CN110969526A - Overlapping community processing method and device and electronic equipment - Google Patents
Overlapping community processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN110969526A CN110969526A CN201911291105.6A CN201911291105A CN110969526A CN 110969526 A CN110969526 A CN 110969526A CN 201911291105 A CN201911291105 A CN 201911291105A CN 110969526 A CN110969526 A CN 110969526A
- Authority
- CN
- China
- Prior art keywords
- communities
- community
- nodes
- overlapped
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title description 9
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 10
- 230000003542 behavioural effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Technology Law (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a method and a device for processing overlapping communities and electronic equipment, relates to the technical field of data processing, and solves the technical problem that the identification process of a user is influenced by the overlapping condition of the communities. The method comprises the following steps: establishing a model of a relation graph based on the relation among a plurality of sample objects, wherein the relation graph comprises a plurality of nodes for representing the sample objects, and the nodes are correspondingly marked with labels for representing behavior data; the following steps are repeatedly executed until the model of the relational graph is in accordance with the expectation: dividing the nodes into a plurality of communities by utilizing a label propagation algorithm according to the labels; if the multiple communities have overlapped communities, determining the node contact degree between any two overlapped communities in the overlapped communities; if the node contact ratio is greater than the preset contact ratio, carrying out community combination on the two overlapped communities; and judging whether the model of the relationship graph after the community combination is in accordance with the expectation.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing overlapping communities and an electronic device.
Background
Currently, many factors need to be considered in identifying the risk of fraud for a user. For example, the individual's fraud risk is identified based on the individual's historical loan performance, basic income expenditure profiles, demographic information, etc.
However, in the process of performing cluster division on a plurality of users with fraud risk degrees, there is a case that one user belongs to more than two clusters at the same time, and the overlapping of the clusters easily affects the identification process of the user, so that the identification result is unclear.
Disclosure of Invention
The invention aims to provide a method and a device for processing overlapping communities and electronic equipment, and aims to solve the technical problem that the identification process of a user is influenced by the overlapping condition of the communities.
In a first aspect, an embodiment of the present application provides a method for processing overlapping communities, where behavior data of a plurality of sample objects is predetermined; the method comprises the following steps:
establishing a model of a relation graph based on the relation among the plurality of sample objects, wherein the relation graph comprises a plurality of nodes used for representing the sample objects, and the nodes are correspondingly marked with labels used for representing the behavior data;
repeatedly executing the following steps until the model of the relation graph is in accordance with the expectation:
dividing the nodes into a plurality of communities by utilizing a label propagation algorithm according to the labels;
if overlapping communities exist in a plurality of the communities, determining the node contact degree between any two overlapping communities in the overlapping communities;
if the node contact ratio is greater than a preset contact ratio, carrying out community combination on the two overlapped communities;
and judging whether the model of the relationship graph after the community combination is in accordance with the expectation.
In one possible implementation, the step of determining a node contact ratio between any two overlapping communities in the overlapping communities comprises:
determining the number of coincident nodes between any two of the overlapping communities;
and calculating the ratio of the number of the overlapped nodes to the number of all nodes in the two overlapped communities respectively, and taking the ratio as the node overlapping degree.
In one possible implementation, if the node contact degree is greater than a preset contact degree, the step of merging the two overlapped communities comprises:
and if the node coincidence degrees corresponding to the two overlapped communities are both greater than a preset coincidence degree, carrying out community combination on the two overlapped communities.
In one possible implementation, the method further includes:
and determining the danger probability of each community in the relationship graph model according to the content of the label.
In one possible implementation, the method further includes:
acquiring behavior data of an object to be identified;
determining a target community to which the object to be recognized belongs by using the model of the relation graph according to the behavior data of the object to be recognized;
and determining the danger probability of the object to be identified according to the danger probability of the target community.
In one possible implementation, the step of determining the risk probability of the object to be identified according to the risk probability of the target community includes:
if the number of the target communities is multiple, respectively determining the danger probability of each target community;
calculating the degree centrality of the target node corresponding to the object to be identified in the model of the relational graph in each target community;
and determining the danger probability of the object to be identified according to the weighted average value of the degree centrality of the target nodes in each target community.
