Updated on 2024-01-04 GMT+08:00

Real-time Recommendation

Table 1 parameters parameter description

Parameter

Mandatory

Description

Type

Value Range

Default Value

sources

Yes

Vertex ID. Multiple vertices are supported.

String

The number of source vertices cannot exceed the upper limit (30 by default, which can be changed using source_limit). Use commas (,) to separate the IDs.

-

alpha

No

Weight coefficient. A larger value indicates a longer step.

Double

A real number between 0 and 1 (excluding 0 and 1)

0.85

N

No

Total number of walk steps

Integer

1 to 200000

10000

nv

No

Parameter indicating that the walk process ends ahead of schedule: minimum number of access times of a potential recommended vertex

NOTE:

If a vertex is accessed during random walk and the number of access times reaches nv, the vertex will be recorded as the potential recommended vertex.

Integer

1 to 10

5

np

No

Parameter indicating that the walk process ends ahead of schedule: number of potential recommended vertices

NOTE:

If the number of potential recommended vertices of a source vertex reaches np, the random walk for the source vertex ends ahead of schedule.

Integer

1 to 2000

1000

label

No

Expected type of the vertex to be output.

NOTE:
  • Expected type of the vertex to be output. If the value is null, the original calculation result of the algorithm is output without considering the vertex type.
  • If the value is not null, vertices with the label are filtered from the calculation result.

String

Vertex label

-

directed

No

Whether to consider the edge direction

Boolean

true or false

true

source_limit

No

Maximum number of source vertices

Int

1~100000

30

restricted

No

Whether to accept invalid source vertices

restricted=true: If a vertex that does not exist in the graph is passed to sources, an error is reported.

restricted=false: A vertex that does not exist in the graph can be passed to sources. However, if all source vertices do not exist, an error is reported.

Bool

true or false

true

Table 2 response_data parameter description

Parameter

Type

Description

score

List

Score of each vertex, which reflects the recommendation degree. A larger value indicates a higher recommendation degree. The format is as follows:

[{vertexId: scoreValue},...]

where

vertexId is of the string type.

scoreValue is of the double type.

sources

List

ID of the source vertex