CN111724007B - Risk evaluation method, evaluation device, intelligent system and storage device - Google Patents
Risk evaluation method, evaluation device, intelligent system and storage device Download PDFInfo
- Publication number
- CN111724007B CN111724007B CN201910204495.2A CN201910204495A CN111724007B CN 111724007 B CN111724007 B CN 111724007B CN 201910204495 A CN201910204495 A CN 201910204495A CN 111724007 B CN111724007 B CN 111724007B
- Authority
- CN
- China
- Prior art keywords
- target
- risk
- group
- cluster
- clustering
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a risk evaluation method, an evaluation device, an intelligent system and a storage device, wherein the evaluation method comprises the following steps: the method comprises the steps of obtaining a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected; acquiring risk statistical parameters of each group of target clusters to be selected; and determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy, as a target cluster. The risk assessment method and the risk assessment device can reduce the deviation of risk assessment of a single target object, are not only efficient, but also can achieve efficient and accurate risk assessment of the target object.
Description
Technical Field
The present disclosure relates to the field of risk management technologies, and in particular, to a risk evaluation method, an evaluation apparatus, an intelligent system, and a storage apparatus.
Background
In recent years, risk assessment has been widely developed in various fields. For example, in the financial industry, timely, efficient and accurate risk management is increasingly important as the consumer financial industry rapidly develops. However, if the traffic distribution area is too dispersed and the customer base is unbalanced, the risk management using the field research method has a very high hysteresis and labor cost.
For example, in store risk statistics, existing risk management has the following problems: (1) The original risk rating of the retail stores is unreasonable, and 98% of the retail stores fall (or default) into the general risk rating due to unstable contract volume; (2) The risk management of the new stores has hysteresis, and the rating of the new stores can be effectively rated only when the stores have more contract quantity.
That is, prior art risk management does not efficiently and accurately determine store risk levels for small, conglomerate numbers of retail stores and new stores.
Disclosure of Invention
The technical problem mainly solved by the application is to provide a risk evaluation method, an evaluation device, an intelligent system and a storage device, which can efficiently and accurately evaluate the risk of scattered target objects to be evaluated.
In order to solve the above technical problem, the first technical solution adopted by the present application is: provided is a risk evaluation method including:
the method comprises the steps of obtaining a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected;
acquiring risk statistical parameters of each group of target clusters to be selected;
and determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset conditions, as target clusters.
In order to solve the above technical problem, the second technical solution adopted by the present application is: provides a risk evaluation device, which comprises a cluster analysis calculation module, a risk statistical parameter calculation module and a target cluster determination module,
the cluster analysis and calculation module is used for acquiring a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected;
the risk statistical parameter calculation module is used for acquiring risk statistical parameters of each group of target clusters to be selected;
the target cluster determining module is used for determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset conditions, as a target cluster.
In order to solve the above technical problem, the third technical solution adopted by the present application is: an intelligent system is provided, wherein the intelligent system comprises a human-computer interaction control circuit, a processor and a computer program capable of running on the processor, which are coupled with each other, and when the processor executes the computer program, the risk evaluation method of any one of the above is realized.
In order to solve the above technical problem, a fourth technical solution adopted by the present application is: there is provided a storage device having program data stored thereon, the program data realizing any of the above-described risk assessment methods when executed by a processor.
Compared with the prior art, the beneficial effects of this application are: according to the method, a plurality of clustering strategies are firstly obtained, a plurality of target objects to be evaluated at present are clustered according to each clustering strategy, and a plurality of groups of target clusters to be selected including at least one target cluster to be selected are obtained; and acquiring the risk statistical parameters of each group of target clusters to be selected, determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset conditions, as target clusters. According to the risk parameter clustering method and system, the risk common clustering is carried out on the target objects according to the risk parameters, and then the risk condition of each target object can be determined based on the overall risk evaluation of the target objects in the clustering, so that the deviation of carrying out the risk evaluation on a single target object can be reduced, the efficiency is high, and the efficient and accurate risk evaluation on the target objects can be realized.
Drawings
FIG. 1 is a schematic flow chart diagram of one embodiment of the risk assessment method of the present application;
FIG. 2 is a schematic diagram illustrating a distribution of a group of candidate target clusters in step 101 of FIG. 1;
FIG. 3 is a schematic flow chart diagram of another embodiment of the risk assessment method of the present application;
FIG. 4 is a schematic configuration diagram of an embodiment of the risk assessment apparatus according to the present invention;
FIG. 5 is a schematic configuration diagram of another embodiment of the risk assessment apparatus according to the present application;
FIG. 6 is a schematic block diagram of an embodiment of the intelligent system of the present application;
FIG. 7 is a schematic structural diagram of an embodiment of a memory device according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
As shown in fig. 1, fig. 1 is a schematic flow chart of an embodiment of the risk assessment method of the present application.
The method comprises the following steps:
step 101: the method comprises the steps of obtaining a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected.
Clustering, the process of dividing a collection of physical or abstract objects into classes composed of similar objects, is called clustering. The clusters generated by clustering are a collection of a set of data objects that are similar to objects in the same cluster and distinct from objects in other clusters. "groups by groups, groups by people" has a large number of classification problems in the natural and social sciences. Clustering analysis, also known as cluster analysis, is a statistical analysis method for studying (sample or index) classification problems. The clustering analysis originates from taxonomy, but clustering is not equal to classification. Clustering differs from classification in that the class into which clustering is required is unknown. The content of the clustering analysis is very rich, and a system clustering method, an ordered sample clustering method, a dynamic clustering method, a fuzzy clustering method, a graph theory clustering method, a clustering prediction method and the like are adopted.
