CN109492116A - The method and device of character relation network struction - Google Patents
The method and device of character relation network struction Download PDFInfo
- Publication number
- CN109492116A CN109492116A CN201811430598.2A CN201811430598A CN109492116A CN 109492116 A CN109492116 A CN 109492116A CN 201811430598 A CN201811430598 A CN 201811430598A CN 109492116 A CN109492116 A CN 109492116A
- Authority
- CN
- China
- Prior art keywords
- personage
- road
- information
- motion track
- crossing
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of method and devices of character relation network struction, wherein the method for character relation network struction includes: the trace information acquired in specified region, wherein trace information includes the motion track of personage and personage corresponds to the motion track of vehicle;According to the road information in trace information and specified region, road network information is obtained;According to preset rules, coded treatment is carried out to road network information, obtains the corresponding multiple vectors of road network information, wherein the corresponding vector of every road information of road network information;According to multiple vectors, the relevance between each personage is determined, obtain the character relation network in specified region.Trace information is constructed in conjunction with road information character relation network and by obtaining multiple vectors to road network information coding by the present invention, not only reduces the computation complexity of data information, and improve the accuracy of character relation network struction.
Description
Technical field
The present invention relates to relational network constructing technology fields, a kind of method more particularly, to character relation network struction and
Device.
Background technique
With the continuous social and economic development, the relationship between personage becomes increasingly complex, in order to preferably study personage it
Between relationship, generally the relationship between personage can intuitively be changed, for example pass through network display;Existing method is to text mostly
Information carries out morphological analysis, establishes knowledge base, then carry out pattern match matching using the knowledge base, extracts character relation, such
Method needs to handle a large amount of text information, and computation complexity is higher, and the accuracy of character relation network struction is poor.
It is high for above-mentioned character relation network creating method computation complexity, and the accuracy of character relation network struction compared with
The problem of difference, not yet puts forward effective solutions.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of method and device of character relation network struction, to reduce
Data computation complexity and the accuracy for improving character relation network struction.
In a first aspect, the embodiment of the invention provides a kind of method of character relation network struction, this method comprises: acquisition
Trace information in specified region, wherein trace information includes the motion track of personage and personage corresponds to the motion track of vehicle;
According to the road information in trace information and specified region, road network information is obtained;Road network information includes personage in particular link
Mobile message;Mobile message includes at least personage by way of particular link, one of frequency and speed;According to default rule
Then, coded treatment is carried out to road network information, obtains the corresponding multiple vectors of road network information, wherein every road of road network information
Information corresponds to a vector;According to multiple vectors, the relevance between each personage is determined, obtain the character relation in specified region
Network.
Further, above-mentioned acquisition specify region in personage motion track the step of, including it is one of following or
It is a variety of: to use the relevant information of public transport by personage, obtain the motion track of personage;Identity card is used by personage
Place relevant information, obtain the motion track of personage;The image information captured by bayonet or camera obtains people
The motion track of object;The motion track that personage rides is obtained, using the motion track ridden as the moving rail of personage
Mark.
Further, above-mentioned acquisition specify region in vehicle motion track the step of, including it is one of following or
It is a variety of: by the record of bayonet, to obtain the motion track of vehicle;The automobile image captured by camera, obtains vehicle
Motion track;By the coordinate of the acquisition of MAC collector and the MAC Address of vehicle binding, the motion track of vehicle is obtained.
Further, the above-mentioned road information according in trace information and specified region, the step of obtaining road network information, packet
It includes: obtaining road information in specified region;Road information includes the road information between crossing and crossing;Wherein, the road between crossing
Road information includes that the speed for walking through road and number, vehicle pass through the speed and number of road;Personage walks through road
The calculation formula of speed V be V=L/ Δ T, L indicates the length of road, and Δ T indicates that personage passes through the time needed for road;Root
According between crossing, crossing road information and trace information obtain road network information, using crossing as network node in road network information, road
Road between mouthful is as even side.
Further, above-mentioned according to preset rules, coded treatment is carried out to road network information, it is corresponding multiple to obtain road network information
The step of vector, comprising: road network information is encoded using one-hot coding mode, has M crossing in road network information, then
The null vector of an a length of M is established accordingly, wherein each crossing corresponds to a position in null vector;Judge trace information
Whether by crossing, if corresponding position sets 1 in null vector by crossing;According to default rule, road network information pair is obtained
The multiple vectors answered;Pass through the multiple vectors of database purchase.
