CN110874362A - Data association analysis method and device - Google Patents
Data association analysis method and device Download PDFInfo
- Publication number
- CN110874362A CN110874362A CN201911039044.4A CN201911039044A CN110874362A CN 110874362 A CN110874362 A CN 110874362A CN 201911039044 A CN201911039044 A CN 201911039044A CN 110874362 A CN110874362 A CN 110874362A
- Authority
- CN
- China
- Prior art keywords
- data
- track
- time
- space
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2255—Hash tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a data association analysis method and a device, which respond to an indication of data association of an associated object, and search clustering data information obtained by aggregating different types of data of the associated object in a database, wherein the different types of data comprise hash values obtained by converting longitude and latitude of each type of data through a geohash algorithm; constructing a first space-time trajectory of the associated object according to the found hash value in the clustering data information; determining track points of at least one detection object meeting the association condition with the track points, and constructing a second space-time track belonging to the same detection object; and determining the detection object corresponding to the second space-time trajectory of which the similarity with the first space-time trajectory is greater than the similarity threshold value as the detection object having the association relation with the associated object. By utilizing the method provided by the invention, the space-time trajectory behavior of the associated object can be extracted and analyzed to obtain other objects accompanying and in the same line by inputting the name of any object.
Description
Technical Field
The invention relates to the technical field of big data and distributed computing, in particular to a data association analysis method and device.
Background
In the existing technology for searching for a target by mass data, after the search target is determined in the data governance process, how to obtain the search target data from the mass data for line tracking becomes a challenge in the field of target tracking.
Specifically, due to the increasing diversification of various front-end monitoring devices such as video monitoring, human faces, vehicle gates and the like, when data corresponding to a search target is determined to be analyzed and mined, available data types are more and more, and how to normalize different types of data to the same platform becomes an industry difficulty.
In the prior target searching system and solution, most of the data are mining and application modes of mass data (single-dimensional data) acquired by a single type of equipment, and the data analysis mining mode has the advantages of clear target, accurate retrieval, prominent core information, flattened data, relatively simple data operation and the like; however, the disadvantages of the method are obvious, the multi-dimensional data cannot be fused, the information relation between the multi-dimensional data cannot be established, and the play space of the multi-dimensional data in some service scene fields is limited.
Disclosure of Invention
The invention provides a method and a device for data association analysis, which are used for solving the problems that video monitoring, WIFI acquisition and passing card ports belong to different systems and are built in different stages, equipment point location information of different system data is maintained independently, point location relationship maintenance is complex and complicated, data fusion analysis is carried out by manually establishing physical association among point locations by using the traditional method for data association, but the point location information maintenance cost is huge and the manual operation error rate is higher; or the distance is calculated through longitude and latitude, and the method has the problems of large calculated amount and low performance.
A first aspect of the present invention provides a data association analysis method, including:
responding to an instruction of performing data association on an associated object, and searching clustering data information obtained by aggregating different types of data of the associated object in a database, wherein the different types of data comprise hash values obtained by converting longitude and latitude of each type of data acquired through a geohash algorithm;
constructing a first spatiotemporal trajectory of the associated object according to the found hash value in the clustering data information;
determining track points of at least one detection object meeting association conditions with the track points based on the track points in the first space-time track, and constructing a second space-time track belonging to the same detection object;
and determining the detection object corresponding to the second spatio-temporal trajectory with the similarity of the first spatio-temporal trajectory being greater than a similarity threshold as the detection object having the association relation with the associated object.
Optionally, different types of data are acquired, where the different types of data include monitoring data acquired by monitoring equipment and terminal data interactively acquired by a terminal associated with the object, and the different types of data include object identification information and a hash value obtained by converting longitude and latitude of the acquired type of data by a geohash algorithm;
and after preprocessing the different types of data, aggregating all types of data belonging to the same object according to the object identification information in the different types of data to obtain the cluster data information of the associated object, and sending the cluster data information to a database.
Optionally, the determining the track point of the at least one detection object which satisfies the association condition with the track point includes:
and determining the track points of the detection object with the acquisition time in the same time interval as the acquisition time of the track points in the first space-time trajectory as the track points of at least one detection object meeting the association condition with the track points in the first space-time trajectory.
Optionally, it is determined that a fixed time difference is subtracted from the track point acquisition time in the first space-time trajectory, the track point acquisition time in the first space-time trajectory plus the fixed time difference is determined as the start time of the same time interval, and the end time of the same time interval is determined, where the duration of the fixed time difference is determined according to the moving speed difference between the associated object and the detection object.
Optionally, the determining the track point of the at least one detection object which satisfies the association condition with the track point includes:
and determining the track points of the detection object with the position in the same space range as the position of the track points in the first space-time trajectory into the track points of at least one detection object which meets the association condition with the track points in the first space-time trajectory.
Optionally, the position of the track point in the first space-time trajectory is used as a central point of a hash value squared figure, and an area where the hash value squared figure corresponding to the central point is located is determined as a space range where the track point in the first space-time trajectory is located.
Optionally, when the motion modes of the associated object and the detection object are the same, calculating the trajectory similarity between the associated object and the detection object by using a trajectory similarity calculation formula corresponding to the same motion mode;
and when the motion modes of the associated object and the detection object are different, calculating the track similarity of the associated object and the detection object by using track similarity calculation formulas corresponding to different motion modes.
Optionally, the method for preprocessing the different types of data includes:
filtering the different types of data according to a preset filtering rule;
and performing data format conversion, code conversion and value conversion on the different types of data after the filtering operation to unify the different types of data into code identification data.
A second aspect of the present invention provides an apparatus for data association analysis, the apparatus comprising the following modules:
the system comprises a clustering data information acquisition module, a data association module and a data association module, wherein the clustering data information acquisition module is used for responding to an instruction of performing data association on an associated object and searching clustering data information obtained by aggregating different types of data of the associated object in a database, and the different types of data comprise hash values obtained by converting longitude and latitude of collected data through a geohash algorithm;
the first space-time trajectory establishing module is used for establishing a first space-time trajectory of the associated object according to the found hash value in the clustering data information;
the second space-time track establishing module is used for determining track points of at least one detection object meeting the association condition with the track points based on the track points in the first space-time track and establishing a second space-time track belonging to the same detection object;
and the association detection module is used for determining a detection object corresponding to the second spatiotemporal trajectory, of which the similarity with the first spatiotemporal trajectory is greater than a similarity threshold, as a detection object having an association relationship with the association object.
