CN-121998751-A - Service resource allocation method, device, equipment and storage medium

CN121998751ACN 121998751 ACN121998751 ACN 121998751ACN-121998751-A

Abstract

The invention discloses a method, a device, equipment and a storage medium for configuring resources of a service, which comprise the steps of splicing a state cluster label of a target cluster with characteristic information to obtain updated characteristic information; the method comprises the steps of inputting updated characteristic information into an abnormal risk assessment model corresponding to a target cluster to obtain abnormal probability, determining a risk level adjustment coefficient of a current service according to a state cluster label, determining a resource configuration parameter of the current service according to the abnormal probability and the risk level adjustment coefficient, and carrying out resource configuration on the current service according to the resource configuration parameter. The method comprises the steps of updating the characteristics of a current service through a state cluster label of a matched target cluster to enrich the characteristic information of the current service, directly acquiring abnormal probability by adopting a pre-trained abnormal risk assessment model based on the updated characteristic information, and comprehensively and accurately determining the resource configuration parameters of the current service based on the abnormal probability and a risk level adjustment coefficient determined by the state cluster label.

Inventors

SHI PENGHAO
Jin Lanyi
LI RONG
LI JIAYUAN

Assignees

中国工商银行股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260213

Claims (10)

1. A method for configuring resources of a service, the method comprising: Determining a matched target cluster from a cluster set according to the characteristic information of the current service, and splicing a state cluster label of the target cluster with the characteristic information to obtain updated characteristic information; inputting the updated characteristic information into an abnormal risk assessment model corresponding to the target cluster to obtain abnormal probability; Determining a risk level adjustment coefficient of the current service according to the state cluster label, and determining a resource configuration parameter of the current service according to the abnormal probability and the risk level adjustment coefficient; and carrying out resource allocation on the current service according to the resource allocation parameters.
2. The method of claim 1, wherein before determining the matched target cluster from the cluster set according to the characteristic information of the current service, the method further comprises: acquiring characteristic information of a sample service, and clustering the sample service according to the characteristic information of the sample service to acquire a plurality of clustering clusters; Carrying out state identification on each cluster to obtain the state of the cluster, and adding a state cluster label to the cluster according to the state; And constructing the cluster set according to the cluster added with the state cluster label.
3. The method of claim 1, wherein the determining the matched target cluster from the cluster set according to the characteristic information of the current service comprises: Calculating the distance between the characteristic information and the center of each cluster in the cluster set; And taking the cluster with the smallest distance as the target cluster matched with the current service.
4. The method of claim 1, wherein before the inputting the updated feature information into the anomaly risk assessment model corresponding to the target cluster to obtain the anomaly probability, further comprises: acquiring a corresponding sub-data set aiming at each cluster, and acquiring an optimal super-parameter combination corresponding to the sub-data set by adopting an improved sparrow algorithm; And configuring a gradient lifting decision tree based frame according to the optimal super-parameter combination, and training the configured gradient lifting decision tree based frame by adopting the sub-data set to obtain an abnormal risk assessment model corresponding to the cluster.
5. The method of claim 4, wherein said employing a modified sparrow algorithm to obtain an optimal super-parameter combination corresponding to said sub-data set comprises: Randomly generating an initialization population of a specified size for each of the sub-data sets; Calculating individual fitness and ordering to determine random step sizes of a finder, an alerter, a follower and the follower, updating positions of the finder and the alerter, and updating the positions of the follower based on the random step sizes; And evaluating the individual with updated positions, and taking the obtained global optimal solution as the optimal super-parameter combination when the iteration condition is met.
6. The method of claim 1, wherein determining the risk level adjustment factor for the current service based on the status cluster tag comprises: determining the risk type of the current service according to the state cluster label, wherein the risk type comprises low risk, medium risk and high risk; and determining the risk level adjustment coefficient of the current service according to the risk type.
7. The method of claim 1, wherein said determining the resource configuration parameters of the current service based on the anomaly probability and the risk level adjustment factor comprises: Acquiring an operation environment of a current service, and determining basic resource parameters and dynamic adjustment items according to the operation environment; acquiring a first product result of the abnormal probability and a first weight and a second product result of the risk level adjustment coefficient and a second weight; and taking the basic resource parameter, the dynamic adjustment item, the addition result of the first product result and the second product result as the resource configuration parameter of the current service.
8. A resource allocation apparatus for a service, the apparatus comprising: The updated characteristic information acquisition module is used for determining a matched target cluster from a cluster set according to the characteristic information of the current service, and splicing the state cluster label of the target cluster with the characteristic information to acquire updated characteristic information; The abnormal probability evaluation module is used for inputting the updated characteristic information into an abnormal risk evaluation model corresponding to the target cluster to obtain abnormal probability; The resource allocation parameter determining module is used for determining a risk level adjustment coefficient of the current service according to the state cluster label and determining a resource allocation parameter of the current service according to the abnormal probability and the risk level adjustment coefficient; And the resource allocation module is used for carrying out resource allocation on the current service according to the resource allocation parameters.
9. An electronic device, the electronic device comprising: One or more processors; Storage means for storing one or more programs, When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.
10. A storage medium having stored thereon computer program of instructions, which when executed by a processor, performs the method of any of claims 1-7.

Description

Service resource allocation method, device, equipment and storage medium Technical Field The present invention relates to the field of financial science and technology, and in particular, to a method, an apparatus, a device, and a storage medium for allocating resources of a service. Background A banking system usually executes a large amount of businesses each day to meet the handling requirements of different customers, and the demands of customers with similar types are usually executed in a batch processing manner for the businesses, and resources are usually configured in a fixed manner for the businesses in the same batch, so as to improve the execution efficiency of the businesses. Because the transactions processed by different businesses are difficult to distinguish, the excessive resources may exist in the business for executing simple businesses in the execution process, the insufficient resources may exist in the business for executing complex businesses, and even the situation of business interruption may occur, so that the normal execution of the whole business is affected, the handling requirements of clients cannot be met, and the service experience of the clients is reduced. Disclosure of Invention The invention provides a method, a device, equipment and a storage medium for configuring resources of a service, so as to realize accurate and efficient configuration of the resources of the service. According to a first aspect of the present invention, there is provided a method for configuring resources of a service, the method comprising determining a matched target cluster from a cluster set according to feature information of a current service, and splicing a state cluster tag of the target cluster with the feature information to obtain updated feature information; inputting the updated characteristic information into an abnormal risk assessment model corresponding to the target cluster to obtain abnormal probability; Determining a risk level adjustment coefficient of the current service according to the state cluster label, and determining a resource configuration parameter of the current service according to the abnormal probability and the risk level adjustment coefficient; and carrying out resource allocation on the current service according to the resource allocation parameters. According to another aspect of the present invention, there is provided a resource allocation apparatus for a service, the apparatus comprising: The updated characteristic information acquisition module is used for determining a matched target cluster from a cluster set according to the characteristic information of the current service, and splicing the state cluster label of the target cluster with the characteristic information to acquire updated characteristic information; The abnormal probability evaluation module is used for inputting the updated characteristic information into an abnormal risk evaluation model corresponding to the target cluster to obtain abnormal probability; The resource allocation parameter determining module is used for determining a risk level adjustment coefficient of the current service according to the state cluster label and determining a resource allocation parameter of the current service according to the abnormal probability and the risk level adjustment coefficient; And the resource allocation module is used for carrying out resource allocation on the current service according to the resource allocation parameters. According to another aspect of the present invention, there is provided an electronic device including one or more processors; Storage means for storing one or more programs, The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the methods described in any of the embodiments of the present invention. According to another aspect of the invention, there is provided a storage medium having stored thereon computer program which when executed by a processor implements a method according to any of the embodiments of the invention. According to the technical scheme, the characteristics of the current service are updated through the state cluster labels of the matched target clusters, so that the characteristic information of the current service is enriched, the abnormal probability is directly obtained by adopting the pre-trained abnormal risk assessment model based on the updated characteristic information, the running condition of the current service is rapidly identified, the resource configuration parameters of the current service are comprehensively and accurately determined based on the abnormal probability and the risk level adjustment coefficient determined by the state cluster labels, and the accurate and efficient configuration of service resources is realized according to the resource configuration parameters. It should be understood that the description in this section is not intended to identify