of the N-1 sub-feature indexes occupying another sub-feature index are respectively obtained, the predicted values of the weight of the N-1 sub-feature indexes occupying another sub-feature index in a second preset time are respectively predicted by utilizing the first prediction rule, and then the predicted values of the weight of the second type of indexes occupying another sub-feature index in the second preset time are obtained through calculation. E.g. y1、y2、y3、y4The weight ratio at y is respectively omega1、ω2、ω3、ω4And ω is1+ω2+ω3+ω41. Separately predict omega2、ω3、ω4The prediction method of the predicted value in the second preset time is the same as the first prediction rule, and is not described herein. Omega is obtained by calculation1And predicting the value within a second preset time. Wherein:
ω1 prediction＝1-ω2 prediction-ω3 prediction-ω4 prediction。
Then, predicting the predicted value of the sub-characteristic index in second preset time according to the sub-characteristic index meeting the stability hypothesis and a first prediction rule; for example, the sub-feature index satisfying the stability assumption may be y, y2、y3、y4Any one of them.
And finally, calculating the predicted value of the second type of index in the second preset time according to the predicted value of the sub-characteristic index in the second preset time and the weight predicted value corresponding to the second type of index. When the sub-feature index satisfying the stability assumption is y2、y3、y4First get y of any one of2、y3、y4And calculating the corresponding predicted value according to the predicted value of the weight to obtain the predicted value of y. And according to the predicted value of y and omega1Calculating the predicted value of y1The predicted value of (2).
b3, when the characteristic index is a third-class index, predicting the predicted value of the characteristic index in a second preset time by using a preset third prediction rule corresponding to the third-class index.
The third prediction rule includes:
firstly, according to the periodic characteristics of the third-class index, the historical time sequence data of the third-class index are split, and a plurality of sub-time sequence data corresponding to the third-class index are obtained. For example, by dividing the performance of 12 months per year according to the periodic rules of the business, the performance is divided into three groups of data with small performance fluctuation. Suppose there has been historical data from 2012-2018 for each month FYP. The data are divided by the method to respectively obtain three groups of data: 1. 4, 7, 10 (2012-; 2. 5, 8, 11(2012 and 2018); 3. 6, 9, 12(2012 and 2018).
And then, selecting the sub-time sequence data corresponding to the prediction time point, and predicting the predicted value of the third type index in the second time according to the selected sub-time sequence data and the first prediction rule. For example, when predicting the FYP prediction value of 1(4, 7, 10) month in 2019, selecting the group of data 1, 4, 7, 10(2012-2018) for prediction; when predicting the FYP prediction value of 2(5, 8, 11) months in 2019, selecting the group of data of 2, 5, 8, 11(2012-2018) for prediction; when predicting the FYP prediction value of 3(6, 9, 12) months in 2019, the data of 3, 6, 9, 12(2012-2018) are selected for prediction.
b4, when the characteristic index is a fourth type index, predicting the predicted value of the characteristic index in a second preset time by using a preset fourth prediction rule corresponding to the fourth type index.
The fourth prediction rule includes:
firstly, data points meeting triggering conditions in the historical time sequence data of the fourth type of indexes are determined. Assume that the setpoint determined in the historical timing data are 2016-07 and 2017-06.
And then, calculating the adjustment coefficient of each determined data point, and zooming the data before each data point according to the adjustment coefficient to obtain the adjusted historical time sequence data.
Taking 2016-07 as an example, the calculation formula of the adjustment coefficient a corresponding to the data point is as follows:
a＝ma_12(2017-06)/ma_12(2016-06)
wherein, ma _12(2017-06) represents the mean value of the index in 12 months before 6 months in 2017 (including 6 months in 2017), and ma _12(2016-06) represents the mean value of the index in 12 months before 6 months in 2016 (including 2016 6 months in 2016).
Based on the calculated adjustment factor a, data points before 2016 month 7 were scaled, i.e., the historical values were multiplied by the adjustment factor a.
