Monitoring interesting subjects

Patent metadata

Field	Value
Publication number	US-9912769-B2
Application number	US-201615277088-A
Country	US
Kind code	B2
Filing date	Sep 27, 2016
Priority date	Jun 26, 2013
Publication date	Mar 6, 2018
Grant date	Mar 6, 2018

Abstract

Methods and systems for monitoring interesting subjects. A method including: selecting, based on a first collection of interesting subjects, a set of critical nodes including at least one critical node which participates in one or more interesting subjects in the first collection; and monitoring contents posted by the one or more critical nodes in the set so as to find a second collection of interesting subjects. The set of critical nodes which participate in one or more interesting subjects in the first collection of interesting subjects is selected based on the first collection, as objects to be monitored, thereby reducing the number of contents posted by the nodes to be monitored as compared with monitoring all the user nodes, so that interesting subjects such as hot news or hot events can be found in real time with high efficiency and low cost.

First claim

What is claimed is:

1. A method for monitoring interesting subjects, the method comprising:
selecting, based on a first collection of interesting subjects, a set of critical nodes including at least one critical node which participates in one or more interesting subjects in the first collection;
monitoring contents posted by the one or more critical nodes in the set so as to find a second collection of interesting subjects;
updating the set of critical nodes based on the second collection of interesting subjects, including deleting nodes satisfying a second specific condition and adding new critical nodes that participate in one or more interesting subjects in the second collection;
wherein the second specific condition includes one more of the following conditions:
the condition where the quality of a node is smaller than a fourth specific threshold; and
the condition where the quality of a node is of the smallest ones;

wherein the quality of a node represents an efficiency for finding one or more interesting subjects by monitoring contents posted by this node; and
calculating a quality of a node through the following formula:

Q
⁡

(
i
)

=

a
*

N
post
S

⁡

(
i
)

N
post
S

⁡

(
all
)

+

b
*

N
post
S

⁡

(
i
)

N
post
All

⁡

(
i
)

wherein:
Q(i) represents the quality of a critical node i, a and b are constant weights;
N post S (i) represents the number of contents posted by the critical node i which are related with one or more interesting subjects S in the second collection;
N post S (all) represents the number of contents posted by all the critical nodes in the set which are related with the one or more interesting subjects S in the second collection; and
N post All (i) represents the total number of all the contents posted by the critical node i.

2. The method according to claim 1 , wherein the selecting is performed based on one or more of:
a limit to the number of critical nodes in the set to be selected; and
a limit to the total number of contents posted by the critical nodes in the set to be selected.

3. The method according to claim 1 , wherein:
the first collection of interesting subjects is a collection of interesting subjects known within a first specific time period; and
the second collection of interesting subjects is a collection of interesting subjects found within a second specific time period which is different from the first specific time period.

4. The method according to claim 1 , wherein the step of selecting, based on a first collection of interesting subjects, a set of critical nodes including at least one critical node which participates in one or more interesting subjects in the first collection, comprises:
obtaining a plurality of participating nodes which participate in one or more interesting subjects in the first collection; and
selecting, from the plurality of participating nodes, a set including at least one participating node that satisfies a first specific condition, as the set of critical nodes.

5. The method according to claim 4 , wherein the participating nodes, which participate in the interesting subjects, include nodes that post contents related to these interesting subjects within a third specific time period since these interesting subjects were posted for the first time.

6. The method according to claim 4 , wherein the first specific condition comprises making a coverage gain for the set that includes the participating nodes so that the first specific condition covers the first collection;
wherein the coverage gain satisfies one of the following conditions:
the coverage gain is larger than a first specific threshold; and
the coverage gain is the largest;

wherein the coverage gain represents a degree to which contents posted by the set including the participating nodes cover the first collection of interesting subjects.

7. The method according to claim 6 , wherein the coverage gain for the set to cover the first collection is calculated through the following formula:
G=αR covered +βR uncovered
wherein:
G represents the coverage gain;
α and β represent weight constants, respectively;
R covered represents an efficiency coefficient related to the number of the posted contents relevant to the interesting subjects covered by the set;
R uncovered represents an extent coefficient related to the number of the posted contents relevant to the interesting subjects not covered by the set;

the interesting subjects covered by the set are the interesting subjects for which the number of the participating nodes in the set participating in the interesting subjects is larger than a second specific threshold; and
the interesting subjects not covered by the set are the interesting subjects for which the number of the participating nodes in the set participating in the interesting subjects is smaller than or equal to the second specific threshold.

8. The method according to claim 7 , wherein:

R
covered

=

N
post
c

N
post
t

;

and

R
uncovered

=

N
post
u

N
post
t

Assignees

• IBM

Inventors

• Gong Min
• Hu Guoqiang
• Qi Yi
• Wang Yu
• Yan Junchi

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• H04L51/32

  Electricity · mapped topic

• G06Q10/10

  Office automation; Time management · CPC title

• G06Q50/01

  Physics · mapped topic