In the embodiment, the clustering strategy is to divide a plurality of target objects located within a preset distance range into a target cluster to be selected; the preset distance ranges in different clustering strategies are different. The preset distance range may be, but is not limited to, a circular range with a preset radius, and the preset radius may be 10m, 50m, 100m, 200m, 300m, 500m, 1000m, and the like, and may be set according to specific situations, which is not limited in the present application. The target object may be a legal person, a store, a natural person, etc., and is not limited herein.
In an alternative embodiment, the latitude and longitude information of the plurality of target objects is obtained, for example, the latitude and longitude information of the plurality of target objects is obtained through a GPS system. And determining the distance between a plurality of target objects according to the longitude and latitude information of each target object, and further determining a clustering strategy. And clustering the plurality of target objects according to each clustering strategy to obtain a group of target clusters to be selected. To illustrate the clustering strategy in this embodiment, please refer to fig. 2, and fig. 2 is a schematic distribution diagram of a group of candidate target clusters in step 101 of fig. 1.
As shown in fig. 2, in one particular embodiment, the target object is still illustrated as a store. A plurality of stores are scattered and distributed on the map. And acquiring longitude and latitude information of a plurality of stores, and determining the distance between the plurality of stores according to the longitude and latitude information of the plurality of stores. And taking all stores within the preset distance range as a group of stores to be selected, thereby obtaining one or more groups of stores to be selected. For example, in the present embodiment, the group of candidate store clusters includes 5 candidate store clusters. In other embodiments, a different number of candidate store groups are determined according to the number of stores, which is not limited in this application.
For example, the group of candidate store clusters includes 5 candidate store clusters, and the first candidate store cluster 11 and the second candidate store cluster 12 are two of them. The first group of candidate stores 11 includes 4 first stores 111, the second group of candidate stores 12 includes 10 second stores 121, and other groups of candidate stores in the same group of candidate stores are similar to the first group of candidate stores 11 and the second group of candidate stores 12, which is not described herein again. In other embodiments, the number of stores in the group of stores to be selected is determined by the total number of stores and a clustering strategy, such as a preset radius of a cluster, which is not limited in this application.
Similarly, according to a plurality of different other clustering strategies, clustering is performed on a plurality of stores to be evaluated currently according to each clustering strategy, so that a plurality of groups of stores to be selected with the number corresponding to the clustering strategies can be obtained.
Step 102: and acquiring the risk statistical parameters of each group of target clusters to be selected.
In this embodiment, the risk statistical parameters of each group of candidate target clusters include at least one of the following: an intra-cluster risk dispersion degree parameter of each target cluster to be selected in the group, an inter-cluster risk dispersion degree parameter between different target clusters to be selected in the group, and a risk stability degree parameter of each target cluster to be selected in the group.
In a preferred embodiment, the intra-group risk dispersion degree parameter of the candidate target group is a variance of risk levels of stores in the candidate target group. The parameter of the discrete degree of the inter-group risk between different target clusters to be selected in the group is the variance of the risk grade of each target cluster to be selected in the group. The risk grade of the target cluster to be selected is determined by the risk grade of each target object in the target cluster to be selected; and the risk stability degree parameter of the target cluster to be selected represents the risk grade change condition of the target cluster to be selected in a fixed time interval. Further, the risk stability degree parameter of the target cluster to be selected is a monthly risk stability value of the target cluster to be selected.
Therefore, in order to obtain the risk statistical parameters of each group of target clusters to be selected, the risk level of each target object is firstly obtained. In a specific embodiment, contract overdue rates of a plurality of target objects in a preset time period are firstly acquired, and risk levels of the target objects are determined by utilizing the contract overdue rates, for example, risk evaluation is performed on each target object in each target cluster to be selected respectively to obtain the risk level of each target object. For example, risk assessment is performed on each target object separately based on the contract overdue rate of the target object in the previous 4 months.
Further, in order to more accurately obtain the risk level of the target object with a smaller number of contracts, whether the number of contracts of the target object in the preset time period is lower than the preset number of contracts is judged; and if the number of the target objects is less than the preset number of the contracts, determining the average value of the risk levels of other target objects of the target cluster in which the target objects less than the preset number of the contracts are located as the risk level of the target objects less than the preset number of the contracts. For example, taking the target object as a store, the risk levels of other stores in the group of stores to be selected where the number of contracts is lower than the preset number of contracts are averaged, and the average of the risk levels of the other stores is taken as the risk level of the store where the number of contracts is lower than the preset number of contracts. In other embodiments, the risk level of the store with the contract quantity lower than the preset contract quantity may be determined according to other manners, which is not limited in this application. Generally, the target objects with the number of contracts being lower than the preset number of contracts are new target objects, and when the target objects are applied to a store scene, the target objects are new stores.
In a specific embodiment, if the contract overdue rate of the target object for the preset time period is [0,0.035], the risk rating of the target object is 1; the risk level of the target object is 2 if the contract overdue rate of the target object in the preset time period is (0.035,0.07), the risk level of the target object is 3 if the contract overdue rate of the target object in the preset time period is (0.07,0.105), the risk level of the target object is 4 if the contract overdue rate of the target object in the preset time period is (0.105,0.195), and the risk level of the target object is 5 if the contract overdue rate of the target object in the preset time period exceeds 0.195.
After the risk grade of the target object is obtained through the method, the intra-group risk discrete degree parameter of each target cluster to be selected is obtained through calculation. Specifically, the risk grade of the target object is utilized to calculate the variance of the risk grade of each target object in the target cluster to be selected, and the intra-cluster risk discrete degree parameter is determined. Further, the risk level of the target cluster to be selected is determined through the variance of the risk levels of all target objects in the target cluster to be selected. And calculating to obtain the variance of the risk grade of each target cluster to be selected in the group of each target cluster to be selected by utilizing the risk grade of each target cluster to be selected, and determining the inter-cluster risk discrete degree parameter between different target clusters to be selected.
In an optional embodiment, the risk stability degree parameter of each candidate target cluster in different candidate target clusters is further determined according to the risk level variation of the candidate target clusters in a preset interval fixed time period.
