CN108257070A - Suspect's localization method, device, electronic equipment and storage medium - Google Patents
Suspect's localization method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN108257070A CN108257070A CN201810157386.5A CN201810157386A CN108257070A CN 108257070 A CN108257070 A CN 108257070A CN 201810157386 A CN201810157386 A CN 201810157386A CN 108257070 A CN108257070 A CN 108257070A
- Authority
- CN
- China
- Prior art keywords
- node
- personnel
- accomplice
- behavior
- group number
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004807 localization Effects 0.000 title claims abstract description 28
- 230000006399 behavior Effects 0.000 claims description 179
- 238000000605 extraction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 11
- 239000003814 drug Substances 0.000 abstract description 8
- 229940079593 drug Drugs 0.000 abstract description 8
- 208000001613 Gambling Diseases 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002574 poison Substances 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
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
- 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
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of suspect's localization method, device, electronic equipment and storage mediums.Wherein method includes：Behavior relation data are obtained, wherein, behavior relation data include the behavior relation of multiple behavior personnel and each behavior personnel；Crime case data are obtained, and criminal gang's relational network figure is built based on crime case data；According to behavior relation data and criminal gang's relational network figure, the holotopy network being suspected of committing a crime is generated；According to holotopy network, suspect is positioned from multiple behavior personnel.This method can greatly improve the case handling efficiency of public security officer, greatly reduce the human cost of public security, improve the locating effect of suspect, be particularly involved in drug traffic, having the significant effect of comparison on the relational network that isodensity of gambling is high.
Description
Technical field
The present invention relates to technical field of information processing more particularly to a kind of suspect's localization method, device, electronics to set
Standby and computer readable storage medium.
Background technology
At present, in cracking of cases, public security officer often obtains and investigates clue by personnel's relationship.In the prior art
Relationship analysis be only capable of analyzing personnel's relationship by public security officer itself, and be only capable of starting with from single personnel, by
The interpersonal relationship of point analysis, carrys out screening suspect.But the mode of this positioning suspect, from single
Relational network node is started with, and is analyzed one by one, and as the node relationships number of degrees increase, generating the side of relationship can be exponentially increased, this nothing
The plenty of time of public security officer can be consumed by doubting, and substantially increased manpower screening cost, caused locating effect poor, positioning method is not
Enough intelligences.
Invention content
The purpose of the present invention is intended to solve one of the technical issues of above-mentioned at least to a certain extent.
For this purpose, first purpose of the present invention is to propose a kind of suspect's localization method.This method can be very big
Ground improves the case handling efficiency of public security officer, greatly reduces the human cost of public security, improves the locating effect of suspect, especially
It is to be involved in drug traffic, having the significant effect of comparison on the relational network that isodensity of gambling is high.
Second object of the present invention is to propose a kind of suspect's positioning device.
Third object of the present invention is to propose a kind of electronic equipment.
Fourth object of the present invention is to propose a kind of computer readable storage medium.
In order to achieve the above objectives, suspect's localization method that first aspect present invention embodiment proposes, including：It obtains
Behavior relation data, wherein, the behavior relation data include the behavior relation of multiple behavior personnel and each behavior personnel；It obtains
Crime case data are taken, and criminal gang's relational network figure is built based on the crime case data；According to the behavior relation
Data and criminal gang's relational network figure, generate the holotopy network being suspected of committing a crime；According to the holotopy net
Network figure positions suspect from the multiple behavior personnel.
In order to achieve the above objectives, suspect's positioning device that second aspect of the present invention embodiment proposes, including：First
Acquisition module, for obtaining behavior relation data, wherein, the behavior relation data include multiple behavior personnel and each behavior
The behavior relation of personnel；Second acquisition module, for obtaining crime case data；Module is built, for being based on the crime case
Number of packages is according to structure criminal gang's relational network figure；Generation module, for according to the behavior relation data and the criminal gang
Relational network figure generates the holotopy network being suspected of committing a crime；Locating module, for according to the holotopy network,
Suspect is positioned from the multiple behavior personnel.
In order to achieve the above objectives, the electronic equipment that third aspect present invention embodiment proposes, including：Memory, processor
And the computer program that can be run on the memory and on the processor is stored in, the processor performs described program
When, realize suspect's localization method described in first aspect present invention embodiment.
In order to achieve the above objectives, the non-transitorycomputer readable storage medium that fourth aspect present invention embodiment proposes,
Computer program is stored thereon with, the crime described in first aspect present invention embodiment is realized when described program is executed by processor
Suspect's localization method.
Suspect's localization method, device, electronic equipment and storage medium according to embodiments of the present invention, can obtain row
For relation data, wherein, behavior relation data includes the behavior relation of multiple behavior personnel and each behavior personnel, and obtains
Crime case data, and criminal gang's relational network figure is built based on crime case data, later, according to behavior relation data and
Criminal gang's relational network figure generates the holotopy network being suspected of committing a crime, finally, according to holotopy network, from more
Suspect is positioned in a behavior personnel.A kind of intelligentized positioning method is provided as a result, i.e., by being closed from global analysis
It is network, combines the business experience that public security officer handles a case, look for automatically has behavior relation with multiple and different criminal gangs
Suspect, greatly improve the case handling efficiency of public security officer, greatly reduce the human cost of public security, improve suspect
Locating effect, be particularly involved in drug traffic, having the significant effect of comparison on the relational network that isodensity of gambling is high.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
It obtains significantly or is recognized by the practice of the present invention.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow chart of suspect's localization method according to an embodiment of the invention；
Fig. 2 is the exemplary plot of criminal gang's relational network figure according to embodiments of the present invention；
Fig. 3 is the stream of the accomplice personnel node progress group number mark in the relational graph according to embodiments of the present invention to accomplice
Cheng Tu；
Fig. 4 is the exemplary plot of holotopy network being suspected of committing a crime according to embodiments of the present invention；
Fig. 5 is each behavior personnel's node in the calculating holotopy network according to an embodiment of the invention
The flow chart of relevant information；
Fig. 6 is the structure diagram of suspect's positioning device according to an embodiment of the invention；
Fig. 7 is the structure diagram according to suspect's positioning device of a specific embodiment of the invention；
Fig. 8 is the structure diagram according to suspect's positioning device of another specific embodiment of the invention；
Fig. 9 is the structure diagram according to suspect's positioning device of another specific embodiment of the invention；
Figure 10 is the structure diagram of electronic equipment according to an embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings suspect's localization method, device, electronic equipment and the calculating of the embodiment of the present invention are described
Machine readable storage medium storing program for executing.
Fig. 1 is the flow chart of suspect's localization method according to an embodiment of the invention.It should be noted that this
Suspect's localization method of inventive embodiments can be applied to suspect's positioning device of the embodiment of the present invention, the crime
Suspect's positioning device can be configured on electronic equipment.Wherein, which can be personal computer, mobile terminal
Can be the hardware device that mobile phone, tablet computer, personal digital assistant etc. have various operating systems Deng, the mobile terminal.
As shown in Figure 1, suspect's localization method can include：
S110 obtains behavior relation data, wherein, behavior relation data include multiple behavior personnel and each behavior personnel
Behavior relation.
Optionally, the Ticketing information that client is bought, the booking are obtained from the booking website of various traffic trip tools
Information may include identity information (such as identification card number, name), the booking time, booking number, origin, destination, purchase train number,
Buy seat number etc.；The lodging information of lodging personnel, the lodging information packet can be also obtained from the server in various lodging shops
The identity information (such as identification card number, name) of lodging personnel is included, the time is moved in, moves in duration, lodging personnel number, moves in room
Number etc..
After the Ticketing information and the lodging information of lodging personnel bought in acquisition client, the booking of the acquisition can be believed
Breath and lodging information carry out data analysis, to obtain behavior caused by each behavior personnel and each behavior personnel
Relationship.As a kind of example, the behavior relation may include but be not limited to same train relationship, with aircraft relationship, with lodging relationship
Deng.
It for example, can be by these after the Ticketing information and the lodging information of lodging personnel bought in acquisition client
Client and lodging personnel as behavior personnel, wherein, if there is a situation where to belong to same person in the client and lodging personnel,
Then using this belong to same person client and lodging personnel as a behavior personnel；Also, from the Ticketing information and lodging
Behavior relation caused by each behavior personnel is found out in information.For example, behavioral data can as the form shown in table 1 below into
Row information stores, and has behavior personnel A, B, C and D in behavior data, and, there is " train adjacent seat between behavior personnel A and B
Twice " and the behavior relation of " train with ticket booking 1 time ", there is " train adjacent seat is twice " between behavior personnel A and C and " train is same
There is the behavior relation of " aircraft is with ticket booking 3 times ", behavior personnel B and D between behavior personnel A and D in the behavior relation of ticket booking 1 time "
Between exist " train adjacent seat is twice ", " with stay 3 times " and " aircraft adjacent seat 1 time " behavior relation.
Table 1
| Src_ID | Dest_ID | Value |
| A | B | 1001:2；1002:1 |
| A | C | 1001:2；1002:1 |
| A | D | 2002:3 |
| B | D | 1001:2；3003:3；2001:1 |
Wherein, Src_ID represents that starting involved party person (node) ID, Dest_ID represent purpose behavior personnel (node) ID,
Value represents that behavior relation value, such as relations codes on probation represent, such as 1001:2 represent train adjacent seat twice, and 1002:1 generation
The same ticket booking of table train 1 time, 2002:3, which represent aircraft, books tickets 3 times together, and 3003:3 representatives are same to stay 3 times, and 2001:1 represents aircraft neighbour
1 inferior, multiple relationship semicolon separateds of seat.
S120 obtains crime case data, and builds criminal gang's relational network figure based on crime case data.
Optionally, crime case data are obtained, and build based on the crime case data from the server end of public security department
Go out criminal gang's relational network figure.
As a kind of example, the criminal in crime case data is extracted, and extract the accomplice in crime case data
Personnel's relationship, wherein, the case type (i.e. accomplice relationship) that accomplice personnel relationship includes personnel concerning the case, is related to, later, with crime
Personnel are node, and accomplice personnel relationship is node relationships, establish accomplice relational graph, and using connected graph algorithm to accomplice relational graph
In accomplice personnel node carry out group number mark, using the accomplice relational graph where the identical accomplice personnel's node of group number as
Criminal gang's relational network figure.
Which that is, can be extracted in comprising criminal, and from crime case number of packages in from crime case number of packages
The personnel for being related to identical case are extracted, and determine the case type involved by the personnel, it later, can be using criminal as section
Point, accomplice personnel relationship are node relationships (i.e. using accomplice personnel relationship as side), accomplice relational graph are built, then, using figure
Computational frame realizes connected graph algorithm, accomplice personnel is labeled as the identical criminal gang of group number, to obtain the crime group
Partner's relational network figure.
For example, as shown in Fig. 2, give criminal gang's exemplary plot of relational network figure, wherein, criminal gang's network of personal connections
Network figure contains the accomplice relational graph of 3 different criminal gangs, and each accomplice relational graph has itself corresponding group number.As
A kind of example, the accomplice relational graph can be stored by the form shown in table 2 below into row information, it is assumed that be wrapped in accomplice relational graph
A containing personnel concerning the case, b, c and d, and there is the accomplice relationship of " with taking drugs 1 time " between the personnel a and b, exist between personnel a and c
There is the accomplice relationship of " with taking drugs 1 time " and " with burglary 1 time " between personnel b and c in the accomplice relationship of " with taking drugs 1 time ",
There is the accomplice relationship " with burglary 1 time " between personnel b and d, exist between personnel c and d same " with burglary 1 time "
Case relationship.
Table 2
| Src_ID | Dest_ID | Value |
| a | b | 4001:1 |
| a | c | 4001:1 |
| b | c | 4001:1；4002:1 |
| b | d | 4002:1 |
| c | d | 4002:1 |
Wherein, Src_ID represents that starting personnel (node) ID, Dest_ID represent that purpose personnel (node) ID, Value are represented
Accomplice relation value can try out the expression of accomplice relations codes, for example, 4001:2 representatives are same to take drugs 2 times, and 4002:1 represents with the robber that enters the room
Surreptitiously 1 is inferior, multiple accomplice relationship semicolon separateds.
Optionally, in one embodiment of the invention, as shown in figure 3, described utilize connected graph algorithm to the accomplice
The specific implementation process that accomplice personnel node in relational graph carries out group number mark may include following steps：
S310 determines the node corresponding to each accomplice personnel in accomplice relational graph, and sets each accomplice in accomplice relational graph
The initial group number of personnel's node；
Optionally, the node in accomplice relational graph corresponding to each accomplice personnel is first determined, and will be in the accomplice relational graph
Initial group number of the node ID of each accomplice personnel node as each accomplice personnel node.
Itself group number of each accomplice personnel node is sent to neighbor node by S320 respectively；
The group number that each accomplice personnel node receives and itself group number are compared by S330；
S340, if the group number that each accomplice personnel node receives is less than itself group number of each accomplice personnel node,
Itself group number of each accomplice personnel node is then set as the group number received, and returns and performs the step S320；
S350, if the group number that each accomplice personnel node receives is greater than or equal to itself group of each accomplice personnel node
Number then controls each accomplice personnel node to stop sending group number.
For example, by taking the accomplice relational graph of a, b, c, d in Fig. 2 as an example, the step of figure calculating is carried out to the accomplice relational graph
It is rapid as follows：
It 1) can be first using the node ID of each node in the accomplice relational graph as the initial group number of each node；
2) itself group number of each node in the accomplice relational graph is first sent to neighbor node by first run iteration；
3) for each node, the group number that upper wheel iteration receives is compared with itself group number, if receive
Group number is less than itself group number, then itself group number of the node is set as group minimum in the group number received compiles
Number, and continue to send itself group number to neighbor node；
4) when the group number received is less than or equal to itself group number of node, iteration stopping, the i.e. node stop hair
Send group number.
For example, iterative process can be as follows：
First run iteration：
a->b:A represents the value a that a sends itself group number groupid to b；
| ID | groupid | Send (transmission) | Recv (reception) |
| a | a | a->b:a；a->c:a | null |
| b | b | b->a:b；b->c:b；b->d:b | null |
| c | c | c->a:c；c->b:c；c->d:c | null |
| d | d | d->c:d；d->b:d | null |
Second wheel iteration：
Since the group number groupid that a is received is b and c, all bigger than itself group number groupid, iteration stopping, a is no longer
Itself groupid is all set as the value smaller than itself groupid received by other nodes of transmission message, as shown in table below；
| ID | GroupID | send | recv |
| a | a | null | b；c |
| b | a | b->a:a；b->c:a；b->d:a | a,d |
| c | a | c->a:a；c->b:a；c->d:a | a,b,d |
| d | b | d->c:b；d->b:b | b,c |
Third round iteration：
It takes turns iteration on a nodes to have stopped, the groupid that b, c node epicycle receive is not less than itself groupid, iteration
Stop, the groupid that d node epicycles receive is smaller than itself groupid, itself groupid is updated, as shown in table below；
| ID | GroupID | send | recv |
| a | a | null | null |
| b | a | null | a,b |
| c | a | null | a,b |
| d | b | d->c:a；d->b:a | a,a |
Fourth round iteration：
A, b, c node in iteration round before to stop, and d nodes epicycle does not receive any message, iteration stopping, final a,
B, tetra- accomplice personnel's nodes of c, d, the groupid of itself are same value, i.e., this four artificial same criminal gangs are such as following
Shown in table；
Group number mark is carried out to the accomplice personnel node in accomplice relational graph using connected graph algorithm as a result, in this way, can
Using the accomplice relational graph where the identical accomplice personnel's node of group number as criminal gang's relational network figure.
S130 according to behavior relation data and criminal gang's relational network figure, generates the holotopy network being suspected of committing a crime
Figure.
Optionally, personnel concerning the case's node in criminal gang's relational network figure is extracted, and based on each behavior
The behavior relation of personnel finds out personnel concerning the case's node with behavior relation, and based on described from personnel concerning the case's node
On the basis of criminal gang's relational network figure, personnel concerning the case's node with behavior relation is saved with corresponding behavior personnel
Point carries out side connection, the holotopy network being suspected of committing a crime described in generation, wherein, the side connection is used to indicate connection and generates
The node of behavior relation.
For example, by taking criminal gang's relational network figure shown in Fig. 2 as an example, have in criminal gang's relational network figure
3 different accomplice relational graphs, can first extract all personnel concerning the case's node a, b in criminal gang's relational network figure, c,
D, e, f, g, h, i, j, k and l, and based on the behavior relation of each behavior personnel, found out from these personnel concerning the case's nodes
Personnel concerning the case's node with behavior relation is closed such as node a, b, c, d, e, f, g, h, i, j and l, and based on the criminal gang
It is on the basis of network, these personnel concerning the case's nodes with behavior relation is subjected to side company with corresponding behavior personnel node
It connects, the holotopy network being suspected of committing a crime described in generation.
For example, it is assumed that behavior personnel node corresponding with personnel concerning the case's node a, b, e is node A, with relating to
The corresponding behavior personnel nodes of case personnel's node b, f, h, j be node B, behavior personnel corresponding with personnel concerning the case's node c, d, i
Node be node C, behavior personnel node corresponding with personnel concerning the case's node g be node D and E, it is corresponding with personnel concerning the case's node j, l
Behavior personnel node for node F, the node in figure corresponding to capitalization English letter is behavior personnel's node, small English alphabet
Corresponding node is personnel concerning the case's node, and the side connection between personnel concerning the case's node represents to generate accomplice relationship between node, relates to
Side connection between case personnel node and behavior personnel's node represents to generate behavior relation between node.
According to holotopy network, suspect is positioned from multiple behavior personnel by S140.
Optionally, using figure Computational frame algorithm, each behavior personnel's node in the holotopy network is calculated
Relevant information, wherein, the relevant information include with each behavior personnel node have behavior relation criminal gang's number,
The behavior relation quantity generated with criminal, and according to preset ordering rule, to the phase of each behavior personnel node
It closes information to be ranked up, finally, will put in order the corresponding behavior personnel node of relevant information that meets preset condition, be positioned as
The suspect.
That is, using figure Computational frame algorithm, each behavior personnel are calculated in the holotopy network
The relevant information of node, wherein, which may include but be not limited to：There is behavior relation and more from how many different cliques
Few different criminal has behavior relation, the behavior relation quantity generated with criminal, the row generated with criminal
For relationship type etc..Later, the relevant information being calculated can be ranked up according to certain ordering rule, and will arrangement
Sequence meets the corresponding behavior personnel node of relevant information of preset condition, is positioned as the suspect, and export the criminal
Guilty suspect is to be supplied to user (such as public security officer).
As a kind of example, as shown in figure 5, described utilize figure Computational frame algorithm, the holotopy network is calculated
In the specific implementation process of relevant information of each behavior personnel's node may include following steps：
Based on each node and side information in holotopy network, destination node is determined from each node by S510,
In, which is used to indicate the node that self attributes are accomplice personnel node and side information is behavior relation；
S520 by the node serial number, group number and side information of destination node, is sent to involved party corresponding with destination node
Member's node, the corresponding behavior personnel node are used to indicate the node that behavior relation is generated with destination node；
S530 according to the node serial number, group number and side information received, calculates each row in holotopy network
Relevant information for personnel's node.
For example, the iterative process for figure calculating being carried out to holotopy network can be as follows：1) first run iteration is sentenced first
The self attributes and side information of each node in disconnected figure, if the self attributes of node is accomplice personnel nodes, (as shown in Figure 4 is small
Write the node corresponding to English alphabet), and side information is behavior relation (the corresponding section of capital and small letter English alphabet as shown in Figure 4
Side connection between point), then by the node serial number, group number and side information of the node itself, it is sent to the involved party of corresponding sides
Member's node.For example, by taking holotopy network shown in Fig. 4 as an example, node a things done in first run iteration are as follows：Section
Point a judges itself for accomplice personnel's node, obtains the side information of node a, it (is respectively a that node a, which has three sides,<->b,a<->
c,a<->A), only side information " a<->A " is behavior relation, at this point, can be by the node serial number, group number and side information of node a
“a<->A " (side information that will represent behavior relation) is sent to behavior personnel's node A of corresponding sides.
2) the second wheel iteration：For behavior personnel node according to the node serial number, group number and side information received, calculating should
The relevant information of behavior personnel's node, such as：There are behavior relation, the criminal different with how many from how many different cliques
There are behavior relation, the behavior relation quantity generated with criminal, the behavior relation type generated with criminal etc..
In this way, after the relevant information of each behavior personnel node is obtained, it can be according to the relevant information, according to certain row
Node in the top as suspect and is recommended use by sequence rule to each behavior personnel node carry out sequence sequence
Family.
Suspect's localization method according to embodiments of the present invention, can obtain behavior relation data, wherein, the behavior closes
Coefficient evidence includes the behavior relation of multiple behavior personnel and each behavior personnel, and obtains crime case data, and based on crime
Case data build criminal gang's relational network figure, later, according to behavior relation data and criminal gang's relational network figure, generation
The holotopy network being suspected of committing a crime finally, according to holotopy network, suspicion of crime is positioned from multiple behavior personnel
People.A kind of intelligentized positioning method is provided as a result, i.e., by from global analysis's relational network, combining public security officer and doing
The business experience of case looks for the suspect for having behavior relation with multiple and different criminal gangs, greatly improves public affairs automatically
The case handling efficiency of peace personnel greatly reduces the human cost of public security, improves the locating effect of suspect, is particularly relating to
There is the significant effect of comparison on the high relational network of poison, gambling isodensity.
Corresponding with suspect's localization method that above-mentioned several embodiments provide, a kind of embodiment of the invention also carries
For a kind of suspect's positioning device, due to suspect's positioning device provided in an embodiment of the present invention and above-mentioned several realities
The suspect's localization method for applying example offer is corresponding, therefore is also fitted in the embodiment of aforementioned suspect's localization method
For suspect's positioning device provided in this embodiment, it is not described in detail in the present embodiment.Fig. 6 is according to the present invention
The structure diagram of suspect's positioning device of one embodiment.As shown in fig. 6, suspect's positioning device 600
It can include：First acquisition module 610, the second acquisition module 620, structure module 630, generation module 640 and locating module
650。
Specifically, the first acquisition module 610 can be used for obtaining behavior relation data, wherein, behavior relation data include more
A behavior personnel and the behavior relation of each behavior personnel.
Second acquisition module 620 can be used for obtaining crime case data.
Module 630 is built to can be used for building criminal gang's relational network figure based on crime case data.As a kind of example,
As shown in fig. 7, the structure module 630 can include：First extraction unit 631, the second extraction unit 632, first establishing unit
633rd, group number mark unit 634 and second establishes unit 635.Wherein, the first extraction unit 631 is used to extract crime case number of packages
Criminal in；Second extraction unit 632 is used to extract accomplice personnel's relationship in crime case data, wherein, accomplice
The case type that personnel's relationship includes personnel concerning the case, is related to；First establishing unit 633 is used for using criminal as node, accomplice
Personnel's relationship is node relationships, establishes accomplice relational graph；Group number mark unit 634 is used to close accomplice using connected graph algorithm
It is the accomplice personnel node progress group number mark in figure；Second, which establishes unit 635, is used for the identical accomplice personnel of group number
Accomplice relational graph where node is as criminal gang's relational network figure.
As a kind of example, group number mark unit 634 can be specifically used for：Determine each accomplice people in the accomplice relational graph
Node corresponding to member, and the initial group number of each accomplice personnel node in the accomplice relational graph is set；It respectively will be described each
Itself group number of accomplice personnel's node is sent to neighbor node；Group number that each accomplice personnel node is received with from
Body group number is compared；If the group number that each accomplice personnel node receives is less than each accomplice personnel node
Itself group number of each accomplice personnel node is then set as the group number received, and returned by itself group number
Perform described the step of itself group number of each accomplice personnel node is sent to neighbor node respectively；It is if described each same
The group number that case personnel's node receives is greater than or equal to itself group number of each accomplice personnel node, then controls described each
Accomplice personnel node stops sending group number.
Generation module 640 can be used for according to behavior relation data and criminal gang's relational network figure, generate what is be suspected of committing a crime
Holotopy network.As a kind of example, as shown in figure 8, the generation module 640 can include：Extraction unit 641 determines
Unit 642 and generation unit 643.Wherein, extraction unit 641 is used to extract personnel concerning the case's section in criminal gang's relational network figure
Point；Determination unit 642 is used for the behavior relation based on each behavior personnel, is found out from personnel concerning the case's node with behavior relation
Personnel concerning the case's node；Generation unit 643 is used to be based on the basis of criminal gang's relational network figure, will be with behavior relation
Personnel concerning the case's node carries out side connection with corresponding behavior personnel node, generates the holotopy network being suspected of committing a crime, wherein,
Side connection is used to indicate the node that connection generates behavior relation.
Locating module 650 can be used for according to holotopy network, and suspect is positioned from multiple behavior personnel.Make
For a kind of example, as shown in figure 9, the locating module 650 can include：Computing unit 651, sequencing unit 652 and positioning unit
653.Wherein, computing unit 651 is used for using figure Computational frame algorithm, calculates each behavior personnel section in holotopy network
The relevant information of point, wherein, relevant information includes the criminal gang's number for having behavior relation with each behavior personnel node, with violating
The behavior relation quantity that guilty person person generates；Sequencing unit 652 is used for according to preset ordering rule, to each behavior personnel node
Relevant information be ranked up；Positioning unit 653 meets the corresponding behavior of relevant information of preset condition for that will put in order
Personnel's node, is positioned as suspect.
Wherein, in one embodiment of the invention, computing unit 651 can be specifically used for：Based on holotopy network
In each node and side information, determine destination node from each node, wherein, it is same that destination node, which is used to indicate self attributes,
Case personnel node and the node that side information is behavior relation；By the node serial number, group number and side information of destination node, send
The corresponding behavior personnel node of destination node is given, corresponding behavior personnel node is used to indicate generates behavior pass with destination node
The node of system；According to the node serial number, group number and side information received, each involved party in holotopy network is calculated
The relevant information of member's node.
Suspect's positioning device according to embodiments of the present invention can obtain behavior relation number by the first acquisition module
According to, wherein, behavior relation data includes the behavior relation of multiple behavior personnel and each behavior personnel, and the second acquisition module obtains
Crime case data are taken, structure module is based on crime case data and builds criminal gang's relational network figure, and generation module is according to row
For relation data and criminal gang's relational network figure, the holotopy network being suspected of committing a crime is generated, locating module is according to the overall situation
Relational network figure positions suspect from multiple behavior personnel.A kind of intelligentized positioning method is provided as a result, i.e.,
By from global analysis's relational network, combining the business experience that public security officer handles a case, looking for automatically and multiple and different crimes
There is the suspect of behavior relation in clique, greatly improves the case handling efficiency of public security officer, greatly reduces the manpower of public security
Cost improves the locating effect of suspect, is particularly being involved in drug traffic, is having the comparison significant on the relational network that isodensity of gambling is high
Effect.
In order to realize above-described embodiment, the invention also provides a kind of electronic equipment.
Figure 10 is the structure diagram of electronic equipment according to an embodiment of the invention.As shown in Figure 10, which sets
Standby 1000 can include：It memory 1010, processor 1020 and is stored on memory 1010 and can be transported on processor 1020
Capable computer program 1030 when processor 1020 performs described program 1030, realizes any of the above-described a embodiment institute of the present invention
The suspect's localization method stated.
In order to realize above-described embodiment, the invention also provides a kind of non-transitorycomputer readable storage medium, thereon
Computer program is stored with, realizes that the crime described in any of the above-described a embodiment of the present invention is disliked when described program is executed by processor
Doubt people's localization method.
In the description of the present invention, it is to be understood that term " first ", " second " are only used for description purpose, and cannot
It is interpreted as indicating or implies relative importance or imply the quantity of the technical characteristic indicated by indicating.Define as a result, " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In the description of the present invention, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " example ", " is specifically shown " some embodiments "
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment of the present invention or example.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It is combined in an appropriate manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the different embodiments or examples described in this specification and the feature of different embodiments or examples
It closes and combines.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
Module, segment or the portion of the code of the executable instruction of one or more the step of being used to implement specific logical function or process
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, to perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) it uses or combines these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
It puts.The more specific example (non-exhaustive list) of computer-readable medium is including following：Electricity with one or more wiring
Connecting portion (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can be for example by carrying out optical scanner to paper or other media, then into edlin, interpretation or when necessary with it
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the present invention can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.If for example, with hardware come realize in another embodiment, can be under well known in the art
Any one of row technology or their combination are realized：With for the logic gates to data-signal realization logic function
Discrete logic, have suitable combinational logic gate circuit application-specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, the program when being executed, one or a combination set of the step of including embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, it can also
That each unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and is independent product sale or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although it has been shown and retouches above
The embodiment of the present invention is stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, those of ordinary skill in the art can be changed above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (14)
1. a kind of suspect's localization method, which is characterized in that including：
Behavior relation data are obtained, wherein, the behavior relation data include the row of multiple behavior personnel and each behavior personnel
For relationship；
Crime case data are obtained, and criminal gang's relational network figure is built based on the crime case data；
According to the behavior relation data and criminal gang's relational network figure, the holotopy network being suspected of committing a crime is generated
Figure；
According to the holotopy network, suspect is positioned from the multiple behavior personnel.
2. suspect's localization method as described in claim 1, which is characterized in that described to be built based on crime case data
Criminal gang's relational network figure, including：
Extract the criminal in the crime case data；
Accomplice personnel's relationship in the crime case data is extracted, wherein, the accomplice personnel relationship includes personnel concerning the case, relates to
And case type；
Using the criminal as node, the accomplice personnel relationship is node relationships, establishes accomplice relational graph；
Group number mark is carried out to the accomplice personnel node in the accomplice relational graph using connected graph algorithm；
Using the accomplice relational graph where the identical accomplice personnel's node of group number as criminal gang's relational network figure.
3. suspect's localization method as claimed in claim 2, which is characterized in that described to utilize connected graph algorithm to described
Accomplice personnel node in accomplice relational graph carries out group number mark, including：
It determines the node corresponding to each accomplice personnel in the accomplice relational graph, and each accomplice people in the accomplice relational graph is set
The initial group number of member's node；
Itself group number of each accomplice personnel node is sent to neighbor node respectively；
The group number that each accomplice personnel node receives is compared with itself group number；
If the group number that each accomplice personnel node receives is less than itself group number of each accomplice personnel node,
Itself group number of each accomplice personnel node is set as the group number received, and returns and performs the general respectively
The step of itself group number of each accomplice personnel node is sent to neighbor node；
If the group number that each accomplice personnel node receives is greater than or equal to itself group of each accomplice personnel node
Number then controls each accomplice personnel node to stop sending group number.
4. suspect's localization method as described in claim 1, which is characterized in that described according to behavior relation data and institute
Criminal gang's relational network figure is stated, generates the holotopy network being suspected of committing a crime, including：
Extract personnel concerning the case's node in criminal gang's relational network figure；
Based on the behavior relation of each behavior personnel, found out from personnel concerning the case's node with the case-involving of behavior relation
Personnel's node；
On the basis of criminal gang's relational network figure, by personnel concerning the case's node with behavior relation with it is corresponding
Behavior personnel node carry out side connection, the holotopy network being suspected of committing a crime described in generation, wherein, the side connection is used for
Indicate that connection generates the node of behavior relation.
5. suspect's localization method according to any one of claims 1 to 4, which is characterized in that described according to the overall situation
Relational network figure positions suspect from the multiple behavior personnel, including：
Using figure Computational frame algorithm, the relevant information of each behavior personnel's node in the holotopy network is calculated,
In, the relevant information includes the criminal gang's number and criminal that have behavior relation with each behavior personnel node
The behavior relation quantity of generation；
According to preset ordering rule, the relevant information of each behavior personnel node is ranked up；
By the corresponding behavior personnel node of relevant information for meeting preset condition that puts in order, it is positioned as the suspect.
6. suspect's localization method as claimed in claim 5, which is characterized in that it is described to utilize figure Computational frame algorithm,
The relevant information of each behavior personnel node in the holotopy network is calculated, including：
Based on each node and side information in the holotopy network, destination node is determined from each node,
In, the destination node is used to indicate the node that self attributes are accomplice personnel node and the side information is behavior relation；
By the node serial number, group number and side information of the destination node, it is sent to involved party corresponding with the destination node
Member's node, the corresponding behavior personnel node are used to indicate the node that behavior relation is generated with the destination node；
According to the node serial number, group number and side information received, each involved party in the holotopy network is calculated
The relevant information of member's node.
7. a kind of suspect's positioning device, which is characterized in that including：
First acquisition module, for obtaining behavior relation data, wherein, the behavior relation data include multiple behavior personnel and
The behavior relation of each behavior personnel；
Second acquisition module, for obtaining crime case data；
Module is built, for being based on crime case data structure criminal gang's relational network figure；
Generation module, for according to the behavior relation data and criminal gang's relational network figure, generating what is be suspected of committing a crime
Holotopy network；
Locating module, for according to the holotopy network, suspect to be positioned from the multiple behavior personnel.
8. suspect's positioning device as claimed in claim 7, which is characterized in that the structure module includes：
First extraction unit, for extracting the criminal in the crime case data；
Second extraction unit, for extracting accomplice personnel's relationship in the crime case data, wherein, the accomplice personnel are closed
It is the case type for including personnel concerning the case, being related to；
First establishing unit, for using the criminal as node, the accomplice personnel relationship to be node relationships, establishes accomplice
Relational graph；
Group number marks unit, for carrying out group's volume to the accomplice personnel node in the accomplice relational graph using connected graph algorithm
Number mark；
Second establishes unit, for using the accomplice relational graph where the identical accomplice personnel's node of group number as the crime group
Partner's relational network figure.
9. suspect's positioning device as claimed in claim 8, which is characterized in that the group number mark unit is specifically used
In：
It determines the node corresponding to each accomplice personnel in the accomplice relational graph, and each accomplice people in the accomplice relational graph is set
The initial group number of member's node；
Itself group number of each accomplice personnel node is sent to neighbor node respectively；
The group number that each accomplice personnel node receives is compared with itself group number；
If the group number that each accomplice personnel node receives is less than itself group number of each accomplice personnel node,
Itself group number of each accomplice personnel node is set as the group number received, and returns and performs the general respectively
The step of itself group number of each accomplice personnel node is sent to neighbor node；
If the group number that each accomplice personnel node receives is greater than or equal to itself group of each accomplice personnel node
Number then controls each accomplice personnel node to stop sending group number.
10. suspect's positioning device as claimed in claim 7, which is characterized in that the generation module includes：
Extraction unit, for extracting personnel concerning the case's node in criminal gang's relational network figure；
Determination unit, for the behavior relation based on each behavior personnel, being found out from personnel concerning the case's node has
Personnel concerning the case's node of behavior relation；
Generation unit, will be described case-involving with behavior relation on the basis of being based on criminal gang's relational network figure
Personnel's node and corresponding behavior personnel node carry out side connection, the holotopy network being suspected of committing a crime described in generation, wherein,
The side connection is used to indicate the node that connection generates behavior relation.
11. suspect's positioning device as described in any one of claim 7 to 10, which is characterized in that the positioning mould
Block includes：
Computing unit for utilizing figure Computational frame algorithm, calculates each behavior personnel's node in the holotopy network
Relevant information, wherein, the relevant information includes the criminal gang for having behavior relation with each behavior personnel node
Number, the behavior relation quantity generated with criminal；
Sequencing unit, for according to preset ordering rule, being ranked up to the relevant information of each behavior personnel node；
Positioning unit for the corresponding behavior personnel node of relevant information that meets preset condition of putting in order, is positioned as institute
State suspect.
12. suspect's positioning device as claimed in claim 11, which is characterized in that the computing unit is specifically used for：
Based on each node and side information in the holotopy network, destination node is determined from each node,
In, the destination node is used to indicate the node that self attributes are accomplice personnel node and the side information is behavior relation；
By the node serial number, group number and side information of the destination node, it is sent to involved party corresponding with the destination node
Member's node, the corresponding behavior personnel node are used to indicate the node that behavior relation is generated with the destination node；
According to the node serial number, group number and side information received, each involved party in the holotopy network is calculated
The relevant information of member's node.
13. a kind of electronic equipment, including：It memory, processor and is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that when the processor performs described program, realize as any in claim 1 to 6
Suspect's localization method described in.
14. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the journey
Such as suspect's localization method according to any one of claims 1 to 6 is realized when sequence is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810157386.5A CN108257070A (en) | 2018-02-24 | 2018-02-24 | Suspect's localization method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810157386.5A CN108257070A (en) | 2018-02-24 | 2018-02-24 | Suspect's localization method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108257070A true CN108257070A (en) | 2018-07-06 |
Family
ID=62745192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810157386.5A Pending CN108257070A (en) | 2018-02-24 | 2018-02-24 | Suspect's localization method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108257070A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580260A (en) * | 2019-08-07 | 2019-12-17 | 北京明略软件系统有限公司 | Data mining method and device for specific group |
| CN110717425A (en) * | 2019-09-26 | 2020-01-21 | 深圳市商汤科技有限公司 | Case association method and device, electronic equipment and storage medium |
| CN110738431A (en) * | 2019-10-28 | 2020-01-31 | 北京明略软件系统有限公司 | Method and device for allocating monitoring resources |
| CN110825785A (en) * | 2019-11-05 | 2020-02-21 | 佳都新太科技股份有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN111090681A (en) * | 2019-11-12 | 2020-05-01 | 高新兴科技集团股份有限公司 | Group mining method, device, equipment and storage medium |
| CN111210118A (en) * | 2019-12-23 | 2020-05-29 | 北京市新技术应用研究所 | Crime suspect comprehensive influence evaluation method based on social network analysis |
| CN111935634A (en) * | 2020-08-17 | 2020-11-13 | 范松 | Personnel positioning system |
| CN111984831A (en) * | 2020-08-21 | 2020-11-24 | 北京明略软件系统有限公司 | Method and apparatus for theft event information mining |
| CN112416922A (en) * | 2021-01-25 | 2021-02-26 | 北京数网信息技术有限公司 | Group partner association data mining method, device, equipment and storage medium |
-
2018
- 2018-02-24 CN CN201810157386.5A patent/CN108257070A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580260A (en) * | 2019-08-07 | 2019-12-17 | 北京明略软件系统有限公司 | Data mining method and device for specific group |
| CN110580260B (en) * | 2019-08-07 | 2023-05-26 | 北京明智和术科技有限公司 | Data mining method and device for specific group |
| CN110717425A (en) * | 2019-09-26 | 2020-01-21 | 深圳市商汤科技有限公司 | Case association method and device, electronic equipment and storage medium |
| CN110738431B (en) * | 2019-10-28 | 2022-06-17 | 北京明略软件系统有限公司 | Method and device for allocating monitoring resources |
| CN110738431A (en) * | 2019-10-28 | 2020-01-31 | 北京明略软件系统有限公司 | Method and device for allocating monitoring resources |
| CN110825785A (en) * | 2019-11-05 | 2020-02-21 | 佳都新太科技股份有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN111090681A (en) * | 2019-11-12 | 2020-05-01 | 高新兴科技集团股份有限公司 | Group mining method, device, equipment and storage medium |
| CN111090681B (en) * | 2019-11-12 | 2023-08-15 | 高新兴科技集团股份有限公司 | Method, device, equipment and storage medium for group excavation |
| CN111210118A (en) * | 2019-12-23 | 2020-05-29 | 北京市新技术应用研究所 | Crime suspect comprehensive influence evaluation method based on social network analysis |
| CN111935634A (en) * | 2020-08-17 | 2020-11-13 | 范松 | Personnel positioning system |
| CN111935634B (en) * | 2020-08-17 | 2023-06-02 | 范松 | Personnel positioning system |
| CN111984831A (en) * | 2020-08-21 | 2020-11-24 | 北京明略软件系统有限公司 | Method and apparatus for theft event information mining |
| CN112416922A (en) * | 2021-01-25 | 2021-02-26 | 北京数网信息技术有限公司 | Group partner association data mining method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108257070A (en) | Suspect's localization method, device, electronic equipment and storage medium | |
| US10671936B2 (en) | Method for clustering nodes of a textual network taking into account textual content, computer-readable storage device and system implementing said method | |
| Ali et al. | Adam deep learning with SOM for human sentiment classification | |
| Schneider et al. | Urban growth in Chengdu, Western China: application of remote sensing to assess planning and policy outcomes | |
| Saavedra et al. | Asymmetric disassembly and robustness in declining networks | |
| Zhang et al. | User community discovery from multi-relational networks | |
| Jiang et al. | Fema: flexible evolutionary multi-faceted analysis for dynamic behavioral pattern discovery | |
| Yu et al. | A node deployment algorithm based on van der Waals force in wireless sensor networks | |
| Ríos et al. | Dark web portal overlapping community detection based on topic models | |
| CN107872436A (en) | A kind of account recognition methods, apparatus and system | |
| CN103733190B (en) | For the method and apparatus protecting the privacy of network data | |
| Elalfi et al. | Extracting rules from trained neural network using GA for managing E-business | |
| Mirani et al. | Sentiment analysis of isis related tweets using absolute location | |
| Kutty et al. | A people-to-people recommendation system using tensor space models | |
| CN108153824A (en) | The determining method and device of targeted user population | |
| Isah et al. | Bipartite network model for inferring hidden ties in crime data | |
| Kazienko et al. | Evaluation of node position based on email communication | |
| Lyzinski et al. | Matchability of heterogeneous networks pairs | |
| CN110413900A (en) | More social networks account matching process based on viterbi algorithm | |
| Chen et al. | A novel approach to uncover health care frauds through spectral analysis | |
| Qiu et al. | Graph simplification and matching using commute times | |
| Huang et al. | Social friend recommendation based on network correlation and feature co-clustering | |
| Liang et al. | Federal learning edge network based sentiment analysis combating global COVID-19 | |
| Punde et al. | Fake product review monitoring & removal and sentiment analysis of genuine reviews | |
| Lookman et al. | A framework for occupational fraud detection by social network analysis |
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: 20180706 |
|
| RJ01 | Rejection of invention patent application after publication |