Taking 2017-06 as an example, the calculation formula of the adjustment coefficient b corresponding to the data point is as follows:
b＝ma_12(2018-05)/ma_12(2017-05)
wherein, ma _12(2018-05) represents the mean value of the index in 12 months before 2018 month 5 (including 2018 month 5), and ma _12(2017-05) represents the mean value of the index in 12 months before 2017 month 5 (including 2017 month 5).
Based on the calculated adjustment factor b, the data points 6 months ago 2017 are scaled, i.e., the historical values (or adjusted adjustment values) are multiplied by the adjustment factor b.
It will be appreciated that the data points in the middle of 2016 and 7-2017 and 6-month are scaled by b only once, and that the data points prior to 2016 and 7-month are scaled by a b factor by two. With the two scaling operations, the stability assumption is more consistent for the entire historical timing data.
And finally, predicting the predicted value of the fourth type of index within second preset time according to the adjusted historical time sequence data and the first prediction rule.
In the practical application process, after the historical time sequence data is processed, the degree of deviation of prediction can be effectively reduced.
After the predicted values of the characteristic indexes of the target to be evaluated in the second preset time are obtained through the steps, the predicted values of the target to be evaluated in the second preset time are calculated based on the relation between the characteristic indexes and the target to be evaluated.
Taking NBEV as an example, the calculation relationship between the target to be evaluated and each feature index is as follows:
NBEV (month on-duty manpower) dangerous seed activity rate activity person average piece FYP Margin
Wherein, Margin is a constant coefficient corresponding to a certain dangerous species within a certain time.
Therefore, the formula for calculating the predicted value of NBEV to be evaluated in the second preset time is as follows:
NBEVpredictionRate of dangerous seed activityPredictionMovable human body uniform partsPredictionAll the pieces FYPPrediction*Margin
Step S3, calculating the deviation degree of the predicted value and the planned value according to the planned value and the predicted value of the target to be evaluated within a second preset time, and inquiring the preset risk level matched with the target to be evaluated according to the preset matching rule corresponding to each preset risk level and the deviation degree.
The calculation formula of the deviation epsilon is as follows:
ε＝(P-Q)/Q
wherein, P is the corresponding predicted value of the target to be evaluated, and Q is the corresponding plan value of the target to be evaluated.
The preset risk levels include a first risk level, a second risk level and a third risk level.
The matching rule of the first risk level includes: and judging whether the deviation degree meets a preset first matching condition, if so, determining that the target to be evaluated is matched with a first risk level. For example, the first matching condition may be configured to: the degree of deviation is within the first interval (-1, -0.5).
The matching rule of the second risk level includes: and judging whether the deviation degree meets a preset second matching condition, and if so, determining that the second risk level of the target to be evaluated is matched. For example, the second matching condition may be configured to: the degree of deviation is within the second interval (-0.5, 0).
The matching rule of the third risk level includes: and judging whether the deviation degree meets a preset third matching condition, if so, determining that the target to be evaluated is matched with a third risk level. For example, the third matching condition may be configured to: the degree of deviation is within the third interval [0, + ∞).
And step S4, taking the inquired preset risk level matched with the target to be evaluated as the corresponding risk level of the target to be evaluated.
In the embodiment, the characteristic indexes of the target to be evaluated are classified, and the prediction values of the characteristic indexes are respectively predicted by using a prediction method corresponding to the index type in short time, so that the prediction values of the target to be evaluated are obtained; and automatically determining the risk level corresponding to the target to be evaluated by matching the deviation degree of the predicted value and the planned value of the target to be evaluated with each preset risk level. Compared with the prior art, on one hand, the method realizes automation of risk assessment, reduces consumption of human resources, and improves assessment efficiency, on the other hand, due to the fact that different prediction methods are adopted for different types of characteristic indexes, accuracy of prediction of the target to be assessed is improved, and a unified preset matching rule is combined to serve as an assessment standard, and therefore accuracy of assessment results is improved.
Further, in another embodiment, the risk assessment method of the present invention further comprises:
and step S5, generating early warning information corresponding to the risk grade based on the risk grade corresponding to the target to be evaluated, and feeding the early warning information back to a preset terminal.