In a specific embodiment, with continued reference to fig. 2, a first candidate target cluster 11 and a second candidate target cluster 12 are illustrated.
First, the risk level of each target object in the first target cluster 11 to be selected and the second target cluster 12 to be selected is obtained. The variance of the risk level of each first target object 111 in the first candidate target cluster 11 is determined according to the risk level of each first target object 111 in the first candidate target cluster 11. And determining the variance of the risk level of each second target object 111 in the second candidate target cluster 12 according to the risk level of each second target object 121 in the second candidate target cluster 12. Similarly, the variance of the risk level of each target object in each cluster of targets to be selected in the group can be obtained. In a specific embodiment, the average value of the variances of the risk levels of the target objects in the candidate target clusters in the group is used as the intra-cluster risk dispersion degree parameter of the candidate target clusters. In other embodiments, the variance of the risk level of each target object in each candidate target cluster in the group may be processed in other manners to serve as the intra-cluster risk dispersion degree parameter of the candidate target cluster, which is not limited in the present application.
Further, an average risk level of each first target object 111 in the first target cluster 11 to be selected is obtained and used as a risk level of the first target cluster 11 to be selected; the average risk level of each second target object 121 in the second candidate target cluster 12 is obtained as the risk level of the second candidate target cluster 12. In the same way, the risk level of other target clusters to be selected can be obtained. And further acquiring the variance of the risk grade of the first target cluster 11 to be selected, the risk grade of the second target cluster 12 to be selected and the risk grade of other target clusters to be selected. In a specific embodiment, the average value of the variance of the risk levels in each candidate target cluster in the group is used as the parameter of the inter-cluster risk dispersion degree of the candidate target cluster.
Further, at least two-month risk levels of the first candidate target cluster 11 are obtained, and a variance of the at least two-month risk levels of the first candidate target cluster 11 is used as a monthly risk stable value of the first candidate target cluster 11. Similarly, the monthly risk stability values of the second candidate target cluster 12 and each of the other candidate target clusters can be obtained. For example, if the risk levels of the first candidate target cluster 11 for two months are 5 and 5, respectively, the monthly risk stability value of the first candidate target cluster 11 is 0, and a smaller monthly risk stability value indicates a more stable risk level of the candidate target cluster. In a specific embodiment, in each candidate target cluster, a ratio of the number of the candidate target clusters, of which monthly risk stability values are smaller than a preset stability value, to the total number of the candidate target clusters is used as a risk stability degree parameter in the group, that is, the larger the ratio, the more stable the risk level of the candidate target cluster is. In another specific embodiment, the sum of the monthly risk stability values of each candidate target cluster is used as the risk stability parameter in the group, that is, the smaller the sum of the monthly risk stability values of each candidate target cluster is, the more stable the risk level of the candidate target cluster is. In other embodiments, the risk stability degree parameter in the group may also be determined according to the weekly risk level or the quarterly risk level of the target cluster to be selected, and the like, and it is only necessary that the risk stability degree parameter of the target cluster to be selected represents the risk level change condition of the target cluster to be selected in a fixed time interval, and the application does not limit this.
Step 103: and determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset conditions, as target clusters.
Specifically, if the intra-group risk dispersion degree parameter in each group of the target group to be selected is smaller than a first threshold, the intra-group risk dispersion degree parameter in the group is larger than a second threshold, that is, the intra-group dispersion program is small, the inter-group dispersion degree is high, and the difference between the intra-group risk dispersion degree parameter and the intra-group risk dispersion degree parameter in the group is larger than a third threshold; and/or when the risk stability degree parameter in the group is larger than a fourth threshold value, determining the clustering strategy of the group of target clusters to be selected as a target clustering strategy, and determining the group of target clusters to be selected obtained by corresponding clustering of the target clustering strategy as a target cluster.
The risk stability degree parameter is the ratio of the number of the target clusters to be selected with the monthly risk stability value smaller than the preset stability value to the total number of the clusters of the store to be selected. The first threshold, the second threshold, the third threshold, and the fourth threshold are set according to specific situations, which are not limited in the present application.
In this embodiment, at least one group of target clusters to be selected whose risk statistical parameters satisfy preset parameter conditions is selected. If the selected target clusters to be selected are a group, taking the selected target clusters to be selected as target clusters; and if the selected target clusters to be selected are multiple groups, extracting a group of target clusters to be selected meeting preset conditions from the multiple groups of target clusters to be selected as target clusters.
In a specific embodiment, if a plurality of clustering strategies meeting preset conditions exist, acquiring a target clustering amount of which the number of target clustering in a group exceeds a preset value; and determining the target cluster to be selected with the maximum ratio of the target cluster amount to the total number of the target clusters in the group as the target cluster.
For example, if the preset value is 4,a, the number of the candidate target clusters in which the number of the target objects in the group a exceeds 4 is 6, and the total number of the candidate target clusters in the group is 10, the ratio of the number of the candidate target clusters in which the number of the target objects in the group a exceeds 4 to the total number of the candidate target clusters in the group a is 60%. The ratio of the number of the target clusters to be selected with the number of the target objects in the group B exceeding 4 to the total number of the target clusters to be selected in the group B is 50%. And taking the A group of target clusters to be selected as target clusters.
In another embodiment, after determining a group of target clusters, further performing risk evaluation on each target cluster in the group, and determining the risk evaluation result of the target object in the target cluster from the risk evaluation result of each target cluster.
Specifically, the overall contract overdue rate of each target group in the preset time period is obtained according to the contract overdue rates of the multiple target objects in the preset time period, and risk evaluation is respectively carried out on each target group according to the overall contract overdue rate of each target store group in the preset time period. The overall contract overdue rate of a target cluster is the ratio of the contract overdue number of each target object in the target cluster in a preset time period to the total contract number.