Optionally, the apparatus further includes a data obtaining module, configured to obtain different types of data, where the different types of data include monitoring data collected by a monitoring device and terminal data collected by a terminal associated with the object in an interactive manner, and the different types of data include object identification information and a hash value obtained by converting longitude and latitude of the collected type of data by a geohash algorithm;
and after preprocessing the different types of data, aggregating all types of data belonging to the same object according to the object identification information in the different types of data to obtain the cluster data information of the associated object, and sending the cluster data information to a database.
Optionally, the second spatiotemporal trajectory creation module is specifically configured to,
the determining the track point of at least one detection object which meets the association condition with the track point comprises the following steps:
and determining the track points of the detection object with the acquisition time in the same time interval as the acquisition time of the track points in the first space-time trajectory as the track points of at least one detection object meeting the association condition with the track points in the first space-time trajectory.
Optionally, the second spatiotemporal trajectory establishing module is specifically configured to determine that a fixed time difference is subtracted from the trajectory point acquisition time in the first spatiotemporal trajectory, determine, as the start time of the same time interval, that a fixed time difference is added to the trajectory point acquisition time in the first spatiotemporal trajectory, and determine, as the end time of the same time interval, a duration of the fixed time difference according to a difference in moving speeds of the associated object and the detection object.
Optionally, the second spatiotemporal trajectory creation module is specifically configured to,
determining the track point of at least one detection object meeting the association condition with the track point, wherein the method comprises the following steps:
and determining the track points of the detection object with the position in the same space range as the position of the track points in the first space-time trajectory into the track points of at least one detection object which meets the association condition with the track points in the first space-time trajectory.
Optionally, the second spatiotemporal trajectory creation module is specifically configured to,
and taking the position of the track point in the first space-time track as the central point of the hash value squared figure, and determining the area where the hash value squared figure corresponding to the central point is located, wherein the area is the space range where the track point in the first space-time track is located.
Optionally, the association detection module is specifically configured to,
when the motion modes of the associated object and the detection object are the same, calculating the track similarity of the associated object and the detection object by using a track similarity calculation formula corresponding to the same motion mode;
and when the motion modes of the associated object and the detection object are different, calculating the track similarity of the associated object and the detection object by using track similarity calculation formulas corresponding to different motion modes.
Optionally, the cluster data information obtaining module is specifically configured to, where the method for preprocessing the different types of data includes:
filtering the different types of data according to a preset filtering rule;
and performing data format conversion, code conversion and value conversion on the different types of data after the filtering operation to unify the different types of data into code identification data.
A third aspect of the present invention provides an apparatus for data association analysis, the apparatus comprising a processor and a memory, the memory having stored therein a computer program, the processor being configured to execute the computer program in the memory, the computer program being configured to perform the method for data association analysis provided by the first aspect of the present invention.
A fourth aspect of the present invention provides a computer medium having stored thereon computer instructions which, when executed by a processor, implement the method of data correlation analysis provided by the first aspect of the present invention.
By utilizing the data association analysis method and device provided by the invention, a data analysis system aiming at video monitoring, passing through a vehicle at a checkpoint, face in the vehicle, WIFI, RFID and other big data is provided, and the space-time trajectory behavior of the associated object can be extracted and analyzed to obtain other objects accompanying and in the same line by inputting the name of any object. When vehicle or personnel information is inquired according to conditions such as time and space information, license plate numbers, the number of the same vehicle and the like, other vehicles, human faces, MAC, RFID and the objects in the same row meeting the conditions are mined and displayed on the data association platform at the same time.
Drawings
FIG. 1 is a schematic diagram of a data correlation analysis system;
FIG. 2 is a schematic diagram of a system architecture of a data analysis platform;
FIG. 3 is a flow chart of the steps of a method of data correlation analysis;
FIG. 4 is a schematic diagram of spatiotemporal trajectory joining;
FIG. 5 is a schematic diagram of the spatial range of a Sudoku;
fig. 6a to 6c are schematic diagrams of ways of finding a point satisfying the association condition according to the track point;
FIG. 7 is an interface diagram of a data association platform;
FIG. 8 is a block diagram of an apparatus for data association analysis;
fig. 9 is a schematic structural diagram of a data association analysis apparatus.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, and to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. 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.
The embodiments of the present invention will be described in further detail with reference to the drawings attached hereto. It is to be understood that the embodiments described herein are merely illustrative and explanatory of the invention and are not restrictive thereof.
Referring to fig. 1, a schematic diagram of a data association analysis system is shown, where the data association analysis system includes: the monitoring system comprises a monitoring class data acquisition device 101, a terminal interaction acquisition device 102, a data analysis clustering server 103 connected with the monitoring class data acquisition device 101 and the terminal interaction acquisition device 102, a clustering data information database 104 connected with the data analysis clustering server 103, and a data analysis platform 105, wherein the monitoring class data acquisition device 101 and the terminal interaction acquisition device 102 send acquired data of an object to the data analysis clustering server 103, and the monitoring class data acquisition device 101 comprises: the device can be deployed at places such as road gates, indoors or outdoors, and the data collected by the device includes but is not limited to: the vehicle monitoring system comprises a vehicle bayonet picture, a human face snapshot picture, a monitoring video file and the like, and particularly, the vehicle bayonet picture data collected at a road bayonet are mainly used for collecting license plate numbers of vehicles and facial pictures of drivers and passengers in the vehicles, the human face snapshot picture collected by a photographing device is mainly used for collecting data information of human faces such as age and sex, the video file collected by the video monitoring device is used for shooting, and the data information of human external appearance information such as wearing, stride and motion forms is mainly collected.
And the terminal interaction acquisition device 102 comprises: WIFI probe equipment, fence equipment, RFID collection equipment, the data that above-mentioned equipment was gathered include but not limited to: the WIFI probe collects data, the RFID collects data and electronic fence data, and the purpose of collecting the data is mainly to collect relevant information of a terminal interacting with the terminal interaction collection equipment, specifically, the WIFI probe equipment or the electronic fence equipment collects the relevant information of the terminal interacting with the WiFi probe equipment or the electronic fence equipment and the longitude and latitude of the position of the terminal.
After the data analysis server 103 acquires various data information sent by the monitoring data acquisition device 101 and the terminal interaction acquisition device 102, the data analysis server 103 preprocesses and performs cluster analysis on the various data information, and sends clustered data to the cluster data information database 104, wherein the cluster data information database 104 can exist in the data analysis server 103 or can exist independently outside the data analysis server 103; when the system of the data analysis platform 105 responds to the instruction of performing data association on the associated object, a data association instruction is sent to the data analysis server 103, the data analysis server 103 extracts cluster information related to the associated object from the cluster data information database 104, the associated data is analyzed in the data analysis server 103, a detection object related to the associated object is found, and when a detection object meeting an association condition is detected, the related information of the detection object is sent to the data association platform 105 to be displayed through the data association platform 105.
