CN-114117785-B - Situation awareness realization method, device, equipment and medium

CN114117785BCN 114117785 BCN114117785 BCN 114117785BCN-114117785-B

Abstract

The embodiment of the invention discloses a situation awareness realization method, a situation awareness realization device, situation awareness realization equipment and a situation awareness realization medium. The method comprises the steps of taking at least two nodes in a system as target nodes, obtaining risk level data corresponding to each target node respectively, determining association relations among the target nodes, establishing a conditional probability distribution model for nodes with first association relations in the target nodes based on conditional probability and risk level data, establishing a joint probability distribution model for nodes with second association relations in the target nodes based on joint probability distribution and risk level data, and carrying out situation awareness according to the conditional probability distribution model and the joint probability distribution model to obtain situation awareness results. By adopting the technical scheme, the association relation among the target nodes is analyzed, the corresponding probability distribution model is established in different modes according to different association relations, the algorithm difficulty is reduced by calculating the probability distribution, the flexibility of situation awareness modeling is improved, and the technical effect of modeling cost is reduced is achieved.

Inventors

CHEN YUANYOU
XU LISHA

Assignees

上海派拉软件股份有限公司

Dates

Publication Date: 20260512
Application Date: 20211124

Claims (8)

1. The realization method of situation awareness is characterized by comprising the following steps: Taking at least two nodes in the system as target nodes, and acquiring risk level data corresponding to each target node respectively; Determining the association relation between the target nodes, wherein the association relation between the target nodes comprises a first association relation and/or a second association relation, the nodes with the first association relation belong to different functions, data flow between the nodes exists, and the nodes with the second association relation belong to the same function; For the nodes with the first association relation in the target nodes, establishing a conditional probability distribution model based on conditional probability and the risk level data; establishing a joint probability distribution model for the nodes with the second association relation in the target nodes based on joint probability distribution and the risk level data; Carrying out situation awareness according to the conditional probability distribution model and the joint probability distribution model to obtain situation awareness results; Performing situation awareness according to the conditional probability distribution model and the joint probability distribution model to obtain situation awareness results, wherein the situation awareness results comprise: Predicting an expected value of a risk level corresponding to a node to be evaluated at a future time point according to the node to be evaluated at the current time point and the corresponding risk level, wherein the time interval between the future time point and the current time point is a first preset time interval; Predicting a first risk level of the node to be evaluated at a future time point according to the conditional probability distribution model and the risk level of a first type node corresponding to the node to be evaluated at the current time point, wherein the first risk level is determined according to the risk level of the node to be evaluated at the predicted future time point, which is determined according to the risk level of the node to be evaluated in the time range from the current time point to the future time point, wherein the node to be evaluated has data flow and belongs to different functions, and the second risk level is determined according to the risk level of a second type node corresponding to the joint probability distribution model and the node to be evaluated at the current time point, and is determined according to the risk level of the node to be evaluated, which has data flow and belongs to the same function, at the predicted future time point; calculating to obtain situation awareness results of the nodes to be evaluated at future time points according to expected values of risk levels corresponding to the nodes to be evaluated, the first risk levels and the second risk levels by using a preset mode; the preset mode is represented by the following expression: Wherein a and b represent constants, and a+b=1 is satisfied; the risk level data of the node to be evaluated at a future time point is represented, wherein l represents the total number of nodes of the first type corresponding to the node to be evaluated, and n represents the total number of nodes of the second type corresponding to the node to be evaluated; a desired value representing a risk level corresponding to the node to be evaluated at a future point in time; The risk level data of the first type node corresponding to the node to be evaluated at a future time point is represented; the risk level data of the node to be evaluated and the corresponding second class node at the future time point are represented; and the risk level data of the node to be evaluated at the future time point represents situation awareness results.
2. The method of claim 1, wherein the establishing a conditional probability distribution model for the node having the first association among the target nodes based on conditional probability and the risk level data comprises: For a first type node with the first association relation in the target data nodes, acquiring first data sets respectively corresponding to the first type node; taking a time period with a data transmission flow direction between the first data sets as a first target time period, and dividing the data sets corresponding to the first target time period by using a first preset time interval to obtain a plurality of first data segments; and determining the risk level corresponding to each first data segment by using a first preset rule, and establishing a conditional probability distribution model according to the risk level corresponding to each first data segment.
3. The method of claim 1, wherein the establishing a joint probability distribution model for the nodes of the target nodes having the second association based on the joint probability distribution and the risk level data comprises: For a second class node with the second association relation in the target data nodes, acquiring second data sets respectively corresponding to the second class node; Dividing a data set corresponding to the second target time period by using a first preset time interval to obtain a plurality of second data segments by taking the time period with data correlation between the second data sets as a second target time period; and determining the risk level corresponding to each second data segment by using a second preset rule, and establishing a joint probability distribution model according to the risk level corresponding to each second data segment.
4. The method according to claim 1, wherein after the calculating obtains the situation awareness result of the node to be evaluated at the future time point, the method further comprises: And processing the nodes to be evaluated with the risk level data higher than a preset threshold value.
5. The method of claim 1, wherein, before taking at least two nodes in the system as target nodes and acquiring risk level data corresponding to each target node, the method further comprises: Acquiring historical data corresponding to nodes in a preset time period, and determining risk level data corresponding to each node according to the historical data.
6. A situation awareness implementation apparatus, comprising: the risk level data acquisition module is used for taking at least two nodes in the system as target nodes and acquiring risk level data corresponding to each target node respectively; The association relation determining module is used for determining association relation among the target nodes, wherein the association relation among the target nodes comprises a first association relation and/or a second association relation, the nodes with the first association relation belong to different functions, data flow among the nodes exists, and the nodes with the second association relation belong to the same function; the probability distribution model building module is used for building a conditional probability distribution model based on conditional probability and the risk level data for the nodes with the first association relation in the target nodes; The situation awareness result obtaining module is used for carrying out situation awareness according to the conditional probability distribution model and the joint probability distribution model to obtain a situation awareness result; The situation awareness result obtaining module is specifically configured to predict an expected value of a risk level corresponding to a node to be evaluated at a future time point according to the node to be evaluated at the current time point and the corresponding risk level, where a time interval between the future time point and the current time point is a first preset time interval; Predicting a first risk level of the node to be evaluated at a future time point according to the conditional probability distribution model and the risk level of a first type node corresponding to the node to be evaluated at the current time point, wherein the first risk level is determined according to the risk level of the node to be evaluated at the predicted future time point, which is determined according to the risk level of the node to be evaluated in the time range from the current time point to the future time point, wherein the node to be evaluated has data flow and belongs to different functions, and the second risk level is determined according to the risk level of a second type node corresponding to the joint probability distribution model and the node to be evaluated at the current time point, and is determined according to the risk level of the node to be evaluated, which has data flow and belongs to the same function, at the predicted future time point; calculating to obtain situation awareness results of the nodes to be evaluated at future time points according to expected values of risk levels corresponding to the nodes to be evaluated, the first risk levels and the second risk levels by using a preset mode; the preset mode is represented by the following expression: Wherein a and b represent constants, and a+b=1 is satisfied; the risk level data of the node to be evaluated at a future time point is represented, wherein l represents the total number of nodes of the first type corresponding to the node to be evaluated, and n represents the total number of nodes of the second type corresponding to the node to be evaluated; a desired value representing a risk level corresponding to the node to be evaluated at a future point in time; The risk level data of the first type node corresponding to the node to be evaluated at a future time point is represented; the risk level data of the node to be evaluated and the corresponding second class node at the future time point are represented; and the risk level data of the node to be evaluated at the future time point represents situation awareness results.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-5.

Description

Situation awareness realization method, device, equipment and medium Technical Field The embodiment of the invention relates to the technical field of computers, in particular to a situation awareness realization method, a situation awareness realization device, situation awareness realization equipment and a situation awareness realization medium. Background The situation awareness (Situation Awareness) of the wind control scene is a common means for modeling a complex wind control system, and belongs to a common modeling method of situation awareness. The situation awareness modeling method commonly used in the prior art is, for example, a situation awareness modeling method for awareness learning. However, the modeling method has higher algorithm difficulty and algorithm complexity, and needs to be reevaluated for different situation awareness problems, so that the cost is higher. Disclosure of Invention The embodiment of the invention provides a situation awareness realization method, a device, equipment and a medium, which can optimize the existing situation awareness realization scheme. In a first aspect, an embodiment of the present invention provides a method for implementing situation awareness, including: Taking at least two nodes in the system as target nodes, and acquiring risk level data corresponding to each target node respectively; Determining the association relation between the target nodes, wherein the association relation between the target nodes comprises a first association relation and/or a second association relation, the nodes with the first association relation belong to different functions, data flow between the nodes exists, and the nodes with the second association relation belong to the same function; For the nodes with the first association relation in the target nodes, establishing a conditional probability distribution model based on conditional probability and the risk level data; establishing a joint probability distribution model for the nodes with the second association relation in the target nodes based on joint probability distribution and the risk level data; And carrying out situation awareness according to the conditional probability distribution model and the joint probability distribution model to obtain situation awareness results. In a second aspect, an embodiment of the present invention provides a situation awareness implementation apparatus, including: the risk level data acquisition module is used for taking at least two nodes in the system as target nodes and acquiring risk level data corresponding to each target node respectively; The association relation determining module is used for determining association relation among the target nodes, wherein the association relation among the target nodes comprises a first association relation and/or a second association relation, the nodes with the first association relation belong to different functions, data flow among the nodes exists, and the nodes with the second association relation belong to the same function; the probability distribution model building module is used for building a conditional probability distribution model based on conditional probability and the risk level data for the nodes with the first association relation in the target nodes; And the situation awareness result obtaining module is used for carrying out situation awareness according to the conditional probability distribution model and the joint probability distribution model to obtain a situation awareness result. In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements a situation awareness implementation method as provided by the embodiment of the present invention when executing the computer program. In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a situation awareness implementation method as provided by embodiments of the present invention. The embodiment of the invention provides a situation awareness implementation scheme, at least two nodes in a system are used as target nodes, risk level data corresponding to each target node is acquired, and then the association relation among the target nodes is determined, wherein the association relation among the target nodes comprises a first association relation and/or a second association relation, the nodes with the first association relation belong to different functions, data flow among the nodes exists, and the nodes with the second association relation belong to the same function. The method comprises the steps of establishing a conditional probability distribution model through nodes with first association relations in target nodes based on conditional probability