In one possible implementation, the sample object is an individual user;
the behavioural data comprises any one or more of:
historical loan information, payment overdue information, bad record information and a plurality of contact conditions among the individual users.
In a second aspect, there is provided a overlapping community processing apparatus that determines behavior data of a plurality of sample objects in advance; the device comprises:
the establishing module is used for establishing a model of a relation graph based on the relation among the sample objects, the relation graph comprises a plurality of nodes used for representing the sample objects, and the nodes are correspondingly marked with labels used for representing the behavior data;
the dividing module is used for dividing the nodes into a plurality of communities according to the labels by utilizing a label propagation algorithm;
the determining module is used for determining the node contact degree between any two overlapped communities in the overlapped communities if the overlapped communities exist in a plurality of communities;
the merging module is used for merging the two overlapped communities if the node contact ratio is greater than a preset contact ratio;
the judging module is used for judging whether the model of the relationship graph after the community combination meets the expectation;
the dividing module, the determining module, the combining module and the judging module are repeatedly executed until the model of the relational graph is in accordance with expectation.
In a third aspect, an embodiment of the present application further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program that is executable on the processor, and the processor implements the method of the first aspect when executing the computer program.
In a fourth aspect, this embodiment of the present application further provides a computer-readable storage medium storing machine executable instructions, which, when invoked and executed by a processor, cause the processor to perform the method of the first aspect.
The embodiment of the application brings the following beneficial effects:
the method, the device and the electronic equipment for processing the overlapped communities provided by the embodiment of the application can establish a model of a relationship graph containing a plurality of nodes based on the relationship among a plurality of sample objects, wherein the nodes can represent the sample objects, labels of the nodes can represent behavior data of the sample objects, then, a dividing process of the communities in the relationship graph model can be repeatedly executed until the model of the relationship graph is judged to be in accordance with expectation, in the process of dividing the communities, the nodes can be divided into a plurality of communities according to the labels by using a label propagation algorithm, in the case of the overlapped communities, the node overlap ratio of the overlapped communities can be determined, and when the node overlap ratio is greater than the preset overlap ratio, the two overlapped communities are subjected to community combination, in the scheme, by determining the node overlap ratio between the overlapped communities, and determining whether the overlapped communities are combined or not according to the comparison condition between the node overlap ratio and the preset overlap ratio, so that the finally obtained community distribution result in the relationship graph model is more reasonable and accords with the actual condition, and the influence of the divided community overlap condition on the identification process is reduced.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the detailed description of the present application or the technical solutions in the prior art, the drawings needed to be used in the detailed description of the present application or the prior art description will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart illustrating a method for processing overlapping communities according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram illustrating an example of cluster merging in the overlapping community processing method according to the embodiment of the present application;
FIG. 3 is a block diagram illustrating an overlapping community processing apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram illustrating an electronic device provided in an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "comprising" and "having," and any variations thereof, as referred to in the embodiments of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
At present, the problem of inconsistency among multiple data sources cannot be checked, and when contradictions exist among various types of information provided by a borrower, the fraud risk of the borrower is underestimated due to the fact that the borrower cannot identify the contradictions. Furthermore, in complex networks, there is a possibility that a person belongs to multiple communities, and if a point is forced into a community, it may lead to poor community or fraudulent group identification.
Based on the above, the embodiment of the application provides a method and a device for processing overlapping communities and an electronic device. The method can solve the technical problem that the identification process of the user is influenced by the cluster overlapping condition.
Embodiments of the present invention are further described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for processing overlapping communities according to an embodiment of the present disclosure. Wherein behavior data of a plurality of sample objects is predetermined. As shown in fig. 1, the method includes:
s110, establishing a model of the relation graph based on the relation among the plurality of sample objects.
Note that the relationship graph includes a plurality of nodes for representing the sample object, and the nodes are labeled with labels for representing the behavior data.