In a specific embodiment, if the overall contract overdue rate of the target cluster in the preset time period is [0,0.035], the risk rating of the target cluster is 1; the risk grade of the target cluster is 2 if the overall contract overdue rate of the target cluster in the preset time period is (0.035,0.07), the risk grade of the target cluster is 3 if the overall contract overdue rate of the target cluster in the preset time period is (0.07,0.105), the risk grade of the target cluster is 4 if the overall contract overdue rate of the target cluster in the preset time period is (0.105,0.195), and the risk grade of the target cluster is 5 if the overall contract overdue rate of the target cluster in the preset time period exceeds 0.195.
Different from the prior art, the risk condition of each target object is determined based on the overall risk assessment of the target objects in the cluster by clustering the risk common of the target objects according to the risk parameters, so that the deviation of risk assessment of a single target object can be reduced, the efficiency is high, and the target objects can be efficiently and accurately assessed for the risk.
As shown in fig. 3, fig. 3 is a schematic flow chart of another embodiment of the risk assessment method of the present application. The difference between this embodiment and any of the above embodiments is that step 301 is included before obtaining a plurality of clustering strategies, and clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected.
The risk evaluation method of the present embodiment specifically includes:
step 301: and acquiring a plurality of target objects which are positioned in a preset position range and have the number of contracts not exceeding a contract preset value.
In a specific embodiment, the target object is taken as a store as an example. The number of contracts is the total number of contracts in the last 4 months, and the preset value of the contract is 60. Namely, if the target object is located in the preset position range and the number of contracts does not exceed the contract preset value, the target object is a clustering target object, and the target object can be a small store when being applied to a store risk assessment scene; if the target object is located in the preset position range and the number of the contracts exceeds the contract preset value, the store is indicated to be a non-clustering target object, and the store can be a big store when the store is applied to a store risk assessment scene. Firstly, the clustering analysis is carried out on the clustering target objects after the non-clustering target objects are removed, so that the risk stability of the clustering target objects can be ensured.
Step 302: the method comprises the steps of obtaining a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected.
This step is the same as step 101, and please refer to step 101 and the description of the relevant text, which are not described herein again.
Step 303: and acquiring the risk statistical parameters of each group of target clusters to be selected.
This step is the same as step 102, and please refer to step 102 and the description of the relevant text specifically, which is not described herein again.
Step 304: and determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by correspondingly clustering the clustering strategies meeting the preset conditions, as target clusters.
This step is the same as step 103, and please refer to step 103 and the description of the relevant text, which are not described herein again.
Different from the prior art, the risk condition of each target object is determined based on the overall risk assessment of the target objects in the cluster by clustering the risk common of the target objects according to the risk parameters, so that the deviation of risk assessment of a single target object can be reduced, the efficiency is high, and the target objects can be efficiently and accurately assessed for the risk.
Different from any one of the above embodiments, in the embodiment, first, a plurality of target objects which are located within a preset position range and have a number of contracts not exceeding a preset number of contracts are obtained as target objects for determining a clustering strategy, so that the risk stability of the target objects within a preset number of contracts can be effectively ensured, and efficient and accurate risk assessment on the target objects is further improved. Obviously, the above is an example performed by being smaller than a certain preset value, and the method of the present invention can be applied to other preset value ranges.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of the risk assessment device of the present application. In this embodiment, the risk evaluation device includes an acquisition cluster analysis calculation module 401, a risk statistical parameter calculation module 402, and a target cluster determination module 403.
In this embodiment, the cluster analysis calculating module 401 obtains a plurality of target objects located within a preset position range and having a contract number not exceeding a contract preset value.
In one specific embodiment, the target object is a store, the number of contracts is the total number of contracts in the last 4 months, and the preset value of the contract is 60. Namely, if the target object is located in the preset position range and the number of contracts does not exceed the contract preset value, the target object is a clustering target object, and the target object can be a small store when the target object is applied to a store risk assessment scene; if the target object is located in the preset position range and the number of the contracts exceeds the contract preset value, the store is indicated to be a non-clustering target object, and the store can be a big store when the store is applied to a store risk assessment scene. Firstly, the clustering analysis is carried out on the clustering target objects after the non-clustering target objects are removed, so that the risk stability of the clustering target objects can be ensured.
In this embodiment, the clustering analysis and calculation module 401 obtains a plurality of clustering strategies, and clusters a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, where each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected includes at least one target cluster to be selected.
In the embodiment, the preset clustering strategy is to divide stores located within a preset distance range among a plurality of target objects into a target cluster to be selected; the preset distance ranges in different preset clustering strategies are different. The preset distance range is a circular range with a preset radius, and the preset radius may be 10m, 50m, 100m, 200m, 300m, 500m, 1000m, and the like, and may be set according to specific situations, which is not limited in the present application.
In a preferred embodiment, the cluster analysis calculating module 401 in an optional embodiment obtains longitude and latitude information of a plurality of target objects, such as the longitude and latitude information of a plurality of target objects obtained by a GPS system. And determining the distance between a plurality of target objects according to the longitude and latitude information of each target object, and further determining a clustering strategy. And clustering the target objects according to each clustering strategy to obtain a group of target clusters to be selected.
In this embodiment, the risk statistical parameter calculation module 402 obtains risk statistical parameters of multiple groups of target clusters to be selected.
In this embodiment, the risk statistical parameter of each group of candidate target clusters includes at least one of the following: the intra-group risk dispersion degree parameter of each target cluster to be selected in the group, the inter-group risk dispersion degree parameter between different target clusters to be selected in the group, and the risk stability degree parameter of each target cluster to be selected in the group.
