CN109492116B - Method and device for building character relationship network - Google Patents
Method and device for building character relationship network Download PDFInfo
- Publication number
- CN109492116B CN109492116B CN201811430598.2A CN201811430598A CN109492116B CN 109492116 B CN109492116 B CN 109492116B CN 201811430598 A CN201811430598 A CN 201811430598A CN 109492116 B CN109492116 B CN 109492116B
- Authority
- CN
- China
- Prior art keywords
- information
- road
- person
- vehicle
- track
- 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.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a device for constructing a character relationship network, wherein the method for constructing the character relationship network comprises the following steps: acquiring track information in a designated area, wherein the track information comprises a movement track of a person and a movement track of a vehicle corresponding to the person; obtaining road network information according to the track information and the road information in the designated area; according to a preset rule, coding road network information to obtain a plurality of vectors corresponding to the road network information, wherein each piece of road information of the road network information corresponds to one vector; and determining the relevance among the people according to the vectors to obtain a people relation network in the specified area. The invention combines the track information and the road information to construct the character relationship network and obtains a plurality of vectors by encoding the road network information, thereby not only reducing the calculation complexity of the data information, but also improving the accuracy of constructing the character relationship network.
Description
Technical Field
The invention relates to the technical field of relational network construction, in particular to a method and a device for constructing a character relational network.
Background
With the continuous development of social economy, the relationships between the characters are more and more complex, and in order to better study the relationships between the characters, the relationships between the characters are generally visualized, such as through network display; most of the existing methods are to perform lexical analysis on text information, establish a knowledge base, perform pattern matching by using the knowledge base, and extract character relations.
Aiming at the problems that the person relationship network establishing method is high in calculation complexity and the person relationship network establishing accuracy is poor, an effective solution is not provided.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for constructing a human relationship network, so as to reduce the complexity of data calculation and improve the accuracy of the human relationship network construction.
In a first aspect, an embodiment of the present invention provides a method for building a person relationship network, where the method includes: acquiring track information in a designated area, wherein the track information comprises a movement track of a person and a movement track of a vehicle corresponding to the person; obtaining road network information according to the track information and the road information in the designated area; the road network information comprises the movement information of people on the specified road; the movement information includes at least one of a manner, frequency, and speed of the person passing through the designated road; according to a preset rule, coding road network information to obtain a plurality of vectors corresponding to the road network information, wherein each piece of road information of the road network information corresponds to one vector; and determining the relevance among the people according to the vectors to obtain a people relation network in the specified area.
Further, the step of acquiring the movement trajectory of the person in the designated area includes one or more of the following steps: obtaining a movement track of a person by using related information of public transport means by the person; acquiring the movement track of the person through the related information of the place where the person uses the identity card; obtaining the movement track of a person through image information captured by a bayonet or a camera; and acquiring the movement track of the vehicle on which the person rides, and taking the movement track of the vehicle on which the person rides as the movement track of the person.
Further, the step of acquiring the movement trajectory of the vehicle in the designated area includes one or more of the following steps: obtaining the moving track of the vehicle through the recording of the bayonet; obtaining the moving track of the vehicle through the vehicle image captured by the camera; and acquiring the coordinates of the MAC address bound with the vehicle through the MAC collector to obtain the moving track of the vehicle.
Further, the step of obtaining the road network information based on the trajectory information and the road information in the designated area includes: acquiring road information in a specified area; the road information comprises intersections and road information among the intersections; the road information between the intersections comprises the speed and the frequency of walking through the road and the speed and the frequency of vehicles passing through the road; the calculation formula of the speed V of the person walking through the road is V ═ L/Delta T, L represents the length of the road, and Delta T represents the time required by the person to pass through the road; and obtaining road network information according to the road information and the track information among the intersections, wherein the intersections are used as network nodes in the road network information, and the roads among the intersections are used as connecting edges.
