Graph data processing method, apparatus, and device, and medium

Patent metadata

Field	Value
Publication number	US-12210571-B2
Application number	US-202017797876-A
Country	US
Kind code	B2
Filing date	Nov 4, 2020
Priority date	Feb 28, 2020
Publication date	Jan 28, 2025
Grant date	Jan 28, 2025

Abstract

A graph data processing method includes: acquiring target graph data to be processed; compiling statistics on the target graph data according to a first preset rule, so as to divide the target graph data into a plurality of graph data blocks and determine a boundary value and weight of each of the plurality of graph data blocks; and storing the boundary value and weight of each of the plurality of graph data blocks in a corresponding memory according to a second preset rule, so as to schedule the target graph data during a graph calculation process by use of the boundary values and the weights.

First claim

What is claimed is:

1. A graph data processing method, comprising:
acquiring target graph data to be processed;
compiling statistics on the target graph data according to a first preset rule, so as to divide the target graph data into a plurality of graph data blocks and determine a boundary value and a weight of each of the plurality of graph data blocks, wherein the compiling the statistics on the target graph data according to the first preset rule, so as to divide the target graph data into the plurality of graph data blocks and determine the boundary value and the weight of each of the plurality of graph data blocks comprises:
compiling the statistics on the target graph data according to the first preset rule to determine a flag value corresponding to each piece of data in the target graph data; and
dividing the target graph data into the plurality of graph data blocks according to the flag values, and determining the boundary value and the weight of each of the plurality of graph data blocks, wherein dividing the target graph data into the plurality of graph data blocks according to the flag values and determining the boundary value and the weight of each of the plurality of graph data blocks comprises:
judging whether a current flag value is a second preset flag value;
in response to the current flag value being the second preset flag value, determining the current flag value as a first position flag value, and determining the second preset flag value closest to the current flag value before the current flag value, so as to determine a second position flag value;
dividing corresponding target graph data from a next flag value adjacent to the second position flag value to the current flag value determined as the first position flag value into one of the plurality of graph data blocks, and determining the target graph data corresponding to the current flag value as a boundary value of a current graph data block;
determining a data amount of the current graph data block as a weight of the current graph data block; and

storing the boundary value and the weight of each of the plurality of graph data blocks in a corresponding memory according to a second preset rule, so as to invoke the target graph data during a graph calculation process by use of the boundary values and the weights.

2. The graph data processing method according to claim 1 , wherein before the compiling the statistics on the target graph data according to the first preset rule, the method further comprises:
arranging the target graph data in a sequence from smallest to largest; or
arranging the target graph data in a sequence from largest to smallest.

3. The graph data processing method according to claim 1 , wherein the compiling the statistics on the target graph data according to the first preset rule to determine the flag value corresponding to each piece of data in the target graph data comprises:
comparing the data with a next piece of data adjacent to the data, so as to judge whether the data is the same as the next piece of data adjacent to the data;
in response to the data being the same as the next piece of data adjacent to the data, determining a first preset flag value as the flag value corresponding to the data; and
in response to the data being different from the next piece of data adjacent to the data, determining the second preset flag value as the flag value corresponding to the data.

4. The graph data processing method according to claim 3 , wherein during the comparing the data with the next piece of data adjacent to the data, the method further comprises:
in response to the data being a last piece of data in the target graph data, determining 0 as the next piece of data adjacent to the data, so as to compare the data with the next piece of data adjacent to the data.

5. The graph data processing method according to claim 1 , wherein the storing the boundary value and the weight of each of the plurality of graph data blocks in the corresponding memory according to the second preset rule comprises:
storing the boundary value and the weight of each of the plurality of graph data blocks to a corresponding target address by taking the boundary value of the graph data block as a target address, so as to store the boundary value and the weight of each of the plurality of graph data blocks in the corresponding memory.

6. A graph data processing device, comprising:
a memory and a processor,
wherein the memory is configured to store a computer program; and
the processor is configured to execute the computer program to:
acquire target graph data to be processed;
compile statistics on the target graph data according to a first preset rule, so as to divide the target graph data into a plurality of graph data blocks and determine a boundary value and a weight of each of the plurality of graph data blocks, wherein the processor is configured to compile the statistics on the target graph data according to the first preset rule, so as to divide the target graph data into the plurality of graph data blocks and determine the boundary value and the weight of each of the plurality of graph data blocks by executing the computer program to:
compile the statistics on the target graph data according to the first preset rule to determine a flag value corresponding to each piece of data in the target graph data; and
divide the target graph data into the plurality of graph data blocks according to the flag values, and determine the boundary value and the weight of each of the plurality of graph data blocks, wherein the processor is configured to divide the target graph data into the plurality of graph data blocks according to the flag values and determine the boundary value and the weight of each of the plurality of graph data blocks by executing the computer program to:
judge whether a current flag value is a second preset flag value;
in response to the current flag value being the second preset flag value, determine the current flag value as a first position flag value, and determine the second preset flag value closest to the current flag value before the current flag value, so as to determine a second position flag value;
divide corresponding target graph data from a next flag value adjacent to the second position flag value to the current flag value determined as the first position flag value into one of the plurality of graph data blocks, and determine the target graph data corresponding to the current flag value as a boundary value of a current graph data block; and
determine a data amount of the current graph data block as a weight of the current graph data block; and

store the boundary value and the weight of each of the plurality of graph data blocks in a corresponding memory according to a second preset rule, so as to invoke the target graph data during a graph calculation process by use of the boundary values and the weights.

7. The graph data processing device according to claim 6 , wherein the processor is configured to execute the computer program to:
arrange the target graph data in a sequence from smallest to largest; or
arrange the target graph data in a sequence from largest to smallest.

8. The graph data processing device according to claim 6 , wherein the processor is configured to execute the computer program to:
compare the data with a next piece of data adjacent to the data, so as to judge whether the data is the same as the next piece of data adjacent to the data;
in response to the data being the same as the next piece of data adjacent to the data, determine a first preset flag value as the flag value corresponding to the data; and
in response to the data being different from the next piece of data adjacent to the data, determine

Assignees

• Inspur Suzhou Intelligent Technology Co Ltd

Inventors

• Wang Yuanli
• Mei Guoqiang
• Wang Jiangwei

Classifications

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06T7/13

  Edge detection · CPC title

• G06F16/9024 Primary

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F16/51 Primary

  Indexing; Data structures therefor; Storage structures · CPC title