Therefore, in order to obtain the risk statistical parameters of each group of candidate target clusters, in this embodiment, the risk statistical parameter calculation module 402 first obtains the risk level of each target object. In a specific embodiment, contract overdue rates of a plurality of target objects in a preset time period are obtained, and risk levels of the target objects are determined by using the contract overdue rates, for example, risk evaluation is performed on each target object in each target cluster to be selected respectively, so that risk levels of each target object are obtained. For example, risk assessment is performed on each target object separately based on the contract overdue rate of the target object in the previous 4 months.
Further, in order to obtain the risk level of the target object with a smaller number of contracts more accurately, whether the number of contracts of the target object in the preset time period is lower than the preset number of contracts is judged; and if the number of the target objects is less than the preset number of the contracts, determining the average value of the risk levels of the other target objects of the target cluster in which the target objects with the number less than the preset number of the contracts are located as the risk level of the target objects with the number less than the preset number of the contracts. For example, taking the target object as a store, the risk levels of other stores in the group of stores to be selected where the number of contracts is less than the preset number of contracts are averaged, and the average of the risk levels of the other stores is taken as the risk level of the store where the number of contracts is less than the preset number of contracts. In other embodiments, the risk level of the store with the contract number lower than the preset contract number may be determined in other manners, which is not limited in this application. Generally, the target objects with the number of contracts being lower than the preset number of contracts are new target objects, and when the method is applied to a store scene, the target objects are new stores.
In a specific embodiment, if the contract overdue rate of the target object for the preset time period is [0,0.035], the risk rating of the target object is 1; the risk grade of the target object is 2 if the contract overdue rate of the target object in the preset time period is (0.035,0.07), the risk grade of the target object is 3 if the contract overdue rate of the target object in the preset time period is (0.07,0.105), the risk grade of the target object is 4 if the contract overdue rate of the target object in the preset time period is (0.105,0.195), and the risk grade of the target object is 5 if the contract overdue rate of the target object in the preset time period exceeds 0.195.
After the risk level of each target object is obtained in the above manner, the risk statistical parameter calculation module 402 calculates and obtains the intra-group risk discrete degree parameter of each target group to be selected. Specifically, the risk statistical parameter calculation module 402 calculates the variance of the risk levels of the target objects in the target cluster to be selected by using the risk levels of the target objects, and determines the intra-cluster risk discrete degree parameter. Further, the risk level of the target cluster to be selected is determined through the variance of the risk levels of all target objects in the target cluster to be selected. And calculating to obtain the variance of the risk grade of each target cluster to be selected in the group of each target cluster to be selected by utilizing the risk grade of each target cluster to be selected, and determining the inter-cluster risk discrete degree parameter between different target clusters to be selected.
In an optional embodiment, the risk stability degree parameter of each target cluster to be selected in different target cluster groups to be selected is further determined according to the risk level change of the target cluster to be selected in a preset interval fixed time period.
In this embodiment, the target cluster determining module 403 determines a clustering strategy meeting a preset condition according to the risk statistical parameters of each group of target clusters to be selected, and determines a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset condition, as a target cluster.
Specifically, if the intra-group risk dispersion degree parameter in each group of the target group to be selected is smaller than a first threshold, the intra-group risk dispersion degree parameter in the group is larger than a second threshold, that is, the intra-group dispersion program is small, the inter-group dispersion degree is high, and the difference between the intra-group risk dispersion degree parameter and the intra-group risk dispersion degree parameter in the group is larger than a third threshold; and/or when the risk stability degree parameter in the group is larger than a fourth threshold value, determining the clustering strategy of the group of target clusters to be selected as a target clustering strategy, and determining the group of target clusters to be selected obtained by corresponding clustering of the target clustering strategy as a target cluster.
The risk stability degree parameter is the ratio of the number of the target clusters to be selected with the monthly risk stability value smaller than the preset stability value to the total number of the clusters of the store to be selected. The first threshold, the second threshold, the third threshold, and the fourth threshold are set according to specific situations, and the present application does not limit this.
In this embodiment, at least one group of target clusters to be selected whose risk statistical parameters satisfy preset parameter conditions is selected. If the selected target clusters to be selected are a group, taking the selected target clusters to be selected as target clusters; and if the selected target clusters to be selected are multiple groups, extracting a group of target clusters to be selected meeting preset conditions from the multiple groups of target clusters to be selected as target clusters.
In a specific embodiment, if a plurality of clustering strategies meeting a preset condition are adopted, the target clustering amount of which the number of target clustering in a group exceeds a preset value is obtained; and determining the target cluster to be selected with the maximum ratio of the target cluster amount to the total number of the target clusters in the group as the target cluster.
For example, the preset value is 4,a, the number of candidate store clusters in which the number of target objects in the group a exceeds 4 is 6, and the total number of candidate target clusters in the group is 10, and then the ratio of the number of candidate target clusters in which the number of target objects in the group a exceeds 4 to the total number of candidate target clusters in the group is 60%. The ratio of the number of the target clusters to be selected with the number of the target objects in the group B exceeding 4 to the total number of the target clusters to be selected in the group B is 50%. And taking the A group of target clusters to be selected as target clusters.
In other embodiments, after determining a set of target clusters, the risk evaluation device further includes, in addition to the risk evaluation device, an acquisition cluster analysis calculation module 501, a risk statistical parameter calculation module 502, a target cluster determination module 503, and a risk evaluation calculation module 504. As shown in fig. 5, the risk evaluation calculation module 504 is configured to perform risk evaluation on each target cluster in the group, and determine a risk evaluation result of a target object in the target cluster according to the risk evaluation result of each target cluster.
Specifically, the risk evaluation calculation module 504 obtains the overall contract overdue rate of each target cluster in the preset time period according to the contract overdue rates of the targets in the preset time period, and performs risk evaluation on each target cluster according to the overall contract overdue rate of each target cluster in the preset time period. The overall contract overdue rate of a target cluster is the ratio of the contract overdue number of each target object in the target cluster in a preset time period to the total contract number.