Fig. 2 is a schematic diagram of a system specific structure of the data analysis platform;
the data analysis platform is divided into four layers, including a data access layer 201, a data analysis layer 202, a data relationship establishment layer 203, and a data platform display layer 204.
The data access layer 201 is used for accessing various data information acquired by the monitoring equipment and the terminal interactive acquisition equipment into the data analysis layer 202;
various types of data information are stored in the Kafka message middleware firstly, and are extracted to the data analysis layer 202 in a streaming mode in a SparkStreaming mode;
the data analysis layer 202 performs structured processing on the extracted pictures and videos collected by the monitoring devices, and converts the pictures and videos into structured data of the vehicle and the face, wherein the structured data includes but is not limited to: shooting the appearance characteristics, the form steps and the like of personnel, wherein the picture and the video file contain longitude and latitude information of the collected data, and converting the longitude and latitude information of the data into a hash value through a geohash algorithm and sending the hash value to a database; in addition, the collected pictures and videos can also collect face information, the personnel are subjected to cluster analysis through the face information, and various data information belonging to the same person are sent to a database together.
Before the database receives the data information, the data needs to be processed through data filtering, data standardization and the like, and finally structured and clustered data are stored in various databases.
The data relation establishing layer 203 is used for establishing a space-time track of the object based on the hash value by extracting data of various databases in the data analysis layer and external databases and combining the hash value representing longitude and latitude stored in the databases, performing fusion analysis on multi-dimensional data based on the space-time track and track points in the space-time track, establishing a relation map between the objects, performing data indexing according to virtual identification of the data, performing data statistical analysis and the like.
In the data platform display layer 204, the established association relationship, the object map and the distribution condition of the track points are extracted to obtain relevant files of the object in real time, track analysis is performed on the object, analysis of the relationship among different objects is performed, the passing times among the objects are inquired, the footfall of the object is analyzed based on the track points of the object, the day and night travel condition and travel rules of the object are analyzed, the blank track is subjected to detailed analysis by utilizing resources in other databases, real-time monitoring and control can be performed by combining a population database, and the footfall and travel rules of personnel and vehicles can be analyzed according to the distribution condition of the track points. The travel maps of the personnel can be established by establishing the space-time trajectory, and the information is simultaneously accessed into the data association platform, so that the platform has richer searchability.
Example 1
In this embodiment, based on the system of the data analysis platform, the clustering data of different types of data is aggregated by applying an information clustering manner in the embodiment of the present invention;
firstly, various data information is extracted from a message middleware kafka, the data is respectively stored in various databases according to different data types, specifically, the data needs to be clustered according to the data types, for example, pictures obtained from road gate pictures are clustered, the information contained in the road gate pictures comprises license plate numbers of vehicles, human face characteristics of passengers and drivers in the vehicles and the models and colors of the vehicles, the gate pictures collected with the license plate numbers are classified into one type according to the different license plate numbers and are packaged and stored in the vehicle database, or the various data information containing the human face characteristics are packaged and stored in the human face database according to the shot human face information collected by drivers in the vehicles, wherein the clustering mode is not limited to the method, and the clustering mode is not limited to the method here any more
And when the various data information comprises the collected data, the latitude and longitude of the collected object are also included, the latitude and longitude are converted into a hash value through a geohash algorithm, and the hash value are stored in corresponding databases together.
The computing principle of the geohash algorithm is as follows: the known latitude range is [ -90,90], and the longitude range is [ -180,180] ]; firstly, dividing a latitude range (-90,90) into a left interval and a right interval (-90,0) and (0,90), if the latitude value of the data is positioned in the left interval, coding the latitude value into 0, otherwise, coding the latitude value into 1; if the point location latitude value is in the right interval, continuing to divide (0,90) into (0,45) and (45,90) left and right intervals; if the left interval is located, the code is 0, otherwise, the code is 1; similarly, if the point latitude value is in the first interval, (0,45) is further divided into (0,22.5) and (22.5, 45). And analogizing in turn, calculating binary codes of the longitude and latitude, and combining the longitude and latitude codes from high to low after calculating the longitude and latitude codes, wherein odd numbers are longitudes and even numbers are latitudes. The detailed coding interval and the coding details are not described herein, as should be understood by those skilled in the art.
The invention provides a data association analysis method, which is applied to a server side and can provide a concrete method basis for data analysis for a data analysis server;
the specific steps of the method are shown in figure 3,
step S301, in response to an instruction of performing data association on an associated object, searching clustering data information obtained by aggregating different types of data of the associated object in a database, wherein the different types of data comprise hash values obtained by converting longitude and latitude of collected data of each type through a geohash algorithm;
after logging in the data association platform through the terminal, sending an instruction for performing data association on the associated object to the data analysis server through the data association platform, and searching cluster data information obtained by aggregating different types of data of the associated object in the database by the data analysis server in response to the instruction for performing data association on the associated object.
The terminal associates the corresponding name of the object by inputting to the data association platform, the data analysis server extracts the different types of data information about the object from the database by responding to the name of the associated object,
specific different types of data information include: monitoring data acquired by the monitoring data acquisition equipment and terminal interaction acquisition data acquired by the terminal interaction acquisition equipment;
the monitoring class data includes: vehicle passing card port picture data, human face snapshot data and monitoring video data
The terminal interactive data acquisition comprises the following steps: WIFI probe data, RFID acquisition data and electronic fence data.
Specifically, the car passing card port picture data comprises: the system is mainly used for collecting the license plate number of the vehicle, the facial pictures of a driver and passengers in the vehicle, and the specific information such as the vehicle speed, the vehicle model and the vehicle color;
the face snapshot data includes: the method comprises the steps that the collected main target is a human face, and clustering analysis is carried out on the human face by collecting characteristic information of the human face, such as skin color, human face characteristics, hair length and other detailed information;
monitoring video data includes: the method is used for collecting appearance information such as the advancing speed, the step size, the height, the fat and thin degree, the appearance characteristics and the like of a person.
The WIFI probe data is information such as a mac address of the terminal equipment and an equipment IMEI code acquired by a terminal connected with the WIFI probe;
the RFID data acquisition is specifically time and longitude and latitude information obtained when an analysis object passes through an RFID detection gateway when carrying an RFID label;
the detection mode of the electronic fence data is similar to that of the RFID, an electronic fence equipment area is set, and when equipment exceeds the coverage area of the electronic fence, the electronic fence records the passing time and the longitude and latitude information of the equipment
The specific type of the associated object may be: the system comprises human face portrait or identity data, terminal mac address data and vehicle data, wherein the identity data can be virtual identity information, an identity card number or human face structural information and the like, the vehicle data can be a license plate number or a motor vehicle code number and the like of a vehicle, and the terminal data can be equipment mac address information of a terminal acquired by RFID equipment or WiFi probe equipment. When different types of data are collected, the longitude and latitude of the data are included, the longitude and latitude are calculated through a geohash algorithm to obtain hash values corresponding to the longitude and latitude, and all information and hash value data related to the input associated object information are extracted from a clustering data information database based on the input associated object information.
For example: inputting the identification number of a person into the data association platform, acquiring all data information of the person corresponding to the identification number by the data association platform, such as face data information corresponding to the identification number, vehicle data information corresponding to the identification number and terminal data information of a mobile phone corresponding to the identification number, and importing data with a hash value into the data analysis platform to construct a space-time trajectory.
Step S302, constructing a first spatiotemporal trajectory of the associated object according to the found hash value in the clustering data information;
and each hash value corresponds to latitude and longitude information, and first track information of the associated object is established according to all hash values of the associated object. The establishment mode can be that, as an optional implementation mode, the near connection can be carried out according to the longitude and latitude information of the hash value to construct a complete space-time trajectory;
as another optional implementation, the complete spatiotemporal trajectory may be constructed by connecting the longitude and latitude points corresponding to each hash value according to the time of the acquired data corresponding to each hash value and the time sequence of the acquired data.
Because the quantity of the acquired data is not fixed, a threshold value for constructing the space-time trajectory can be set, and because too few acquisition points increase errors, when the hash value trace points of the associated object are too few, the corresponding space-time trajectory of the associated object is not established.
Referring to fig. 4, a spatiotemporal trajectory is formed by sequentially connecting longitude and latitude points corresponding to hash values in a time sequence, where a start point 301, a first intermediate point 302, a second intermediate point 303, a third intermediate point 304, a fourth intermediate point 305, a fifth intermediate point 306, and an end point 307, together form a spatiotemporal trajectory of an associated object, where the diagram is only used as a reference position point and is not limited to the establishment of a spatiotemporal trajectory using several trajectory points.
Step S303, determining track points of at least one detection object which meet association conditions with the track points based on the track points in the first space-time track, and constructing a second space-time track belonging to the same detection object;
as an optional implementation manner, the condition that the track point satisfies the association is specifically that the track points of other detection objects appearing in the same time period and the same spatial range of the associated object are the track points satisfying the association condition.
As another alternative, the spatio-temporal trajectory established for certain specific trajectory points may also be determined according to the requirement and the calculation speed without being limited too much.
In the first embodiment, the same time period may be, the track point acquisition time-fixed time difference in the first space-time trajectory is a start time of the same time interval, and the track point acquisition time + fixed time difference in the first space-time trajectory is an end time of the same time interval, where a duration of the fixed time difference is determined according to a moving speed difference between the associated object and the detection object. For example, the types of the associated object and the detection object are both human, and the fixed time difference is set to a longer time, such as 3 minutes, because the traveling speed of the human is relatively slow, and if the types of the associated object and the detection object are different, such as human and vehicle, because the traveling speed difference is large, the fixed time difference is set to a shorter time, such as 1 minute, and the duration of the fixed time difference is not limited to the specific time described in the embodiment.
And determining the track points of the detection objects in the same space range as the track points of at least one detection object which meet the association conditions with the track points in the first space-time trajectory.
As an optional implementation manner, the position of the track point in the first space-time trajectory is used as the central point of the squared difference of the hash value, and the area in the squared difference corresponding to the central point is determined to be the spatial range in which the track point in the first space-time trajectory is located.
For example, as shown in fig. 5, WX4G0 is the center point of the hash value squared table at the center of the track point, and the squared table centered on the hash value at the center of the track point is the spatial range of the track point.
As another optional implementation, a fixed latitude and longitude range interval may be set, and the track point in the range interval is marked as being in the same track range as the track point.
As shown in fig. 6a, the trace points of other detection objects collected in the same time period with the starting point 301 are shown;
wherein there are a plurality of other trace points in the graph that are in the same time range as the trace point.
Fig. 6b shows a plurality of other trace points in the same spatial range as the trace point, where the trace points are acquired in the same spatial range as the starting point 301.
As shown in fig. 6C, after the time condition and the space condition are combined for screening, the trace points a, B, and C of all other detection objects that satisfy the two range conditions simultaneously;
after track points of which the associated objects meet the association conditions are obtained, all track point information of the objects corresponding to the track points A, B and C is obtained from the clustering data information database, and the time-space track corresponding to the track points A, B, C is calculated and established according to the track point information.
Step S304, determining the detection object corresponding to the second spatiotemporal trajectory with the similarity of the first spatiotemporal trajectory being greater than the similarity threshold as the detection object having the association relation with the association object.
Firstly, setting a similarity threshold, and judging that the correlation object corresponding to the first space-time trajectory and the detection object corresponding to the second space-time trajectory have a correlation relationship when the similarity between the first space-time trajectory and the second space-time trajectory is greater than the similarity threshold and greater than the similarity.
Specifically, as an optional implementation manner, the track similarity calculation method adopts a DTW similarity calculation method to perform similarity measurement calculation, and performs similarity calculation on two sequences with different lengths.
For example, the sequence of all trace points of the associated object is P ═ P1, P2, … …, pm }, P is the set of all trace points of the associated spatio-temporal trajectory sequence, P1 represents the first trace point in the spatio-temporal trajectory of the associated object, pm represents the mth trace point in the spatio-temporal trajectory of the associated object, and the sequence of all trace points of the detected object is Q ═ { Q1, Q1, … …, qn } Q is the set of all trace points of the detected spatio-temporal trajectory sequence, wherein Q1 represents the first trace point in the spatio-temporal trajectory of the detected object, pm represents the mth trace point in the spatio-temporal trajectory of the detected object, the distance between the corresponding associated trace point and the detected trace point is calculated as follows,
wherein dist (p)i,qj) Representing the Euclidean distance in space of two tracing points, the Euclidean distance being the "ordinary" (i.e. straight line) distance between two points in Euclidean space, and D (p)i,qj) Indicating the distance of two different data sources,
for example, when piAnd q isjWhen the motion types of the locus points are consistent, such as vehicle checkpoints, the same type of distance range threshold value is taken, for example, D (p)i,qj)＝1km；
When p isiAnd q isjWhen the motion types of the point locations of the track are inconsistent, such as vehicles and people respectively, different types of distance range thresholds are adopted, for example, D (p)i,qj)＝3km；
When p isiAnd q isjWhen the types of the track points are the human face and the vehicle in the same vehicle, the threshold value of the distance range in the same vehicle is taken, for example, D (p)i,qj)＝0.1km；
Wherein time dist (p)i,qj) Representing the temporal distance in space of two trace points, T (p)i,qj) Representing the temporal distance of two different data sources.
For example, when piAnd q isjWhen the motion types of the locus points are consistent, such as vehicle gates, the same type of time range threshold value, such as T (p)i,qj)＝1min；
When p isiAnd q isjWhen the types of motion of the locus points are not consistent, e.g. divideFor vehicles and persons, respectively, different types of time range thresholds are taken, e.g. T (p)i,qj)＝3min；
When p isiAnd q isjWhen the types of the track points are the human face in the same vehicle and the vehicle, a time range threshold value in the same vehicle is taken, such as T (p)i,qj)＝0.1min；
When p isiAnd q isjWhen the track points simultaneously satisfy the distance range threshold value and the time range threshold value, the set of track points (p) is recordedi,qj) Is 1, otherwise the distance is noted as 0.
And sequentially calculating the distances between all track points of the associated object and all track points of the detected object.
The final trajectory similarity is calculated by the following formula:
wherein
The sum of the distances between all track points of the associated object and all track points of the detected object is calculated.
While
The distance sum of all track points of the associated object and the distance sum of all track points of the detected object are smaller.
And when sim (P, Q) is larger than the track similarity threshold, judging that the association relation exists between the associated object and the detection object.
As another optional implementation manner, by analyzing the co-occurrence times of the track points of the associated object and the detected object, when the co-occurrence times exceeds a preset threshold, it is recorded that the associated object and the detected object have an association relationship
And when all the related detection objects are judged, sending the information of all the detection objects to the data related platform, and displaying the co-occurrence times of the data on the data related platform according to the distance value.
As an optional implementation manner, on the data association platform, by clicking a data co-occurrence number option, the data association platform may specifically display longitude and latitude and relative position information of each co-occurrence of the detection object and the associated object on the simulated map.
As another optional implementation manner, when the track point number of the detection object is less than the track point number threshold, the co-occurrence information of the detection object may also be sent to the data association platform, but it is not determined that the detection object and the association object have a direct association relationship.
As shown in fig. 7, the interface diagram is an interface diagram of a data association platform, where an association object input field 701 is used to input a virtual identity corresponding to a detection object, a detection object specific information field 702 is used to display co-occurrence times and the virtual identity of the detection object, and a specific trend diagram of a spatiotemporal trajectory displayed by a detection object spatiotemporal trajectory diagram 703.
As an optional implementation manner, when various types of data access the data analysis server, the different types of data may be preprocessed, and according to object identification information in the different types of data, all types of data belonging to the same object are aggregated to obtain clustered data information of the object, and the clustered data information is sent to the database.
After a big data platform in a data analysis server receives different types of structured data, the method for preprocessing the different types of data specifically comprises the following steps:
filtering the different types of data according to the filtering rules of the different types of data;
specifically, the data filtering process mainly performs filtering operation on data which does not meet the standard specification or is invalid in the service data. Defining a filtering rule of the data before data integration, and setting an error level of the data according with the filtering rule. When data meeting the cleaning rule is encountered in the data integration process, the system sets the service data as problem data and classifies the data according to the severity of errors.
For example: filtering the picture with too low pixel value or blur in the bayonet picture, for example, classifying the picture with ghost or blur in the face picture as a general error type, classifying the picture as a serious error type when the face does not appear in the face picture, converting the data into a problem data type, and storing the problem data type in an error type database.
Carrying out data format conversion, code conversion and value conversion on the different types of data after the filtering operation, and unifying the different types of data into code identification data;
because the data types extracted by the big data platform have various forms, the data needs to be subjected to unified data format, for example, the birth date of a person is unified into eight-bit character date for format conversion; the sex data of the personnel is converted into national standard sex codes or the identification number of the personnel is converted into 18-bit identification number for conversion.
And defining the hash value and the code identification data as preprocessing information of each type of data according to the hash value obtained by converting the longitude and latitude information of different types of data through a geohash algorithm.
Specifically, the two-dimensional longitude and latitude are converted into the one-dimensional hash value by using the Geohash algorithm, the complexity is reduced to O (N) by adopting the hash to carry out complexity calculation, and compared with the original data correlation, the complexity of the calculation is O (N) because the two-dimensional data correlation is carried out by the longitude and latitude2) Thus reducing the computational complexity.
Example 2
The embodiment of the invention provides a device for data association analysis, which comprises the following modules:
a cluster data information obtaining module 801, configured to search cluster data information obtained by aggregating different types of data of an associated object in a database in response to an instruction for performing data association on the associated object, where the different types of data include hash values obtained by converting longitudes and latitudes of acquired data of each type by a geohash algorithm;
a first spatiotemporal trajectory establishing module 802, configured to construct a first spatiotemporal trajectory of the associated object according to the found hash value in the clustered data information;
a second spatiotemporal trajectory establishing module 803, configured to determine, based on the trajectory points in the first spatiotemporal trajectory, trajectory points of at least one detection object that satisfy an association condition with the trajectory points, and construct a second spatiotemporal trajectory that belongs to the same detection object;
an association detection module 804, configured to determine a detection object corresponding to the second spatio-temporal trajectory, where a similarity of the first spatio-temporal trajectory is greater than a similarity threshold, as a detection object having an association relationship with the association object.
Optionally, the apparatus further includes a data obtaining module 805, configured to obtain different types of data, where the different types of data include monitoring data collected by a monitoring device and terminal data collected by a terminal associated with the object through interaction, and the different types of data include object identification information and a hash value obtained by converting longitude and latitude of the collected type of data by a geohash algorithm;
and after preprocessing the different types of data, aggregating all types of data belonging to the same object according to the object identification information in the different types of data to obtain the cluster data information of the associated object, and sending the cluster data information to a database.
