# US 12,184,530 B2 · Method and device for selecting recommended node in behavior deviation model

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

- Number: US 12,184,530 B2
- Document ID: US12184530B2
- Status: Granted
- Kind: B2
- Application number: 17/543,726
- Filed: 2021-12-06
- Published: 2022-06-16
- Granted: 2024-12-31
- Earliest claimed: 2020-12-16
- Assignees: Tsinghua University
- Applicants: Tsinghua University
- Inventors: Ke Xu; Yangfei Guo; Xiaoliang Wang; Mingxing Liu
- Web page: https://patentgrep.com/patent/US12184530B2

## CPC

- H04L 45/02: Topology update or discovery
- H04L 41/12: Discovery or management of network topologies
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 45/22: {Alternate routing}
- H04L 45/34: {Source routing}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- 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)

## Abstract

A method for selecting a recommended node in a behavior deviation model includes: determining a candidate path starting from a delegation node to a target node based on a preset network topology; determining candidate recommended nodes passing through each candidate path, and acquiring a first behavior deviation corresponding to the target node at each candidate node; reading a second behavior deviation of each candidate recommended node from a central node in the network topology; calculating an average deviation value for the target node based on second behavior deviations and first behavior deviations; determining a candidate path with the smallest average deviation value as a target candidate path; and in response to the average deviation value of the target candidate path being less than or equal to a preset warning value, determining the candidate recommended node on the target candidate path as a recommended node.

## Claims

### Claim 1

A method for selecting a recommended node in a behavior deviation model, comprising:
determining a delegation node and a target node in a current communication scenario;
determining a plurality of candidate paths with the delegation node as a start node and the target node as an end node based on a preset network topology;
determining at least one candidate node passing through each of the candidate paths, and acquiring a first behavior deviation corresponding to the target node at each candidate node, wherein the first behavior deviation is a deviation degree of the candidate node between current interaction behaviors with the target node and normal interaction behaviors with the target node;
reading a second behavior deviation of each candidate node from a central node in the network topology, wherein the second behavior deviation is a deviation degree of the candidate node between current interaction behaviors with other nodes and normal interaction behaviors with other nodes;
calculating an average deviation value for the target node based on second behavior deviations and first behavior deviations of all the candidate nodes in each candidate path;
determining a candidate path with a smallest average deviation value as a target candidate path; and
in response to the average deviation value of the target candidate path being less than or equal to a preset warning value, determining the candidate node on the target candidate path as a recommended node;
wherein the method further comprises:
in response to a behavior deviation corresponding to the target node being locally stored at the delegation node, acquiring recording time of the behavior deviation; and
entering a recommended node selection mode in response to determining that time difference between a current time and the recording time is greater than a preset time threshold.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
in response to the average deviation value being greater than the preset warning value, determining whether the average deviation value is greater than or equal to a preset maximum value, wherein the preset maximum value is greater than the warning value;
in response to the average deviation value being greater than the preset maximum value, feeding back a notification message to the delegation node, in which the notification message indicates a forbidden communication connection between the delegation node and the target node; and
in response to the average deviation value being less than or equal to the preset maximum value, calculating a difference value between the average deviation value and the warning value, determining a reduced packet distribution rate corresponding to the difference value, and adjusting a preset packet distribution rate from the delegation node to the communication node based on the reduced packet distribution rate.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
locally storing the first behavior deviation corresponding to the target node in each candidate node; and
determining the first behavior deviation corresponding to the target node at each candidate node, by:
reading the first behavior deviation corresponding to the target node locally stored at each candidate node.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
acquiring a fourth behavior deviation of a neighbor node adjacent to each candidate node, wherein the fourth behavior deviation is a behavior deviation of the neighbor node between current interaction behaviors with the candidate node and normal interaction behaviors with the candidate node; and
acquiring the second behavior deviation of each candidate node by calculating the fourth behavior deviation based on a preset formula, and storing the second behavior deviation in a deviation table of the central node.

