CN112258093A - Risk level data processing method and device, storage medium and electronic equipment - Google Patents
Risk level data processing method and device, storage medium and electronic equipmentDownload PDFInfo
- Publication number
- CN112258093A CN112258093ACN202011345770.1ACN202011345770ACN112258093ACN 112258093 ACN112258093 ACN 112258093ACN 202011345770 ACN202011345770 ACN 202011345770ACN 112258093 ACN112258093 ACN 112258093A
- Authority
- CN
- China
- Prior art keywords
- risk
- value
- time
- calculating
- threshold
- 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.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Complex Calculations (AREA)
Abstract
Description
Technical Field
The present application relates to the field of computers, and in particular, to a method and an apparatus for processing risk level data, a storage medium, and an electronic device.
Background
In the related art, with the development of the internet, a scoring model or a scoring model is often used in many fields, such as credit scoring or risk coefficient scoring, and generally, some data of an entity is collected to extract relevant features related to scoring, and then a certain scoring model is used to score each entity at different grades. For the existing scoring model, one way is to train and learn a scoring model by means of a supervised learning method in the field of artificial intelligence when partial label data exists, and directly output a score for subsequently provided user characteristics; the other mode is that firstly, experts in some fields set different importance coefficients for different characteristics, then an integral score is obtained through synthesis, and finally, a scoring interval threshold value is set according to expert knowledge, and continuous score values are mapped to discrete score grades.
The solutions in the related art have three disadvantages: in many application scenes, no mark label data exists, or only a small amount of label data exists, so that in many practical scenes, a model cannot be trained by means of an AI algorithm or a model with good effect is obtained; the importance coefficient of each dimension characteristic depending on the scoring needs expert knowledge and data analysis to set, and the specific importance coefficient is a continuous numerical value and is difficult to accurately set weight; after the scores are calculated, how to divide the regions also needs to depend on expert knowledge, and the rules are invariable after being formed, for a piece of data, the scores which cannot be obtained unless the model is modified can be obtained, and considering that time sequence data are dynamically changed, the real distribution of the data can be changed, so that the model cannot automatically correct the scores, a fixed set of grade division criteria is adopted at each moment, the risk grade division is inaccurate, and the reference is low.
In view of the above problems in the related art, no effective solution has been found at present.
Disclosure of Invention
In order to solve the technical problem or at least partially solve the technical problem, the present application provides a risk level data processing method and apparatus, a storage medium, and an electronic device.
According to an aspect of an embodiment of the present application, there is provided a method for processing risk level data, including: acquiring risk characteristic data of a plurality of target areas at a first time; for each target region, calculating a first risk value for the risk profile at the first time; calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time, wherein the second time is a historical time of the first time; and dividing the risk levels of the target areas according to the risk level threshold value.
Further, calculating a first risk value for the risk profile at the first time comprises: determining a weight value of each risk dimension, wherein each risk dimension corresponds to one risk characteristic data; and calculating a first risk value at the first time according to the risk characteristic data and the corresponding weight value in a weighting manner.
Further, prior to determining the weight value for each risk dimension, the method further comprises: setting a comparison scale value between every two risk dimensions, and constructing a comparison matrix according to the comparison scale values; judging whether the comparison matrix is reasonable or not based on consistency check; if the comparison matrix is reasonable, calculating the eigenvector of the maximum eigenvalue in the comparison matrix through matrix decomposition, wherein elements of the eigenvector correspond to the risk dimensionality of the risk characteristic data; and determining element values in the feature vectors as weight coefficients of corresponding risk dimensions.
Further, calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time comprises: ranking a plurality of first risk values for the plurality of target regions; selecting a specific first risk value in the sequence based on the position of a predetermined quantile; adding the specific first risk value to a threshold window of the preset quantile, wherein the threshold window also comprises a plurality of second risk values, and each second risk value corresponds to a second time; and calculating a risk grade threshold value of the preset quantile according to the specific first risk value and the plurality of second risk values.
Further, after adding the particular first risk value to the threshold window of the preset quantile, the method further comprises: judging whether the stored value of the threshold value window overflows or not; if the stored value of the threshold window overflows, deleting a specified stored value with the earliest storage time in the threshold window.
Further, calculating a risk level threshold for the predetermined quantile based on the specific first risk value and the plurality of second risk values comprises: calculating an average of the particular first risk value and a number of the second risk values; and determining the average value as a risk grade threshold value of the preset quantile.
Further, classifying the risk levels of the plurality of target regions according to the risk level thresholds comprises: comparing, for each target region, the first risk value to the risk level threshold; if the first risk value is greater than the risk level threshold, determining that the target area is a first risk level; and if the first risk value is smaller than the risk level threshold value, determining that the target area is a second risk level.
According to another aspect of the embodiments of the present application, there is also provided a data processing apparatus for risk classification, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring risk characteristic data of a plurality of target areas at a first time; a first calculation module for calculating, for each target region, a first risk value of the risk characteristic data at the first time; a second calculation module to calculate a risk level threshold from the first risk value of the risk profile and a second risk value at a second time, wherein the second time is a historical time of the first time; and the dividing module is used for dividing the risk levels of the target areas according to the risk level threshold value.