Wherein the sample object may be a user. In this step, a relationship graph model between multiple users may be established based on the contact conditions between multiple users.
The following steps are repeatedly executed until the model of the relational graph is in accordance with the expectation:
and S120, dividing the nodes into a plurality of communities according to the labels by using a label propagation algorithm.
The label propagation algorithm is a graph-based semi-supervised learning method, and the basic idea is to use label information of labeled nodes to predict label information of unlabeled nodes. And establishing a relation complete graph model by utilizing the relation between the samples, wherein in the complete graph, the nodes comprise marked data and unmarked data, the edges of the nodes represent the similarity of the two nodes, and the labels of the nodes are transmitted to other nodes according to the similarity. The label data is just like a source, label-free data can be labeled, and the greater the similarity of the nodes, the easier the label is to propagate.
In this step, the relationship graph may be initialized, each node in the graph is listed as a separate community, and a plurality of nodes form a plurality of communities. Then, the content is divided into more reasonable communities according to the label content by using a label propagation algorithm.
And S130, if the overlapped communities exist in the plurality of communities, determining the node contact degree between any two overlapped communities in the overlapped communities.
The overlapped communities refer to nodes which are overlapped among a plurality of communities divided. For example, a number of nodes belong to both community a and community B.
The node contact degree may have various forms, for example, the number of the overlapped nodes may be included, the occupation ratio of the overlapped nodes in the community may be included, and the like.
S140, if the node contact degree is larger than the preset contact degree, carrying out community combination on the two overlapped communities.
The merging refers to merging several communities into one community, that is, all of the merged communities are the same community.
For example, if the number of the overlapped nodes is larger than the preset number of nodes, or the occupation ratio of the overlapped nodes in the community is larger than the preset ratio, the overlapped communities are merged into one community.
S150, judging whether the model of the relationship graph after the community combination is in accordance with the expectation. If yes, go to step S160; if not, step S120 is re-executed.
It should be noted that a variety of criteria are contemplated. For example, the node convergence degree in the model of the relational graph reaches a preset convergence degree by dividing the cluster, the iteration number in the label propagation process may meet the preset number, and the like.
And S160, obtaining a model conforming to the expected relation graph.
The method for processing the overlapped communities can be used as a community identification method based on label propagation, is low in calculation cost and is suitable for the situation of low data processing amount. Whether the overlapped communities are combined or not is determined by determining the node contact degree between the overlapped communities and according to the comparison condition between the node contact degree and the preset contact degree, so that the finally obtained community distribution result in the relation graph model is more reasonable and accords with the actual condition, and the influence caused by the identification process based on the overlapped communities is reduced.
The above steps are described in detail below.
In some embodiments, the step S130 may include the following steps:
step a, determining the number of coincident nodes between any two overlapped communities in the overlapped communities.
And b, calculating the ratio of the number of the overlapped nodes to the number of all nodes in two overlapped communities, and taking the ratio as the node overlapping degree.
For example, the currently overlapped communities may be analyzed, the number of overlapped nodes in the currently overlapped communities is calculated, the ratio of the number of overlapped nodes to the number of all nodes in the overlapped communities is calculated, and the node overlap ratio is further obtained.
The node contact ratio is determined according to the occupation ratio of the superposed nodes, so that the calculated node contact ratio takes the influence degree of the superposed conditions on the whole cluster into consideration, and the calculated node contact ratio can be more reasonable.
In some embodiments, the step S140 may include the following steps:
and if the node coincidence degrees corresponding to the two overlapped communities are both greater than the preset coincidence degree, merging the two overlapped communities.
For example, a threshold value alpha representing a threshold value of the degree of overlap between two communities may be preset. After the node overlap ratio between the overlapping community A and the overlapping community B is calculated, if points of the community A exceeding alpha percent are already present in the overlapping community B, the overlapping community A and the overlapping community B are merged.