It can be understood that when the target to be evaluated corresponds to the first risk level, it indicates that the predicted value is much smaller than the planned value, so the risk is higher, and first warning information is generated, for example, the risk is higher, please pay attention to in time; when the target to be evaluated corresponds to a second risk level, the predicted value is smaller than the planned value, so that the risk is relatively low, and second early warning information is generated, for example, the target to be evaluated has the risk and is required to pay attention to in time; and when the target to be evaluated corresponds to a third risk level, indicating that the predicted value is greater than the planned value, so that no risk exists, and generating third early warning information, for example, the target to be evaluated has no risk temporarily and is required to pay attention to in time.
Further, in another embodiment, the risk assessment method of the present invention further comprises:
and respectively determining the adjustment predicted value of each characteristic index of the target to be evaluated based on the plan value, and generating prompt information based on the adjustment predicted value and the predicted value and feeding the prompt information back to a preset terminal.
For example, taking a feature index, which is a feature index of the current time of the month, as an example, the calculation formula of the adjustment value of the feature index is:
similarly, the adjustment values of other characteristic indexes can be calculated by using the formula. By feeding back the adjustment value and the predicted value of each characteristic index to the preset terminal, strategic adjustment suggestions can be provided for managers.
The invention also provides an electronic device.
Fig. 2 is a schematic diagram of an electronic device according to an embodiment of the invention.
In this embodiment, the electronic device 1 may be a server, a smart phone, a tablet computer, a portable computer, a desktop computer, or other terminal equipment with a data processing function, where the server may be a rack server, a blade server, a tower server, or a cabinet server.
The electronic device 1 comprises a memory 11, a processor 12 and a network interface 13.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic apparatus 1 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic apparatus 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic apparatus 1.
The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as the risk assessment program 10, but also to temporarily store data that has been output or will be output.
Processor 12, which in some embodiments may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip, executes program code or processes data stored in memory 11, such as risk assessment program 10.
The network interface 13 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is generally used to establish a communication connection between the electronic apparatus 1 and other electronic devices, such as a default terminal. The components 11-13 of the electronic device 1 communicate with each other via a program bus.
Fig. 2 only shows the electronic device 1 with the components 11-13, and it will be understood by a person skilled in the art that the structure shown in fig. 2 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
Optionally, the electronic device 1 may further comprise a user interface, the user interface may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further comprise a standard wired interface, a wireless interface.
Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch screen, or the like. The display, which may also be referred to as a display screen or display unit, is used for displaying information processed in the electronic apparatus 1 and for displaying a visualized user interface.
In the embodiment of the electronic device 1 shown in fig. 2, the memory 11 as a computer-readable storage medium stores the program code of the risk assessment program 10, and the processor 12 implements any of the steps of the risk assessment method as described above when executing the program code of the risk assessment program 10.
Alternatively, in other embodiments, the risk assessment program 10 can be divided into one or more modules, one or more modules being stored in the memory 11 and executed by the one or more processors 12 to implement the present invention, wherein a module refers to a series of computer program instruction segments capable of performing a specific function.
For example, referring to FIG. 3, a block diagram of the risk assessment program 10 of FIG. 2 is shown.
In an embodiment of the risk assessment program 10, the risk assessment program 10 only includes the module 110 and 140, wherein:
an obtaining module 110, configured to obtain a historical value of a feature index of an object to be evaluated within a first preset time, a planned value of the object to be evaluated within a second preset time, preset classification rules, prediction rules corresponding to each preset index type, and preset matching rules corresponding to each preset risk level;
the prediction module 120 is configured to analyze the index types corresponding to the feature indexes according to preset classification rules, predict a predicted value of the feature index within a second preset time according to a prediction rule corresponding to each preset index type, and calculate a predicted value of the target to be evaluated within the second preset time;
the query module 130 is configured to calculate a deviation between the predicted value and the planned value according to the planned value and the predicted value of the target to be evaluated within a second preset time, and query a preset risk level matched with the target to be evaluated according to a preset matching rule corresponding to each preset risk level and the deviation; and
the determining module 140 is configured to use the queried preset risk level matching the target to be evaluated as the corresponding risk level of the target to be evaluated.