Further, the first calculation module includes: the determining unit is used for determining a weight value of each risk dimension, wherein each risk dimension corresponds to one risk characteristic data; and the calculating unit is used for calculating a first risk value of the first time according to the risk characteristic data and the corresponding weight value in a weighting manner.
Further, the apparatus further comprises: the setting module is used for setting a comparison scale value between every two risk dimensions before the first calculation module determines the weight value of each risk dimension, and constructing a comparison matrix according to the comparison scale value; the judging module is used for judging whether the comparison matrix is reasonable or not based on consistency check; the third calculation module is used for calculating the eigenvector of the maximum eigenvalue in the comparison matrix through matrix decomposition if the comparison matrix is reasonable, wherein elements of the eigenvector correspond to the risk dimension of the risk characteristic data; and the determining module is used for determining the element values in the feature vectors as the weight coefficients of the corresponding risk dimensions.
Further, the second calculation module includes: a ranking unit configured to rank the plurality of first risk values of the plurality of target regions; a selection unit for selecting a specific first risk value in the sequence based on the position of a predetermined quantile; an adding unit, configured to add the specific first risk value to a threshold window of the preset quantile, where the threshold window further includes a plurality of second risk values, and each second risk value corresponds to a second time; and the calculating unit is used for calculating the risk grade threshold of the preset quantile according to the specific first risk value and the plurality of second risk values.
Further, the second calculation module further comprises: a judging unit, configured to judge whether stored values of a threshold window of the preset quantile are overflowed after the adding unit adds the specific first risk value to the threshold window; and the deleting unit is used for deleting a specified storage value with the earliest storage time in the threshold window if the storage values of the threshold window overflow.
Further, the calculation unit includes: a calculating subunit, configured to calculate an average value of the specific first risk value and a number of the second risk values; a determining subunit, configured to determine the average value as a risk level threshold of the preset quantile.
Further, the dividing module includes: a comparison unit for comparing, for each target area, the first risk value and the risk level threshold; a determining unit, configured to determine that the target area is a first risk level if the first risk value is greater than the risk level threshold; and if the first risk value is smaller than the risk level threshold value, determining that the target area is a second risk level.
According to another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program that executes the above steps when the program is executed.
According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; wherein: a memory for storing a computer program; a processor for executing the steps of the method by running the program stored in the memory.
Embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the steps of the above method.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
in the embodiment of the application, risk characteristic data of a plurality of target areas at a first time are obtained, and for each target area, a first risk value of the risk characteristic data at the first time is calculated, calculating a risk level threshold based on the first risk value of the risk profile and the second risk value at the second time, the risk levels of a plurality of target areas are divided according to the risk level threshold value, and by calculating the risk level threshold value according to the risk values of the current time and the historical time, the threshold value can be adaptively adjusted along with the distribution of data and the time, and further, the risk grade model is dynamically adjusted, the influence of human factors on the threshold value is reduced, the technical problem that the risk grade division in the related technology is inaccurate is solved, the influence of environmental change on the risk grade is reduced, the accuracy of the risk grade is improved, and the more accurate monitoring of the regional risk state is realized.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
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 described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method of data processing for risk classes according to an embodiment of the present invention;
FIG. 2 is a flow chart of an implementation of an embodiment of the present invention;
FIG. 3 is a block diagram of a data processing apparatus for risk classification according to an embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments, and the illustrative embodiments and descriptions thereof of the present application are used for explaining the present application and do not constitute a limitation to the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another similar entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 a process, method, article, or apparatus that comprises the element.
In this embodiment, a risk level data processing method is provided, and fig. 1 is a flowchart of a risk level data processing method according to an embodiment of the present invention, as shown in fig. 1, the flowchart includes the following steps:
step S102, acquiring risk characteristic data of a plurality of target areas at a first time;
in this embodiment, the number of target regions is greater than 1, the first time may be a time of a current division cycle, and the risk feature data may be data of one or more dimensions. In one example, the risk level is a city safety level, the indexes of the risk characteristic data may include the number of dangerous chemical enterprises in a region, real-time population flow in the region, real-time number of dangerous chemical vehicles in the region, historical monitoring and early warning number in the region, and the like, and the indexes of the risk characteristic data collected in each target region are the same. The target area of the present embodiment is not limited to a specific geographic area, but may also be a virtual object, such as a crowd range, a communication area, and the like.
Step S104, calculating a first risk value of the risk characteristic data at a first time for each target area;
for each target area, calculating a first risk value of the corresponding target area according to the acquired risk characteristic data of the target area at the first time, wherein the first risk value is a quantitative value based on the risk characteristic data.
Step S106, calculating a risk level threshold according to a first risk value of the risk characteristic data and a second risk value at a second time, wherein the second time is historical time of the first time;
optionally, the second time includes one or more historical times, and the risk level threshold is a critical value for classifying the risk level.
And step S108, dividing the risk levels of the target areas according to the risk level threshold values.
The embodiment is applied to the fields of interest level division, capability level division and the like besides risk level division.