Further, above-mentioned to determine the relevance between each personage according to multiple vectors, the personage obtained in specified region is closed
The step of being network, comprising: obtain the corresponding multiple vectors of all persons;Every two personage is calculated in its corresponding each vector
In relevance, obtain the average value W of relevance;Calculate the relevance average value W of personage A and personage B(A,B)Formula beWherein, n indicates that the sum of the vector in database, D indicate in i-th of vector
The number that personage A and personage B occurs simultaneously in the road,Indicate the average speed of personage A walking in i-th of vector,Indicate the average speed that personage A in i-th of vector rides,Indicate the number of personage A walking in i-th of vector,Indicate in i-th of vector that personage A rides the number passed through,Indicate the average speed of walking in i-th of vector of personage B
Degree,Indicate the average speed that personage B in i-th of vector rides,Indicate time of personage B walking in i-th of vector
Number,Indicate in i-th of vector that personage B rides the number passed through;Relational network is constructed according to the average value of relevance,
Wherein, relational network establishes connection, weight of the relevance as connection using personage as node between the node of relevant property.
Second aspect, the embodiment of the present invention also provide a kind of device of character relation network struction, which includes: information
Acquisition module, for acquiring the trace information in specified region, wherein trace information includes motion track and the personage couple of personage
Answer the motion track of vehicle;Road network information obtains module, for obtaining according to the road information in trace information and specified region
Road network information;Road network information includes mobile message of the personage in particular link;Mobile message includes at least personage by specifying
One of mode, frequency and speed of road;Coding module, for carrying out coded treatment to road network information, obtaining according to preset rules
To the corresponding multiple vectors of road network information, wherein the corresponding vector of every road information of road network information;Character relation network
Determining module obtains the character relation net in specified region for determining the relevance between each personage according to multiple vectors
Network.
Further, above- mentioned information acquisition module is also used to realize one or more of following: being used by personage public
The relevant information of the vehicles altogether, obtains the motion track of personage;By personage using the relevant information in the place of identity card, obtain
Take the motion track of personage;The image information captured by bayonet or camera obtains the motion track of personage;Obtain people
A motion track that object is ridden, using the motion track ridden as the motion track of personage.
Further, above- mentioned information acquisition module is also used to realize one or more of following: by the note of bayonet
Record, obtains the motion track of vehicle;The automobile image captured by camera obtains the motion track of vehicle;It is adopted by MAC
The coordinate of storage acquisition and the MAC Address of vehicle binding, obtains the motion track of vehicle.
Further, above-mentioned road network information obtains module, is also used to: obtaining road information in specified region;Road information packet
Include the road information between crossing and crossing;Wherein, the road information between crossing includes the speed and number, vehicle for walking through road
Pass through the speed and number of road;The calculation formula that personage walks through the speed V of road is V=L/ Δ T, and L indicates road
Length, Δ T indicates that personage passes through the time needed for road;According between crossing, crossing road information and trace information obtain
Road network information, using crossing as network node in road network information, the road between crossing is as even side.
The embodiment of the present invention bring it is following the utility model has the advantages that
The present invention provides a kind of method and device of character relation network struction, the track letter in specified region is collected
After breath, according to the road information in the trace information and specified region, road network information is obtained;According still further to preset rules, to road network
Information carries out coded treatment, obtains the corresponding multiple vectors of road network information, and then determine the relevance between each personage, is referred to
Determine the character relation network in region.Trace information is constructed in conjunction with road information character relation network and led to by the present invention
It crosses and multiple vectors is obtained to road network information coding, not only reduce the computation complexity of data information, and improve personage pass
It is the accuracy of network struction.
Other features and advantages of the present invention will illustrate in the following description, alternatively, Partial Feature and advantage can be with
Deduce from specification or unambiguously determine, or by implementing above-mentioned technology of the invention it can be learnt that.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, better embodiment is cited below particularly, and match
Appended attached drawing is closed, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the method for character relation network struction provided in an embodiment of the present invention;
Fig. 2 is the flow chart of the method for another character relation network struction provided in an embodiment of the present invention;
Fig. 3 is that road network information provided in an embodiment of the present invention encodes to obtain in the preset rules of corresponding multiple vectors every
The flow chart of the selection rule of road;
Fig. 4 is a kind of structural schematic diagram of the device of character relation network struction provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
The method of character relation network struction is to carry out morphological analysis to text information mostly in the prior art, establishes data
Library, then pattern match is carried out to extract character relation using the database, to establish character relation network, but need to handle a large amount of
Text information, computation complexity is high, and the accuracy of personage's relevance is poor, be based on this, provided in an embodiment of the present invention one
The method and device of kind character relation network struction, the rule and the police that can be applied to research information propagation are found crime and are disliked
It doubts in the scenes such as people and criminal gang.