Further, in other embodiments, the risk assessment program 10 further comprises a module 150:
and the early warning module 150 is configured to generate early warning information corresponding to the risk level based on the risk level corresponding to the target to be evaluated, and feed back the early warning information to a preset terminal.
It should be noted that the functions or operation steps implemented by the modules 110-150 are consistent with the above method embodiments, and are not described in detail here.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a risk assessment program 10, and when executed by a processor, the risk assessment program 10 implements the following operations:
an acquisition step: acquiring a historical value of a characteristic index of a target to be evaluated in a first preset time, a planned value of the target to be evaluated in a second preset time, preset classification rules, prediction rules corresponding to all preset index types and preset matching rules corresponding to all preset risk levels;
analyzing the index types corresponding to the characteristic indexes according to preset classification rules, predicting the predicted values of the characteristic indexes within second preset time according to the prediction rules corresponding to the preset index types, and calculating the predicted values of the target to be evaluated within the second preset time;
calculating the deviation degree of the predicted value and the planned value according to the planned value and the predicted value of the target to be evaluated within a second preset time, and inquiring the preset risk level matched with the target to be evaluated according to the preset matching rule corresponding to each preset risk level and the deviation degree; and
and determining, namely taking the inquired preset risk level matched with the target to be evaluated as the corresponding risk level of the target to be evaluated.
The embodiment of the computer readable storage medium of the present invention is substantially the same as the embodiment of the risk assessment method, and will not be described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A risk assessment method applicable to an electronic device is characterized by comprising the following steps:
an acquisition step: acquiring a historical value of a characteristic index of a target to be evaluated in a first preset time, a planned value of the target to be evaluated in a second preset time, preset classification rules, prediction rules corresponding to all preset index types and preset matching rules corresponding to all preset risk levels;
analyzing the index types corresponding to the characteristic indexes according to preset classification rules, predicting the predicted values of the characteristic indexes within second preset time according to the prediction rules corresponding to the preset index types, and calculating the predicted values of the target to be evaluated within the second preset time;
calculating the deviation degree of the predicted value and the planned value according to the planned value and the predicted value of the target to be evaluated within a second preset time, and inquiring the preset risk level matched with the target to be evaluated according to the preset matching rule corresponding to each preset risk level and the deviation degree; and
and determining, namely taking the inquired preset risk level matched with the target to be evaluated as the corresponding risk level of the target to be evaluated.
2. The risk assessment method according to claim 1, wherein the index types include a first index, a second index, a third index and a fourth index, and the classifying the preset indexes according to preset classification rules includes:
generating historical time sequence data of the characteristic indexes according to historical values of the characteristic indexes within first preset time;
when the historical time sequence data of the characteristic indexes meet a preset first classification condition, determining the characteristic indexes as first class indexes;
when the historical time sequence data of the characteristic indexes meet a preset second classification condition, determining the characteristic indexes as second class indexes;
when the historical time sequence data of the characteristic indexes meet a preset third classification condition, determining the characteristic indexes as third class indexes; and
and when the historical time sequence data of the characteristic indexes meet a preset fourth classification condition, determining the characteristic indexes to be fourth-class indexes.
3. The risk assessment method according to claim 2, wherein the predicting the predicted value of the feature index in the second preset time according to the prediction rule corresponding to each preset index type comprises:
when the characteristic index is a first-class index, predicting a predicted value of the characteristic index within second preset time by using a preset first prediction rule corresponding to the first-class index;
when the characteristic index is a second-class index, predicting the predicted value of the preset index in a second preset time by using a preset second prediction rule corresponding to the second-class index;
when the characteristic index is a third type index, predicting the predicted value of the characteristic index in second preset time by using a preset third prediction rule corresponding to the third type index; and
and when the characteristic index is a fourth type index, predicting the predicted value of the characteristic index in second preset time by using a preset fourth prediction rule corresponding to the fourth type index.