Obtaining risk characteristic data of a plurality of target areas at a first time through the steps, calculating a first risk value of the risk characteristic data at the first time aiming at each target area, calculating a risk level threshold based on the first risk value of the risk profile and the second risk value at the second time, the risk levels of a plurality of target areas are divided according to the risk level threshold value, and by calculating the risk level threshold value according to the risk values of the current time and the historical time, the threshold value can be adaptively adjusted along with the distribution of data and the time, and then the risk grade model is dynamically adjusted, the influence of human factors on the threshold value is reduced, the technical problem that the risk grade division in the related technology is inaccurate is solved, the influence of environmental change on the risk grade is reduced, the accuracy of the risk grade is improved, and the more accurate monitoring of the regional risk state is realized.
In one embodiment of this embodiment, calculating the first risk value of the risk profile at the first time comprises:
s11, determining a weight value of each risk dimension, wherein each risk dimension corresponds to one risk characteristic data;
optionally, before determining the weight value of each risk dimension, the weight value of each risk dimension is calculated based on an AHP (Analytic Hierarchy Process), and the AHP is a simple, flexible and practical multi-criterion decision method for quantitatively analyzing qualitative problems. The AHP-based process for calculating the weight value of each risk dimension comprises the following steps: setting a comparison scale value between every two risk dimensions, and constructing a comparison matrix according to the comparison scale values; judging whether the comparison matrix is reasonable or not based on consistency check; if the comparison matrix is reasonable, calculating the eigenvector of the maximum eigenvalue in the comparison matrix through matrix decomposition, wherein elements of the eigenvector correspond to the risk dimensionality of the risk eigenvalue data; and determining element values in the feature vectors as weight coefficients of the corresponding risk dimensions. By the scheme, automatic calculation of the weight coefficient is realized.
The comparison scale value is a comparison with an importance degree for the evaluation index, such as the comparison scale value a14By 5 is meant that the ratio of the importance of the first risk dimension to the fourth risk dimension is 5, the higher the comparison scale value, the greater the importance of the first risk dimension relative to the fourth risk dimension. Consistency checks refer to determining allowable ranges of inconsistency for pairs of comparison matrices, e.g. a14＝5，a43When 2, then a13＝a14*a43In some instances, strict agreement is not required and a range of differences may be allowed.
And S12, calculating a first risk value at a first time according to the risk characteristic data and the corresponding weight value in a weighting mode.
In one example, the three risk profiles are ABC, respectively, with their corresponding weight values weighted as ABC, where a + b + c is 1, by calculating the first risk value Aa + Bb + Cc.
In one embodiment of this embodiment, calculating the risk level threshold from the first risk value of the risk profile and the second risk value at the second time comprises: ranking a plurality of first risk values for a plurality of target regions; selecting a specific first risk value in the sequence based on the position of a predetermined quantile; adding a specific first risk value to a threshold window of a preset quantile point, wherein the threshold window also comprises a plurality of second risk values, and each second risk value corresponds to a second time; and calculating a risk grade threshold value of the preset quantile according to the specific first risk value and the plurality of second risk values.
In this embodiment, the sequences may be sorted from small to large, or sorted from large to small, and a sequence is generated, where the length of the sequence is the number of target regions, a value in the sequence corresponding to the first risk value of each target region, and quantiles (quantiles) are also called quantiles, which are numerical points that divide the probability distribution range of a random variable into several equal parts, where the value in this embodiment is the dividing position of the sequence, and if the sequence m is divided into n ranges, n-1 quantiles are required, and since the positions of the quantiles are fixed, and the values of the quantiles dynamically change along with the time period, the risk level threshold calculated by using the quantiles also dynamically changes.
Optionally, after adding the specific first risk value to the threshold window of the preset quantile, the method further includes: judging whether the stored value of the threshold value window overflows or not; if the stored value of the threshold window overflows, a specified stored value with the earliest storage time is deleted in the threshold window. In other embodiments, a stored value may be randomly deleted from the threshold window, or a value meeting a predetermined condition (e.g., a maximum value, a minimum value) may be deleted from the threshold window, so as to reduce fluctuation of the threshold and make the risk level threshold relatively smooth, or a stored value (the first risk value at the first time) may be added to the original threshold window without deleting the stored value.
In one example, 5 target regions are included, first risk values of the target regions are respectively 3, 2, 5, 1, 4, and 6, the sequence 654321 is obtained by sorting from large to small, the preset quantile point includes two positions, namely, a fourth value and a fifth value of the sequence, namely, 3 and 2, the fourth value further includes a second risk value (3, 2) in a threshold window of the fourth value, the fifth value further includes a second risk value (1, 2, 1) in a threshold window of the fifth value, a risk level threshold corresponding to the fourth value of the sequence is finally calculated according to the first risk value (3) and the second risk value (3, 2), and a risk level threshold corresponding to the fifth value of the sequence is finally calculated according to the first risk value (2) and the second risk value (1, 2, 1).
In one embodiment of this embodiment, calculating the risk level threshold by an average value, and calculating the risk level threshold of the preset quantile according to the specific first risk value and the plurality of second risk values includes: calculating an average value of the specific first risk value and the plurality of second risk values; and determining the average value as a risk level threshold value of the preset quantile. In other embodiments, the risk level threshold may also be calculated based on the median, the mean or median after the maximum and minimum values are removed.
In one implementation of this embodiment, classifying the risk levels of the plurality of target regions according to the risk level threshold includes: comparing, for each target region, the first risk value to a risk level threshold; if the first risk value is larger than the risk level threshold value, determining that the target area is a first risk level; and if the first risk value is smaller than the risk level threshold value, determining the target area as a second risk level.