For convenient for understanding the present embodiment, first to a kind of character relation network structure disclosed in the embodiment of the present invention
The method built describes in detail.
A kind of flow chart of the method for character relation network struction shown in Figure 1, personage's relational network building
The specific steps of method include:
Step S102 acquires the trace information in specified region, wherein the trace information include personage motion track and
The personage corresponds to the motion track of vehicle.
The acquisition trajectories information in specified region, can preferably obtain the relevance of personage, wherein the moving rail of personage
The acquisition pattern of mark includes but is not limited to following manner: moving rail when personage is using vehicles such as bus, shared bicycles
Mark;Internet bar, hotel etc. use the people information in the place of identity card;The character image information that bayonet, camera etc. capture;Root
According to the owner information of vehicle, the motion track of the corresponding vehicle of the personage can be considered as to the motion track etc. of the personage.
Above-mentioned bayonet is usually the entrance for having defence and checking facility, for example, cell doorway, company's entrance or station
Deng the bayonet of place setting.
The acquisition pattern of the motion track of the corresponding vehicle of above-mentioned personage includes but is not limited to following manner: vehicle passes through card
Record information when mouth;MAC (Media Access Control Address, media access control address) collector collects
With vehicle binding MAC Address coordinate;The influence etc. for the automobile that camera captures.
Above-mentioned MAC Address is usually the address for being used to confirm on-line apparatus position;Under normal circumstances, it each sets on the net
Standby (for example, automobile, bus etc. of networking) has unique MAC Address to be corresponding to it.
Step S104 obtains road network information according to the road information in above-mentioned trace information and specified region;Road network letter
Breath includes mobile message of the personage in particular link;The mobile message includes at least personage by way of particular link, frequency
One of rate and speed.
Road information in above-mentioned specified region includes the road information between crossing and the crossing, that is to say, that Mei Gecheng
City region generally includes multiple crossings, and a road is just had between every two crossing, has complicated phase between road
It connects, forms the road information in the region.
Above-mentioned trace information is combined with the road information in specified region, obtains road network information, wherein make with crossing
For network node, the road between crossing forms road network information as even side, which includes personage in particular link
Mobile message, the mobile message are usually to pass through above-mentioned trace information to obtain.
Above-mentioned mobile message may include personage by way of particular link, one of frequency and speed or more
Kind, wherein personage may include walking by way of particular link, take public transport or self-driving etc.;Personage passes through
The frequency of particular link may include the number that personage walks through the number of particular link, vehicle passes through in particular link
Deng;The speed that personage passes through particular link may include that personage walks through the average speed of the road, vehicle on the road
The average speed etc. of traveling.
Step S106 carries out coded treatment to above-mentioned road network information, it is corresponding to obtain the road network information according to preset rules
Multiple vectors, wherein the corresponding vector of every road information of the road network information.
Information in above-mentioned road network information in order to obtain carries out coded treatment according to preset rules to road network information, by road
Net information MAP at multiple low dimensionals vector, in this way, convert the road network information data of multidimensional to the vector of multiple low dimensionals,
Reduce the complexity of information calculating, wherein every road information corresponds to a vector, includes the selection at crossing in the vector
The mobile message of road between information and the crossing being selected.
Step S108 determines the relevance between each personage according to multiple vectors, obtains the character relation in specified region
Network.
The relevance between each personage is calculated according to the information in each vector, wherein the information in vector includes personage
The average speed of the road is walked through by the number of particular link, personage, vehicle passes through the average speed of the road, personage
Walk through the number of the road, number that vehicle passes through etc..
According to the relevance between above-mentioned personage, the node of relevant property can be established into even side, node using personage as node
Between relevance construct character relation network as the weight on even side.
The embodiment of the invention provides a kind of methods of character relation network struction, this method comprises: collecting specified area
After trace information in domain, according to the road information in the trace information and specified region, road network information is obtained;According still further to default
Rule carries out coded treatment to road network information, obtains the corresponding multiple vectors of road network information, and then determine the pass between each personage
Connection property obtains the character relation network in specified region.Trace information is constructed in conjunction with road information personage and closed by the present invention
It is network and by obtaining multiple vectors to road network information coding, not only reduces the computation complexity of data information, and
Improve the accuracy of character relation network struction.