### Claim 5 (depends on 4)

The method of claim 4, wherein the preset formula is expressed by:
d
g
-
node
=
∑
i
neighb
⁢
o
⁢
u
⁢
r
⁢
d
i
→
no
⁢
d
⁢
e
neighbour
where dg-node is a second behavior deviation of a candidate node node, di→mode is a fourth behavior deviation of a neighbor node to the candidate node node, neighbour represents a number of neighbor nodes of the candidate node node, neighbour being an integer.

### Claim 6 (depends on 1)

The method of claim 1, wherein acquiring the first behavior deviation corresponding to the target node at each candidate node comprises:
calculating a time duration from a moment of entering the recommended node selection mode to a moment of each candidate node receiving a data packet of a recommendation request; and
acquiring the first behavior deviation corresponding to the target node at each candidate node in response to the time duration being less than or equal to a preset threshold.

### Claim 7

An electronic device, comprising:
a processor, and
a memory configured to store computer instructions executable by the processor,
wherein the processor is configured to:
determine a delegation node and a target node in a current communication scenario;
determine at least one candidate path with the delegation node as a start node and the target node as an end node based on a preset network topology;
determine a plurality of candidate node passing through each of the candidate paths, and acquire a first behavior deviation corresponding to the target node at each candidate node, wherein the first behavior deviation is a deviation degree of the candidate node between current interaction behaviors with the target node and normal interaction behaviors with the target node;
read a second behavior deviation of each candidate node from a central node in the network topology, wherein the second behavior deviation is a deviation degree of the candidate node between current interaction behaviors with other nodes and normal interaction behaviors with other nodes;
calculate an average deviation value for the target node based on second behavior deviations and first behavior deviations of all the candidate nodes in each candidate path;
determine a candidate path with a smallest average deviation value as a target candidate path; and
in response to the average deviation value of the target candidate path being less than or equal to a preset warning value, determine the candidate node on the target candidate path as a recommended node;
wherein the processor is further configured to:
in response to a behavior deviation corresponding to the target node being locally stored at the delegation node, acquire recording time of the behavior deviation; and
enter a recommended node selection mode in response to determining that time difference between a current time and the recording time is greater than a preset time threshold.

### Claim 8 (depends on 7)

The device of claim 7, wherein the processor is further configured to:
in response to the average deviation value being greater than the preset warning value, determine whether the average deviation value is greater than or equal to a preset maximum value, wherein the preset maximum value is greater than the warning value;
in response to the average deviation value being greater than the preset maximum value, feed back a notification message to the delegation node, in which the notification message indicates a forbidden communication connection between the delegation node and the target node; and
in response to the average deviation value being less than or equal to the preset maximum value, calculate a difference value between the average deviation value and the warning value, determining a reduced packet distribution rate corresponding to the difference value, and adjust a preset packet distribution rate from the delegation node to the communication node based on the reduced packet distribution rate.

### Claim 9 (depends on 7)

The device of claim 7, wherein the processor is further configured to:
locally store the first behavior deviation corresponding to the target node in each candidate node; and
determine the first behavior deviation corresponding to the target node at each candidate node, by:
reading the first behavior deviation corresponding to the target node locally stored at each candidate node.

### Claim 10 (depends on 7)

The device of claim 7, wherein the processor is further configured to:
acquire a fourth behavior deviation of a neighbor node adjacent to each candidate node, wherein the fourth behavior deviation is a behavior deviation of the neighbor node between current interaction behaviors with the candidate node and normal interaction behaviors with the candidate node; and
acquire the second behavior deviation of each candidate node by calculating the fourth behavior deviation based on a preset formula, and storing the second behavior deviation in a deviation table of the central node.