Further, the step of encoding the road network information according to the preset rule to obtain a plurality of vectors corresponding to the road network information includes: coding road network information by adopting a one-hot coding mode, and correspondingly establishing a zero vector with the length of M if M intersections exist in the road network information, wherein each intersection corresponds to one position in the zero vector; judging whether the track information passes through the intersection or not, and if the track information passes through the intersection, setting a corresponding position in the zero vector to be 1; obtaining a plurality of vectors corresponding to the road network information according to a preset rule; a plurality of vectors is stored by a database.
Further, the step of determining the relevance between the persons according to the plurality of vectors to obtain the person relation network in the designated area includes: acquiring a plurality of vectors corresponding to all the characters; calculating the relevance of each two characters in each corresponding vector to obtain the average value W of the relevance; calculating the average value W of the relationship between the person A and the person B(A,B)Is of the formula
Wherein n represents the total number of vectors in the database, and D represents the number of people A and B in the ith vectorThe number of simultaneous occurrences of (a) and (b),
representing the average speed of the person a walking in the ith vector,
representing the average speed of the vehicle by which person a is multiplied in the ith vector,
indicating the number of walks by person a in the ith vector,
indicates the number of times the vehicle on which the person a has traveled in the ith vector,
representing the average speed of walking in the i-th vector of person B,
representing the average speed of the vehicle by which person B is multiplied in the ith vector,
indicating the number of walks by person B in the ith vector,
indicating the number of times the vehicle on which the person B passes in the ith vector; and constructing a relation network according to the average value of the relevance, wherein the relation network takes the characters as nodes, connection is established between the nodes with the relevance, and the relevance is used as the weight of the connection.
In a second aspect, an embodiment of the present invention further provides an apparatus for building a personal relationship network, where the apparatus includes: the information acquisition module is used for acquiring track information in the designated area, wherein the track information comprises the movement track of a person and the movement track of a vehicle corresponding to the person; the road network information obtaining module is used for obtaining road network information according to the track information and the road information in the specified area; the road network information comprises the movement information of people on the specified road; the movement information includes at least one of a manner, frequency, and speed of the person passing through the designated road; the encoding module is used for encoding the road network information according to a preset rule to obtain a plurality of vectors corresponding to the road network information, wherein each piece of road information of the road network information corresponds to one vector; and the character relation network determining module is used for determining the relevance among the characters according to the plurality of vectors to obtain the character relation network in the specified area.
Further, the information acquisition module is further configured to implement one or more of the following: obtaining a movement track of a person by using related information of public transport means by the person; acquiring the movement track of the person through the related information of the place where the person uses the identity card; obtaining the movement track of a person through image information captured by a bayonet or a camera; and acquiring the movement track of the vehicle on which the person rides, and taking the movement track of the vehicle on which the person rides as the movement track of the person.
Further, the information acquisition module is further configured to implement one or more of the following: obtaining the moving track of the vehicle through the recording of the bayonet; obtaining the moving track of the vehicle through the vehicle image captured by the camera; and acquiring the coordinates of the MAC address bound with the vehicle through the MAC collector to obtain the moving track of the vehicle.
Further, the road network information obtaining module is further configured to: acquiring road information in a specified area; the road information comprises intersections and road information among the intersections; the road information between the intersections comprises the speed and the frequency of walking through the road and the speed and the frequency of vehicles passing through the road; the calculation formula of the speed V of the person walking through the road is V ═ L/Delta T, L represents the length of the road, and Delta T represents the time required by the person to pass through the road; and obtaining road network information according to the road information and the track information among the intersections, wherein the intersections are used as network nodes in the road network information, and the roads among the intersections are used as connecting edges.
The embodiment of the invention has the following beneficial effects:
the invention provides a method and a device for constructing a character relationship network, which are used for acquiring track information in a specified area and then obtaining road network information according to the track information and road information in the specified area; and coding the road network information according to a preset rule to obtain a plurality of vectors corresponding to the road network information, and further determining the relevance among all the people to obtain a people relation network in the specified area. The invention combines the track information and the road information to construct the character relationship network and obtains a plurality of vectors by encoding the road network information, thereby not only reducing the calculation complexity of the data information, but also improving the accuracy of constructing the character relationship network.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention as set forth above.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for building a character relationship network according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for building a human relationship network according to an embodiment of the present invention;
fig. 3 is a flowchart of a selection rule of each road in a preset rule of a plurality of vectors obtained by encoding road network information according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for building a character relationship network according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Most of the methods for constructing the character relationship network in the prior art are to perform lexical analysis on text information, establish a database, and then perform pattern matching by using the database to extract character relationships so as to establish the character relationship network, but a large amount of text information needs to be processed, the calculation complexity is high, and the accuracy of character relevance is poor.
For the convenience of understanding the embodiment, a method for constructing a character relationship network disclosed in the embodiment of the present invention is first described in detail.
Referring to a flowchart of a method for building a personal relationship network shown in fig. 1, the method for building a personal relationship network includes the following specific steps:
step S102, track information in the designated area is collected, wherein the track information comprises the movement track of a person and the movement track of a vehicle corresponding to the person.
The track information is collected in the designated area, and the relevance of the person can be better obtained, wherein the obtaining mode of the movement track of the person includes but is not limited to the following modes: the movement trajectory of a person when using a bus, a shared bicycle, or other transportation means; the person information of the places using the identity cards, such as internet bars, hotels and the like; person image information captured by a bayonet, a camera and the like; the moving track of the vehicle corresponding to the person can be regarded as the moving track of the person according to the owner information of the vehicle.
The gate is generally a gate with a defense and inspection facility, for example, a gate of a cell, a company entrance, or a station.
The method for obtaining the movement track of the vehicle corresponding to the person includes, but is not limited to, the following methods: recording information when the vehicle passes through the gate; the coordinates of the MAC Address bound with the vehicle, which are collected by a MAC (Media Access Control Address) collector; the influence of the car captured by the camera, etc.
The MAC address is typically an address used to identify the location of the device on the network; typically, each networked device (e.g., networked automobile, bus, etc.) has a unique MAC address associated with it.
Step S104, obtaining road network information according to the track information and road information in the specified area; the road network information comprises the movement information of people on a specified road; the movement information includes at least one of a manner, frequency, and speed of the person passing through the designated road.
The road information in the designated area includes intersections and road information between intersections, that is, each urban area generally includes a plurality of intersections, and each two intersections have a road, and the roads are interconnected in an intricate manner to form the road information of the area.
And combining the track information with road information in the designated area to obtain road network information, wherein the road network information is formed by taking intersections as network nodes and taking roads among the intersections as connecting edges, the road network information comprises the movement information of the people on the designated roads, and the movement information is generally obtained through the track information.
The movement information may include one or more of a manner, frequency and speed of a person passing through a designated road, wherein the manner of the person passing through the designated road may include walking, riding a public transportation vehicle, self-driving, and the like; the frequency with which the person passes through the specified road may include the number of times the person walks through the specified road, the number of times the vehicle passes over the specified road, and the like; the speed at which the person traverses the designated link may include an average speed at which the person walks across the link, an average speed at which the vehicle is traveling on the link, and the like.
Step S106, according to a preset rule, encoding the road network information to obtain a plurality of vectors corresponding to the road network information, where each piece of road information of the road network information corresponds to one vector.
In order to obtain the information in the road network information, the road network information is encoded according to a preset rule, and the road network information is mapped into a plurality of low-dimensional vectors, so that multi-dimensional road network information data is converted into the plurality of low-dimensional vectors, and the complexity of information calculation is reduced, wherein each piece of road information corresponds to one vector, and the vector comprises the selection information of intersections and the movement information of roads between the selected intersections.
And step S108, determining the relevance among the people according to the vectors to obtain a people relation network in the specified area.
The association between the persons is calculated based on the information in each vector, which includes the number of times the person passes through a specified link, the average speed at which the person walks through the link, the average speed at which the vehicle passes through the link, the number of times the person walks through the link, the number of times the vehicle passes, and the like.
According to the relevance among the people, the people are used as nodes, the nodes with the relevance are used for establishing connecting edges, and the relevance among the nodes is used as the weight of the connecting edges to establish a people relation network.
The embodiment of the invention provides a method for constructing a character relationship network, which comprises the following steps: acquiring track information in the designated area, and then obtaining road network information according to the track information and road information in the designated area; and coding the road network information according to a preset rule to obtain a plurality of vectors corresponding to the road network information, and further determining the relevance among all the people to obtain a people relation network in the specified area. The invention combines the track information and the road information to construct the character relationship network and obtains a plurality of vectors by encoding the road network information, thereby not only reducing the calculation complexity of the data information, but also improving the accuracy of constructing the character relationship network.
Referring to FIG. 2, a flow chart of another method for building a people relationship network is shown; the method is realized on the basis of the method for constructing the character relationship network shown in the figure 1; the method comprises the following specific steps:
step S202, track information in the designated area is collected.
The track information comprises the moving track of a person and the moving track of a vehicle corresponding to the person; the step of acquiring the movement track of the person in the designated area comprises one or more of the following steps: (1) obtaining a movement track of a person by using related information of public transport means by the person; (2) acquiring the movement track of the person through the related information of the place where the person uses the identity card; (3) obtaining the movement track of a person through image information captured by a bayonet or a camera; (4) and acquiring the movement track of the vehicle on which the person rides, and taking the movement track of the vehicle on which the person rides as the movement track of the person.
According to the collected movement track of the person and the actual road condition in the area, the following movement track of the person can be obtained: < [ T5, T6], road C; [ T7, T8], road D … >, the trajectory being shown as a person on road C at time [ T5, T6], on road D at time [ T7, T8], etc.
The step of acquiring the movement track of the vehicle in the designated area includes one or more of the following steps: (1) obtaining the moving track of the vehicle through the recording of the bayonet; (2) obtaining the moving track of the vehicle through the vehicle image captured by the camera; (3) and acquiring the coordinates of the MAC address bound with the vehicle through the MAC collector to obtain the moving track of the vehicle.
According to the collected moving track of the vehicle and the actual road condition in the area, the following moving track of the vehicle can be obtained: < [ T1, T2], road A; [ T3, T4], road B … ], the trajectory being indicated as the vehicle driving on road A at time [ T1, T2], on road B at time [ T3, T4], etc.
Step S204, acquiring road information in the specified area; the road information comprises intersections and road information among the intersections; wherein, the road information between the intersections comprises the speed and the times of walking through the road and the speed and the times of passing through the road by vehicles.
The above formula for calculating the speed V of the person walking through the road is V ═ L/Δ T, L indicates the length of the road, and Δ T indicates the time required for the person to pass through the road.
Step S206, obtaining road network information according to the road information and the track information of the intersections, wherein the intersections are used as network nodes in the road network information, and the roads between the intersections are used as connecting edges.
For a certain road a, the road network information of the road a can be represented by the following vector:
the vectors are multidimensional and have high computational complexity, wherein P is1A person 1 is shown to be represented by,
representing the speed at which the person 1 walks through the road a,
representing the speed of the person 1 riding in the vehicle through the road a,
indicating the number of times the person 1 walks through the road a,
representing the number of times a person 1 takes a vehicle to pass through road a, and so on, P2A representation of a person 2 is shown,
representing the speed at which the person 2 walks through the road a,
representing the speed of the person 2 riding in the vehicle through the road a,
indicating the number of times the person 2 walks through the road a,
indicating the number of times the person 2 takes the vehicle to pass through the road a.
Step S208, a one-hot coding mode is adopted to code road network information, if M intersections exist in the road network information, a zero vector with the length of M is correspondingly established, wherein each intersection corresponds to one position in the zero vector.
The one-hot encoding is usually also called a one-bit efficient encoding mode, and mainly uses an M-bit status register to encode M states, each state is provided with its independent register bit, and only one bit is valid at any time; one-hot encoding is usually a representation of the classification variables as binary vectors.
Step S210, judging whether the track information passes through the intersection, and if the track information passes through the intersection, setting a corresponding position in the zero vector to be 1.
Step S212, obtaining a plurality of vectors corresponding to the road network information according to a preset rule; a plurality of vectors is stored by a database.
The multi-dimensional vectors of the road network information can be correspondingly formed into a plurality of low-dimensional vectors according to a preset rule, so that the calculation complexity of data is reduced.
The preset rule may be: starting from the starting node (corresponding to the intersection), a path that never passes is randomly selected to pass through to the next intersection, and the calculation method of the selection probability of each path is shown in fig. 3.
Referring to fig. 3, when at the first intersection, the calculation formula of the picking probability of each road can be expressed as:
wherein n represents the number of roads connected to the first intersectionAmount, PjIndicates the probability that the jth road connected with the intersection is selected, LjIndicating the length, L, of the jth road connected to the intersectioniIndicating the length of the ith road connected to the intersection.
And then judging whether the next road junction is directly connected with the previous road junction or not, if so, the calculation formula of the selection probability of each road when the next road is selected can be expressed as follows:
wherein, PjRepresenting the probability of selecting the jth road of the intersection vector, n representing the number of roads connected to the intersection, k representing the number of roads connected to the previous intersection, LiIndicates the length of the ith road, LLRepresenting the road length from the previous intersection to the current intersection; otherwise, the calculation formula of the selection probability of each road when the next road is selected can be expressed as:
after the next intersection is reached, continuing to select the roads which never run through according to the selection rule of each road when the next road is selected; when the vehicle walks through N intersections, the wandering records are stored and stored in a database as vectors, and the calculation formula of N is as follows:
wherein M is the total number of intersections in the road network information.
Step S214, obtaining a plurality of vectors corresponding to all persons: and calculating the relevance of each two characters in each corresponding vector to obtain the average value W of the relevance.
Calculating the average value W of the relationship between the person A and the person B(A,B)Is of the formula
Where n represents the total number of vectors in the database, D represents the number of times people a and B appear simultaneously in the road in the ith vector,
representing the average speed of the person a walking in the ith vector,
representing the average speed of the vehicle by which person a is multiplied in the ith vector,
indicating the number of walks by person a in the ith vector,
indicates the number of times the vehicle on which the person a has traveled in the ith vector,
representing the average speed of walking in the i-th vector of person B,
representing the average speed of the vehicle by which person B is multiplied in the ith vector,
indicating the number of walks by person B in the ith vector,
the number of times the vehicle on which the person B passes in the ith vector is indicated.
The larger the value of the relevance average value W, the stronger the relevance between two persons.
And S216, constructing a relationship network according to the average value of the relevance, wherein the relationship network takes the person as a node, connection is established between the nodes with the relevance, and the relevance is used as the weight of the connection.
In the embodiment, the road network information is encoded in a one-hot encoding mode, and a plurality of vectors corresponding to the road network information are obtained through a preset rule, so that the calculation complexity is reduced.
In correspondence to the embodiment of the method for building the personal relationship network, refer to a schematic structural diagram of a device for building the personal relationship network shown in fig. 4; the device includes:
the information acquisition module 40 is used for acquiring track information in the designated area, wherein the track information comprises a movement track of a person and a movement track of a vehicle corresponding to the person;
a road network information obtaining module 41, configured to obtain road network information according to the track information and the road information in the designated area; the road network information comprises the movement information of people on the specified road; the movement information includes at least one of a manner, frequency, and speed of the person passing through the designated road;
the encoding module 42 is configured to encode the road network information according to a preset rule to obtain a plurality of vectors corresponding to the road network information, where each piece of road information of the road network information corresponds to one vector;
and a person relationship network determining module 43, configured to determine, according to the plurality of vectors, a relationship between persons, so as to obtain a person relationship network in the designated area.
Further, the information acquisition module is further configured to implement one or more of the following: obtaining a movement track of a person by using related information of public transport means by the person; acquiring the movement track of the person through the related information of the place where the person uses the identity card; obtaining the movement track of a person through image information captured by a bayonet or a camera; and acquiring the movement track of the vehicle on which the person rides, and taking the movement track of the vehicle on which the person rides as the movement track of the person.
Further, the information acquisition module is further configured to implement one or more of the following: obtaining the moving track of the vehicle through the recording of the bayonet; obtaining the moving track of the vehicle through the vehicle image captured by the camera; and acquiring the coordinates of the MAC address bound with the vehicle through the MAC collector to obtain the moving track of the vehicle.
Further, the road network information obtaining module is further configured to: acquiring road information in a specified area; the road information comprises intersections and road information among the intersections; the road information between the intersections comprises the speed and the frequency of walking through the road and the speed and the frequency of vehicles passing through the road; the calculation formula of the speed V of the person walking through the road is V ═ L/Delta T, L represents the length of the road, and Delta T represents the time required by the person to pass through the road; and obtaining road network information according to the road information and the track information among the intersections, wherein the intersections are used as network nodes in the road network information, and the roads among the intersections are used as connecting edges.
The device for building the character relationship network provided by the embodiment of the invention has the same technical characteristics as the method for building the character relationship network provided by the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
The method and the device for constructing the character relationship network provided by the embodiment of the invention extract the relevance of the characters through the track information, improve the accuracy of the relevance of the characters, merge the data and reduce the complexity of calculation; and the graph is mapped into a vector, so that the result accuracy is higher.
The computer program product of the method and the apparatus for building a character relationship network according to the embodiments of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, and will not be described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and/or the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. A method for building a character relationship network, the method comprising:
acquiring track information in a designated area, wherein the track information comprises a movement track of a person and a movement track of a vehicle corresponding to the person;
obtaining road network information according to the track information and the road information in the specified area; the road network information comprises the movement information of the people on the specified road; the movement information includes at least one of a manner, a frequency, and a speed of the person passing through the specified road;
according to a preset rule, coding the road network information to obtain a plurality of vectors corresponding to the road network information, wherein each piece of road information of the road network information corresponds to one vector;
determining the relevance among all the people according to the vectors to obtain a people relation network in the specified area;
the step of determining the relevance between the people according to the vectors to obtain the people relation network in the specified area comprises the following steps:
obtaining a plurality of vectors corresponding to all the characters;
calculating the relevance of each two characters in each corresponding vector to obtain the average value W of the relevance; calculating the average value W of the relationship between the person A and the person B(A,B)Is of the formula
Where n represents the total number of vectors in the database, D represents the number of times people a and B appear simultaneously in the road in the ith vector,
representing the average speed of the person a walking in the ith vector,
representing the average speed of the vehicle by which person a is multiplied in the ith vector,
indicating the number of walks by person a in the ith vector,
indicates the number of times the vehicle on which the person a has traveled in the ith vector,
representing the average speed of walking in the i-th vector of person B,
representing the average speed of the vehicle by which person B is multiplied in the ith vector,
indicating the number of walks by person B in the ith vector,
indicating the number of times the vehicle on which the person B passes in the ith vector;
and constructing a relationship network according to the average value of the relevance, wherein the relationship network takes people as nodes, connection is established between the nodes with the relevance, and the relevance is used as the weight of the connection.
2. The method of claim 1, wherein the step of collecting the movement track of the person in the designated area comprises one or more of the following:
obtaining a movement track of a person through related information of the person using a public transport means;
acquiring the movement track of a person through related information of a place where the person uses the identity card;
obtaining the movement track of the person through image information captured by a bayonet or a camera;
and acquiring the movement track of the vehicle on which the person rides, and taking the movement track of the vehicle on which the person rides as the movement track of the person.
3. The method of claim 1, wherein the step of acquiring the movement trajectory of the vehicle within the designated area comprises one or more of:
obtaining the moving track of the vehicle through the recording of a bayonet;
obtaining a moving track of a vehicle through a vehicle image captured by a camera;
and acquiring the coordinates of the MAC address bound with the vehicle through the MAC collector to obtain the moving track of the vehicle.
4. The method according to claim 1, wherein the step of obtaining road network information based on the track information and the road information in the designated area comprises:
acquiring road information in a specified area; the road information comprises intersections and road information among the intersections; wherein the road information between the intersections comprises the speed and the times of walking through the road and the speed and the times of vehicles passing through the road; the calculation formula of the speed V of the person walking through the road is V ═ L/Delta T, L represents the length of the road, and Delta T represents the time required by the person to pass through the road;
and obtaining road network information according to the intersections, the road information among the intersections and the track information, wherein the intersections are used as network nodes in the road network information, and the roads among the intersections are used as connecting edges.
5. The method according to claim 1, wherein said step of encoding said road network information according to a predetermined rule to obtain a plurality of vectors corresponding to said road network information comprises:
coding the road network information by adopting a one-hot coding mode, and correspondingly establishing a zero vector with the length of M if M intersections exist in the road network information, wherein each intersection corresponds to one position in the zero vector;
judging whether the track information passes through the intersection or not, and if the track information passes through the intersection, setting a corresponding position in the zero vector to be 1;
obtaining a plurality of vectors corresponding to the road network information according to the preset rule; storing a plurality of said vectors by means of a database.
6. An apparatus for persona relationship network construction, the apparatus comprising:
the system comprises an information acquisition module, a storage module and a display module, wherein the information acquisition module is used for acquiring track information in a designated area, and the track information comprises a movement track of a person and a movement track of a vehicle corresponding to the person;
the road network information obtaining module is used for obtaining road network information according to the track information and the road information in the specified area; the road network information comprises the movement information of the people on the specified road; the movement information includes at least one of a manner, a frequency, and a speed of the person passing through the specified road;
the encoding module is used for encoding the road network information according to a preset rule to obtain a plurality of vectors corresponding to the road network information, wherein each piece of road information of the road network information corresponds to one vector;
the character relation network determining module is used for determining the relevance among the characters according to the vectors to obtain the character relation network in the designated area;
the person relationship network determination module is further configured to: obtaining a plurality of vectors corresponding to all the characters; calculating the relevance of each two characters in each corresponding vector to obtain the average value W of the relevance; calculating the average value W of the relationship between the person A and the person B(A,B)Is of the formula
Where n represents the total number of vectors in the database, D represents the number of times people a and B appear simultaneously in the road in the ith vector,
representing the average speed of the person a walking in the ith vector,
representing the average speed of the vehicle by which person a is multiplied in the ith vector,
shows person A is atThe number of walks in the i vectors,
indicates the number of times the vehicle on which the person a has traveled in the ith vector,
representing the average speed of walking in the i-th vector of person B,
representing the average speed of the vehicle by which person B is multiplied in the ith vector,
indicating the number of walks by person B in the ith vector,
indicating the number of times the vehicle on which the person B passes in the ith vector; and constructing a relationship network according to the average value of the relevance, wherein the relationship network takes people as nodes, connection is established between the nodes with the relevance, and the relevance is used as the weight of the connection.
7. The apparatus of claim 6, wherein the information collection module is further configured to implement one or more of:
obtaining a movement track of a person through related information of the person using a public transport means;
acquiring the movement track of a person through related information of a place where the person uses the identity card;
obtaining the movement track of the person through image information captured by a bayonet or a camera;
and acquiring the movement track of the vehicle on which the person rides, and taking the movement track of the vehicle on which the person rides as the movement track of the person.
8. The apparatus of claim 6, wherein the information collection module is further configured to implement one or more of:
obtaining the moving track of the vehicle through the recording of a bayonet;
obtaining a moving track of a vehicle through a vehicle image captured by a camera;
and acquiring the coordinates of the MAC address bound with the vehicle through the MAC collector to obtain the moving track of the vehicle.
9. The apparatus of claim 6, wherein the road network information obtaining module is further configured to:
acquiring road information in a specified area; the road information comprises intersections and road information among the intersections; wherein the road information between the intersections comprises the speed and the times of walking through the road and the speed and the times of vehicles passing through the road; the calculation formula of the speed V of the person walking through the road is V ═ L/Delta T, L represents the length of the road, and Delta T represents the time required by the person to pass through the road;
and obtaining road network information according to the intersections, the road information among the intersections and the track information, wherein the intersections are used as network nodes in the road network information, and the roads among the intersections are used as connecting edges.
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 CN109492116A (en) | 2019-03-19 |
| CN109492116B true 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) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Family Cites Families (3)
| 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 |
| US20130246185A1 (en) * | 2012-01-04 | 2013-09-19 | Sparkbase LLC | System and method for sharing incentives among groups |
| US8819078B2 (en) * | 2012-07-13 | 2014-08-26 | Hewlett-Packard Development Company, L. P. | Event processing for graph-structured data |
-
2018
- 2018-11-27 CN CN201811430598.2A patent/CN109492116B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| Analysis of pedestrian dynamics from a vehicle perspective;Julian F.P Kooij等;《2014 IEEEIntelligent Vehicles Symposium》;20140717;1445-1450页 * |
| 山地城市道路平面交叉口行人交通特性研究;余昌学;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20130615;C034-198 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109492116A (en) | 2019-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | A fast trajectory outlier detection approach via driving behavior modeling | |
| CN109492583A (en) | A kind of recognition methods again of the vehicle based on deep learning | |
| CN110428091A (en) | Risk Identification Method and relevant device based on data analysis | |
| CN109523186B (en) | Urban area division method and device | |
| CN108229567A (en) | Driver identity recognition methods and device | |
| CN112101187B (en) | Road identification method and device and electronic equipment | |
| CN116486622A (en) | Traffic intelligent planning system and method based on road data | |
| CN109492116B (en) | Method and device for building character relationship network | |
| CN117456482B (en) | Abnormal event identification method and system for traffic monitoring scene | |
| CN117372969B (en) | Monitoring scene-oriented abnormal event detection method | |
| Karczmarek et al. | Choquet integral-based aggregation for the analysis of anomalies occurrence in sustainable transportation systems | |
| CN117151959B (en) | Real-time video analysis method, system and storage medium for city management | |
| CN107730717B (en) | A kind of suspicious card identification method of public transport based on feature extraction | |
| CN115565376B (en) | Vehicle journey time prediction method and system integrating graph2vec and double-layer LSTM | |
| CN112052405A (en) | Passenger searching area recommendation method based on driver experience | |
| Prezioso et al. | Machine Learning Insights for Behavioral Data Analysis Supporting the Autonomous Vehicles Scenario | |
| CN109656972A (en) | The determination method and device of region public security degree | |
| CN112015937B (en) | Picture geographic positioning method and system | |
| CN112651992B (en) | Track tracking method and system | |
| CN114492544A (en) | Model training method and device and traffic incident occurrence probability evaluation method and device | |
| CN114792397A (en) | SAR image urban road extraction method, system and storage medium | |
| Yang et al. | Intelligent intersection vehicle and pedestrian detection based on convolutional neural network | |
| Murrar et al. | Machine Learning Algorithms for Transportation Mode Prediction: A Comparative Analysis | |
| CN113643564B (en) | Parking data restoration method and device, computer equipment and storage medium | |
| Jain et al. | Machine Learning-Based Real-Time Traffic Control System |
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 |