In the presence of multiple risk level thresholds, it is necessary to determine an area range in which the first risk value is located, and the area range is defined by the risk level thresholds. In one example, the method includes two risk level thresholds, which are a first threshold and a second threshold, where 0-the first threshold is preset as a low risk level, the first-the second thresholds are medium risk levels, and higher than the second threshold as a high risk level, when dividing the risk level of a target area, multiple risk level thresholds need to be compared, an area range where a first risk value is located is determined, and finally, the risk level is determined according to the area range where the first risk value of the target threshold is located, and if the first area is within the range from 0-the first threshold, the first area is a low risk level, and so on.
Fig. 2 is an implementation flowchart of an embodiment of the present invention, which is to describe a scheme of the embodiment in detail based on a specific application scenario, and specifically, for the application scenario, a task of performing risk level classification on a parcel in real time is performed, specifically, for the application scenario, real-time risk of an area and the like are classified by using some real-time data information related to hazardous chemical substances in a city, and a risk level is applied to different entities at each time, where the risk level includes m parcels (target areas), and each parcel acquires risk feature data of n dimensions, which is described with reference to fig. 2, and the process includes:
step A: extracting relevant influence characteristics such as the number of dangerous chemical enterprises in a region, real-time population flow in the region, real-time dangerous chemical vehicle number in the region, historical monitoring and early warning number in the region and the like aiming at the scene to form m characteristic vectors xi(i ═ 1,2 … m), thisThe risk levels for a plot area are all closely related; aiming at the characteristics, a pairwise comparison judgment matrix is constructed by an AHP (analytic hierarchy process) method, and then a specific weight coefficient of each characteristic is obtained through calculation.
And B: since most scenes will not have label data, there is also no label for the scene. At one moment, the relevant feature values in each block in the city can be collected, then a risk score value is calculated according to the feature weight coefficient obtained in the last step, and the division of the risk score value is performed by adopting the position of the data distribution branch point. For example, in most scenes, normal proportions always occupy most of the scenes, while abnormal proportions always occupy less of the scenes, so that k +1 risk grades can be classified by selecting values of k different quantiles according to score values sorted from small to large, for example, three grades of risk grades can be classified by selecting a 90 quantile point value and a 95 quantile point value, specifically, when a region risk score value is greater than 95 quantile points, the region is considered to be high risk, when the region risk score value is between the 90 quantile point value and the 95 quantile point value, the region is considered to be medium risk, otherwise, the region is low risk.
And C: considering that the data is dynamically changed in real time and the characteristics of the data are changed with time, a threshold window with a fixed size is added to store the threshold values at a plurality of moments, specifically, at each moment, the score p of each land block is calculated for the data firstly1,p2,…,pmThen, the value of each quantile is obtained, since the position of the quantile is fixed but the value of the quantile is changed, by using this characteristic, the value of the quantile required at each moment is stored in a threshold window, for example, the window size is 24, then the values of the quantile in the last 24 time slices are stored in the threshold window in real time, and for the moment T, the value of the quantile in the last 24 time slices is storediWill TiStoring the quantiles obtained by time calculation into a threshold window, discarding the earliest history record at the leftmost side of the window when the window data volume overflows, and then counting the history mean value of each quantile in the threshold window to be used as the threshold of the current timeAnd then, dividing the risk level of each area at the moment, and outputting the risk level of each area.
By adopting the scheme of the embodiment, a plurality of quantiles are set according to the distribution of data, the grade interval is divided, an Analytic Hierarchy Process (AHP) is adopted to calculate importance weight values in advance for each dimensional feature of the structure, for dynamic time sequence data, the feature values of all current samples are counted at each moment and then a score is calculated according to the weight, then the quantile point values of all sample sorting scores at the current moment are added into a threshold window after meeting a certain condition, then the average value of all quantiles in the calculation window is updated, so that the threshold can be adaptively adjusted along with the distribution of the data, and then each sample at the current moment is graded.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions 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) 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.
Example 2
In this embodiment, a data processing apparatus for risk level is further provided, which is used to implement the foregoing embodiments and preferred embodiments, and the description that has been already made is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 3 is a block diagram of a risk level data processing apparatus according to an embodiment of the present invention, as shown in fig. 3, the apparatus includes: an acquisition module 30, a first calculation module 32, a second calculation module 34, a partitioning module 36, wherein,
an obtaining module 30, configured to obtain risk characteristic data of a plurality of target areas at a first time;
a first calculation module 32 for calculating, for each target region, a first risk value of the risk characteristic data at the first time;
a second calculation module 34 for calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time, wherein the second time is a historical time of the first time;
a dividing module 36, configured to divide the risk levels of the multiple target areas according to the risk level threshold.
Optionally, the first computing module includes: the determining unit is used for determining a weight value of each risk dimension, wherein each risk dimension corresponds to one risk characteristic data; and the calculating unit is used for calculating a first risk value of the first time according to the risk characteristic data and the corresponding weight value in a weighting manner.