In a specific embodiment, if the overall contract overdue rate for the target cohort over the preset time period is [0,0.035], the risk rating for the target cohort is 1; the risk grade of the target cluster is 2 if the overall contract overdue rate of the target cluster in the preset time period is (0.035,0.07), the risk grade of the target cluster is 3 if the overall contract overdue rate of the target cluster in the preset time period is (0.07,0.105), the risk grade of the target cluster is 4 if the overall contract overdue rate of the target cluster in the preset time period is (0.105,0.195), and the risk grade of the target cluster is 5 if the overall contract overdue rate of the target cluster in the preset time period exceeds 0.195.
Different from the prior art, the risk condition of each target object is determined based on the overall risk assessment of the target objects in the cluster by clustering the risk common of the target objects according to the risk parameters, so that the deviation of risk assessment of a single target object can be reduced, the efficiency is high, and the target objects can be efficiently and accurately assessed for the risk.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of the intelligent system of the present application. The intelligent system is an intelligent customer service system or other intelligent terminals, network terminals, a PC (personal computer) and the like. The intelligent system 60 of this embodiment includes a human-computer interaction control circuit 602, and a processor 601 coupled to the human-computer interaction control circuit. A computer program executable on the processor 601. The processor 601, when executing the computer program, can implement the risk assessment method of any of the embodiments described in fig. 1 to 3 and the associated text.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a memory device according to an embodiment of the present application. The application also provides a structural schematic diagram of an implementation mode of the storage device. In this embodiment, the storage device 70 stores processor-executable computer instructions 71, and the computer instructions 71 are used for executing the method for evaluating an insurance product according to any one of the embodiments described in fig. 1 to 3 and the associated text.
The storage device 70 may be a medium that can store the computer instructions 71, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may be a server that stores the computer instructions, and the server can send the stored computer instructions 71 to other devices for operation, or can execute the stored computer instructions by itself.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a unit or a division of units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each of the units may exist alone physically, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
The above embodiments are merely examples and are not intended to limit the scope of the present disclosure, and all modifications, equivalents, and flow charts using the contents of the specification and drawings of the present disclosure or those directly or indirectly applied to other related technical fields are intended to be included in the scope of the present disclosure.
Claims (12)
1. A risk assessment method, characterized in that the assessment method comprises:
the method comprises the steps of obtaining a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected;
acquiring risk statistical parameters of each group of target clusters to be selected;
determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset conditions, as target clusters;
and respectively performing risk evaluation on each target cluster in the group, and determining the risk evaluation result of the target object in the target cluster according to the risk evaluation result of each target cluster.
2. The risk assessment method according to claim 1,
the acquiring of the risk statistical parameters of each group of target clusters to be selected comprises:
acquiring the risk level of a target object in each target cluster to be selected;
calculating to obtain intra-group risk discrete degree parameters of each target cluster to be selected by utilizing the risk grade of the target object; determining inter-cluster risk discrete degree parameters between different target clusters to be selected in each group of target clusters to be selected according to the intra-cluster risk discrete degree parameters of each target cluster to be selected; and/or determining the risk stability degree parameter of each target cluster to be selected in different target cluster groups to be selected according to the risk grade change of the target cluster to be selected in a preset interval fixed time period.
3. The risk evaluation method according to claim 2, wherein the calculating of the intra-group risk dispersion degree parameter of each target cluster to be selected by using the risk level of the target object comprises:
calculating the variance of the risk grade of each target object in the target cluster to be selected by utilizing the risk grade of the target object, and determining the intra-cluster risk discrete degree parameter;
determining inter-cluster risk dispersion degree parameters between different target clusters to be selected in each group of target clusters to be selected according to the intra-cluster risk dispersion degree parameters of each target cluster to be selected comprises:
determining the risk grade of the target cluster to be selected according to the variance of the risk grade of each target object in the target cluster to be selected;
and calculating to obtain the variance of the risk grade of each target cluster to be selected in the group of each target cluster to be selected by utilizing the risk grade of each target cluster to be selected, and determining the inter-cluster risk discrete degree parameter between different target clusters to be selected.
4. The risk evaluation method according to claim 2 or 3, wherein the determining a clustering strategy meeting a preset condition according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset condition, as a target cluster comprises:
if the intra-group risk dispersion degree parameter in each group of the target group to be selected is smaller than a first threshold value, the inter-group risk dispersion degree parameter in the group is larger than a second threshold value, and the difference between the inter-group risk dispersion degree parameter in the group and the intra-group risk dispersion degree parameter is larger than a third threshold value; and/or when the risk stability degree parameter in the group is greater than a fourth threshold value, determining a clustering strategy of the group of target clusters to be selected as a target clustering strategy, and determining a group of target clusters to be selected, which are obtained by clustering corresponding to the target clustering strategy, as a target cluster.
5. The risk evaluation method according to claim 2, wherein the step of obtaining the risk level of the target object in each target cluster to be selected comprises:
respectively obtaining the contract overdue rate of each target object in a preset time period, and determining the risk level of each target object in the preset time period by using the contract overdue rate.
6. The risk assessment method according to claim 5, wherein the step of respectively acquiring the contract overdue rate of each target object in a preset time period and determining the risk level of each target object in the preset time period by using the contract overdue rate comprises:
judging whether the contract quantity of the target object in the preset time period is lower than a preset contract quantity or not;
and if the number of the target objects is less than the preset number of the contracts, determining the average value of the risk levels of the other target objects of the target cluster in which the target objects less than the preset number of the contracts are located as the risk level of the target objects less than the preset number of the contracts.
7. The risk assessment method according to claim 1,
the clustering strategy is to divide the target objects positioned in a preset distance range in the plurality of target objects into a target cluster to be selected; the preset distance ranges corresponding to different clustering strategies are different;
the obtaining of the multiple clustering strategies and the clustering of the multiple target objects to be evaluated at present according to each clustering strategy to obtain multiple groups of target clusters to be selected comprises the following steps:
acquiring longitude and latitude information of a plurality of target objects, and determining the distance between the plurality of target objects according to the longitude and latitude information of the plurality of target objects;
and clustering the target objects according to each clustering strategy based on the distances among the target objects to obtain a group of target clusters to be selected.
8. The risk evaluation method according to claim 1, wherein the step of determining a clustering strategy meeting a preset condition according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by corresponding clustering according to the clustering strategy meeting the preset condition, as a target cluster specifically comprises:
if the number of the clustering strategies meeting the preset condition is multiple, acquiring the target clustering amount of which the number of the target clustering in the group exceeds the preset value; and determining the target cluster to be selected with the maximum ratio of the target cluster amount to the total number of the target clusters in the group as the target cluster.
9. The risk evaluation method according to claim 1, wherein the obtaining of the plurality of clustering strategies and the clustering of the plurality of target objects to be evaluated according to each clustering strategy obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and before the step of including at least one target cluster to be selected in each group of target clusters to be selected, the method further comprises:
and acquiring the target objects which are positioned in a preset position range and have the contract quantity not exceeding a contract preset value.
10. A risk assessment device for implementing the risk assessment method of claim 1, the risk assessment device comprising a cluster analysis calculation module, a risk statistical parameter calculation module, a target cluster determination module, a risk assessment calculation module,
the cluster analysis and calculation module is used for acquiring a plurality of clustering strategies, clustering a plurality of target objects to be evaluated currently according to each clustering strategy to obtain a plurality of groups of target clusters to be selected, wherein each clustering strategy corresponds to one group of target clusters to be selected, and each group of target clusters to be selected comprises at least one target cluster to be selected;
the risk statistical parameter calculation module is used for acquiring risk statistical parameters of each group of target clusters to be selected;
the target cluster determining module is used for determining a clustering strategy meeting preset conditions according to the risk statistical parameters of each group of target clusters to be selected, and determining a group of target clusters to be selected, which are obtained by correspondingly clustering the clustering strategies meeting the preset conditions, as a target cluster;
the risk evaluation calculation module is used for respectively carrying out risk evaluation on each target cluster in the group, and determining the risk evaluation result of the target object in the target cluster according to the risk evaluation result of each target cluster.
11. An intelligent system, characterized in that the intelligent system comprises a human-computer interaction control circuit, a processor and a computer program operable on the processor, which are coupled to each other, and when the processor executes the computer program, the steps of the risk assessment method according to any one of claims 1 to 9 are implemented.
12. A storage device having stored thereon program data that, when executed by a processor, implements the risk assessment method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204495.2A CN111724007B (en) | 2019-03-18 | 2019-03-18 | Risk evaluation method, evaluation device, intelligent system and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204495.2A CN111724007B (en) | 2019-03-18 | 2019-03-18 | Risk evaluation method, evaluation device, intelligent system and storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111724007A CN111724007A (en) | 2020-09-29 |
| CN111724007B true CN111724007B (en) | 2022-12-06 |
Family
ID=72563079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910204495.2A Active CN111724007B (en) | 2019-03-18 | 2019-03-18 | Risk evaluation method, evaluation device, intelligent system and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111724007B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651190A (en) * | 2016-12-28 | 2017-05-10 | 深圳微众税银信息服务有限公司 | Enterprise risk level assessment method and system |
| CN106779723A (en) * | 2016-12-26 | 2017-05-31 | 中国银联股份有限公司 | A kind of mobile terminal methods of risk assessment and device |
| CN107194767A (en) * | 2017-05-17 | 2017-09-22 | 深圳前海跨海侠跨境电子商务有限公司 | A kind of indicating risk method and system for being used to buy platform on behalf |
| CN107330619A (en) * | 2017-06-30 | 2017-11-07 | 国核电力规划设计研究院有限公司 | Determine method, device and the computer-readable recording medium of comprehensive evaluation value |
| CN107369095A (en) * | 2017-06-15 | 2017-11-21 | 阿里巴巴集团控股有限公司 | A kind of data processing method of vehicle insurance business, apparatus and system |
| CN107544253A (en) * | 2017-03-17 | 2018-01-05 | 中国人民解放军91049部队 | Based on the retired method of controlling security of large-scale missile equipment for improving Based on Entropy method |
| CN107578331A (en) * | 2017-09-19 | 2018-01-12 | 马上消费金融股份有限公司 | The method and system of risk monitoring and control after a kind of loan |
| CN107679946A (en) * | 2017-09-28 | 2018-02-09 | 平安科技（深圳）有限公司 | Fund Products Show method, apparatus, terminal device and storage medium |
| CN107798597A (en) * | 2017-10-09 | 2018-03-13 | 上海二三四五金融科技有限公司 | A kind of dynamic excessive risk visitor group detection method and system |
| CN108009711A (en) * | 2017-11-23 | 2018-05-08 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and readable storage medium storing program for executing |
| CN108053149A (en) * | 2018-01-05 | 2018-05-18 | 东南大学 | A kind of photovoltaic electric station grid connection methods of risk assessment for considering meteorologic factor |
| CN108108866A (en) * | 2016-11-24 | 2018-06-01 | 阿里巴巴集团控股有限公司 | A kind of method and device of risk control |
| CN108376310A (en) * | 2018-02-06 | 2018-08-07 | 深圳前海大观信息技术有限公司 | Building fire risk class appraisal procedure |
| CN108846532A (en) * | 2018-03-21 | 2018-11-20 | 宁波工程学院 | Business risk appraisal procedure and device applied to logistics supply platform chain |
| CN108959934A (en) * | 2018-06-11 | 2018-12-07 | 平安科技（深圳）有限公司 | Safety risk estimating method, device, computer equipment and storage medium |
| CN108985602A (en) * | 2018-07-04 | 2018-12-11 | 国网经济技术研究院有限公司 | It is a kind of meter and risk power grid classification item input-output evaluation of urban method and system |
| CN109064002A (en) * | 2018-07-26 | 2018-12-21 | 阿里巴巴集团控股有限公司 | Vehicle risk appraisal procedure, device and equipment |
| CN109387715A (en) * | 2018-10-29 | 2019-02-26 | 全球能源互联网研究院有限公司 | A kind of converter valve state online evaluation method and device based on grey cluster |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160012235A1 (en) * | 2014-02-10 | 2016-01-14 | Vivo Security Inc. | Analysis and display of cybersecurity risks for enterprise data |
-
2019
- 2019-03-18 CN CN201910204495.2A patent/CN111724007B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108108866A (en) * | 2016-11-24 | 2018-06-01 | 阿里巴巴集团控股有限公司 | A kind of method and device of risk control |
| CN106779723A (en) * | 2016-12-26 | 2017-05-31 | 中国银联股份有限公司 | A kind of mobile terminal methods of risk assessment and device |
| CN106651190A (en) * | 2016-12-28 | 2017-05-10 | 深圳微众税银信息服务有限公司 | Enterprise risk level assessment method and system |
| CN107544253A (en) * | 2017-03-17 | 2018-01-05 | 中国人民解放军91049部队 | Based on the retired method of controlling security of large-scale missile equipment for improving Based on Entropy method |
| CN107194767A (en) * | 2017-05-17 | 2017-09-22 | 深圳前海跨海侠跨境电子商务有限公司 | A kind of indicating risk method and system for being used to buy platform on behalf |
| CN107369095A (en) * | 2017-06-15 | 2017-11-21 | 阿里巴巴集团控股有限公司 | A kind of data processing method of vehicle insurance business, apparatus and system |
| CN107330619A (en) * | 2017-06-30 | 2017-11-07 | 国核电力规划设计研究院有限公司 | Determine method, device and the computer-readable recording medium of comprehensive evaluation value |
| CN107578331A (en) * | 2017-09-19 | 2018-01-12 | 马上消费金融股份有限公司 | The method and system of risk monitoring and control after a kind of loan |
| CN107679946A (en) * | 2017-09-28 | 2018-02-09 | 平安科技（深圳）有限公司 | Fund Products Show method, apparatus, terminal device and storage medium |
| CN107798597A (en) * | 2017-10-09 | 2018-03-13 | 上海二三四五金融科技有限公司 | A kind of dynamic excessive risk visitor group detection method and system |
| CN108009711A (en) * | 2017-11-23 | 2018-05-08 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and readable storage medium storing program for executing |
| CN108053149A (en) * | 2018-01-05 | 2018-05-18 | 东南大学 | A kind of photovoltaic electric station grid connection methods of risk assessment for considering meteorologic factor |
| CN108376310A (en) * | 2018-02-06 | 2018-08-07 | 深圳前海大观信息技术有限公司 | Building fire risk class appraisal procedure |
| CN108846532A (en) * | 2018-03-21 | 2018-11-20 | 宁波工程学院 | Business risk appraisal procedure and device applied to logistics supply platform chain |
| CN108959934A (en) * | 2018-06-11 | 2018-12-07 | 平安科技（深圳）有限公司 | Safety risk estimating method, device, computer equipment and storage medium |
| CN108985602A (en) * | 2018-07-04 | 2018-12-11 | 国网经济技术研究院有限公司 | It is a kind of meter and risk power grid classification item input-output evaluation of urban method and system |
| CN109064002A (en) * | 2018-07-26 | 2018-12-21 | 阿里巴巴集团控股有限公司 | Vehicle risk appraisal procedure, device and equipment |
| CN109387715A (en) * | 2018-10-29 | 2019-02-26 | 全球能源互联网研究院有限公司 | A kind of converter valve state online evaluation method and device based on grey cluster |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111724007A (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107657500B (en) | Stock recommendation method and server | |
| CN108833139B (en) | OSSEC alarm data aggregation method based on category attribute division | |
| CN104820862A (en) | Establishment method for electricity market supply-demand early-warning model based on dynamic clustering | |
| CN113486983A (en) | Big data office information analysis method and system for anti-fraud processing | |
| CN111724007B (en) | Risk evaluation method, evaluation device, intelligent system and storage device | |
| CN116610821B (en) | Knowledge graph-based enterprise risk analysis method, system and storage medium | |
| CN112506901A (en) | Data quality measuring method, device and medium | |
| CN116611914A (en) | Salary prediction method and device based on grouping statistics | |
| CN110580265A (en) | ETL task processing method, device, equipment and storage medium | |
| CN115860465A (en) | Enterprise associated data processing early warning method, system and device | |
| KR20130142353A (en) | System for monitoring client | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN114579157A (en) | Application updating method and device, computer equipment and storage medium | |
| CN114897097A (en) | Power consumer portrait method, device, equipment and medium | |
| CN110246026B (en) | Data transfer output combination setting method and device and terminal equipment | |
| CN114626730A (en) | Resource allocation method, device, computer equipment and computer readable storage medium | |
| CN111722977A (en) | System inspection method and device and electronic equipment | |
| CN111507397A (en) | Abnormal data analysis method and device | |
| CN110162747A (en) | A kind of pretreatment and recommended method based on feature | |
| CN115563555B (en) | Data-driven Internet card user value classification method, device and medium | |
| CN113434705B (en) | Cash-up quota adjusting method and system based on relation map | |
| CN111754056B (en) | Model evaluation method and related device | |
| CN110245775B (en) | User collection and payment data analysis method and device and computer equipment | |
| CN114155038B (en) | Epidemic situation affected user identification method | |
| CN117408743A (en) | Service viscosity evaluation method and device, electronic equipment and chip |
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 |