The flow chart of the method for another character relation network struction shown in Figure 2;This method people shown in Fig. 1
It is realized on the basis of the method for object relational network building;The specific steps of this method, comprising:
Step S202 acquires the trace information in specified region.
Above-mentioned trace information includes the motion track of personage and the motion track of vehicle corresponding with personage;Wherein acquisition is specified
The step of motion track of personage in region, including one or more of following: (1) public transport is used by personage
The relevant information of tool obtains the motion track of personage;(2) it is obtained by personage using the relevant information in the place of identity card
The motion track of personage;(3) image information captured by bayonet or camera obtains the motion track of personage;(4) it obtains
The motion track that personage rides is taken, using the motion track ridden as the motion track of personage.
According to the motion track of collected personage in conjunction with the real road situation in region, available following people
The motion track of object: < [T5, T6], road C;[T7, T8], road D ... >, which is expressed as personage and exists at [T5, the T6] moment
On road C, at [T7, the T8] moment on road D etc..
The step of motion track of the vehicle in region, is specified in above-mentioned acquisition, including one or more of following: (1)
By the record of bayonet, the motion track of vehicle is obtained;(2) automobile image captured by camera obtains the shifting of vehicle
Dynamic rail mark;(3) by the coordinate of the acquisition of MAC collector and the MAC Address of vehicle binding, the motion track of vehicle is obtained.
According to the motion track of collected vehicle in conjunction with the real road situation in region, available following vehicle
Motion track: < [T1, T2], road A;[T3, T4], road B ... >, which is expressed as vehicle and exists at [T1, the T2] moment
Traveling on road A travels etc. at [T3, the T4] moment on road B.
Step S204 obtains road information in specified region;The road information includes the road information between crossing and crossing;
Wherein, the road information between the crossing includes that the speed for walking through the road and number, vehicle pass through the speed of road and secondary
Number.
The calculation formula that above-mentioned personage walks through the speed V of road is V=L/ Δ T, and L indicates the length of road, Δ T table
Time needed for object of leting others have a look at passes through road.
Step S206, according between above-mentioned crossing, crossing road information and trace information obtain road network information, the road network letter
Using crossing as network node in breath, the road between crossing is as even side.
For a certain road A, the road network information of road A can be indicated with following vectors:
Above-mentioned vector is multidimensional, and computation complexity is higher, wherein P1Indicate personage 1,Indicate that personage 1 walks through
The speed of road A,Indicate the speed that personage 1 rides public transportation means through road A,Indicate that personage 1 walks through road A's
Number,Indicate the number that personage 1 rides public transportation means through road A, and so on, P2Indicate personage 2,Indicate personage 2
The speed of road A is walked through,Indicate the speed that personage 2 rides public transportation means through road A,Indicate that 2 walking of personage is logical
The number of road A is crossed,Indicate the number that personage 2 rides public transportation means through road A.
Step S208 encodes road network information using one-hot coding mode, there is M crossing in the road network information,
The null vector of an a length of M is then established accordingly, wherein each crossing corresponds to a position in null vector.
Above-mentioned one-hot coding is also commonly known as an efficient coding mode, mainly using M bit status register come pair
M state is encoded, each state by his independent register-bit, and only have when any one effectively;one-
Hot coding is usually expression of the classified variable as binary vector.
Step S210 judges trace information whether by crossing, if corresponding position is set in null vector by the crossing
1。
Step S212 obtains the corresponding multiple vectors of road network information according to default rule;It is multiple by database purchase
Vector.
The multi-C vector of road network information can be correspondingly formed the vector of multiple low dimensionals according to default rule, thus
Reduce the computation complexity to data.
Above-mentioned default rule may is that (to be equivalent to the above-mentioned crossing), randomly selects one never from start node
For the path link passed by next crossing, the calculation method of the selection probability of every road is as shown in Figure 3.
Referring to Fig. 3, at first crossing, the calculation formula of the selection probability of every road be may be expressed as:Wherein, n indicates the quantity for the road being connected with first crossing, PjIndicate the j-th strip road being connected with the crossing
The probability that road is selected, LjIndicate the length for the j-th strip road being connected with the crossing, LiIndicate i-th road being connected with the crossing
The length on road.
