CN108052641A - The personnel's infectiosity coefficient calculation method calculated based on large scale network - Google Patents
The personnel's infectiosity coefficient calculation method calculated based on large scale network Download PDFInfo
- Publication number
- CN108052641A CN108052641A CN201711396287.4A CN201711396287A CN108052641A CN 108052641 A CN108052641 A CN 108052641A CN 201711396287 A CN201711396287 A CN 201711396287A CN 108052641 A CN108052641 A CN 108052641A
- Authority
- CN
- China
- Prior art keywords
- personnel
- infectiosity
- network
- large scale
- calculated based
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention discloses a kind of personnel's infectiosity coefficient calculation methods calculated based on large scale network, it is related to public safety technical field, technical solution is to include S1, the essential information basic database that information is recorded including human criminal is established by way of importing external data base；S2, the basic database established by S1 establish the catenet comprising personnel's essential information and personnel's relation；S3, the previous conviction in personal information in S1 basic databases set the initial value of the infectiosity of each personnel, are iterated by the network to S2 and the final infectiosity of each personnel is calculated.The beneficial effects of the invention are as follows：Can obtain the reasonable infectiosity of each personnel in network, to distinguish the safe class of personnel, for criminal investigation, solve a case, linguistic context, the security protections means such as monitoring provide strong support data, the highly beneficial improvement in public safety.
Description
Technical field
The present invention relates to public safety technical field, more particularly to a kind of personnel's infectiosity calculated based on large scale network
Coefficient calculation method.
Background technology
Extensive relational network analytical technology is developed rapidly in recent years, especially with Open Source Platforms such as Spark
Parallel, distributed map analysis module gradually move to maturity, relational network more than ten million node magnitude is calculated as
For possibility.The progress of technology extends practical application scene, for example, large-scale social network sites need to handle the customer relationship of magnanimity,
E-commerce website needs to predict target user, and search engine needs to find most associated paper information, etc..It is existing to answer
Internet arena is concentrated on most of, and for substantial amounts of socialization data, the technology of forefront how is introduced, to be had
The information of value, does not arouse enough attention.Particularly, in public safety field, people are imaged by individual
The modes such as record, Internet bar's registration record, mobile communication record, previous conviction, wifi probes are moved in head, traffic block port, hotel, note
The status information of substantial amounts of personnel or equipment has been recorded, how the information of these magnanimity has been associated, and is obtained it and take feature and rule
Rule had both had potential major application value and an arduous technological challenge.
The content of the invention
In order to realize foregoing invention purpose, it is associated for magnanimity personal information and obtains its feature and rule is asked
Topic, the present invention provide a kind of personnel's infectiosity coefficient calculation method calculated based on large scale network, including,
S1, the essential information basic database that information is recorded including human criminal is established by way of importing external data base；
S2, the basic database established by S1 establish the catenet comprising personnel's essential information and personnel's relation；Wherein save
Point expression personnel, record the person related information, the relation between side expression personnel；
S3, the previous conviction in personal information in S1 basic databases set the initial value of the infectiosity of each personnel,
It is iterated by the network to S2 and the final infectiosity of each personnel is calculated.
Preferably, the external data base imported in the S1 includes at least permanent resident population's database, previous conviction storehouse, hotel
Move in storehouse, Internet bar's register base, with administrative staff storehouse.
Preferably, in the S2, each network node represent the relevant information of personnel include at least name, identification card number,
Criminal type, hotel move in record, the relation between each network edge expression personnel, including at least relation of living together or go together.
Preferably, the specific calculation procedure of the S3 is：
S301, all personnel is divided by two classifications according to the basic database first：Emphasis personnel, non-emphasis personnel；
Wherein emphasis personnel refer to the personnel with previous conviction, the more low factor of personal integrity value, and non-emphasis personnel refer to ordinary people；
S302, data are initially talked about, according to the classification of S301, initial value infectiosity is set to different classes of personnel；
S303, computing is iterated, in the first iteration, chooses the node of all emphasis personnel as starting point, to connected
Other all nodes send the 1/2 of autoinfection degree；Adjacent node will receive value and will be added with itself current infectiosity,
Obtain updated infectiosity；
S304, in successive iterations calculating, choose all non-zero non-emphasis personnel nodes, current infection sent to adjacent node
The 1/2 of degree, the value received is added in autoinfection degree by adjacent node；Continue this process until the infectiosity of all nodes
It no longer updates or reaches the iterations threshold value determined by experimental result.
Preferably, infectiosity is initially talked about in the S302 to be set as, the node of the emphasis personnel with previous conviction is set
Infectiosity for 1, normal artificial 0.
Preferably, the iterations threshold value of the S304 is 4 times.
The advantageous effect that technical solution provided in an embodiment of the present invention is brought is：It can obtain the conjunction of each personnel in network
Manage infectiosity, to distinguish the safe class of personnel, for criminal investigation, solve a case, linguistic context, the security protections means such as monitoring provide strong support
Data, the highly beneficial improvement in public safety.
Description of the drawings
Fig. 1 is the flow chart of the embodiment of the present invention.
Fig. 2 is personnel's network diagram of the embodiment of the present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.Certainly, specific embodiment described herein is not used to only to explain the present invention
Limit the present invention.
Embodiment 1
The present invention provides a kind of personnel's infectiosity coefficient calculation method calculated based on large scale network, including
S1, the essential information basic database that information is recorded including human criminal is established by way of importing external data base；
S2, the basic database established by S1 establish the catenet comprising personnel's essential information and personnel's relation；Wherein save
Point expression personnel, record the person related information, the relation between side expression personnel；
S3, the previous conviction in personal information in S1 basic databases set the initial value of the infectiosity of each personnel,
It is iterated by the network to S2 and the final infectiosity of each personnel is calculated.
The external data base imported in S1 moves in storehouse, Internet bar including at least permanent resident population's database, previous conviction storehouse, hotel
Register base, with administrative staff storehouse.
In S2, each network node represents that the relevant information of personnel includes at least name, identification card number, criminal type, guest
Record is moved in shop, the relation between each network edge expression personnel, including at least relation of living together or go together.
The specific calculation procedure of S3 is：
S301, all personnel is divided by two classifications according to basic database first：Emphasis personnel, non-emphasis personnel；Wherein
Emphasis personnel refer to the personnel with previous conviction, the more low factor of personal integrity value, and non-emphasis personnel refer to ordinary people；
S302, data are initially talked about, according to the classification of S301, initial value infectiosity is set to different classes of personnel；
S303, computing is iterated, in the first iteration, chooses the node of all emphasis personnel as starting point, to connected
Other all nodes send the 1/2 of autoinfection degree；Adjacent node will receive value and will be added with itself current infectiosity,
Obtain updated infectiosity；
S304, in successive iterations calculating, choose all non-zero non-emphasis personnel nodes, current infection sent to adjacent node
The 1/2 of degree, the value received is added in autoinfection degree by adjacent node；Continue this process until the infectiosity of all nodes
It no longer updates or reaches the iterations threshold value determined by experimental result.
Infectiosity initially to be talked about in S302 to be set as, the infectiosity for setting the node of the emphasis personnel with previous conviction is 1,
Normal artificial 0.
The iterations threshold value of S304 is 4 times.
Exemplified by being applied to public safety, referring to Fig. 1, the key step of personnel's infectiosity computational methods provided by the invention
It is as follows：
Step 1 imports external data.Relevant external data base, such as personnel's essential information storehouse, previous conviction storehouse etc. are chosen,
Unloading enters unified database.One typical personnel's essential information is as follows：
| Name | Identification card number | Native place |
| Zhang San | 18 certificate numbers | Haidian District, Beijing City |
One typical previous conviction information is as follows
| Name | Identification card number | Criminal type |
| Zhang San | 18 certificate numbers | Theft |
One typical personnel's relation record information is as follows
| Name | Identification card number | Same pedestrian | Colleague's relation |
| Zhang San | 18 certificate numbers | Zhao great | Hotel |
| Zhang San | 18 certificate numbers | Li Juan | High ferro |
Step 2, according to the above persons and relation information, build personnel's network, as shown in Figure 2
The various record information of the node table person of leting others have a look at of the above persons' network, can be converted into such as following table view:
Nodal properties table
| ID | Property (V) |
| Zhang San | (identification card number, theft, 1.0) |
| Zhao great | (identification card number, nothing, 0) |
| Li Juan | (identification card number, nothing, 0) |
Section 2 in upper table in Property (V) row represents criminal type, last numerical value represents the infection of counterpart personnel
Degree, when having crime or other illegal acts to record in personnel record's information table, infectiosity is set to 1, and when no illegal act is set to
0。
Side in personnel's network represents the relation between everyone's (node in figure), can be converted into such as following table view:
Side property list
| SrcID | DstID | Property (E) |
| Zhang San | Zhao great | Hotel |
| Zhang San | Li Juan | High ferro |
Wherein SrcID row represent the starting point on side, and DstID row represent the terminal on side, and Property (E) is represented between two nodes
Relation, such as live together a hotel or colleague one row high ferro.
Step 3, the infectiosity for obtaining all nodes.The first time of infectiosity is calculated from emphasis personnel (Zhang San), to
Adjacent node sends the half of autoinfection degree, and updated node state is：
| ID | Property (V) |
| Zhang San | (identification card number, theft, 1.0) |
| Zhao great | (identification card number, nothing, 0.5) |
| Li Juan | (identification card number, nothing, 0.5) |
Subsequent iterative process no longer design focal point personnel node (Zhang San), only from all infectiosities it is non-be 0 non-emphasis people
Member's node (Zhao is big, Li Juan) sets out, and the half of autoinfection degree is sent to adjacent node, continues time process, until all nodes
Infectiosity stablize constant or iterations and reach predetermined threshold value (such as 4 times).
Embodiment 2
According to the step of embodiment 1, concrete operations are：
The personal information record data of outer scattered are imported, the graph structure of description personal information and personnel's relation is established and passes through
Iterative algorithm adjusts the infectiosity of personnel, includes the following steps：
Step 1 imports various external data bases, moves in storehouse, Internet bar comprising permanent resident population's database, previous conviction storehouse, hotel and steps on
Remember storehouse, with administrative staff storehouse etc., be stored in Hbase；
Step 2 builds a big figure comprising all personnel and relation, wherein vertex representation personnel using spark-graphx,
Record the information such as identity, the address of the personnel, the relation between side expression personnel, friend, relatives etc., all information both be from
The external data base that step 1 imports；
Step 3 is iterated figure calculating using Pregel algorithms, score value is infected into administrative staff during iteration
It calculates, detailed process is as follows：
1st, when initialization, the infectiosity for setting the vertex of the emphasis personnel with previous conviction is 1, normal artificial 0.
2nd, in the first iteration, the vertex of all emphasis personnel is chosen as starting point, to other connected all tops
Point sends the half of autoinfection degree.Adjacent vertex will receive value and will be added with itself current infectiosity, after obtaining update
Infectiosity.
3rd, in successive iterations calculating, all non-zero non-emphasis personnel vertex are chosen, current sense is sent to connected vertex
The value received is added in autoinfection degree by the 1/2 of dye degree, adjacent vertex.Continue this process until the infection on all vertex
Degree no longer updates or reaches default iterations threshold value.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modifications, equivalent replacements and improvements are made should all be included in the protection scope of the present invention.
Claims (6)
1. the personnel's infectiosity coefficient calculation method calculated based on large scale network, it is characterised in that：
S1, the essential information basic database that information is recorded including human criminal is established by way of importing external data base；
S2, the basic database established by S1 establish the catenet comprising personnel's essential information and personnel's relation；Wherein save
Point expression personnel, record the person related information, the relation between side expression personnel；
S3, the previous conviction in personal information in S1 basic databases set the initial value of the infectiosity of each personnel,
It is iterated by the network to S2 and the final infectiosity of each personnel is calculated.
2. the personnel's infectiosity coefficient calculation method according to claim 1 calculated based on large scale network, feature are existed
In the external data base imported in the S1 moves in storehouse, Internet bar including at least permanent resident population's database, previous conviction storehouse, hotel
Register base, with administrative staff storehouse.
3. the personnel's infectiosity coefficient calculation method according to claim 1 calculated based on large scale network, feature are existed
In in the S2, each network node represents that the relevant information of personnel includes at least name, identification card number, criminal type, hotel
Move in record, the relation between each network edge expression personnel, including at least relation of living together or go together.
4. the personnel's infectiosity coefficient calculation method according to claim 1 calculated based on large scale network, feature are existed
In the specific calculation procedure of the S3 is：
S301, all personnel is divided by two classifications according to the basic database first：Emphasis personnel, non-emphasis personnel；
Wherein emphasis personnel refer to the personnel for the factor at least having previous conviction, personal integrity value relatively low, and non-emphasis personnel refer to commonly
People；
S302, data are initially talked about, according to the classification of S301, initial value infectiosity is set to different classes of personnel；
S303, computing is iterated, in the first iteration, chooses the node of all emphasis personnel as starting point, to connected
Other all nodes send the 1/2 of autoinfection degree；Adjacent node will receive value and will be added with itself current infectiosity,
Obtain updated infectiosity；
S304, in successive iterations calculating, choose all non-zero non-emphasis personnel nodes, current infection sent to adjacent node
The 1/2 of degree, the value received is added in autoinfection degree by adjacent node；Continue this process until the infectiosity of all nodes
It no longer updates or reaches the iterations threshold value determined by experimental result.
5. the personnel's infectiosity coefficient calculation method according to claim 4 calculated based on large scale network, feature are existed
In, infectiosity initially to be talked about in the S302 and is set as, the infectiosity for setting the node of the emphasis personnel with previous conviction is 1,
Normal artificial 0.
6. the personnel's infectiosity coefficient calculation method according to claim 4 calculated based on large scale network, feature are existed
In the iterations threshold value of the S304 is 4 times.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711396287.4A CN108052641A (en) | 2017-12-21 | 2017-12-21 | The personnel's infectiosity coefficient calculation method calculated based on large scale network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711396287.4A CN108052641A (en) | 2017-12-21 | 2017-12-21 | The personnel's infectiosity coefficient calculation method calculated based on large scale network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108052641A true CN108052641A (en) | 2018-05-18 |
Family
ID=62131344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711396287.4A Pending CN108052641A (en) | 2017-12-21 | 2017-12-21 | The personnel's infectiosity coefficient calculation method calculated based on large scale network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108052641A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062823A (en) * | 2019-09-26 | 2020-04-24 | 北京明略软件系统有限公司 | Social graph analysis method and device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101464877A (en) * | 2008-10-27 | 2009-06-24 | 浙江大学 | System and method for digging related criminal suspect |
| US8694979B2 (en) * | 2012-06-26 | 2014-04-08 | International Business Machines Corporation | Efficient egonet computation in a weighted directed graph |
| CN106934071A (en) * | 2017-04-27 | 2017-07-07 | 北京大学 | Recommendation method and device based on Heterogeneous Information network and Bayes's personalized ordering |
-
2017
- 2017-12-21 CN CN201711396287.4A patent/CN108052641A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101464877A (en) * | 2008-10-27 | 2009-06-24 | 浙江大学 | System and method for digging related criminal suspect |
| US8694979B2 (en) * | 2012-06-26 | 2014-04-08 | International Business Machines Corporation | Efficient egonet computation in a weighted directed graph |
| CN106934071A (en) * | 2017-04-27 | 2017-07-07 | 北京大学 | Recommendation method and device based on Heterogeneous Information network and Bayes's personalized ordering |
Non-Patent Citations (1)
| Title |
|---|
| 童维勤 等: "《大数据技术与应用》", 31 January 2015 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062823A (en) * | 2019-09-26 | 2020-04-24 | 北京明略软件系统有限公司 | Social graph analysis method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Modeling cyber rumor spreading over mobile social networks: A compartment approach | |
| CN104303483B (en) | For the recognition system based on user of social networks | |
| Barbera et al. | Signals from the crowd: uncovering social relationships through smartphone probes | |
| Khan et al. | A cloud-based healthcare framework for security and patients’ data privacy using wireless body area networks | |
| CN108519981A (en) | A kind of decentralization data sharing method of highly effective and safe | |
| CA3032682C (en) | Method for managing information using tree structure based on blockchain, server and terminal using the same | |
| WO2001040972A3 (en) | System and method for authenticating and registering personal background data | |
| CN105376223B (en) | The reliability degree calculation method of network identity relationship | |
| Mirani et al. | Sentiment analysis of isis related tweets using absolute location | |
| CN107276978B (en) | A kind of hiding service source tracing method of the Anonymizing networks of Intrusion Detection based on host fingerprint | |
| JP5949766B2 (en) | Service providing apparatus, service providing method, and storage medium | |
| CN108092766A (en) | A kind of cipher text searching method for verifying authority and its system | |
| CN109284589A (en) | Across the social networks entity identities analytic method of one kind | |
| Chernyshev et al. | On 802.11 access point locatability and named entity recognition in service set identifiers | |
| CN110008402A (en) | A kind of point of interest recommended method of the decentralization matrix decomposition based on social networks | |
| CN108052641A (en) | The personnel's infectiosity coefficient calculation method calculated based on large scale network | |
| KR102366505B1 (en) | An access certification system and method using one time identification | |
| CN103810248A (en) | Method and device for searching for interpersonal relationship based on photos | |
| CN108664808B (en) | A kind of user's sensitivity theme guard method and system towards books search service | |
| Baranchikov et al. | The technique of dynamic data masking in information systems | |
| CN106657164A (en) | Composite identity recognition algorithm for real name authentication, and identity recognition system for real name authentication | |
| CN110535815A (en) | A kind of method and apparatus identifying URL | |
| Ballinger | Impossible Returns, Enduring legacies: recent historiography of displacement and the reconstruction of Europe after World War II | |
| CN108365949A (en) | Client's system of real name approaches to IM, apparatus and system | |
| Sharma | Aadhaar-a unique identification number: Opportunities and challenges ahead |
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: 20180518 |
|
| RJ01 | Rejection of invention patent application after publication |