Optionally, the second spatio-temporal trajectory creation module 803 is specifically configured to,
the determining the track point of at least one detection object which meets the association condition with the track point comprises the following steps:
and determining the track points of the detection object with the acquisition time in the same time interval as the acquisition time of the track points in the first space-time trajectory as the track points of at least one detection object meeting the association condition with the track points in the first space-time trajectory.
Optionally, the second spatiotemporal trajectory creating module 803 is specifically configured to determine that a fixed time difference is subtracted from the trace point acquisition time in the first spatiotemporal trajectory, determine, as the start time of the same time interval, that a fixed time difference is added to the trace point acquisition time in the first spatiotemporal trajectory, and determine, as the end time of the same time interval, a duration of the fixed time difference according to the difference between the moving speeds of the associated object and the detection object.
Optionally, the second spatio-temporal trajectory creation module 803 is specifically configured to,
determining the track point of at least one detection object meeting the association condition with the track point, wherein the method comprises the following steps:
and determining the track points of the detection object with the position in the same space range as the position of the track points in the first space-time trajectory into the track points of at least one detection object which meets the association condition with the track points in the first space-time trajectory.
Optionally, the second spatio-temporal trajectory creation module 803 is specifically configured to,
and taking the position of the track point in the first space-time track as the central point of the hash value squared figure, and determining the area where the hash value squared figure corresponding to the central point is located, wherein the area is the space range where the track point in the first space-time track is located.
Optionally, the association detection module 804 is specifically configured to,
when the motion modes of the associated object and the detection object are the same, calculating the track similarity of the associated object and the detection object by using a track similarity calculation formula corresponding to the same motion mode;
and when the motion modes of the associated object and the detection object are different, calculating the track similarity of the associated object and the detection object by using track similarity calculation formulas corresponding to different motion modes.
Optionally, the clustering data information obtaining module 801 is specifically configured to, where the method for preprocessing the different types of data includes:
filtering the different types of data according to a preset filtering rule;
and performing data format conversion, code conversion and value conversion on the different types of data after the filtering operation to unify the different types of data into code identification data.
Example 3
The embodiment of the invention provides a data association analysis device, which comprises a processor and a memory, wherein the memory is stored with a computer program, and the processor is used for executing a method for the data association analysis of the computer program in the memory;
responding to an instruction of performing data association on an associated object, and searching clustering data information obtained by aggregating different types of data of the associated object in a database, wherein the different types of data comprise hash values obtained by converting longitude and latitude of each type of data acquired through a geohash algorithm;
constructing a first spatiotemporal trajectory of the associated object according to the found hash value in the clustering data information;
determining track points of at least one detection object meeting association conditions with the track points based on the track points in the first space-time track, and constructing a second space-time track belonging to the same detection object;
and determining the detection object corresponding to the second spatio-temporal trajectory with the similarity of the first spatio-temporal trajectory being greater than a similarity threshold as the detection object having the association relation with the associated object.
As shown in fig. 9, wherein the apparatus 900 may have relatively large differences due to different configurations or performances, the apparatus may include one or more Central Processing Units (CPUs) 901 (e.g., one or more processors) and a memory 902, one or more storage media 903 (e.g., one or more mass storage devices) for storing applications 904 or data 905. Memory 902 and storage medium 903 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 903 may include one or more modules (not shown), and each module may include a series of instruction operations in the information processing apparatus. Still further, the central processor 901 may be arranged to communicate with the storage medium 903, and execute a series of instruction operations in the storage medium 903 on the apparatus 900.
The device 900 may also include one or more power supplies 906, one or more wired or wireless network interfaces 907, one or more input-output interfaces 908, and/or one or more operating systems 909, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.
Example 4
The invention provides a computer program medium, wherein the computer program medium stores computer instructions, and the computer instructions are executed by a processor to provide the data correlation analysis method provided by the embodiment.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (11)
1. A data association analysis method is characterized by comprising the following steps:
responding to an instruction of performing data association on an associated object, and searching clustering data information obtained by aggregating different types of data of the associated object in a database, wherein the different types of data comprise hash values obtained by converting longitude and latitude of each type of data acquired through a geohash algorithm;
constructing a first spatiotemporal trajectory of the associated object according to the found hash value in the clustering data information;
determining track points of at least one detection object meeting association conditions with the track points based on the track points in the first space-time track, and constructing a second space-time track belonging to the same detection object;
and determining the detection object corresponding to the second spatio-temporal trajectory with the similarity of the first spatio-temporal trajectory being greater than a similarity threshold as the detection object having the association relation with the associated object.
2. The method of claim 1, further comprising:
acquiring different types of data, wherein the different types of data comprise monitoring data acquired through monitoring equipment and terminal data acquired through terminal interaction associated with the object, and the different types of data comprise object identification information and a hash value obtained by converting the longitude and latitude of the acquired type of data through a geohash algorithm;
and after preprocessing the different types of data, aggregating all types of data belonging to the same object according to the object identification information in the different types of data to obtain the cluster data information of the associated object, and sending the cluster data information to a database.
3. The method according to claim 1 or 2, wherein the determining the track point of the at least one detection object which satisfies the association condition with the track point comprises:
and determining the track points of the detection object with the acquisition time in the same time interval as the acquisition time of the track points in the first space-time trajectory as the track points of at least one detection object meeting the association condition with the track points in the first space-time trajectory.
4. The method of claim 3, further comprising:
and determining the track point acquisition time in the first space-time trajectory minus a fixed time difference, determining the track point acquisition time in the first space-time trajectory plus the fixed time difference as the starting time of the same time interval, and determining the ending time of the same time interval, wherein the duration of the fixed time difference is determined according to the moving speed difference of the associated object and the detection object.
5. The method according to claim 1 or 2, wherein the determining of the track point of the at least one detection object which satisfies the association condition with the track point comprises:
and determining the track points of the detection object with the position in the same space range as the position of the track points in the first space-time trajectory into the track points of at least one detection object which meets the association condition with the track points in the first space-time trajectory.
6. The method of claim 5, further comprising:
and taking the position of the track point in the first space-time track as the central point of the hash value squared figure, and determining the area where the hash value squared figure corresponding to the central point is located, wherein the area is the space range where the track point in the first space-time track is located.
7. The method of claim 1, further comprising:
when the motion modes of the associated object and the detection object are the same, calculating the track similarity of the associated object and the detection object by using a track similarity calculation formula corresponding to the same motion mode;
and when the motion modes of the associated object and the detection object are different, calculating the track similarity of the associated object and the detection object by using track similarity calculation formulas corresponding to different motion modes.
8. The method of claim 2, wherein the method of preprocessing the different types of data comprises:
filtering the different types of data according to a preset filtering rule;
and performing data format conversion, code conversion and value conversion on the different types of data after the filtering operation to unify the different types of data into code identification data.
9. An apparatus for data association analysis, the apparatus comprising:
the system comprises a clustering data information acquisition module, a data association module and a data association module, wherein the clustering data information acquisition module is used for responding to an instruction of performing data association on an associated object and searching clustering data information obtained by aggregating different types of data of the associated object in a database, and the different types of data comprise hash values obtained by converting longitude and latitude of collected data through a geohash algorithm;
the first space-time trajectory establishing module is used for establishing a first space-time trajectory of the associated object according to the found hash value in the clustering data information;
the second space-time track establishing module is used for determining track points of at least one detection object meeting the association condition with the track points based on the track points in the first space-time track and establishing a second space-time track belonging to the same detection object;
and the association detection module is used for determining a detection object corresponding to the second spatiotemporal trajectory, of which the similarity with the first spatiotemporal trajectory is greater than a similarity threshold, as a detection object having an association relationship with the association object.
10. An apparatus for data association analysis, comprising a processor and a memory, the memory having stored therein a computer program, the processor being configured to execute the computer program in the memory, the computer program being configured to perform the method of data association analysis according to any one of claims 1 to 9.
11. A computer program medium, wherein the computer readable storage medium stores computer instructions which, when executed by a processor, implement a data association analysis method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911039044.4A CN110874362A (en) | 2019-10-29 | 2019-10-29 | Data association analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911039044.4A CN110874362A (en) | 2019-10-29 | 2019-10-29 | Data association analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110874362A true CN110874362A (en) | 2020-03-10 |
Family
ID=69717917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911039044.4A Pending CN110874362A (en) | 2019-10-29 | 2019-10-29 | Data association analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110874362A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241117A (en) * | 2020-03-15 | 2020-06-05 | 智博云信息科技(广州)有限公司 | Epidemic situation database updating method and device |
| CN111370139A (en) * | 2020-05-26 | 2020-07-03 | 第四范式（北京）技术有限公司 | Infectious disease tracing method and device, electronic equipment and storage medium |
| CN111476616A (en) * | 2020-06-24 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Trajectory determination method and apparatus, electronic device and computer storage medium |
| CN111651527A (en) * | 2020-04-21 | 2020-09-11 | 高新兴科技集团股份有限公司 | Identity association method, device, equipment and storage medium based on track similarity |
| CN112148808A (en) * | 2020-09-28 | 2020-12-29 | 杭州海康威视系统技术有限公司 | Relationship construction method and device and electronic equipment |
| CN112487256A (en) * | 2020-12-10 | 2021-03-12 | 中国移动通信集团江苏有限公司 | Object query method, device, equipment and storage medium |
| CN112632316A (en) * | 2020-12-21 | 2021-04-09 | 杭州海康威视系统技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112818173A (en) * | 2021-01-21 | 2021-05-18 | 浙江大华技术股份有限公司 | Method and device for identifying associated object and computer readable storage medium |
| CN113468283A (en) * | 2021-06-29 | 2021-10-01 | 北京市商汤科技开发有限公司 | Data processing method, device, equipment and storage medium |
| CN113495270A (en) * | 2020-04-07 | 2021-10-12 | 富士通株式会社 | Monitoring device and method based on microwave radar |
| CN113706574A (en) * | 2020-05-20 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Movement track determining method and device, electronic equipment and storage medium |
| CN113788051A (en) * | 2021-10-26 | 2021-12-14 | 成都运达科技股份有限公司 | Train on-station running state monitoring and analyzing system |
| WO2023273292A1 (en) * | 2021-06-30 | 2023-01-05 | 深圳市城市交通规划设计研究中心股份有限公司 | Resident trip chain generation method based on multi-source data fusion, and vehicle-sharing query method |
| CN116383264A (en) * | 2022-12-26 | 2023-07-04 | 北京码牛科技股份有限公司 | Method and system for continuously mining association behaviors hidden intentionally based on space-time behaviors |
| WO2023125840A1 (en) * | 2021-12-31 | 2023-07-06 | 深圳云天励飞技术股份有限公司 | Personnel association degree analysis method, apparatus, electronic device and storage medium |
| CN116450878A (en) * | 2023-06-15 | 2023-07-18 | 北京瑞莱智慧科技有限公司 | Activity track determining method, activity track determining device, computer equipment and readable storage medium |
| CN117454199A (en) * | 2023-12-20 | 2024-01-26 | 北京数原数字化城市研究中心 | Track association method, system, electronic device and readable storage medium |
| CN117876980A (en) * | 2024-03-12 | 2024-04-12 | 浙江大华技术股份有限公司 | Track construction method |
| CN112487256B (en) * | 2020-12-10 | 2024-05-24 | 中国移动通信集团江苏有限公司 | Object query method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140314275A1 (en) * | 2013-04-19 | 2014-10-23 | Polaris Sensor Technologies, Inc. | Pedestrian Right of Way Monitoring and Reporting System and Method |
| CN107590250A (en) * | 2017-09-18 | 2018-01-16 | 广州汇智通信技术有限公司 | A kind of space-time orbit generation method and device |
| CN108255947A (en) * | 2017-12-13 | 2018-07-06 | 太极计算机股份有限公司 | Portray method, apparatus, mobile terminal and the storage medium of personnel motion trail |
| CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
| CN109977108A (en) * | 2019-04-03 | 2019-07-05 | 深圳市甲易科技有限公司 | A kind of a variety of track collision analysis methods in Behavior-based control track library |
| CN110334111A (en) * | 2019-06-13 | 2019-10-15 | 武汉市公安局视频侦查支队 | A kind of multidimensional trajectory analysis method and device |
-
2019
- 2019-10-29 CN CN201911039044.4A patent/CN110874362A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140314275A1 (en) * | 2013-04-19 | 2014-10-23 | Polaris Sensor Technologies, Inc. | Pedestrian Right of Way Monitoring and Reporting System and Method |
| CN107590250A (en) * | 2017-09-18 | 2018-01-16 | 广州汇智通信技术有限公司 | A kind of space-time orbit generation method and device |
| CN108255947A (en) * | 2017-12-13 | 2018-07-06 | 太极计算机股份有限公司 | Portray method, apparatus, mobile terminal and the storage medium of personnel motion trail |
| CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
| CN109977108A (en) * | 2019-04-03 | 2019-07-05 | 深圳市甲易科技有限公司 | A kind of a variety of track collision analysis methods in Behavior-based control track library |
| CN110334111A (en) * | 2019-06-13 | 2019-10-15 | 武汉市公安局视频侦查支队 | A kind of multidimensional trajectory analysis method and device |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241117A (en) * | 2020-03-15 | 2020-06-05 | 智博云信息科技(广州)有限公司 | Epidemic situation database updating method and device |
| CN113495270A (en) * | 2020-04-07 | 2021-10-12 | 富士通株式会社 | Monitoring device and method based on microwave radar |
| CN111651527A (en) * | 2020-04-21 | 2020-09-11 | 高新兴科技集团股份有限公司 | Identity association method, device, equipment and storage medium based on track similarity |
| CN113706574B (en) * | 2020-05-20 | 2024-01-02 | 杭州海康威视数字技术股份有限公司 | Method and device for determining moving track, electronic equipment and storage medium |
| CN113706574A (en) * | 2020-05-20 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Movement track determining method and device, electronic equipment and storage medium |
| CN111370139A (en) * | 2020-05-26 | 2020-07-03 | 第四范式（北京）技术有限公司 | Infectious disease tracing method and device, electronic equipment and storage medium |
| CN112530600A (en) * | 2020-05-26 | 2021-03-19 | 第四范式（北京）技术有限公司 | Infectious disease tracing method and device, electronic equipment and storage medium |
| CN111476616A (en) * | 2020-06-24 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Trajectory determination method and apparatus, electronic device and computer storage medium |
| CN112148808A (en) * | 2020-09-28 | 2020-12-29 | 杭州海康威视系统技术有限公司 | Relationship construction method and device and electronic equipment |
| CN112148808B (en) * | 2020-09-28 | 2024-02-27 | 杭州海康威视系统技术有限公司 | Relationship construction method and device and electronic equipment |
| CN112487256A (en) * | 2020-12-10 | 2021-03-12 | 中国移动通信集团江苏有限公司 | Object query method, device, equipment and storage medium |
| CN112487256B (en) * | 2020-12-10 | 2024-05-24 | 中国移动通信集团江苏有限公司 | Object query method, device, equipment and storage medium |
| CN112632316A (en) * | 2020-12-21 | 2021-04-09 | 杭州海康威视系统技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112632316B (en) * | 2020-12-21 | 2023-03-14 | 杭州海康威视系统技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112818173A (en) * | 2021-01-21 | 2021-05-18 | 浙江大华技术股份有限公司 | Method and device for identifying associated object and computer readable storage medium |
| CN113468283A (en) * | 2021-06-29 | 2021-10-01 | 北京市商汤科技开发有限公司 | Data processing method, device, equipment and storage medium |
| WO2023273292A1 (en) * | 2021-06-30 | 2023-01-05 | 深圳市城市交通规划设计研究中心股份有限公司 | Resident trip chain generation method based on multi-source data fusion, and vehicle-sharing query method |
| CN113788051A (en) * | 2021-10-26 | 2021-12-14 | 成都运达科技股份有限公司 | Train on-station running state monitoring and analyzing system |
| WO2023125840A1 (en) * | 2021-12-31 | 2023-07-06 | 深圳云天励飞技术股份有限公司 | Personnel association degree analysis method, apparatus, electronic device and storage medium |
| CN116383264B (en) * | 2022-12-26 | 2023-12-01 | 北京码牛科技股份有限公司 | Method and system for continuously mining association behaviors hidden intentionally based on space-time behaviors |
| CN116383264A (en) * | 2022-12-26 | 2023-07-04 | 北京码牛科技股份有限公司 | Method and system for continuously mining association behaviors hidden intentionally based on space-time behaviors |
| CN116450878B (en) * | 2023-06-15 | 2023-09-05 | 北京瑞莱智慧科技有限公司 | Activity track determining method, activity track determining device, computer equipment and readable storage medium |
| CN116450878A (en) * | 2023-06-15 | 2023-07-18 | 北京瑞莱智慧科技有限公司 | Activity track determining method, activity track determining device, computer equipment and readable storage medium |
| CN117454199A (en) * | 2023-12-20 | 2024-01-26 | 北京数原数字化城市研究中心 | Track association method, system, electronic device and readable storage medium |
| CN117876980A (en) * | 2024-03-12 | 2024-04-12 | 浙江大华技术股份有限公司 | Track construction method |
| CN117876980B (en) * | 2024-03-12 | 2024-05-28 | 浙江大华技术股份有限公司 | Track construction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110874362A (en) | Data association analysis method and device | |
| US20220114735A1 (en) | Trajectory cluster model for learning trajectory patterns in video data | |
| CN102843547B (en) | Intelligent tracking method and system for suspected target | |
| CN111476183A (en) | Passenger flow information processing method and device | |
| CN112434566B (en) | Passenger flow statistics method and device, electronic equipment and storage medium | |
| CN110659391A (en) | Video detection method and device | |
| CN116824859B (en) | Intelligent traffic big data analysis system based on Internet of things | |
| CN109740479A (en) | A kind of vehicle recognition methods, device, equipment and readable storage medium storing program for executing again | |
| KR102333143B1 (en) | System for providing people counting service | |
| CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
| CN111586367A (en) | Method, system and terminal equipment for positioning and tracking personnel in space area in real time | |
| CN115167530B (en) | Live working investigation data processing method and system based on multi-dimensional sensing | |
| CN112364176A (en) | Method, equipment and system for constructing personnel action track | |
| CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
| CN114372503A (en) | Cluster vehicle motion trail prediction method | |
| CN111709382A (en) | Human body trajectory processing method and device, computer storage medium and electronic equipment | |
| CN114937293A (en) | Agricultural service management method and system based on GIS | |
| WO2020210960A1 (en) | Method and system for reconstructing digital panorama of traffic route | |
| CN114140719A (en) | AI traffic video analysis technology | |
| CN111738558A (en) | Behavior risk recognition visualization method, behavior risk recognition visualization device, behavior risk recognition equipment and storage medium | |
| CN106454233A (en) | Intelligent crowd-gathering monitoring method and system | |
| CN112732446B (en) | Task processing method and device and storage medium | |
| US20200164509A1 (en) | Systems and methods for enhanced review of automated robotic systems | |
| CN113743380B (en) | Active tracking method based on video image dynamic monitoring | |
| CN112102398B (en) | Positioning method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200310 |