### Claim 11 (depends on 10)

The device of claim 10, wherein the preset formula is expressed by:
d
g
-
node
=
∑
i
neighb
⁢
o
⁢
u
⁢
r
⁢
d
i
→
no
⁢
d
⁢
e
neighbour
where dg-node is a second behavior deviation of a candidate node node, di→node is a fourth behavior deviation of a neighbor node to the candidate node node, neighbour represents a number of neighbor nodes of the candidate node node, neighbour being an integer.

### Claim 12 (depends on 7)

The device of claim 7, wherein the processor is further configured to:
calculate a time duration from a moment of entering the recommended node selection mode to a moment of each candidate node receiving a data packet of a recommendation request; and
acquire the first behavior deviation corresponding to the target node at each candidate node in response to the time duration being less than or equal to a preset threshold.

### Claim 13

A non-transitory computer readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is caused to implement a method for selecting a recommended node in a behavior deviation model, the method comprising:
determining a delegation node and a target node in a current communication scenario;
determining at least one candidate path with the delegation node as a start node and the target node as an end node based on a preset network topology;
determining a plurality of candidate node passing through each of the candidate paths, and acquire a first behavior deviation corresponding to the target node at each candidate node, wherein the first behavior deviation is a deviation degree of the candidate node between current interaction behaviors with the target node and normal interaction behaviors with the target node;
reading a second behavior deviation of each candidate node from a central node in the network topology, wherein the second behavior deviation is a deviation degree of the candidate node between current interaction behaviors with other nodes and normal interaction behaviors with other nodes;
calculating an average deviation value for the target node based on second behavior deviations and first behavior deviations of all the candidate nodes in each candidate path;
determining a candidate path with a smallest average deviation value as a target candidate path; and
in response to the average deviation value of the target candidate path being less than or equal to a preset warning value, determining the candidate node on the target candidate path as a recommended node;
wherein the processor is further caused to implement:
in response to a behavior deviation corresponding to the target node being locally stored at the delegation node, acquiring recording time of the behavior deviation; and
entering a recommended node selection mode in response to determining that time difference between a current time and the recording time is greater than a preset time threshold.

### Claim 14 (depends on 13)

The storage medium of claim 13, wherein the processor is further caused to implement:
in response to the average deviation value being greater than the preset warning value, determining whether the average deviation value is greater than or equal to a preset maximum value, wherein the preset maximum value is greater than the warning value;
in response to the average deviation value being greater than the preset maximum value, feeding back a notification message to the delegation node, in which the notification message indicates a forbidden communication connection between the delegation node and the target node; and
in response to the average deviation value being less than or equal to the preset maximum value, calculating a difference value between the average deviation value and the warning value, determining a reduced packet distribution rate corresponding to the difference value, and adjusting a preset packet distribution rate from the delegation node to the communication node based on the reduced packet distribution rate.

### Claim 15 (depends on 13)

The storage medium of claim 13, wherein the processor is further caused to implement:
locally storing the first behavior deviation corresponding to the target node in each candidate node; and
determining the first behavior deviation corresponding to the target node at each candidate node, by:
reading the first behavior deviation corresponding to the target node locally stored at each candidate node.

### Claim 16 (depends on 13)

The storage medium of claim 13, wherein the processor is further caused to implement:
acquiring a fourth behavior deviation of a neighbor node adjacent to each candidate node, wherein the fourth behavior deviation is a behavior deviation of the neighbor node between current interaction behaviors with the candidate node and normal interaction behaviors with the candidate node; and
acquiring the second behavior deviation of each candidate node by calculating the fourth behavior deviation based on a preset formula, and storing the second behavior deviation in a deviation table of the central node.

### Claim 17 (depends on 16)

The storage medium of claim 16, wherein the preset formula is expressed by:
d
g
-
node
=
∑
i
neighb
⁢
o
⁢
u
⁢
r
⁢
d
i
→
no
⁢
d
⁢
e
neighbour
where dg-node is a second behavior deviation of a candidate node node, di→node is a fourth behavior deviation of a neighbor node to the candidate node node, neighbour represents a number of neighbor nodes of the candidate node node, neighbour being an integer.