Optionally, the apparatus further comprises: the setting module is used for setting a comparison scale value between every two risk dimensions before the first calculation module determines the weight value of each risk dimension, and constructing a comparison matrix according to the comparison scale value; the judging module is used for judging whether the comparison matrix is reasonable or not based on consistency check; the third calculation module is used for calculating the eigenvector of the maximum eigenvalue in the comparison matrix through matrix decomposition if the comparison matrix is reasonable, wherein elements of the eigenvector correspond to the risk dimension of the risk characteristic data; and the determining module is used for determining the element values in the feature vectors as the weight coefficients of the corresponding risk dimensions.
Optionally, the second computing module includes: a ranking unit configured to rank the plurality of first risk values of the plurality of target regions; a selection unit for selecting a specific first risk value in the sequence based on the position of a predetermined quantile; an adding unit, configured to add the specific first risk value to a threshold window of the preset quantile, where the threshold window further includes a plurality of second risk values, and each second risk value corresponds to a second time; and the calculating unit is used for calculating the risk grade threshold of the preset quantile according to the specific first risk value and the plurality of second risk values.
Optionally, the second computing module further includes: a judging unit, configured to judge whether stored values of a threshold window of the preset quantile are overflowed after the adding unit adds the specific first risk value to the threshold window; and the deleting unit is used for deleting a specified storage value with the earliest storage time in the threshold window if the storage values of the threshold window overflow.
Optionally, the computing unit includes: a calculating subunit, configured to calculate an average value of the specific first risk value and a number of the second risk values; a determining subunit, configured to determine the average value as a risk level threshold of the preset quantile.
Optionally, the dividing module includes: a comparison unit for comparing, for each target area, the first risk value and the risk level threshold; a determining unit, configured to determine that the target area is a first risk level if the first risk value is greater than the risk level threshold; and if the first risk value is smaller than the risk level threshold value, determining that the target area is a second risk level.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Example 3
Fig. 4 is a structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device includes aprocessor 41, acommunication interface 42, amemory 43, and acommunication bus 44, where theprocessor 41, thecommunication interface 42, and thememory 43 complete mutual communication through thecommunication bus 44,
amemory 43 for storing a computer program;
theprocessor 41, when executing the program stored in thememory 43, implements the following steps:
acquiring risk characteristic data of a plurality of target areas at a first time; for each target region, calculating a first risk value for the risk profile at the first time; calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time, wherein the second time is a historical time of the first time; and dividing the risk levels of the target areas according to the risk level threshold value.
Further, calculating a first risk value for the risk profile at the first time comprises: determining a weight value of each risk dimension, wherein each risk dimension corresponds to one risk characteristic data; and calculating a first risk value at the first time according to the risk characteristic data and the corresponding weight value in a weighting manner.
Further, prior to determining the weight value for each risk dimension, the method further comprises: setting a comparison scale value between every two risk dimensions, and constructing a comparison matrix according to the comparison scale values; judging whether the comparison matrix is reasonable or not based on consistency check; if the comparison matrix is reasonable, calculating the eigenvector of the maximum eigenvalue in the comparison matrix through matrix decomposition, wherein elements of the eigenvector correspond to the risk dimensionality of the risk characteristic data; and determining element values in the feature vectors as weight coefficients of corresponding risk dimensions.
Further, calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time comprises: ranking a plurality of first risk values for the plurality of target regions; selecting a specific first risk value in the sequence based on the position of a predetermined quantile; adding the specific first risk value to a threshold window of the preset quantile, wherein the threshold window also comprises a plurality of second risk values, and each second risk value corresponds to a second time; and calculating a risk grade threshold value of the preset quantile according to the specific first risk value and the plurality of second risk values.
Further, after adding the particular first risk value to the threshold window of the preset quantile, the method further comprises: judging whether the stored value of the threshold value window overflows or not; if the stored value of the threshold window overflows, deleting a specified stored value with the earliest storage time in the threshold window.
Further, calculating a risk level threshold for the predetermined quantile based on the specific first risk value and the plurality of second risk values comprises: calculating an average of the particular first risk value and a number of the second risk values; and determining the average value as a risk grade threshold value of the preset quantile.
Further, classifying the risk levels of the plurality of target regions according to the risk level thresholds comprises: comparing, for each target region, the first risk value to the risk level threshold; if the first risk value is greater than the risk level threshold, determining that the target area is a first risk level; and if the first risk value is smaller than the risk level threshold value, determining that the target area is a second risk level.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In yet another embodiment provided by the present application, a computer-readable storage medium is further provided, which has instructions stored therein, and when the instructions are executed on a computer, the instructions cause the computer to execute the data processing method of the risk level in any one of the above embodiments.
In yet another embodiment provided by the present application, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method for risk-level data processing as described in any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for processing risk level data, comprising:
acquiring risk characteristic data of a plurality of target areas at a first time;
for each target region, calculating a first risk value for the risk profile at the first time;
calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time, wherein the second time is a historical time of the first time;
and dividing the risk levels of the target areas according to the risk level threshold value.
2. The method of claim 1, wherein calculating a first risk value for the risk profile at the first time comprises:
determining a weight value of each risk dimension, wherein each risk dimension corresponds to one risk characteristic data;
and calculating a first risk value at the first time according to the risk characteristic data and the corresponding weight value in a weighting manner.
3. The method of claim 2, wherein prior to determining the weight value for each risk dimension, the method further comprises:
setting a comparison scale value between every two risk dimensions, and constructing a comparison matrix according to the comparison scale values;
judging whether the comparison matrix is reasonable or not based on consistency check;
if the comparison matrix is reasonable, calculating the eigenvector of the maximum eigenvalue in the comparison matrix through matrix decomposition, wherein elements of the eigenvector correspond to the risk dimensionality of the risk characteristic data;
and determining element values in the feature vectors as weight coefficients of corresponding risk dimensions.
4. The method of claim 1, wherein calculating a risk level threshold from the first risk value of the risk profile and a second risk value at a second time comprises:
ranking a plurality of first risk values for the plurality of target regions;
selecting a specific first risk value in the sequence based on the position of a predetermined quantile;
adding the specific first risk value to a threshold window of the preset quantile, wherein the threshold window also comprises a plurality of second risk values, and each second risk value corresponds to a second time;
and calculating a risk grade threshold value of the preset quantile according to the specific first risk value and the plurality of second risk values.
5. The method according to claim 4, wherein after adding the specific first risk value to the threshold window of the preset quantile, the method further comprises:
judging whether the stored value of the threshold value window overflows or not;
if the stored value of the threshold window overflows, deleting a specified stored value with the earliest storage time in the threshold window.
6. The method of claim 4, wherein calculating a risk level threshold for the predetermined quantile from the particular first risk value and the number of the second risk values comprises:
calculating an average of the particular first risk value and a number of the second risk values;
and determining the average value as a risk grade threshold value of the preset quantile.
7. The method of claim 1, wherein ranking the risk levels of the plurality of target regions according to the risk level threshold comprises:
comparing, for each target region, the first risk value to the risk level threshold;
if the first risk value is greater than the risk level threshold, determining that the target area is a first risk level; and if the first risk value is smaller than the risk level threshold value, determining that the target area is a second risk level.
8. A risk-level data processing apparatus, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring risk characteristic data of a plurality of target areas at a first time;
a first calculation module for calculating, for each target region, a first risk value of the risk characteristic data at the first time;
a second calculation module to calculate a risk level threshold from the first risk value of the risk profile and a second risk value at a second time, wherein the second time is a historical time of the first time;
and the dividing module is used for dividing the risk levels of the target areas according to the risk level threshold value.
9. A storage medium, characterized in that the storage medium comprises a stored program, wherein the program is operative to perform the method steps of any of the preceding claims 1 to 7.
10. An electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; wherein:
a memory for storing a computer program;
a processor for performing the method steps of any of claims 1 to 7 by executing a program stored on a memory.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011345770.1ACN112258093B (en) | 2020-11-25 | 2020-11-25 | Data processing method and device for risk level, storage medium and electronic equipment |
| PCT/CN2021/130712WO2022111327A1 (en) | 2020-11-25 | 2021-11-15 | Risk level data processing method and apparatus, and storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011345770.1ACN112258093B (en) | 2020-11-25 | 2020-11-25 | Data processing method and device for risk level, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112258093Atrue CN112258093A (en) | 2021-01-22 |
| CN112258093B CN112258093B (en) | 2024-06-21 |
Family
ID=74225539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011345770.1AActiveCN112258093B (en) | 2020-11-25 | 2020-11-25 | Data processing method and device for risk level, storage medium and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112258093B (en) |
| WO (1) | WO2022111327A1 (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686477A (en)* | 2021-01-28 | 2021-04-20 | 北京工业大数据创新中心有限公司 | Coal mill blockage early warning method and system |
| CN113793690A (en)* | 2021-08-31 | 2021-12-14 | 医渡云（北京）技术有限公司 | Method, device, storage medium and equipment for evaluating regional risk of infectious disease |
| CN113793076A (en)* | 2021-05-14 | 2021-12-14 | 西安交通大学 | Dynamic risk pool monitoring method, system, equipment and readable storage medium |
| CN113919669A (en)* | 2021-09-26 | 2022-01-11 | 德联易控科技(北京)有限公司 | Method and device for determining risk information of risk control object |
| CN114330991A (en)* | 2021-11-17 | 2022-04-12 | 华能核能技术研究院有限公司 | Method and device for determining risk level of nuclear power production work |
| CN114553516A (en)* | 2022-02-18 | 2022-05-27 | 支付宝(杭州)信息技术有限公司 | Data processing method, device and equipment |
| WO2022111327A1 (en)* | 2020-11-25 | 2022-06-02 | 京东城市(北京)数字科技有限公司 | Risk level data processing method and apparatus, and storage medium and electronic device |
| CN114612138A (en)* | 2022-03-04 | 2022-06-10 | 杭州网易云音乐科技有限公司 | Advertising material processing method and device, computer storage medium, and electronic device |
| CN115033874A (en)* | 2022-05-09 | 2022-09-09 | 北京数美时代科技有限公司 | Account intercepting method and device, electronic equipment and computer storage medium |
| CN115293666A (en)* | 2022-10-10 | 2022-11-04 | 北京帮安迪信息科技股份有限公司 | Quick building method for park safety risk control platform based on low-code platform |
| CN117976237A (en)* | 2024-03-25 | 2024-05-03 | 济南鸿泰医疗管理集团有限公司 | A medical data intelligent analysis system and method based on the Internet of Things |
| CN118075011A (en)* | 2024-03-18 | 2024-05-24 | 北京安胜华信科技有限公司 | A request blocking method, product, device and medium |
| CN119296045A (en)* | 2024-12-11 | 2025-01-10 | 浙江安防职业技术学院 | Security monitoring methods and equipment |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912833B (en)* | 2022-06-09 | 2025-09-16 | 深圳乐信软件技术有限公司 | Targeted screening method, sponsor screening device, and computer-readable storage medium |
| CN115821269B (en)* | 2022-11-04 | 2025-02-25 | 宁德时代新能源科技股份有限公司 | Brake disc anticorrosion method, device, terminal equipment and storage medium |
| CN116151778B (en)* | 2023-04-21 | 2023-07-14 | 安徽常力达电气有限公司 | Transformer production manufacturing process management system based on Internet of things |
| CN117935459B (en)* | 2024-01-25 | 2024-10-29 | 浙江国友工程技术有限公司 | Display control method and system for explosion-proof display screen |
| CN117726308B (en)* | 2024-02-18 | 2024-05-24 | 中铁水利信息科技有限公司 | Smart water conservancy management system and method based on Internet of Things and 5G |
| CN118587852B (en)* | 2024-05-17 | 2024-12-31 | 滨州市农业技术推广中心 | Abnormality alarm method, abnormality alarm system, intelligent gardening weeding equipment and storage medium |
| CN118362335B (en)* | 2024-06-20 | 2024-10-22 | 南京讯联液压技术股份有限公司 | Hydraulic filter data processing method and system based on multidimensional data analysis |
| CN118430217B (en)* | 2024-07-04 | 2024-09-27 | 中钢集团武汉安全环保研究院有限公司 | Safety risk early warning method, device and system |
| CN118965322B (en)* | 2024-10-12 | 2025-02-28 | 北京亿智云科技有限公司 | Copy data set read-write authority management method |
| CN120413460B (en)* | 2025-07-01 | 2025-09-09 | 河北同光半导体股份有限公司 | Substrate notch grade determining method and device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063608A (en)* | 2014-07-01 | 2014-09-24 | 天津市水文水资源勘测管理中心 | Method of determining underground water controlled water level by utilizing risk evaluation |
| CN104881783A (en)* | 2015-05-14 | 2015-09-02 | 中国科学院信息工程研究所 | E-bank account fraudulent conduct and risk detecting method and system |
| CN106096838A (en)* | 2016-06-14 | 2016-11-09 | 广州市恒迅技防系统有限公司 | Building fire safety evaluation method based on model of fuzzy synthetic evaluation and system |
| US20180300486A1 (en)* | 2017-04-18 | 2018-10-18 | International Business Machines Corporation | Management of Alerts Using a Budget-Dependent Adjustable Working Threshold |
| CN108900466A (en)* | 2018-05-30 | 2018-11-27 | 北京五八信息技术有限公司 | Prevent processing method, device, server and the storage medium of fallacious message |
| CN109272340A (en)* | 2018-07-19 | 2019-01-25 | 平安科技（深圳）有限公司 | Parameter threshold determines method, apparatus and computer storage medium |
| CN109377059A (en)* | 2018-10-27 | 2019-02-22 | 平安医疗健康管理股份有限公司 | A kind of data processing method and equipment based on risk management and control |
| CN109858647A (en)* | 2018-12-21 | 2019-06-07 | 河海大学 | A kind of Regional Flooding Hazard Risk Assessment and predictor method coupling GIS and GBDT algorithm |
| CN109934465A (en)* | 2019-02-22 | 2019-06-25 | 北京启安智慧科技有限公司 | A kind of urban safety overall risk analysis method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258093B (en)* | 2020-11-25 | 2024-06-21 | 京东城市(北京)数字科技有限公司 | Data processing method and device for risk level, storage medium and electronic equipment |
- 2020
- 2020-11-25CNCN202011345770.1Apatent/CN112258093B/enactiveActive
- 2021
- 2021-11-15WOPCT/CN2021/130712patent/WO2022111327A1/ennot_activeCeased
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063608A (en)* | 2014-07-01 | 2014-09-24 | 天津市水文水资源勘测管理中心 | Method of determining underground water controlled water level by utilizing risk evaluation |
| CN104881783A (en)* | 2015-05-14 | 2015-09-02 | 中国科学院信息工程研究所 | E-bank account fraudulent conduct and risk detecting method and system |
| CN106096838A (en)* | 2016-06-14 | 2016-11-09 | 广州市恒迅技防系统有限公司 | Building fire safety evaluation method based on model of fuzzy synthetic evaluation and system |
| US20180300486A1 (en)* | 2017-04-18 | 2018-10-18 | International Business Machines Corporation | Management of Alerts Using a Budget-Dependent Adjustable Working Threshold |
| CN108900466A (en)* | 2018-05-30 | 2018-11-27 | 北京五八信息技术有限公司 | Prevent processing method, device, server and the storage medium of fallacious message |
| CN109272340A (en)* | 2018-07-19 | 2019-01-25 | 平安科技（深圳）有限公司 | Parameter threshold determines method, apparatus and computer storage medium |