4. The risk assessment method according to claim 1, wherein the preset risk levels comprise a first risk level, a second risk level and a third risk level;
the first risk level matching rule comprises: judging whether the deviation degree meets a preset first matching condition, if so, determining that the target to be evaluated is matched with a first risk level;
the matching rules of the second risk level include: judging whether the deviation degree meets a preset second matching condition, if so, determining that the second risk level of the target to be evaluated is matched; and
the matching rules of the third risk level include: and judging whether the deviation degree meets a preset third matching condition, if so, determining that the target to be evaluated is matched with a third risk level.
5. The risk assessment method according to any one of claims 1 to 4, wherein after said determining step, the method further comprises:
early warning step: and generating early warning information corresponding to the risk grade based on the risk grade corresponding to the target to be evaluated, and feeding back the early warning information to a preset terminal.
6. An electronic device comprising a memory and a processor, wherein the memory stores a risk assessment program operable on the processor, and wherein the risk assessment program when executed by the processor performs the steps of:
an acquisition step: acquiring a historical value of a characteristic index of a target to be evaluated in a first preset time, a planned value of the target to be evaluated in a second preset time, preset classification rules, prediction rules corresponding to all preset index types and preset matching rules corresponding to all preset risk levels;
analyzing the index types corresponding to the characteristic indexes according to preset classification rules, predicting the predicted values of the characteristic indexes within second preset time according to the prediction rules corresponding to the preset index types, and calculating the predicted values of the target to be evaluated within the second preset time;
calculating the deviation degree of the predicted value and the planned value according to the planned value and the predicted value of the target to be evaluated within a second preset time, and inquiring the preset risk level matched with the target to be evaluated according to the preset matching rule corresponding to each preset risk level and the deviation degree; and
and determining, namely taking the inquired preset risk level matched with the target to be evaluated as the corresponding risk level of the target to be evaluated.
7. The electronic device according to claim 6, wherein the index types include a first index, a second index, a third index and a fourth index, and classifying the preset indexes according to preset classification rules includes:
generating historical time sequence data of the characteristic indexes according to historical values of the characteristic indexes within first preset time;
when the historical time sequence data of the characteristic indexes meet a preset first classification condition, determining the characteristic indexes as first class indexes;
when the historical time sequence data of the characteristic indexes meet a preset second classification condition, determining the characteristic indexes as second class indexes;
when the historical time sequence data of the characteristic indexes meet a preset third classification condition, determining the characteristic indexes as third class indexes; and
and when the historical time sequence data of the characteristic indexes meet a preset fourth classification condition, determining the characteristic indexes to be fourth-class indexes.
8. The electronic device of claim 6, wherein the preset risk levels comprise a first risk level, a second risk level, and a third risk level;
the first risk level matching rule comprises: judging whether the deviation degree meets a preset first matching condition, if so, determining that the target to be evaluated is matched with a first risk level;
the matching rules of the second risk level include: judging whether the deviation degree meets a preset second matching condition, if so, determining that the second risk level of the target to be evaluated is matched; and
the matching rules of the third risk level include: and judging whether the deviation degree meets a preset third matching condition, if so, determining that the target to be evaluated is matched with a third risk level.
9. The electronic device of any of claims 6-8, wherein the risk assessment program, when executed by the processor, further implements the following steps after the determining step:
early warning step: and generating early warning information corresponding to the risk grade based on the risk grade corresponding to the target to be evaluated, and feeding back the early warning information to a preset terminal.
10. A computer-readable storage medium, comprising a risk assessment program which, when executed by a processor, implements the steps of the risk assessment method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910752041.9A CN110648045A (en) | 2019-08-14 | 2019-08-14 | Risk assessment method, electronic device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910752041.9A CN110648045A (en) | 2019-08-14 | 2019-08-14 | Risk assessment method, electronic device and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110648045A true CN110648045A (en) | 2020-01-03 |
Family
ID=69009541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910752041.9A Pending CN110648045A (en) | 2019-08-14 | 2019-08-14 | Risk assessment method, electronic device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110648045A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753963A (en) * | 2020-06-28 | 2020-10-09 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN111803065A (en) * | 2020-06-23 | 2020-10-23 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN113962614A (en) * | 2021-12-21 | 2022-01-21 | 深圳市迪博企业风险管理技术有限公司 | Intelligent examination method and device for business abnormity of listed company |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876600A (en) * | 2018-08-20 | 2018-11-23 | 平安科技（深圳）有限公司 | Warning information method for pushing, device, computer equipment and medium |
| CN109102394A (en) * | 2018-08-14 | 2018-12-28 | 深圳市人民政府金融发展服务办公室 | Methods of risk assessment, device and computer readable storage medium |
| CN109978342A (en) * | 2019-03-01 | 2019-07-05 | 平安科技（深圳）有限公司 | Electronic device, methods of risk assessment and computer readable storage medium |
-
2019
- 2019-08-14 CN CN201910752041.9A patent/CN110648045A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109102394A (en) * | 2018-08-14 | 2018-12-28 | 深圳市人民政府金融发展服务办公室 | Methods of risk assessment, device and computer readable storage medium |
| CN108876600A (en) * | 2018-08-20 | 2018-11-23 | 平安科技（深圳）有限公司 | Warning information method for pushing, device, computer equipment and medium |
| CN109978342A (en) * | 2019-03-01 | 2019-07-05 | 平安科技（深圳）有限公司 | Electronic device, methods of risk assessment and computer readable storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111803065A (en) * | 2020-06-23 | 2020-10-23 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN111803065B (en) * | 2020-06-23 | 2023-12-26 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN111753963A (en) * | 2020-06-28 | 2020-10-09 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN111753963B (en) * | 2020-06-28 | 2024-04-02 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN113962614A (en) * | 2021-12-21 | 2022-01-21 | 深圳市迪博企业风险管理技术有限公司 | Intelligent examination method and device for business abnormity of listed company |
| CN113962614B (en) * | 2021-12-21 | 2022-04-15 | 深圳市迪博企业风险管理技术有限公司 | Intelligent examination method and device for business abnormity of listed company |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108632097B (en) | Abnormal behavior object identification method, terminal device and medium | |
| US11500524B2 (en) | Automatic generation of preferred views for personal content collections | |
| CN112328399A (en) | Cluster resource scheduling method and device, computer equipment and storage medium | |
| CN110648045A (en) | Risk assessment method, electronic device and computer-readable storage medium | |
| CN111552870A (en) | Object recommendation method, electronic device and storage medium | |
| US20150039652A1 (en) | Systems and methods for automated analysis, screening and reporting of group performance | |
| CN113688923B (en) | Order abnormity intelligent detection method and device, electronic equipment and storage medium | |
| CN110796554B (en) | User complaint early warning method and device, computer equipment and storage medium | |
| Liu et al. | Estimation of a total from a population of unknown size and application to estimating recreational red snapper catch in Texas | |
| CN117223016A (en) | Industry specific machine learning application | |
| CN114444863A (en) | Enterprise production safety assessment method, system, device and storage medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN117390087A (en) | Data recommendation method, device, equipment and storage medium | |
| CN111950623B (en) | Data stability monitoring method, device, computer equipment and medium | |
| CN112948705A (en) | Intelligent matching method, device and medium based on policy big data | |
| CN110097250B (en) | Product risk prediction method, device, computer equipment and storage medium | |
| CN109783877B (en) | Time sequence model establishment method, device, computer equipment and storage medium | |
| WO2013061324A2 (en) | A method for estimating the total cost of ownership (tcp) for a requirement | |
| CN113657546B (en) | Information classification method, device, electronic equipment and readable storage medium | |
| CN110874640A (en) | Distribution selection and simulation of intermittent data using Machine Learning (ML) | |
| EP4050536A1 (en) | Analysis device, control method, and program | |
| WO2012044305A1 (en) | Identification of events of interest | |
| US20210405627A1 (en) | Production planning system | |
| CN108681968A (en) | Stock sells method for early warning, device and computer readable storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |