# US 2022/0286351 A1 · Fault rectification operation recommendation method and apparatus, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0286351 A1
- Document ID: US20220286351A1
- Status: Published application
- Kind: A1
- Application number: 17/825,246
- Filed: 2022-05-26
- Published: 2022-09-08
- Earliest claimed: 2019-11-27
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Wenqi LIAO
- Web page: https://patentgrep.com/patent/US20220286351A1

## CPC

- H04L 41/0654: using network fault recovery (ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437)
- G06F 11/0709: {in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems}
- G06F 11/0712: {in a virtual computing platform, e.g. logically partitioned systems}
- G06F 11/0793: {Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40)}
- G06F 11/2252: {using fault dictionaries}
- H04L 41/0659: by isolating or reconfiguring faulty entities
- H04L 41/0663: Performing the actions predefined by failover planning, e.g. switching to standby network elements
- H04L 41/0668: by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
- H04L 41/147: for predicting network behaviour
- H04L 41/40: using virtualisation of network functions or resources, e.g. SDN or NFV entities
- H04W 24/04: Arrangements for maintaining operational condition
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

This application discloses a fault rectification operation recommendation method and apparatus, and a storage medium in the field of communication technologies. In some implementations, after fault information is obtained, a rectification contingency plan corresponding to the fault information may be searched for from a contingency plan library. When the rectification contingency plan corresponding to the fault information cannot be found in the contingency plan library, the fault information may be processed by using a recommendation model to obtain a recommended contingency plan. Further, one operation is selected from one or more candidate operations included in the recommended contingency plan as a fault rectification operation.

## Claims

### Claim 1

A fault rectification operation recommendation method, wherein the method comprises:
obtaining fault information of a faulty node;
in response to determining that a rectification contingency plan corresponding to the fault information does not exist in a contingency plan library, determining a recommended contingency plan based on the fault information by using a recommendation model, wherein the recommended contingency plan comprises one or more candidate operations;
determining a fault rectification operation in the one or more candidate operations comprised in the recommended contingency plan; and
sending the fault rectification operation to the faulty node recommending the faulty node to rectify a fault based on the fault rectification operation.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the fault information comprises a plurality of fault parameters, one or more parameters of the recommendation model comprise a plurality of fault feature factors, and each of the plurality of fault feature factors corresponds to one of the plurality of fault parameters; and
wherein the determining a recommended contingency plan based on the fault information by using a recommendation model comprises:
determining the plurality of fault parameters as inputs of the recommendation model; and
determining the recommended contingency plan based on the plurality of fault feature factors by using the recommendation model.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the one or more parameters of the recommendation model further comprise a configuration impact factor, and the configuration impact factor comprises original configuration information of the faulty node and physical topology information of a network in which the faulty node is located; and
wherein the determining a fault rectification operation in the one or more candidate operations comprised in the recommended contingency plan comprises:
determining a first candidate operation as an input of the recommendation model;
determining a configuration impact degree corresponding to the first candidate operation based on the configuration impact factor by using the recommendation model, wherein the configuration impact degree is a predicted impact degree of the first candidate operation on a configuration of the faulty node and a physical topology of a network in which the faulty node is located, and the first candidate operation is any one of the one or more candidate operations; and
determining a candidate operation corresponding to a smallest configuration impact degree in the one or more candidate operations as the fault rectification operation.

### Claim 4 (depends on 1)

The method according to claim 1, wherein after recommending the fault rectification operation to the faulty node, the method further comprises:
receiving a rectification result fed back by the faulty node, wherein the rectification result comprises routing information and physical topology information of a network in which the faulty node is located after the faulty node rectifies the fault;
determining the routing information and the physical topology information after the fault is rectified as inputs of a data plane verification (DPV) model;
determining a data plane impact degree corresponding to the fault rectification operation by using the DPV model, wherein the data plane impact degree is an actual impact degree caused by the fault rectification operation on a configuration of the faulty node and the physical topology of the network in which the faulty node is located;
generating a fault sample based on the data plane impact degree corresponding to the fault rectification operation, the fault rectification operation, and the fault information; and
adjusting one or more parameters of the recommendation model based on the fault sample.

### Claim 5

An apparatus, wherein the apparatus comprises:
at least one processor; and
one or more memories coupled to the at least one processor and storing instructions which when executed by the at least one processor, cause the apparatus to:
obtain fault information of a faulty node;
in response to determining that a rectification contingency plan corresponding to the fault information does not exist in a contingency plan library, determine a recommended contingency plan based on the fault information by using a recommendation model, wherein the recommended contingency plan comprises one or more candidate operations;
determine a fault rectification operation in the one or more candidate operations comprised in the recommended contingency plan; and
send the fault rectification operation to the faulty node recommending the faulty node to rectify a fault based on the fault rectification operation.

### Claim 6 (depends on 5)

The apparatus according to claim 5, wherein the fault information comprises a plurality of fault parameters, one or more parameters of the recommendation model comprise a plurality of fault feature factors, and each of the plurality of fault feature factors corresponds to one of the plurality of fault parameters; and
wherein the instructions executed by the at least one processor to further cause the apparatus to:
determine the plurality of fault parameters as inputs of the recommendation model; and
determine the recommended contingency plan based on the plurality of fault feature factors by using the recommendation model.

### Claim 7 (depends on 6)

The apparatus according to claim 6, wherein the one or more parameters of the recommendation model further comprise a configuration impact factor, and the configuration impact factor comprises original configuration information of the faulty node and physical topology information of a network in which the faulty node is located; and
wherein the instructions executed by the at least one processor to further cause the apparatus to:
determine a first candidate operation as an input of the recommendation model;
determine a configuration impact degree corresponding to the first candidate operation based on the configuration impact factor by using the recommendation model, wherein the configuration impact degree is a predicted impact degree of the first candidate operation on a configuration of the faulty node and a physical topology of the network in which the faulty node is located, and the first candidate operation is any one of the one or more candidate operations; and
determine a candidate operation corresponding to a smallest configuration impact degree in the one or more candidate operations as the fault rectification operation.

### Claim 8 (depends on 5)

The apparatus according to claim 5, wherein the instructions executed by the at least one processor to further cause the apparatus to:
receive a rectification result fed back by the faulty node, wherein the rectification result comprises routing information and physical topology information of a network in which the faulty node is located after the faulty node rectifies the fault;
determine the routing information and the physical topology information after the fault is rectified as inputs of a data plane verification (DPV) model;
determine a data plane impact degree corresponding to the fault rectification operation by using the DPV model, wherein the data plane impact degree is an actual impact degree caused by the fault rectification operation on a configuration of the faulty node and the physical topology of the network in which the faulty node is located;
generate a fault sample based on the data plane impact degree corresponding to the fault rectification operation, the fault rectification operation, and the fault information; and
adjust one or more parameters of the recommendation model based on the fault sample.

### Claim 9

A non-transitory storage medium, storing a program that is executable by one or more processors, the program including instructions comprising:
obtaining fault information of a faulty node;
in response to determining that a rectification contingency plan corresponding to the fault information does not exist in a contingency plan library, determining a recommended contingency plan based on the fault information by using a recommendation model, wherein the recommended contingency plan comprises one or more candidate operations;
determining a fault rectification operation in the one or more candidate operations comprised in the recommended contingency plan; and
sending the fault rectification operation to the faulty node recommending the faulty node to rectify a fault based on the fault rectification operation.

### Claim 10 (depends on 9)

The non-transitory storage medium according to claim 9, wherein the fault information comprises a plurality of fault parameters, one or more parameters of the recommendation model comprise a plurality of fault feature factors, and each of the plurality of fault feature factors corresponds to one of the plurality of fault parameters; and
wherein the instructions further comprise:
determining the plurality of fault parameters as inputs of the recommendation model, and determining the recommended contingency plan based on the plurality of fault feature factors by using the recommendation model.

### Claim 11 (depends on 10)

The non-transitory storage medium according to claim 10, wherein the one or more parameters of the recommendation model further comprise a configuration impact factor, and the configuration impact factor comprises original configuration information of the faulty node and physical topology information of a network in which the faulty node is located; and
wherein the instructions further comprise:
determining a first candidate operation as an input of the recommendation model;
determining a configuration impact degree corresponding to the first candidate operation based on the configuration impact factor by using the recommendation model, wherein the configuration impact degree is a predicted impact degree of the first candidate operation on a configuration of the faulty node and a physical topology of the network in which the faulty node is located, and the first candidate operation is any one of the one or more candidate operations; and
determining a candidate operation corresponding to a smallest configuration impact degree in the one or more candidate operations as the fault rectification operation.

### Claim 12 (depends on 9)

The non-transitory storage medium according to claim 9, wherein the instructions further comprise:
receiving a rectification result fed back by the faulty node, wherein the rectification result comprises routing information and physical topology information of a network in which the faulty node is located after the faulty node rectifies the fault;
determining the routing information and the physical topology information after the fault is rectified as inputs of a data plane verification (DPV) model;
determining a data plane impact degree corresponding to the fault rectification operation by using the DPV model, wherein the data plane impact degree is an actual impact degree caused by the fault rectification operation on a configuration of the faulty node and the physical topology of the network in which the faulty node is located;
generating a fault sample based on the data plane impact degree corresponding to the fault rectification operation, the fault rectification operation, and the fault information; and
adjusting one or more parameters of the recommendation model based on the fault sample.