For example, as shown in fig. 2, after the current cluster is divided by step S120, there may be a case where, since the node 2 is connected to only the node 1 and the node 3, but not to the node 4, the community calculated when the node 2 is calculated is the community {1,2,3}, and when the node 1 is calculated is the community {1,2,3,4}, the coincidence degree between the community {1,2,3} and the community {1,2,3,4} is greater than the preset coincidence degree, the community {1,2,3} and the community {1,2,3,4} are merged to obtain the same community {1,2,3,4 }. Similarly, if there is only {4} in the coincident nodes between the clusters {1,2,3,4} and {4,5,6,7}, and the coincidence degree is smaller than the predetermined coincidence degree, then there is no merging between the clusters {1,2,3,4} and {4,5,6,7 }.
Whether overlapping clusters are combined or not is determined according to a comparison result between the node overlapping degree and the preset overlapping degree, so that unnecessary cluster combination processes are reduced, overlapping clusters with large overlapping degrees are reasonably combined, and cluster division results obtained after the combination processes are more reasonable and accord with actual conditions.
In some embodiments, the method may further comprise the steps of:
and determining the danger probability of each community in the model of the relationship graph according to the content of the label.
In practical application, because each node in a community has been typed with a label representing the behavior of a sample object, such as an identity label, the behavior similarity matching can be performed according to the actual condition of each component node in the community, so as to obtain the probability that the behavior of each community belongs to the high-risk cluster behavior.
The danger probability of the community can be more accurately determined through the label content representing the behavior of the sample object, so that the calculation result of the danger probability of the community is more accurate and reasonable.
In some embodiments, the method may further comprise the steps of:
step a, acquiring behavior data of an object to be identified;
b, determining a target community to which the object to be recognized belongs by using a model of a relational graph according to the behavior data of the object to be recognized;
and c, determining the danger probability of the object to be identified according to the danger probability of the target community.
For example, in the process of querying and backtracking the object to be recognized, the community distribution closest to the object to be recognized may be called, and the target community to which the object to be recognized belongs may be searched. And judging the probability that the object to be identified is a high-risk group according to the target community to which the object to be identified belongs.
The danger probability of the object to be recognized is recognized through the probability of the high-risk group of the target community to which the object to be recognized belongs, the community connected with the object to be recognized can be used for recognizing the object to be recognized more comprehensively, and therefore the recognition result is more accurate and precise.
Based on the steps a, b and c, the step c may include the following steps:
if the number of the target communities is multiple, respectively determining the danger probability of each target community;
calculating the degree centrality of the target node corresponding to the object to be identified in the model of the relational graph in each target community;
and determining the danger probability of the object to be identified according to the weighted average value of the degree centrality of the target nodes in each target community.
For example, if there are a plurality of target communities, the probabilities are respectively determined, and then an average weighted average of the centralities is calculated according to the centrality weighting, that is, the centrality of the target node in the target community.
Through the calculation process of the degree centrality and the weighted average value of the target nodes in the target community, the real risk probability of the object to be recognized can be calculated more accurately, and the finally determined risk probability of the object to be recognized is more accurate and reasonable.
In some embodiments, the sample object is an individual user; the behavioural data comprises any one or more of: historical loan information of individual users, overdue payment information, bad record information and the contact condition among a plurality of individual users.
By the overlapping community processing method provided by the embodiment of the application, classification and labeling results of dangerous clusters such as fraud groups and the like can be more reasonable, so that the danger probability of the individual user to be identified can be more effectively identified.
FIG. 3 provides a block diagram of an overlapping community processing device. Behavioral data for a plurality of sample objects is predetermined. As shown in fig. 3, the overlapping community processing apparatus 300 includes:
the establishing module 301 is configured to establish a model of a relationship graph based on relationships among a plurality of sample objects, where the relationship graph includes a plurality of nodes used for representing the sample objects, and the nodes are correspondingly labeled with labels used for representing behavior data;
a dividing module 302, configured to divide the plurality of nodes into a plurality of communities according to the tags by using a tag propagation algorithm;
a first determining module 303, configured to determine a node overlap ratio between any two overlapping communities in the overlapping communities if the overlapping communities exist in the multiple communities;
a merging module 304, configured to merge two overlapping communities if the node overlap ratio is greater than a preset overlap ratio;
a determining module 305, configured to determine whether a model of the relationship graph after the community merging meets expectations;
the dividing module, the determining module, the combining module and the judging module are repeatedly executed until the model of the relational graph is in accordance with expectation.
In some embodiments, the first determining module is specifically configured to:
determining the number of coincident nodes between any two overlapped communities in the overlapped communities;
and calculating the ratio of the number of the overlapped nodes to the number of all nodes in two overlapped communities, and taking the ratio as the node overlapping degree.
In some embodiments, the merging module is specifically configured to:
and if the node coincidence degrees corresponding to the two overlapped communities are both greater than the preset coincidence degree, merging the two overlapped communities.
In some embodiments, further comprising:
and the second determining module is used for determining the danger probability of each community in the model of the relationship graph according to the content of the label.
In some embodiments, further comprising:
the acquisition module is used for acquiring behavior data of an object to be identified;
the third determining module is used for determining a target community to which the object to be recognized belongs by using the model of the relational graph according to the behavior data of the object to be recognized;
and the fourth determination module is used for determining the danger probability of the object to be identified according to the danger probability of the target community.
In some embodiments, the fourth determining module is specifically configured to:
if the number of the target communities is multiple, respectively determining the danger probability of each target community;
calculating the degree centrality of the target node corresponding to the object to be identified in the model of the relational graph in each target community;
and determining the danger probability of the object to be identified according to the weighted average value of the degree centrality of the target nodes in each target community.
In some embodiments, the sample object is an individual user;
the behavioural data comprises any one or more of:
historical loan information of individual users, overdue payment information, bad record information and the contact condition among a plurality of individual users.
The overlapping community processing device provided by the embodiment of the application has the same technical characteristics as the overlapping community processing method provided by the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
As shown in fig. 4, an electronic device 400 provided in an embodiment of the present application includes: a processor 401, a memory 402 and a bus, wherein the memory 402 stores machine-readable instructions executable by the processor 401, the processor 401 and the memory 402 communicate via the bus when the electronic device is operated, and the processor 401 executes the machine-readable instructions to perform the steps of the above-mentioned overlapping community processing method.
Specifically, the memory 402 and the processor 401 can be general-purpose memories and processors, which are not limited to the specific embodiments, and the overlapping community processing method can be executed when the processor 401 runs a computer program stored in the memory 402.
Corresponding to the above overlapping community processing method, the present application further provides a computer readable storage medium storing machine executable instructions, which when invoked and executed by a processor, cause the processor to execute the steps of the overlapping community processing method.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for processing overlapping communities is characterized in that behavior data of a plurality of sample objects are predetermined; the method comprises the following steps:
establishing a model of a relation graph based on the relation among the plurality of sample objects, wherein the relation graph comprises a plurality of nodes used for representing the sample objects, and the nodes are correspondingly marked with labels used for representing the behavior data;
repeatedly executing the following steps until the model of the relation graph is in accordance with the expectation:
dividing the nodes into a plurality of communities by utilizing a label propagation algorithm according to the labels;
if overlapping communities exist in a plurality of the communities, determining the node contact degree between any two overlapping communities in the overlapping communities;
if the node contact ratio is greater than a preset contact ratio, carrying out community combination on the two overlapped communities;
and judging whether the model of the relationship graph after the community combination is in accordance with the expectation.
2. The method of claim 1, wherein determining a degree of node overlap between any two of the overlapping communities comprises:
determining the number of coincident nodes between any two of the overlapping communities;
and calculating the ratio of the number of the overlapped nodes to the number of all nodes in the two overlapped communities respectively, and taking the ratio as the node overlapping degree.
3. The method of claim 2, wherein if the node contact degree is greater than a predetermined contact degree, the step of merging the two overlapping communities comprises:
and if the node coincidence degrees corresponding to the two overlapped communities are both greater than a preset coincidence degree, carrying out community combination on the two overlapped communities.
4. The method of claim 1, further comprising:
and determining the danger probability of each community in the relationship graph model according to the content of the label.
5. The method of claim 4, further comprising:
acquiring behavior data of an object to be identified;
determining a target community to which the object to be recognized belongs by using the model of the relation graph according to the behavior data of the object to be recognized;
and determining the danger probability of the object to be identified according to the danger probability of the target community.
6. The method of claim 5, wherein determining the risk probability of the object to be identified based on the risk probability of the target community comprises:
if the number of the target communities is multiple, respectively determining the danger probability of each target community;
calculating the degree centrality of the target node corresponding to the object to be identified in the model of the relational graph in each target community;
and determining the danger probability of the object to be identified according to the weighted average value of the degree centrality of the target nodes in each target community.
7. The method of claim 1, wherein the sample object is a personal user;
the behavioural data comprises any one or more of:
historical loan information, payment overdue information, bad record information and a plurality of contact conditions among the individual users.
8. An overlapping community processing apparatus characterized in that behavior data of a plurality of sample objects is determined in advance; the device comprises:
the establishing module is used for establishing a model of a relation graph based on the relation among the sample objects, the relation graph comprises a plurality of nodes used for representing the sample objects, and the nodes are correspondingly marked with labels used for representing the behavior data;
the dividing module is used for dividing the nodes into a plurality of communities according to the labels by utilizing a label propagation algorithm;
the determining module is used for determining the node contact degree between any two overlapped communities in the overlapped communities if the overlapped communities exist in a plurality of communities;
the merging module is used for merging the two overlapped communities if the node contact ratio is greater than a preset contact ratio;
the judging module is used for judging whether the model of the relationship graph after the community combination meets the expectation;
the dividing module, the determining module, the combining module and the judging module are repeatedly executed until the model of the relational graph is in accordance with expectation.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program operable on the processor, and wherein the processor implements the steps of the method of any of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium having stored thereon machine executable instructions which, when invoked and executed by a processor, cause the processor to execute the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911291105.6A CN110969526A (en) | 2019-12-13 | 2019-12-13 | Overlapping community processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911291105.6A CN110969526A (en) | 2019-12-13 | 2019-12-13 | Overlapping community processing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110969526A true CN110969526A (en) | 2020-04-07 |
Family
ID=70034419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911291105.6A Pending CN110969526A (en) | 2019-12-13 | 2019-12-13 | Overlapping community processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969526A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111756568A (en) * | 2020-05-06 | 2020-10-09 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing community discovery |
| CN112235120A (en) * | 2020-10-12 | 2021-01-15 | 济南欣格信息科技有限公司 | Group combination method and electronic equipment |
| CN114638007A (en) * | 2022-05-10 | 2022-06-17 | 富算科技(上海)有限公司 | Method, system, device and medium for determining community relation based on graph data |
| CN116991794A (en) * | 2023-05-24 | 2023-11-03 | 阿里云计算有限公司 | Data management method, system, device, equipment and medium in data warehouse |
| CN117290689A (en) * | 2023-09-21 | 2023-12-26 | 湖北太昇科技有限公司 | Smart home-based user binding method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400299A (en) * | 2013-07-02 | 2013-11-20 | 西安交通大学 | Method for detecting network overlapped communities based on overlapped point identification |
| CN103425737A (en) * | 2013-07-03 | 2013-12-04 | 西安理工大学 | Overlapping community discovery method for network |
| CN103729475A (en) * | 2014-01-24 | 2014-04-16 | 福州大学 | Multi-label propagation discovery method of overlapping communities in social network |
| WO2018077039A1 (en) * | 2016-10-27 | 2018-05-03 | 腾讯科技（深圳）有限公司 | Community discovery method, apparatus, server, and computer storage medium |
| CN110297912A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Cheat recognition methods, device, equipment and computer readable storage medium |
-
2019
- 2019-12-13 CN CN201911291105.6A patent/CN110969526A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400299A (en) * | 2013-07-02 | 2013-11-20 | 西安交通大学 | Method for detecting network overlapped communities based on overlapped point identification |
| CN103425737A (en) * | 2013-07-03 | 2013-12-04 | 西安理工大学 | Overlapping community discovery method for network |
| CN103729475A (en) * | 2014-01-24 | 2014-04-16 | 福州大学 | Multi-label propagation discovery method of overlapping communities in social network |
| WO2018077039A1 (en) * | 2016-10-27 | 2018-05-03 | 腾讯科技（深圳）有限公司 | Community discovery method, apparatus, server, and computer storage medium |
| CN110297912A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Cheat recognition methods, device, equipment and computer readable storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111756568A (en) * | 2020-05-06 | 2020-10-09 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing community discovery |
| CN112235120A (en) * | 2020-10-12 | 2021-01-15 | 济南欣格信息科技有限公司 | Group combination method and electronic equipment |
| CN112235120B (en) * | 2020-10-12 | 2022-06-10 | 济南欣格信息科技有限公司 | Group combination method and electronic equipment |
| CN114638007A (en) * | 2022-05-10 | 2022-06-17 | 富算科技(上海)有限公司 | Method, system, device and medium for determining community relation based on graph data |
| CN114638007B (en) * | 2022-05-10 | 2022-08-23 | 富算科技(上海)有限公司 | Method, system, device and medium for determining community relation based on graph data |
| CN116991794A (en) * | 2023-05-24 | 2023-11-03 | 阿里云计算有限公司 | Data management method, system, device, equipment and medium in data warehouse |
| CN116991794B (en) * | 2023-05-24 | 2024-07-23 | 阿里云计算有限公司 | Data management method, system, device, equipment and medium in data warehouse |
| CN117290689A (en) * | 2023-09-21 | 2023-12-26 | 湖北太昇科技有限公司 | Smart home-based user binding method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110969526A (en) | Overlapping community processing method and device and electronic equipment | |
| CN106982196B (en) | Abnormal access detection method and equipment | |
| CN109918584A (en) | Bit coin exchange Address Recognition method, system, device | |
| CN111090807B (en) | Knowledge graph-based user identification method and device | |
| CN111915015B (en) | Abnormal value detection method and device, terminal equipment and storage medium | |
| CN116596095B (en) | Training method and device of carbon emission prediction model based on machine learning | |
| CN111242358A (en) | Enterprise information loss prediction method with double-layer structure | |
| CN114298176A (en) | Method, device, medium and electronic equipment for detecting fraudulent user | |
| CN112036476A (en) | Data feature selection method and device based on two-classification service and computer equipment | |
| CN111145006A (en) | Automobile financial anti-fraud model training method and device based on user portrait | |
| CN113449012A (en) | Internet service mining method based on big data prediction and big data prediction system | |
| CN115098679A (en) | Method, device, equipment and medium for detecting abnormality of text classification labeling sample | |
| CN113313479A (en) | Payment service big data processing method and system based on artificial intelligence | |
| CN113723555A (en) | Abnormal data detection method and device, storage medium and terminal | |
| CN115294397A (en) | Classification task post-processing method, device, equipment and storage medium | |
| CN108830302B (en) | Image classification method, training method, classification prediction method and related device | |
| CN113472860A (en) | Service resource allocation method and server under big data and digital environment | |
| CN110807159B (en) | Data marking method and device, storage medium and electronic equipment | |
| CN116541792A (en) | Method for carrying out group partner identification based on graph neural network node classification | |
| CN113285977B (en) | Network maintenance method and system based on block chain and big data | |
| CN113627514A (en) | Data processing method and device of knowledge graph, electronic equipment and storage medium | |
| CN114780649A (en) | Method and device for identifying structured data entity type | |
| CN116092094A (en) | Image text recognition method and device, computer readable medium and electronic equipment | |
| CN112463964A (en) | Text classification and model training method, device, equipment and storage medium | |
| CN115186773B (en) | Passive active field adaptive model training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200407 |
|
| RJ01 | Rejection of invention patent application after publication |