| CN109377059A (en)* | 2018-10-27 | 2019-02-22 | 平安医疗健康管理股份有限公司 | A kind of data processing method and equipment based on risk management and control |
| CN109858647A (en)* | 2018-12-21 | 2019-06-07 | 河海大学 | A kind of Regional Flooding Hazard Risk Assessment and predictor method coupling GIS and GBDT algorithm |
| CN109934465A (en)* | 2019-02-22 | 2019-06-25 | 北京启安智慧科技有限公司 | A kind of urban safety overall risk analysis method and system |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022111327A1 (en)* | 2020-11-25 | 2022-06-02 | 京东城市(北京)数字科技有限公司 | Risk level data processing method and apparatus, and storage medium and electronic device |
| CN112686477A (en)* | 2021-01-28 | 2021-04-20 | 北京工业大数据创新中心有限公司 | Coal mill blockage early warning method and system |
| CN113793076A (en)* | 2021-05-14 | 2021-12-14 | 西安交通大学 | Dynamic risk pool monitoring method, system, equipment and readable storage medium |
| CN113793076B (en)* | 2021-05-14 | 2022-08-30 | 西安交通大学 | Dynamic risk pool monitoring method, system, equipment and readable storage medium |
| CN113793690B (en)* | 2021-08-31 | 2024-03-12 | 医渡云（北京）技术有限公司 | Method, device, storage medium and equipment for regional risk assessment of infectious diseases |
| CN113793690A (en)* | 2021-08-31 | 2021-12-14 | 医渡云（北京）技术有限公司 | Method, device, storage medium and equipment for evaluating regional risk of infectious disease |
| CN113919669A (en)* | 2021-09-26 | 2022-01-11 | 德联易控科技(北京)有限公司 | Method and device for determining risk information of risk control object |
| CN113919669B (en)* | 2021-09-26 | 2022-10-11 | 德联易控科技(北京)有限公司 | Method and device for determining risk information of risk control object |
| CN114330991A (en)* | 2021-11-17 | 2022-04-12 | 华能核能技术研究院有限公司 | Method and device for determining risk level of nuclear power production work |
| CN114553516A (en)* | 2022-02-18 | 2022-05-27 | 支付宝(杭州)信息技术有限公司 | Data processing method, device and equipment |
| CN114612138A (en)* | 2022-03-04 | 2022-06-10 | 杭州网易云音乐科技有限公司 | Advertising material processing method and device, computer storage medium, and electronic device |
| CN115033874A (en)* | 2022-05-09 | 2022-09-09 | 北京数美时代科技有限公司 | Account intercepting method and device, electronic equipment and computer storage medium |
| CN115293666A (en)* | 2022-10-10 | 2022-11-04 | 北京帮安迪信息科技股份有限公司 | Quick building method for park safety risk control platform based on low-code platform |
| CN118075011A (en)* | 2024-03-18 | 2024-05-24 | 北京安胜华信科技有限公司 | A request blocking method, product, device and medium |
| CN117976237A (en)* | 2024-03-25 | 2024-05-03 | 济南鸿泰医疗管理集团有限公司 | A medical data intelligent analysis system and method based on the Internet of Things |
| CN117976237B (en)* | 2024-03-25 | 2024-06-18 | 济南鸿泰医疗管理集团有限公司 | Medical data intelligent analysis system and method based on Internet of things |
| CN119296045A (en)* | 2024-12-11 | 2025-01-10 | 浙江安防职业技术学院 | Security monitoring methods and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112258093B (en) | 2024-06-21 |
| WO2022111327A1 (en) | 2022-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112258093B (en) | Data processing method and device for risk level, storage medium and electronic equipment | |
| CN112734559B (en) | Enterprise credit risk evaluation method and device and electronic equipment | |
| CN111797320B (en) | Data processing method, device, equipment and storage medium | |
| CN108764375B (en) | Method and device for cross-provincial matching of expressway freight vehicles | |
| CN111160959B (en) | User click conversion prediction method and device | |
| CN111126419B (en) | Dot clustering method and device | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN108664605B (en) | Model evaluation method and system | |
| CN109995611B (en) | Traffic classification model establishing and traffic classification method, device, equipment and server | |
| CN115545103A (en) | Abnormal data identification method, label identification method and abnormal data identification device | |
| CN114238267A (en) | Data quality evaluation method and device, electronic equipment and storage medium | |
| CN113553754A (en) | Memory, fire risk prediction model construction method, system and device | |
| CN113554350A (en) | Activity evaluation method and apparatus, electronic device and computer readable storage medium | |
| CN119379428A (en) | A method for dynamic monitoring and report generation of financial risks based on multi-source data | |
| CN112906765A (en) | RBF neural network-based customer money laundering risk grading method and system | |
| CN112835952A (en) | Stock index-based calculation analysis method and system | |
| CN112365156A (en) | Data processing method, data processing device, terminal and storage medium | |
| CN111046972A (en) | Feature selection method and device | |
| CN116739395A (en) | Enterprise outward migration prediction method, device, equipment and storage medium | |
| CN110059749A (en) | Screening technique, device and the electronic equipment of important feature | |
| Lampert et al. | The bane of skew: Uncertain ranks and unrepresentative precision | |
| CN113673595A (en) | A data processing method, device and equipment | |
| CN112700270A (en) | Grading data processing method, device, equipment and storage medium | |
| CN112529316A (en) | Service quality assessment method and device | |
| CN112308294A (en) | Default probability prediction method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |