CN111143496A - Method and device for determining target objects with similar tracks - Google Patents
Method and device for determining target objects with similar tracks Download PDFInfo
- Publication number
- CN111143496A CN111143496A CN201911315974.8A CN201911315974A CN111143496A CN 111143496 A CN111143496 A CN 111143496A CN 201911315974 A CN201911315974 A CN 201911315974A CN 111143496 A CN111143496 A CN 111143496A
- Authority
- CN
- China
- Prior art keywords
- entity
- node
- time
- target
- relationship
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/909—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The embodiment of the disclosure discloses a method and a device for determining target objects with similar tracks. One embodiment of the method comprises: the method includes the steps of constructing an initial relationship graph according to an obtained entity relationship data set representing the relationship between an acquisition device entity and an acquired object entity, creating space-time nodes representing time information and position information in the initial relationship graph according to time information and position information when the acquisition device entity acquires the acquired object entity, connecting the first entity nodes and the second entity nodes to the corresponding space-time nodes to obtain a total relationship graph, and determining a second target acquired object similar to the track of the first target acquired object based on the total relationship graph.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for determining target objects with similar tracks.
Background
With the advent of the big data age, more and more scenes are expected to realize the mining of related data through big data. The mining based on the incidence relation between the related data can be applied to solving the difficult problems of related services in a plurality of fields.
Disclosure of Invention
The embodiment of the disclosure provides a method and a device for determining target objects with similar tracks.
In a first aspect, an embodiment of the present disclosure provides a method for determining target objects with similar trajectories, the method including: the method comprises the steps of constructing an initial relation graph according to an obtained entity relation data set representing the relation between an acquisition equipment entity and an acquired object entity, creating space-time nodes representing time information and position information in the initial relation graph according to time information and position information when the acquisition equipment entity acquires the acquired object entity, connecting the first entity nodes and the second entity nodes to the corresponding space-time nodes to obtain a total relation graph, and determining a second target acquired object similar to the track of the first target acquired object on the basis of the total relation graph.
In some embodiments, each initial relationship graph corresponds to a type of acquisition device; connecting the first entity node and the second entity node to the corresponding space-time nodes to obtain a total relation graph, wherein the total relation graph comprises the following steps: and fusing the at least two initial relationship graphs based on the space-time nodes in the at least two initial relationship graphs respectively corresponding to the acquisition devices of different types to obtain a total relationship graph.
In some embodiments, determining a second target captured object having a similar trajectory to the first target captured object based on the overall relationship graph comprises: and determining a second target acquired object similar to the track of the first target acquired object from second acquired objects corresponding to the candidate second entity nodes based on the total relation graph.
In some embodiments, determining a second target acquired object with a similar trajectory to the first target acquired object from among the second acquired objects corresponding to the candidate second entity nodes based on the overall relationship map includes: generating a first time-space node sequence according to target time-space nodes associated with second target entity nodes, searching the time-space nodes associated with each candidate second entity node in the general relation graph, and forming a second time-space node sequence corresponding to each candidate second entity node; and determining a second target collected object similar to the track of the first target collected object from second collected objects corresponding to the candidate second entity nodes according to the contact ratio of the time nodes in the first time-space node sequence and the time-space nodes in the second time-space node sequence.
In some embodiments, creating spatiotemporal nodes characterizing time information and location information in an initial relationship graph comprises: aggregating the entity relationship data according to the time period to which the acquisition time information belongs to obtain first entity relationship data subsets corresponding to at least two different time periods respectively; aggregating the entity relationship data according to the position area to which the collected position information belongs to obtain second entity relationship data subsets corresponding to at least two different position areas respectively; and creating a plurality of spatiotemporal nodes in the initial relation graph based on the time period corresponding to each first entity relation data subset and the position area corresponding to each second entity relation data subset.
In some embodiments, the method further comprises: and writing the data representing the acquisition equipment entity, the data of the acquired object entity, the data of the time information and the data of the position information into a storage medium in a data wide table form.
In a second aspect, an embodiment of the present disclosure provides an apparatus for determining target objects with similar trajectories, the apparatus including: the system comprises a first construction unit, a second construction unit and a first determination unit, wherein the first construction unit is configured to construct an initial relation graph according to an obtained entity relation data set representing the relation between an acquisition equipment entity and an acquired object entity, the second construction unit is configured to create a space-time node representing time information and position information in the initial relation graph according to time information and position information when the acquisition equipment entity acquires the acquired object entity, the first entity node and the second entity node are connected to corresponding space-time nodes to obtain an overall relation graph, and the first determination unit is configured to determine a second target acquired object similar to the track of the first target acquired object based on the overall relation graph.
In some embodiments, each of the initial relationship graphs corresponds to one type of the acquisition device, and the second construction unit is further configured to fuse the at least two initial relationship graphs based on spatio-temporal nodes in the at least two initial relationship graphs corresponding to the different types of the acquisition devices, respectively, to obtain the total relationship graph.
In some embodiments, the first determination unit is further configured to: taking a second entity node corresponding to the first target collected object as a second target entity node, searching a target space-time node associated with the second target entity node according to the general relation graph, and taking at least one other second entity node associated with the target space-time node as a candidate second entity node; and determining a second target acquired object similar to the track of the first target acquired object from second acquired objects corresponding to the candidate second entity nodes on the basis of the general relation graph.
In some embodiments, the first determination unit is further configured to: the first determination unit is further configured to: generating a first time-space node sequence according to target time-space nodes associated with second target entity nodes, searching the time-space nodes associated with the candidate second entity nodes in the general relation graph to form a second time-space node sequence corresponding to the candidate second entity nodes, and determining a second target collected object with a track similar to that of the first target collected object from second collected objects corresponding to the candidate second entity nodes according to the coincidence degree of the time nodes in the first time-space node sequence and the time-space nodes in the second time-space node sequence.
In some embodiments, the second construction unit is further configured to create spatiotemporal nodes characterizing time information and location information in the initial relationship graph according to the following steps, including: and aggregating the entity relationship data according to the time period to which the acquisition time information belongs to obtain first entity relationship data subsets corresponding to at least two different time periods respectively, aggregating the entity relationship data according to the position region to which the acquisition position information belongs to obtain second entity relationship data subsets corresponding to at least two different position regions respectively, and creating a plurality of space-time nodes in the initial relationship graph based on the time period corresponding to each first entity relationship data subset and the position region corresponding to each second entity relationship data subset.
In some embodiments, further comprising: and the storage unit is configured to write the data representing the acquisition equipment entity, the data of the acquired object entity, the data of the time information and the data of the position information into the storage medium in a data wide table mode.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.
In a fourth aspect, an embodiment of the disclosure provides a computer-readable medium, on which a computer program is stored, which when executed by a processor, implements the method as described in any of the implementations of the first aspect.
According to the method and the device for determining the target objects with similar tracks, firstly, an initial relation graph is built according to an obtained entity relation data set representing the relation between an acquisition device entity and an acquired object entity, then, according to time information and position information when the acquisition device entity acquires the acquired object entity, a time-space node representing the time information and the position information is built in the initial relation graph, a first entity node and a second entity node are connected to the corresponding time-space node to obtain a total relation graph, and finally, a second target acquired object with similar tracks to the first target acquired object is determined based on the total relation graph, so that the target object information with similar tracks can be extracted quickly through the built relation graph representing the time-space position relation between the entities.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings in which:
FIG. 1 is a diagram of an exemplary system architecture in which an embodiment of the present disclosure may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for determining target objects with similar trajectories according to the present disclosure;
FIG. 3 is a schematic diagram of one application scenario of a method for determining target objects with similar trajectories according to an embodiment of the present disclosure;
FIG. 4 is a flow diagram of yet another embodiment of a method for determining target objects with similar trajectories according to the present disclosure;
FIG. 5 is a schematic diagram illustrating an embodiment of an apparatus for determining target objects with similar trajectories according to the present disclosure;
FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that, in the present disclosure, the embodiments and the features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary architecture 100 to which the method for determining target objects with similar trajectories or the apparatus for determining target objects with similar trajectories of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include a terminal device 101, a communication base station 102, a monitoring device 103, a network 104, and a server 105. The network 104 is used to provide a medium of communication links between the terminal device 101, the communication base station 102, the monitoring device 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The terminal apparatus 101 may be hardware or software. When the terminal device 101 is a hardware, it may be various electronic devices having a display screen and supporting positioning, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal device 101 is software, it can be installed in the electronic devices listed above. It may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The communication base station 102 may be a base station interacting with the terminal device 101, and may receive a message of the terminal device 101. From the acquired message, the location of the user using the terminal device 101 and the time at which the user is at the location can be determined.
The monitoring device 103 may be various monitoring cameras installed on the road, which can capture images of the faces of road users and can determine the location of the users and the time at which the users are present at the above locations.
The server 105 may be a server providing various services, for example, a background server analyzing various types of information provided by the terminal device 101, the communication base station 102, and the monitoring device 103. The background server may summarize and analyze the various types of information provided by the plurality of terminal devices 101, the communication base station 102, and the monitoring device 103, and generate and output a processing result (target object information with similar tracks).
It should be noted that the method for determining target objects with similar trajectories provided by the embodiments of the present disclosure is generally performed by the server 105, and accordingly, the apparatus for determining target objects with similar trajectories is generally disposed in the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for determining target objects with similar trajectories according to the present disclosure is shown. The method for determining the target objects with similar tracks comprises the following steps:
In this embodiment, an executing subject (e.g., the server 105 shown in fig. 1) of the method for determining target objects with similar trajectories may construct an initial relationship diagram representing the relationship between the acquisition device entity and the acquired object entity from data in the entity relationship data set representing the relationship between the acquisition device entity and the acquired object entity. The entity relationship data in the entity relationship data set may record a relationship between the acquisition device entity and the acquired object entity, for example, the entity relationship data may record a correspondence between the acquisition device entity identified by the camera as X and the acquired object entity identified by the face as Y. The entity relationship data may include: an ID of the acquisition device, position information of the acquisition device, an ID of the object acquired by the acquisition device, time information of the object acquired by the acquisition device, and the like. Here, the acquisition device may be a monitoring camera, a communication base station, a fingerprint acquirer, and the acquired object may be a position-variable object, such as a person, a vehicle, or an object (such as a mobile terminal) moving with the person/vehicle. The information of the collected object collected by the collecting device can be an image of a human face, an image or point cloud of a vehicle, a communication signal of a mobile terminal, and fingerprint information of a user. The entity relationship data in the entity relationship data set comprises time information and position information when the acquisition equipment entity acquires the acquired object entity, wherein the position information can be specific geographic coordinates (longitude and latitude), and the time information can be specific date and time. The initial relationship graph includes a first entity node representing the acquisition device entity, a second entity node representing the acquired object entity, and a connection edge representing the relationship between the acquisition device entity and the acquired object entity, for example, an acquisition device entity with a camera identified as X is used as the first entity node, an acquired object entity with a face identified as Y is used as the second entity node, if one piece of data in the entity relationship data set records information that the acquisition device entity X acquires the acquired object entity Y at a certain time, a connection line between the first entity node and the second entity node may be established, and a connection edge representing the relationship between the acquisition device entity with the camera identified as X and the acquired object entity with the face identified as Y is generated.
In this embodiment, the executing entity may create a spatio-temporal node representing time information and position information in the initial relationship graph created in step 201, and specifically, connect the first entity node and the second entity node to corresponding spatio-temporal nodes according to the time information and the position information when the collecting device entity collects the collected object entity, so as to obtain a total relationship graph. The spatio-temporal node may also represent a certain time period and a certain area, for example, the first spatio-temporal node may represent a time period from 1 month, 1 day, 9 hours and 5 minutes in 2019 to 1 month, 1 day, 9 hours and 15 minutes in 2019, and an area with a radius of 50 meters and a building a as a center. The time points or time periods represented by the respective time nodes may be non-overlapping, and the geographical locations or areas represented by the respective time nodes may be non-overlapping. The execution main body can determine corresponding space-time nodes according to time information and position information when the acquisition equipment entity acquires the acquired object entity, the space-time nodes are respectively connected with a first entity node for representing the acquisition equipment entity to acquire and a second entity node for representing the acquired object entity, for example, a time period from 5 minutes in 1 month, 1 day, 9, 2019 to 15 minutes in 1 month, 1 day, 9, 2019 and an area with a building A as a center radius of 50 meters, the acquisition equipment entity with a camera mark X acquires image information of the acquired object entity with a face mark Y, so that the first space-time nodes are respectively connected with a first entity node for representing the acquisition equipment entity with the camera mark X and a second entity node for representing the acquired object entity with the face mark Y.
In some optional implementations of this embodiment, creating spatio-temporal nodes characterizing time information and location information in the initial relationship graph includes: aggregating the entity relationship data according to the time period to which the acquisition time information belongs to obtain first entity relationship data subsets corresponding to at least two different time periods respectively; aggregating the entity relationship data according to the position area to which the collected position information belongs to obtain second entity relationship data subsets corresponding to at least two different position areas respectively; and creating a plurality of spatio-temporal nodes in the initial relationship graph based on the time periods corresponding to the first entity relationship data subsets and the position areas corresponding to the second entity relationship data subsets.
In this optional implementation manner, the execution main body may obtain the acquisition time information from the entity relationship data, and aggregate the acquisition time information to obtain a first entity relationship data subset corresponding to at least two different time periods, and the execution main body may obtain the acquisition position information from the entity relationship data, and aggregate the acquisition position information to obtain a second entity relationship data subset corresponding to at least two different position regions. The execution body may create a plurality of spatiotemporal nodes corresponding to the time period of the first entity relationship data subset and the position area of the second entity relationship data subset obtained after aggregation in the initial relationship graph. For example, the time range from 8/7/2018 to 8/2018 in the collection time information in the entity-relationship data set is divided into a plurality of time periods, and the time points falling into the time periods are aggregated. For example, the collection position information in the entity relation data set is in the area a, the area a may be divided into a plurality of position areas a1, a2, A3, and the collection position information falling into the respective position areas a1, a2, A3 may be aggregated. The execution body may further divide the area into a plurality of grids by way of grid division, where one grid may represent one location area. Through the implementation mode, the time information and the position information of the collected object entity collected by the similar collection equipment entity are aggregated, the time-space node representing the aggregated time period and position area is created, and the storage space of the data is reduced. And because the probability that the time information and the position information of the collected object entity collected by different collecting equipment entities are completely the same is lower, the time information and the position information are aggregated, and the searching range of the target object is favorably expanded.
And step 203, determining a second target acquired object similar to the track of the first target acquired object based on the general relation graph.
In this embodiment, the executing entity may determine, based on a first target acquired object specified in advance, a second target acquired object whose trajectory is similar to that of the first target acquired object from a general relationship graph, where the general relationship graph includes an entity node for representing an entity, a spatio-temporal node for representing time information and position information of the entity, and a connecting edge for representing a relationship between the entity node and the spatio-temporal node. The execution main body may determine a second entity node corresponding to the first target acquired object in the general relationship graph, search for a first entity node associated with the second entity node as a target first entity node, then search for other second entity nodes associated with the target first entity node, and use the acquired object represented by the other second entity nodes as a second target acquired object having a similar track to the first target acquired object.
The method for determining the target object with similar track provided by the above embodiment of the present disclosure, first, constructs an initial relationship graph according to the obtained entity relationship data set representing the relationship between the acquisition device entity and the acquired object entity, then according to the time information and the position information when the acquisition equipment entity acquires the acquired object entity, establishing space-time nodes representing time information and position information in the initial relation graph, connecting the first entity node and the second entity node to the corresponding space-time nodes to obtain a total relation graph, finally determining a second target collected object similar to the track of the first target collected object based on the total relation graph, according to the embodiment, the relevance between the entities in time and space dimensions is improved through the constructed relation graph representing the space-time characteristics between the entities, and the extraction of target object information with similar tracks is facilitated.
In practice, the method can be applied to various scenes for finding co-occurrence accompanying people.
In some optional implementations of this embodiment, the executing entity may determine, based on the general relationship diagram, a second target captured object whose trajectory is similar to the first target captured object by:
the first step is as follows: and taking a second entity node corresponding to the first target collected object as a second target entity node, finding a target space-time node associated with the second target entity node according to the general relation graph, and taking at least one other second entity node associated with the target space-time node as a candidate second entity node.
In this optional implementation manner, the execution main body may use a second entity node corresponding to the first target acquired object as a second target entity node, search for a target space-time node associated with the second target entity node in the general relationship graph, then search for at least one other second entity node associated with the target space-time node, and use the other second entity node as a candidate second entity node. The execution main body firstly determines candidate second target acquired objects which possibly have an association relation with the first target acquired objects through the space-time nodes.
The second step is that: and determining a second target acquired object similar to the track of the first target acquired object from second acquired objects corresponding to the candidate second entity nodes on the basis of the general relation graph.
In this alternative implementation, the executing entity may determine, from among candidate second target acquired objects that may have an association relationship with the first target acquired object, a second target acquired object having a trajectory similar to that of the first target acquired object. The execution main body may determine, in the candidate second target acquired objects that may have an association relationship with the first target acquired object through the space-time node, a second target acquired object having a trajectory similar to that of the first target acquired object according to whether the first target acquired object and the candidate second target acquired object are associated with acquisition devices characterized by more than a preset number of first entity nodes. Through the implementation mode, the second target acquired object which is closely related to the first target acquired object and has similar track is further determined from the candidate second target acquired objects which are possibly in association with the first target acquired object.
Optionally, based on the general relationship graph, determining a second target acquired object having a similar trajectory to the first target acquired object from second acquired objects corresponding to the candidate second entity nodes, including: generating a first time-space node sequence according to target time-space nodes associated with second target entity nodes, searching the time-space nodes associated with each candidate second entity node in the general relation graph, and forming a second time-space node sequence corresponding to each candidate second entity node; and determining a second target collected object similar to the track of the first target collected object from second collected objects corresponding to the candidate second entity nodes according to the coincidence degree of the time nodes in the first time-space node sequence and the time-space nodes in the second time-space node sequence.
In this optional implementation manner, the execution main body may generate a first time-space node sequence from target time-space nodes associated with second target entity nodes, find time-space nodes associated with each candidate second entity node in the general relationship diagram, form a second time-space node sequence corresponding to each candidate second entity node, compare the first time-space node sequence with each second time-space node sequence, determine the coincidence degree of the first time-space node sequence with each second time-space node sequence, select a second acquired object with the highest coincidence degree from second acquired objects corresponding to each candidate second entity node, and use the second acquired object with the highest coincidence degree as a second target acquired object with a track similar to the first target acquired object, where a higher coincidence degree indicates a higher degree of similarity to the first target acquired object track. For example, the execution body may calculate the number of spatio-temporal nodes with the same association of the first spatio-temporal node sequence and each second spatio-temporal node sequence to determine the coincidence degree of the first spatio-temporal node sequence and each second spatio-temporal node sequence. The execution main body can also calculate the proportion of the space-time nodes with the same association between the first space-time node sequence and each second space-time node sequence to all the space-time nodes in each second space-time node sequence respectively to determine the coincidence degree of the first space-time node sequence and each second space-time node sequence. According to the implementation mode, the times that the first target collected object and the second target collected object appear at the same time and the same place can be determined more intuitively through the generated first time-space node sequence and the second time-space node sequence, and the method is favorable for rapidly determining the second target collected object similar to the first target collected object in track.
With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of a method for determining target objects with similar trajectories according to an embodiment of the present disclosure. In the application scenario of fig. 3, a second entity node (e.g., the entity node corresponding to the acquired object a in fig. 3) corresponding to the first target acquired object is determined from the general relationship diagram 301, a target space-time node (e.g., the space-time point 1, the space-time point 2, and the space-time point 3 in fig. 3) associated with the second entity node (e.g., the entity node corresponding to the acquired object a in fig. 3) is found, and then other second entity nodes (e.g., the entity node corresponding to the acquired object B associated with the space-time point 1, the entity node corresponding to the acquired object C associated with the space-time point 2, and the entity nodes corresponding to the other second entity nodes (e.g., the entity node corresponding to the acquired object B, the entity node corresponding to the acquired object C in fig. 3) associated with the target space-time node (e.g., the space-time point 1, the space point 2, and the space point 3) are determined, and the second target acquired object corresponding to the other second entity node (e.g., the acquired object corresponding to the acquired And acquiring a second target acquired object with similar track.
In the method provided by the above embodiment of the present disclosure, the second entity node corresponding to the first target collected object is used as the second target entity node through the constructed general relationship graph, and the target space-time node associated with the second target entity node and the second collected object corresponding to the other second entity nodes associated with the target space-time node are found according to the general relationship graph and are used as the second target collected object having a similar track to the first target collected object, so that the target object information having a similar track can be quickly extracted through the constructed relationship graph representing the characteristics of the space-time relationship between the entities.
With further reference to fig. 4, a flow 400 of yet another embodiment of a method for determining target objects with similar trajectories is shown. The process 400 of the method for determining target objects with similar trajectories includes the following steps:
In this embodiment, an executing subject (such as the server 105 shown in fig. 1) of the method for determining target objects with similar trajectories may respectively construct a corresponding initial relationship diagram for each type of acquisition device with reference to the construction method in step 201, with respect to the acquired data in the entity relationship data set representing the relationship between the acquisition device entity and the acquired object entity. Each initial relation graph corresponds to one type of acquisition equipment. Here, a plurality of types of the acquisition devices may be set in advance according to the data type of the object to be acquired, for example, a biosensing-type acquisition device that acquires biosensing information, a communication-signal-type acquisition device that acquires data communication information, and the like. The biological sensing type collecting equipment can be further subdivided into image collecting equipment for collecting human faces and/or human body images, fingerprint sensing type collecting equipment for collecting fingerprints and the like according to the type difference of collected biological characteristics. The communication signal class acquisition device acquiring the data communication signal may be, for example, a communication base station class acquisition device.
In this embodiment, the execution main body may create a spatiotemporal node representing time information and position information in each initial relationship graph respectively corresponding to one type of acquisition device, and specifically, connect a first entity node and a second entity node to corresponding spatiotemporal nodes according to the time information and the position information when an acquisition device entity acquires an acquired object entity, overlap the same spatiotemporal nodes in at least two initial relationship graphs corresponding to different types of acquisition devices, and connect and fuse the at least two initial relationship graphs to obtain a total relationship graph. For example, the first initial relationship graph corresponding to the image-class acquisition device includes spatio-temporal nodes 11, time nodes 15 and time nodes 17, and the second initial relationship graph corresponding to the fingerprint-class acquisition device includes spatio-temporal nodes 13, spatio-temporal nodes 14 and spatio-temporal nodes 15, so that the same spatio-temporal nodes 15 are included in both the first initial relationship graph and the second initial relationship graph. The space-time nodes 15 in the first initial relationship graph are respectively connected with the acquisition equipment H for acquiring the image class and the corresponding acquired object K, the space-time nodes 15 in the second initial relationship graph are respectively connected with the acquisition equipment E for acquiring the fingerprint class and the corresponding acquired object F, the space-time nodes 5 in the first initial relationship graph are overlapped with the space-time nodes 5 in the second initial relationship graph, then the space-time nodes 5 communicate the acquisition equipment H for the image class, the acquired object K, the acquisition equipment E for the fingerprint class and the acquired object F, and the communication between the first initial relationship graph and the second initial relationship graph is realized according to the mode.
Step 403 is the same as step 203 in the previous embodiment, and the above description for step 203 also applies to step 403, which is not described herein again.
In some optional implementations of the embodiments described above in connection with fig. 2 and 4, the data characterizing the acquiring device entity, the acquired object entity, the time information and the location information are written in the storage medium in the form of a data wide table.
In the optional implementation manner, the positions of different types of data stored in the data wide table are preset, corresponding relations exist among columns in the data wide table, then the data representing the acquisition device entity, the data of the acquired object entity, the data of the time information and the data of the position information are respectively stored in corresponding positions in the data wide table, and finally the various types of data are stored in the storage medium in the form of the data wide table. Storage medium refers to a carrier for storing data, such as a floppy disk, an optical disk, a DVD, a hard disk. Here, the data representing the acquisition device entity may be, for example, an ID of a camera, the data of the acquired object entity may be, for example, an ID of a human face, the data of the time information may be, for example, 16 hours and 20 minutes in 1 month and 1 day in 2019, and the data of the position information may be, for example, longitude 121.70 and latitude 31.20. The execution main body can also back up the data wide table, and further stores the backed-up data in other storage devices, so that data loss caused by the failure of the original system is prevented. The data wide table can record the recording time of each piece of data and provide data support for data rollback (processing errors of programs or data, restoring the programs or the data to the last correct state), data disaster recovery (recovering the data when a system fails), and data backtracking (returning the data at a specified time slicing moment). Through the implementation mode, various types of data with correlation are stored in a data wide table mode, so that the data can be conveniently inquired and dug, and the data extraction efficiency is greatly improved.
As can be seen from fig. 4, in the process 400 for determining target objects with similar trajectories in this embodiment, a plurality of initial relationship graphs corresponding to the types of the acquisition devices are respectively constructed, and the plurality of initial relationship graphs are connected through the same spatio-temporal node to obtain a total relationship graph, so that data of a plurality of types of acquired objects can be fused, the thickness of data features of the acquired objects can be increased, and the objects with similar trajectories can be found more comprehensively based on the total relationship graph fusing the plurality of initial relationship graphs.
With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an apparatus for determining target objects with similar trajectories, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable in various electronic devices.
As shown in fig. 5, the apparatus 500 for determining target objects with similar trajectories provided by the present embodiment includes a first constructing unit 501, a second constructing unit 502, and a first determining unit 503. The first construction unit 501 is configured to construct an initial relationship graph according to an obtained entity relationship data set representing a relationship between an acquisition device entity and an acquired object entity; a second constructing unit 502 configured to create a spatio-temporal node representing time information and position information in the initial relationship graph according to the time information and the position information when the collecting device entity collects the collected object entity, and connect the first entity node and the second entity node to the corresponding spatio-temporal node to obtain a total relationship graph; a first determining unit 503 configured to determine a second target object similar to the trajectory of the first target object based on the overall relationship map. And the first determining unit is configured to determine a second target acquired object similar to the track of the first target acquired object based on the overall relation graph.
In the present embodiment, in the apparatus 500 for determining target objects with similar trajectories: the specific processing of the first constructing unit 501, the second constructing unit 502 and the first determining unit 503 and the technical effects thereof can refer to the related descriptions of step 201, step 202 and step 203 in the corresponding embodiment of fig. 2, which are not repeated herein.
In some optional implementation manners of this embodiment, each initial relationship graph corresponds to one type of the acquisition device; and the second construction unit is further configured to fuse the at least two initial relationship graphs based on the spatio-temporal nodes in the at least two initial relationship graphs respectively corresponding to the acquisition devices of different types to obtain a total relationship graph.
In some optional implementations of this embodiment, the first determining unit is further configured to: taking a second entity node corresponding to the first target collected object as a second target entity node, searching a target space-time node associated with the second target entity node according to the general relation graph, and taking at least one other second entity node associated with the target space-time node as a candidate second entity node; and determining a second target acquired object similar to the track of the first target acquired object from second acquired objects corresponding to the candidate second entity nodes on the basis of the general relation graph.
In some optional implementations of this embodiment, the first determining unit is further configured to: generating a first time-space node sequence according to target time-space nodes associated with second target entity nodes, searching the time-space nodes associated with each candidate second entity node in the general relation graph, and forming a second time-space node sequence corresponding to each candidate second entity node; and determining a second target collected object similar to the track of the first target collected object from second collected objects corresponding to the candidate second entity nodes according to the coincidence degree of the space-time nodes of the first space-time node sequence and the space-time nodes in the second space-time node sequence.
In some optional implementations of this embodiment, the second constructing unit is further configured to create a time-space node representing the time information and the location information in the initial relationship graph according to the following steps, including: aggregating the entity relationship data according to the time period to which the acquisition time information belongs to obtain a first entity relationship data subset combination corresponding to at least two different time periods respectively; aggregating the entity relationship data according to the position area to which the collected position information belongs to obtain second entity relationship data subsets respectively corresponding to at least two different position areas; and creating a plurality of spatiotemporal nodes in the initial relationship graph based on the time periods corresponding to the first entity relationship data subsets and the position areas corresponding to the second entity relationship data subsets.
In some optional implementations of the present embodiment, the storage unit (not shown in the figure) is further included, and is configured to write the data characterizing the acquisition device entity, the data of the acquired object entity, the data of the time information, and the data of the position information into the storage medium in a data wide table form.
In the apparatus provided by the foregoing embodiment of the present disclosure, the first constructing unit 501 constructs an initial relationship graph according to an obtained entity relationship data set representing a relationship between an acquisition device entity and an acquired object entity, the second constructing unit 502 creates a spatio-temporal node representing time information and position information in the initial relationship graph according to time information and position information when the acquisition device entity acquires the acquired object entity, and connects the first entity node and the second entity node to corresponding spatio-temporal nodes to obtain a total relationship graph, the first determining unit 503 determines, based on the total relationship graph, a second target acquired object having a similar trajectory to that of the first target acquired object, and the apparatus is favorable for extracting target object information having a similar trajectory through the constructed relationship graph representing a spatio-temporal position relationship between entities.
Referring now to FIG. 6, and referring now to FIG. 6, a block diagram of an electronic device (e.g., server in FIG. 1) 600 suitable for use in implementing embodiments of the present disclosure is shown. The garment illustrated in fig. 6 is merely an example and should not impose any limitations on the functionality or scope of use of embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate wirelessly or by wire with other devices to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of embodiments of the present disclosure.
It should be noted that the computer readable medium of the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in embodiments of the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: the method comprises the steps of constructing an initial relation graph according to an obtained entity relation data set representing the relation between an acquisition equipment entity and an acquired object entity, creating space-time nodes representing time information and position information in the initial relation graph, connecting a first entity node and a second entity node to corresponding space-time nodes according to the time information and the position information when the acquisition equipment entity acquires the acquired object entity to obtain a total relation graph, and determining a second target acquired object similar to the track of the first target acquired object based on the total relation graph.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first construction unit, a second construction unit, and a first determination unit. Where the names of these elements do not in some cases constitute a limitation on the elements themselves, for example, a first building element may also be described as an "element that builds an initial relationship graph".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also covers other embodiments formed by any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features and (but not limited to) the features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (14)
1. A method for determining target objects with similar trajectories, comprising:
constructing an initial relationship graph according to an obtained entity relationship data set representing the relationship between an acquisition equipment entity and an acquired object entity, wherein the entity relationship data in the entity relationship data set comprises time information and position information when the acquisition equipment entity acquires the acquired object entity; wherein the initial relationship graph comprises a first entity node characterizing the acquisition device entity and a second entity node characterizing the acquired object entity, and a connecting edge characterizing a relationship between the acquisition device entity and the acquired object entity;
establishing a time-space node representing time information and position information in the initial relation graph according to the time information and the position information when the acquisition equipment entity acquires the acquired object entity, and connecting the first entity node and the second entity node to the corresponding time-space node to obtain a total relation graph;
and determining a second target acquired object similar to the track of the first target acquired object based on the overall relation graph.
2. The method according to claim 1, wherein each initial relationship graph corresponds to one acquisition device type; the connecting the first entity node and the second entity node to the corresponding spatio-temporal node to obtain a total relationship graph, including:
and fusing the at least two initial relationship graphs based on the space-time nodes in the at least two initial relationship graphs respectively corresponding to the acquisition devices of different types to obtain a total relationship graph.
3. The method of claim 1, wherein the determining a second target captured object having a similar trajectory as the first target captured object based on the overall relationship graph comprises:
taking a second entity node corresponding to a first target collected object as a second target entity node, finding a target space-time node associated with the second target entity node according to the general relation graph, and taking at least one other second entity node associated with the target space-time node as a candidate second entity node;
and determining a second target acquired object similar to the first target acquired object track from second acquired objects corresponding to the candidate second entity nodes on the basis of the overall relation graph.
4. The method of claim 3, wherein the determining a second target acquired object similar to the first target acquired object trajectory from among the second acquired objects corresponding to the candidate second entity nodes based on the overall relationship graph comprises:
generating a first time-space node sequence according to the target time-space node associated with the second target entity node, searching the time-space node associated with each candidate second entity node in the general relation graph, and forming a second time-space node sequence corresponding to each candidate second entity node;
and determining a second target collected object similar to the track of the first target collected object from second collected objects corresponding to the candidate second entity nodes according to the contact ratio of the time nodes in the first time-space node sequence and the time-space nodes in the second time-space node sequence.
5. The method of claim 1, wherein said creating spatiotemporal nodes characterizing time information and location information in said initial relationship graph comprises:
aggregating the entity relationship data according to the time period to which the acquisition time information belongs to obtain first entity relationship data subsets corresponding to at least two different time periods respectively;
aggregating the entity relationship data according to the position area to which the collected position information belongs to obtain second entity relationship data subsets corresponding to at least two different position areas respectively;
and creating a plurality of spatiotemporal nodes in the initial relationship graph based on the time period corresponding to each first entity relationship data subset and the position area corresponding to each second entity relationship data subset.
6. The method of any of claims 1-5, wherein the method further comprises:
and writing the data representing the acquisition equipment entity, the data of the acquired object entity, the data of the time information and the data of the position information into a storage medium in a data wide table form.
7. An apparatus for determining target objects with similar trajectories, comprising:
the system comprises a first construction unit, a second construction unit and a third construction unit, wherein the first construction unit is configured to construct an initial relation graph according to an obtained entity relation data set representing the relation between an acquisition equipment entity and an acquired object entity, and entity relation data in the entity relation data set comprise time information and position information when the acquisition equipment entity acquires the acquired object entity; wherein the initial relationship graph comprises a first entity node characterizing the acquisition device entity and a second entity node characterizing the acquired object entity, and a connecting edge characterizing a relationship between the acquisition device entity and the acquired object entity;
a second construction unit, configured to create a spatio-temporal node representing time information and position information in the initial relationship graph according to the time information and the position information when the acquisition device entity acquires the acquired object entity, and connect the first entity node and the second entity node to corresponding spatio-temporal nodes to obtain an overall relationship graph;
a first determination unit configured to determine a second target object similar to the trajectory of the first target object based on the overall relationship diagram.
8. The apparatus of claim 7, wherein each initial relationship graph corresponds to a respective acquisition device type; the second construction unit is further configured to fuse the at least two initial relationship graphs based on spatio-temporal nodes in the at least two initial relationship graphs respectively corresponding to different types of acquisition devices to obtain a total relationship graph.
9. The apparatus of claim 7, wherein the first determining unit is further configured to: taking a second entity node corresponding to a first target collected object as a second target entity node, finding a target space-time node associated with the second target entity node according to the general relation graph, and taking at least one other second entity node associated with the target space-time node as a candidate second entity node;
and determining a second target acquired object similar to the first target acquired object track from second acquired objects corresponding to the candidate second entity nodes on the basis of the overall relation graph.
10. The apparatus of claim 9, wherein the first determining unit is further configured to:
generating a first time-space node sequence according to the target time-space node associated with the second target entity node, searching the time-space node associated with each candidate second entity node in the general relation graph, and forming a second time-space node sequence corresponding to each candidate second entity node;
and determining a second target collected object similar to the track of the first target collected object from second collected objects corresponding to the candidate second entity nodes according to the contact ratio of the time nodes in the first time-space node sequence and the time-space nodes in the second time-space node sequence.
11. The apparatus of claim 7, wherein the second construction unit is further configured to create spatio-temporal nodes characterizing time information and location information in the initial relationship graph according to the following steps comprising:
aggregating the entity relationship data according to the time period to which the acquisition time information belongs to obtain first entity relationship data subsets corresponding to at least two different time periods respectively;
aggregating the entity relationship data according to the position area to which the collected position information belongs to obtain second entity relationship data subsets corresponding to at least two different position areas respectively;
and creating a plurality of spatiotemporal nodes in the initial relationship graph based on the time period corresponding to each first entity relationship data subset and the position area corresponding to each second entity relationship data subset.
12. The apparatus of any of claims 7-11, wherein the apparatus further comprises:
and the storage unit is configured to write the data representing the acquisition equipment entity, the data of the acquired object entity, the data of the time information and the data of the position information into the storage medium in a data wide table mode.
13. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911315974.8A CN111143496B (en) | 2019-12-19 | 2019-12-19 | Method and device for determining target objects with similar tracks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911315974.8A CN111143496B (en) | 2019-12-19 | 2019-12-19 | Method and device for determining target objects with similar tracks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111143496A true CN111143496A (en) | 2020-05-12 |
| CN111143496B CN111143496B (en) | 2023-05-26 |
Family
ID=70518825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911315974.8A Active CN111143496B (en) | 2019-12-19 | 2019-12-19 | Method and device for determining target objects with similar tracks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111143496B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112015956A (en) * | 2020-09-04 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Similarity determination method, device, equipment and storage medium for mobile object |
| CN112037927A (en) * | 2020-08-24 | 2020-12-04 | 北京金山云网络技术有限公司 | Method and device for determining co-pedestrian associated with tracked person and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090109020A1 (en) * | 2007-10-29 | 2009-04-30 | At&T Bls Intellectual Property, Inc. | Methods, systems, devices, and computer program products for implementing condition alert services |
| JP2014149717A (en) * | 2013-02-01 | 2014-08-21 | Zenrin Datacom Co Ltd | Information processing apparatus, information processing method, and program |
| CN107315755A (en) * | 2016-04-27 | 2017-11-03 | 杭州海康威视数字技术股份有限公司 | The orbit generation method and device of query object |
| CN108595539A (en) * | 2018-04-04 | 2018-09-28 | 烟台海颐软件股份有限公司 | A kind of recognition methods of trace analogical object and system based on big data |
| CN108694216A (en) * | 2017-04-12 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | A kind of multi-source method of mapping and device |
-
2019
- 2019-12-19 CN CN201911315974.8A patent/CN111143496B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090109020A1 (en) * | 2007-10-29 | 2009-04-30 | At&T Bls Intellectual Property, Inc. | Methods, systems, devices, and computer program products for implementing condition alert services |
| JP2014149717A (en) * | 2013-02-01 | 2014-08-21 | Zenrin Datacom Co Ltd | Information processing apparatus, information processing method, and program |
| CN107315755A (en) * | 2016-04-27 | 2017-11-03 | 杭州海康威视数字技术股份有限公司 | The orbit generation method and device of query object |
| CN108694216A (en) * | 2017-04-12 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | A kind of multi-source method of mapping and device |
| CN108595539A (en) * | 2018-04-04 | 2018-09-28 | 烟台海颐软件股份有限公司 | A kind of recognition methods of trace analogical object and system based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 范恒飞: "基于车联网的车辆运动轨迹追踪技术研究与实现" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037927A (en) * | 2020-08-24 | 2020-12-04 | 北京金山云网络技术有限公司 | Method and device for determining co-pedestrian associated with tracked person and electronic equipment |
| CN112015956A (en) * | 2020-09-04 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Similarity determination method, device, equipment and storage medium for mobile object |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111143496B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9313233B2 (en) | Systems and methods for detecting associated devices | |
| CN110515968B (en) | Method and apparatus for outputting information | |
| CN111897740B (en) | User interface testing method and device, electronic equipment and computer readable medium | |
| JP2022528176A (en) | Methods and devices for detecting the human body | |
| US10147230B2 (en) | Dynamic video visualization | |
| CN110618982B (en) | Multi-source heterogeneous data processing method, device, medium and electronic equipment | |
| CN111143496B (en) | Method and device for determining target objects with similar tracks | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN115631212B (en) | Person accompanying track determining method and device, electronic equipment and readable medium | |
| CN114078277A (en) | One-person-one-file face clustering method and device, computer equipment and storage medium | |
| CN111340015A (en) | Positioning method and device | |
| CN114708545A (en) | Image-based object detection method, device, equipment and storage medium | |
| CN114385772A (en) | Position information generation method, device, equipment and computer readable medium | |
| CN111310595B (en) | Method and device for generating information | |
| CN110928914A (en) | Method and apparatus for outputting information | |
| CN111694875B (en) | Method and device for outputting information | |
| CN111611337B (en) | Terminal data processing system | |
| CN113255819A (en) | Method and apparatus for identifying information | |
| US20150310108A1 (en) | Apparatus and method for collecting media | |
| CN111339394A (en) | Method and device for acquiring information | |
| CN107180073B (en) | POI recommendation method, device, equipment and computer readable storage medium | |
| CN117435963B (en) | Digital asset fraud group determination method, device, electronic equipment and storage medium | |
| US20150082346A1 (en) | System for Selective and Intelligent Zooming Function in a Crowd Sourcing Generated Media Stream | |
| CN116820354B (en) | Data storage method, data storage device and data storage system | |
| CN116384945B (en) | Project management method and 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 |