Next judge whether next crossing has road to be directly connected to a upper crossing, if so, so selecting next
The calculation formula of the selection probability of every road may be expressed as: when roadWherein, PjIndicate selection with
The probability of the j-th strip road of crossing vector, n indicate the quantity for the road being connected with crossing, and k expression is connected with a upper crossing
The quantity of road, LiIndicate the length of i-th road, LLIndicate a crossing to this crossing link length;Otherwise, it selects
The calculation formula of the selection probability of every road may be expressed as: when next road
After reaching next crossing, continue never to pass by according to the selection rule selection of every road when next road of selection
Road;When pass by N number of crossing when, save migration record, and as vector deposit database in, the calculation formula of N are as follows:Wherein M is the crossing sum in road network information.
Step S214 obtains the corresponding multiple vectors of all persons: calculating every two personage in its corresponding each vector
In relevance, obtain the average value W of relevance.
Calculate the relevance average value W of personage A and personage B(A,B)Formula beWherein, n indicates that the sum of the vector in database, D indicate in i-th of vector
The number that personage A and personage B occurs simultaneously in the road,Indicate the average speed of personage A walking in i-th of vector,Indicate the average speed that personage A in i-th of vector rides,Indicate time of personage A walking in i-th of vector
Number,Indicate in i-th of vector that personage A rides the number passed through,Walking is flat in expression i-th of vector of personage B
Equal speed,Indicate the average speed that personage B in i-th of vector rides,Indicate personage B walking in i-th of vector
Number,Indicate in i-th of vector that personage B rides the number passed through.
The value of above-mentioned relevance average value W is bigger, indicates that the relevance of two people is stronger.
Step S216 constructs relational network according to the average value of above-mentioned relevance, wherein the relational network is section with personage
Point establishes connection, weight of the relevance as connection between the node of relevant property.
In the present embodiment, road network information is carried out using one-hot coding mode to encode and pass through default rule, is obtained
Road network information corresponding multiple vectors, reduce computation complexity, and this method has merged trace information, to Data Dimensionality Reduction
Feature vector is extracted with the method for random walk afterwards, keeps result accuracy higher.
The embodiment of method corresponding to above-mentioned character relation network struction, a kind of personage shown in Figure 4 are closed
It is the structural schematic diagram of the device of network struction;The device includes:
Information acquisition module 40, for acquiring the trace information in specified region, wherein trace information includes the shifting of personage
Dynamic rail mark and personage correspond to the motion track of vehicle;
Road network information obtains module 41, for obtaining road network letter according to the road information in trace information and specified region
Breath;Road network information includes mobile message of the personage in particular link;Mobile message includes at least personage and passes through particular link
One of mode, frequency and speed;
Coding module 42, for carrying out coded treatment to road network information, it is corresponding obtaining road network information according to preset rules
Multiple vectors, wherein the corresponding vector of every road information of road network information;
Character relation network determining module 43, for determining the relevance between each personage, being referred to according to multiple vectors
Determine the character relation network in region.
Further, above- mentioned information acquisition module is also used to realize one or more of following: be used by personage
The relevant information of public transport obtains the motion track of personage;The relevant information in the place of identity card is used by personage,
Obtain the motion track of personage;The image information captured by bayonet or camera obtains the motion track of personage;It obtains
A motion track that personage rides, using the motion track ridden as the motion track of personage.
Further, above- mentioned information acquisition module is also used to realize one or more of following: by the note of bayonet
Record obtains the mobile track of vehicle;The automobile image captured by camera obtains the mobile track of vehicle;It is adopted by MAC
The coordinate of storage acquisition and the MAC Address of vehicle binding obtains the mobile track of vehicle.
Further, road network information obtains module, is also used to: obtaining road information in specified region;The road information packet
Include the road information between crossing and crossing;Wherein, the road information between crossing includes the speed and number, vehicle for walking through road
Pass through the speed and number of road;The calculation formula that personage walks through the speed V of road is V=L/ Δ T, and L indicates road
Length, Δ T indicates that personage passes through the time needed for road;According between crossing, crossing road information and trace information obtain
Road network information, using crossing as network node in road network information, the road between crossing is as even side.
The device of a kind of character relation network struction provided in an embodiment of the present invention, with a kind of people provided by the above embodiment
The method technical characteristic having the same of object relational network building reaches identical so also can solve identical technical problem
Technical effect.
The method and device of character relation network struction provided by the embodiment of the present invention extracts personage by trace information
Relevance, improve the accuracy of personage's relevance, and merge to data, reduce the complexity of calculating;Figure is reflected
It penetrates as vector, keeps result accuracy higher.
The computer program product of the method and device of character relation network struction provided by the embodiment of the present invention, including
The computer readable storage medium of program code is stored, the instruction that said program code includes can be used for executing previous methods reality
Method described in example is applied, specific implementation can be found in embodiment of the method, and details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
And/or the specific work process of device, it can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of method of character relation network struction, which is characterized in that the described method includes:
Acquire the trace information in specified region, wherein the trace information include personage motion track and the personage couple
Answer the motion track of vehicle;
According to the road information in the trace information and the specified region, road network information is obtained;The road network information includes
Mobile message of the personage in particular link;The mobile message includes at least the personage and passes through the particular link
One of mode, frequency and speed;
According to preset rules, coded treatment is carried out to the road network information, obtains the corresponding multiple vectors of the road network information,
In, the corresponding vector of the road information of every of the road network information;
According to multiple vectors, the relevance between each personage is determined, obtain the character relation network in the specified region.
2. the method according to claim 1, wherein the motion track of the personage in region is specified in the acquisition
Step, including one or more of following:
The relevant information that public transport is used by personage, obtains the motion track of the personage;
By personage using the relevant information in the place of identity card, the motion track of the personage is obtained;
The image information captured by bayonet or camera obtains the motion track of the personage;
The motion track that personage rides is obtained, using a motion track ridden as the motion track of personage.
3. the method according to claim 1, wherein the motion track of the vehicle in region is specified in the acquisition
Step, including one or more of following:
By the record of bayonet, the motion track of the vehicle is obtained;
The automobile image captured by camera obtains the motion track of the vehicle;
By the coordinate of the acquisition of MAC collector and the MAC Address of vehicle binding, the motion track of the vehicle is obtained.
4. the method according to claim 1, wherein described according in the trace information and the specified region
Road information, the step of obtaining road network information, comprising:
Obtain road information in specified region;The road information includes the road information between crossing and the crossing;Wherein, institute
Stating the road information between crossing includes that the speed for walking through the road and number, vehicle pass through the speed of the road and secondary
Number;The calculation formula that the personage walks through the speed V of road is V=L/ Δ T, and L indicates the length of the road, Δ T table
Time needed for object of leting others have a look at passes through the road;
According between the crossing, the crossing road information and the trace information obtain road network information, the road network information
In using crossing as network node, road between crossing is as even side.
5. being carried out to the road network information the method according to claim 1, wherein described according to preset rules
Coded treatment, the step of obtaining the road network information corresponding multiple vectors, comprising:
The road network information is encoded using one-hot coding mode, has M crossing in the road network information, then accordingly
The null vector for establishing an a length of M, wherein each crossing corresponds to a position in the null vector;
Judge whether the trace information passes through the crossing, if by the crossing, corresponding position in the null vector
Set 1;
According to the preset rules, the corresponding multiple vectors of the road network information are obtained;Pass through the multiple institutes of database purchase
State vector.
6. determining between each personage the method according to claim 1, wherein described according to multiple vectors
Relevance, the step of obtaining the character relation network in the specified region, comprising:
Obtain the corresponding multiple vectors of all persons;
Relevance of the personage in its corresponding each vector described in every two is calculated, the average value W of the relevance is obtained;Meter
Calculate the relevance average value W of personage A and personage B(A,B)Formula beIts
In, n indicates that the sum of the vector in database, D indicate time that personage A and personage B occurs simultaneously in the road in i-th of vector
Number,Indicate the average speed of personage A walking in i-th of vector,Indicate that personage A in i-th of vector rides
Average speed,Indicate the number of personage A walking in i-th of vector,It is logical to indicate in i-th of vector that personage A rides
The number crossed,Indicate the average speed of walking in i-th of vector of personage B,Indicate that personage B is ridden in i-th of vector
Average speed,Indicate the number of personage B walking in i-th of vector,Indicate that personage B is ridden in i-th of vector
The number passed through;
Relational network is constructed according to the average value of the relevance, wherein the relational network is using personage as node, relevant property
Node between establish connection, weight of the relevance as connection.
7. a kind of device of character relation network struction, which is characterized in that described device includes:
Information acquisition module, for acquiring the trace information in specified region, wherein the trace information includes the movement of personage
Track and the personage correspond to the motion track of vehicle;
Road network information obtains module, for obtaining road network according to the road information in the trace information and the specified region
Information;The road network information includes mobile message of the personage in particular link;The mobile message includes at least described
Personage is by way of the particular link, one of frequency and speed;
Coding module, for carrying out coded treatment to the road network information, it is corresponding obtaining the road network information according to preset rules
Multiple vectors, wherein the corresponding vector of the road information of every of the road network information;
Character relation network determining module obtains described for determining the relevance between each personage according to multiple vectors
Character relation network in specified region.
8. device according to claim 7, which is characterized in that the information acquisition module is also used to realize in following
It is one or more kinds of:
The relevant information that public transport is used by personage, obtains the motion track of the personage;
By personage using the relevant information in the place of identity card, the motion track of the personage is obtained;
The image information captured by bayonet or camera obtains the motion track of the personage;
The motion track that personage rides is obtained, using a motion track ridden as the motion track of personage.
9. device according to claim 7, which is characterized in that the information acquisition module is also used to realize in following
It is one or more kinds of:
By the record of bayonet, the motion track of the vehicle is obtained;
The automobile image captured by camera obtains the motion track of the vehicle;
By the coordinate of the acquisition of MAC collector and the MAC Address of vehicle binding, the motion track of the vehicle is obtained.
10. device according to claim 7, which is characterized in that the road network information obtains module, is also used to:
Obtain road information in specified region;The road information includes the road information between crossing and the crossing;Wherein, institute
Stating the road information between crossing includes that the speed for walking through the road and number, vehicle pass through the speed of the road and secondary
Number;The calculation formula that the personage walks through the speed V of road is V=L/ Δ T, and L indicates the length of the road, Δ T table
Time needed for object of leting others have a look at passes through the road;
According between the crossing, the crossing road information and the trace information obtain road network information, the road network information
In using crossing as network node, road between crossing is as even side.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811430598.2A CN109492116B (en) | 2018-11-27 | 2018-11-27 | Method and device for building character relationship network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811430598.2A CN109492116B (en) | 2018-11-27 | 2018-11-27 | Method and device for building character relationship network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109492116A true CN109492116A (en) | 2019-03-19 |
CN109492116B CN109492116B (en) | 2021-08-27 |
Family
ID=65697906
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811430598.2A Active CN109492116B (en) | 2018-11-27 | 2018-11-27 | Method and device for building character relationship network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109492116B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111710162A (en) * | 2020-07-07 | 2020-09-25 | 深圳市数字城市工程研究中心 | Urban road network traffic operation condition monitoring method and system |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020078003A1 (en) * | 2000-12-15 | 2002-06-20 | Krysiak Bruce R. | Method and system for identifying one or more information sources based on one or more trust networks associated with one or more knowledge domains |
CN103150546A (en) * | 2012-12-26 | 2013-06-12 | 冉阳 | Video face identification method and device |
US20130246139A1 (en) * | 2012-01-04 | 2013-09-19 | Sparkbase LLC | System and method for sharing incentives among groups |
US20140019490A1 (en) * | 2012-07-13 | 2014-01-16 | Indrajit Roy | Event processing for graph-structured data |
CN104484999A (en) * | 2014-12-31 | 2015-04-01 | 百度在线网络技术(北京)有限公司 | Method and device for determining dynamic traffic information on basis of user tracks |
CN105512643A (en) * | 2016-01-06 | 2016-04-20 | 北京二郎神科技有限公司 | Image acquisition method and device |
CN105787104A (en) * | 2016-03-21 | 2016-07-20 | 百度在线网络技术(北京)有限公司 | User attribute information acquiring method and device |
CN105894359A (en) * | 2016-03-31 | 2016-08-24 | 百度在线网络技术(北京)有限公司 | Order pushing method, device and system |
CN106969764A (en) * | 2016-01-13 | 2017-07-21 | 北京四维图新科技股份有限公司 | A kind of road matching method, device and vehicular map acquisition system |
CN108074414A (en) * | 2017-12-19 | 2018-05-25 | 广州小鹏汽车科技有限公司 | It is a kind of that path traffic information based reminding method and system are often walked based on user behavior |
CN108109382A (en) * | 2018-02-05 | 2018-06-01 | 青岛大学 | A kind of congestion points based on composite network, congestion line, the discovery method of congestion regions |
CN108848460A (en) * | 2018-05-31 | 2018-11-20 | 重庆市城投金卡信息产业股份有限公司 | People's vehicle correlating method based on RFID and GPS data |
-
2018
- 2018-11-27 CN CN201811430598.2A patent/CN109492116B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020078003A1 (en) * | 2000-12-15 | 2002-06-20 | Krysiak Bruce R. | Method and system for identifying one or more information sources based on one or more trust networks associated with one or more knowledge domains |
US20130246139A1 (en) * | 2012-01-04 | 2013-09-19 | Sparkbase LLC | System and method for sharing incentives among groups |
US20140019490A1 (en) * | 2012-07-13 | 2014-01-16 | Indrajit Roy | Event processing for graph-structured data |
CN103150546A (en) * | 2012-12-26 | 2013-06-12 | 冉阳 | Video face identification method and device |
CN104484999A (en) * | 2014-12-31 | 2015-04-01 | 百度在线网络技术(北京)有限公司 | Method and device for determining dynamic traffic information on basis of user tracks |
CN105512643A (en) * | 2016-01-06 | 2016-04-20 | 北京二郎神科技有限公司 | Image acquisition method and device |
CN106969764A (en) * | 2016-01-13 | 2017-07-21 | 北京四维图新科技股份有限公司 | A kind of road matching method, device and vehicular map acquisition system |
CN105787104A (en) * | 2016-03-21 | 2016-07-20 | 百度在线网络技术(北京)有限公司 | User attribute information acquiring method and device |
CN105894359A (en) * | 2016-03-31 | 2016-08-24 | 百度在线网络技术(北京)有限公司 | Order pushing method, device and system |
CN108074414A (en) * | 2017-12-19 | 2018-05-25 | 广州小鹏汽车科技有限公司 | It is a kind of that path traffic information based reminding method and system are often walked based on user behavior |
CN108109382A (en) * | 2018-02-05 | 2018-06-01 | 青岛大学 | A kind of congestion points based on composite network, congestion line, the discovery method of congestion regions |
CN108848460A (en) * | 2018-05-31 | 2018-11-20 | 重庆市城投金卡信息产业股份有限公司 | People's vehicle correlating method based on RFID and GPS data |
Non-Patent Citations (2)
Title |
---|
JULIAN F.P KOOIJ等: "Analysis of pedestrian dynamics from a vehicle perspective", 《2014 IEEEINTELLIGENT VEHICLES SYMPOSIUM》 * |
余昌学: "山地城市道路平面交叉口行人交通特性研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111710162A (en) * | 2020-07-07 | 2020-09-25 | 深圳市数字城市工程研究中心 | Urban road network traffic operation condition monitoring method and system |
CN111710162B (en) * | 2020-07-07 | 2022-04-01 | 深圳市数字城市工程研究中心 | Urban road network traffic operation condition monitoring method and system |
Also Published As
Publication number | Publication date |
---|---|
CN109492116B (en) | 2021-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107330396A (en) | A kind of pedestrian's recognition methods again based on many attributes and many strategy fusion study | |
Cai et al. | Deep learning-based video system for accurate and real-time parking measurement | |
CN108388888A (en) | A kind of vehicle identification method, device and storage medium | |
CN109697214A (en) | A kind of tourism data analysis system and method | |
CN109948425A (en) | A kind of perception of structure is from paying attention to and online example polymerize matched pedestrian's searching method and device | |
CN106845357A (en) | A kind of video human face detection and recognition methods based on multichannel network | |
CN106295564B (en) | A kind of action identification method of neighborhood Gaussian structures and video features fusion | |
CN106649663B (en) | A kind of video copying detection method based on compact video characterization | |
CN109785629A (en) | A kind of short-term traffic flow forecast method | |
CN109492583A (en) | A kind of recognition methods again of the vehicle based on deep learning | |
CN109523186A (en) | Urban area partitioning method and device | |
CN109214263A (en) | A kind of face identification method based on feature multiplexing | |
CN105469599B (en) | Vehicle tracing and vehicle behavior prediction method | |
CN112668375B (en) | Tourist distribution analysis system and method in scenic spot | |
CN110472999A (en) | Passenger flow pattern analysis method and device based on subway and shared bicycle data | |
CN109508395A (en) | A method of the intelligence based on vehicle retrieval is combined related cases | |
CN106355935A (en) | Server subsystem for on-line management system of parking lot | |
CN114265833A (en) | Vehicle track guiding geographic space-time characteristic visualization analysis platform | |
CN111046213A (en) | Knowledge base construction method based on image recognition | |
CN115050093B (en) | Cross-visual-angle gait recognition method based on staged multistage pyramid | |
CN113255552A (en) | Bus-mounted video passenger OD (origin-destination) analysis system, method and device and storage medium | |
CN111951543B (en) | Flow prediction method and device | |
CN108182382A (en) | Based on the similar Activity recognition method and system of figure | |
CN107635188A (en) | A kind of video frequency vehicle trace analysis method based on Docker platforms | |
CN109492116A (en) | The method and device of character relation network struction |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |