Crowd movement track analysis method and device

Abstract

The crowd movement trajectory analysis method comprises the following steps: acquiring time-space position information of a user in a target research area, and performing data preprocessing on the acquired information; constructing a network structure based on the preprocessed data; nodes of the network structure are blocks of the target research area, and edges of the network structure are moving tracks of the user; the weight of the edge is based on user movement frequency or space-time relevance; obtaining an index of a block association rule based on the constructed network structure; and based on the obtained indexes, determining the space relation between the blocks and the crowd behavior mode. By means of the method, the accuracy, real-time performance and interpretability of movement track correlation analysis can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular, to a method and device for analyzing the movement trajectories of a crowd. Background Art

[0002] In traditional geographic information system research, people often only focus on the analysis of the attributes and spatial information in the geographical space at a certain moment. This actually only describes the breakpoint phenomenon of the research object and does not specifically process continuous temporal data. However, time, space, and attributes are the inherent basic characteristics of geographical entities and geographical phenomena themselves, and are important components reflecting the state and evolution process of geographical entities. With the popularization of urban perception networks and mobile terminal devices, the collection and analysis of crowd movement trajectory data have become key technologies in fields such as smart cities, traffic planning, and public safety. The spatio-temporal trajectory of crowd movement is a sequence of records of the position and time of moving objects. As an important spatio-temporal object data type and information source, the application scope of spatio-temporal trajectories covers many aspects of human behavior. By analyzing spatio-temporal trajectory data, the similarities and abnormal features in the spatio-temporal trajectory data can be extracted, and it is helpful to discover meaningful patterns therein.

[0003] In some known technologies, spatio-temporal trajectory analysis technologies mainly include hotspot area identification and critical path analysis based on community discovery, using spatio-temporal clustering algorithms such as DBSCAN and ST-DBSCAN to extract frequent movement patterns, or using hidden Markov models for trajectory prediction. Traditional Apriori algorithms and their improved schemes are used to discover frequent item sets in mobile behaviors, etc. However, there are still many problems with these current methods. For example, traditional association rule algorithms do not consider the spatio-temporal continuity characteristics of movement trajectories and have limited ability to discover implicit associations in sparse trajectory data; existing complex network models are mostly based on static topological structures and are difficult to reflect the spatio-temporal evolution characteristics of crowd movement patterns in real time; current methods are mostly targeted at specific scenarios and lack a unified multi-scale association rule mining framework; the interpretability is insufficient. Although deep learning models can improve the prediction accuracy, it is difficult to provide rule explanations with spatial semantics. Summary of the Invention

[0004] In order to solve the problems existing in the prior art, the embodiments of the present application provide a method, device, computing device, computer storage medium, and product including a computer program for analyzing the movement trajectories of a crowd, which can effectively improve the accuracy, real-time performance, and interpretability of mobile trajectory association analysis.

[0005] In a first aspect, an embodiment of the present application provides a method for analyzing the movement trajectories of a population, including: obtaining the spatio-temporal location information of users in a target research area, and performing data preprocessing on the obtained information; constructing a network structure based on the preprocessed data; the nodes of the network structure are the blocks in the target research area, and the edges are the movement trajectories of users; the weights of the edges are based on the user movement frequency or spatio-temporal correlation; obtaining the indicators of the block association rules based on the constructed network structure; and determining the spatial connections and population behavior patterns between blocks based on the obtained indicators.

[0006] In some possible embodiments, obtaining the spatio-temporal location information of users in a target research area and performing data preprocessing on the obtained information is specifically: obtaining the user ID, as well as the timestamp, longitude, and latitude information of the user in the target research area; performing data preprocessing on the obtained information, including deleting the information of local aborigines whose place of residence is local, removing duplicate records at the same spatial location within a preset time period, and retaining the last piece of data as valid data.

[0007] In some possible embodiments, the indicators of the block association rules include at least one of support, confidence, and lift, and the indicators are used to measure the association strength and pattern between nodes to analyze the population spatial behavior pattern.

[0008] In some possible embodiments, the constructed network structure is used to confirm the key nodes in the nodes, which is confirmed by judging the indicators, and the judging indicators include at least one of degree centrality, closeness centrality, and betweenness centrality.

[0009] In some possible embodiments, the degree centrality is calculated according to the following formula:

[0010] C = deg(X) / N - 1

[0011] In the formula, C represents the degree centrality, deg represents the degree of node x, x represents a node based on the network structure, N represents the number of nodes in the network structure, and N > 1.

[0012] In some possible embodiments, the closeness centrality is calculated according to the following formula:

[0013]

[0014] In the formula, C(u) represents the closeness centrality, u represents the node for which the closeness centrality is to be calculated, n represents the total number of nodes, and d(u, v) represents the shortest distance between node v and node u.

[0015] In some possible embodiments, the betweenness centrality is calculated according to the following formula:

[0016]

[0017] where C(b) i represents the betweenness centrality, and σ mn represents the number of shortest paths between node m and node n, and σ mn (i) represents the number of shortest paths from node m to node n passing through node i, and G represents the set of nodes.

[0018] In some possible embodiments, the method further includes: performing hierarchical clustering on the blocks in the target research area, including: performing hierarchical clustering on the blocks in the target research area to determine the first clustering result;

[0019] Based on the first clustering result, performing a second-layer binary K-means clustering based on the block load capacity index to determine the second clustering result; merging the first clustering result and the second clustering result to determine the final block classification.

[0020] In some possible embodiments, the method further includes: constructing a two-mode heterogeneity network, where one type of node is individual people with different attributes, and the other type of node is blocks; based on the two-mode network, analyzing the selection preferences of different population attributes for blocks, including: extracting the block nodes with the highest selection degree for different groups, and comparing and analyzing the spatial behavior heterogeneity of the population under the attributes of gender, age, and place of origin.

[0021] In a second aspect, an apparatus for analyzing population movement trajectories provided by an embodiment of the present application includes: an acquisition module, configured to acquire the spatio-temporal location information of a user in a target research area and perform data preprocessing on the acquired information; a processing module, configured to construct a network structure based on the preprocessed data; the nodes of the network structure are the blocks in the target research area, and the edges are the movement trajectories of the user; the weight of the edge is based on the user movement frequency or spatio-temporal correlation; the processing module is further configured to acquire the index of the block association rule based on the constructed network structure; the processing module is further configured to determine the spatial connection between blocks and the population behavior pattern based on the acquired index.

[0022] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, including computer-readable instructions, which when read and executed by a computer, cause the computer to execute the method according to any one of the first aspects.

[0023] In a fourth aspect, an embodiment of the present application provides a computing device, including a processor and a memory, where computer program instructions are stored in the memory, and when the computer program instructions are run by the processor, the method according to any one of the first aspects is executed.

[0024] In a fifth aspect, an embodiment of the present application provides a product containing a computer program, which when the computer program product runs on a processor, causes the processor to execute the method according to any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 is a schematic flowchart of a method for analyzing the movement trajectory of a crowd provided by an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of a device for analyzing the movement trajectory of a crowd provided by an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of the structure of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0030] The term "and / or" in this document describes the associated relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The symbol " / " in this document indicates that the associated objects are in an "or" relationship. For example, A / B represents A or B.

[0031] The terms "first" and "second" in the description and claims of this document are used to distinguish different objects, rather than to describe a specific order of the objects. For example, the first response message and the second response message are used to distinguish different response messages, rather than to describe the specific order of the response messages.

[0032] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner.

[0033] In the description of the embodiments of the present application, unless otherwise specified, "a plurality of" means two or more. For example, a plurality of processing units means two or more processing units, etc.; a plurality of elements means two or more elements, etc.

[0034] To facilitate the understanding of the embodiments of the present application, the following will further explain with specific embodiments in conjunction with the accompanying drawings. The embodiments do not limit the embodiments of the present invention.

[0035] First, the technical terms involved in the embodiments of the present application are introduced:

[0036] 1. Degree centrality, also known as degree centralization, is the most direct metric for characterizing node centrality in network analysis. The larger the node degree of a node, the higher the degree centrality of this node, and the more important this node is in the network.

[0037] Next, the technical solutions provided by the embodiments of the present application are introduced.

[0038] Currently, most spatio-temporal big data research uses areal analysis units (such as plots, grids, etc.), but ignores linear units (such as blocks). Blocks can effectively describe urban spatio-temporal dynamics, understand the pattern of urban functional differentiation, and analyze the internal structure of the city. The block perspective is of great significance for quantitative urban research and can help planners and government decision-makers at many socio-economic levels such as optimizing public resources, promoting urban construction, and alleviating traffic congestion. Block units contain more accurate activity information than areal units such as plots or grids. Exploring the differences between blocks can help us understand how people utilize urban areas, thereby more accurately characterizing the pattern of urban functional differentiation.

[0039] In view of this, the embodiments of the present application provide a method for analyzing population movement trajectories. Taking blocks as the basic units, combining population movement trajectories and road network data, through complex network and association rule analysis, it reveals urban spatio-temporal dynamics, functional differentiation, and population behavior patterns, providing a basis for urban planning, resource optimization, traffic alleviation, etc.

[0040] Considering that the characteristics of a block are reflected in its load capacity and service function, the embodiments of the present application use hierarchical clustering to perform unsupervised classification on the blocks within a city. The standardized block function indicators are used to perform the first-layer binary K-means clustering on the block dataset. Based on the block categories obtained, the load capacity indicators are used to perform the second-layer binary K-means clustering, and the secondary categories are integrated to obtain the final clustering result. Based on the population movement trajectory data, user profile data, and the clustered block data, effective data for studying population spatial behavior and block association rules is obtained. A complex network is used to construct a population spatial behavior network, and the overall network characteristics are analyzed, including the measure of the importance of block network nodes and the measure of the connectivity of the overall network. Secondly, based on the behavior network, block association rules are studied, including the association characteristics of important node pairs and the association characteristics of individual important nodes. Finally, based on individual attributes such as gender, age, and place of origin, various population spatial behaviors and block association rules are analyzed. At the same time, the matching and correlation between the spatio-temporal trajectory data and the geospatial entity data (road network spatial data) are extracted, the spatio-temporal distribution pattern and travel rules of the road network in the urban human settlement environment and the meaningful patterns therein are discovered, and the characteristics, interdependent relationships, and evolution trends of geospatial entities or geographical phenomena in the urban human settlement environment are revealed. Combining the urban road network spatial data and travel trajectory data, different functional areas in the city are analyzed according to the point-of-interest data and people's movement patterns.

[0041] Exemplarily, Figure 1 shows a schematic flowchart of the population movement trajectory analysis method provided by the embodiments of the present application. As Figure 1 shown, the method may include the following steps:

[0042] S11: Obtain the spatio-temporal location information of the user, and perform data preprocessing on the obtained information.

[0043] In this embodiment, first, the target research scope is determined, the spatio-temporal location information of users within the target research scope is collected, and local residents and duplicate records within a short period (or a predetermined time period) are deleted. This provides data for dividing blocks according to block levels later, connecting trajectory points to blocks, and constructing a multi-dimensional matrix.

[0044] Specifically, collect the spatio-temporal location information of all users within the research scope. The collected fields include user ID, timestamp, longitude and latitude information. Perform data preprocessing on the collected information. Data preprocessing includes deleting the information of native residents whose place of residence is local. At the same time, to avoid multiple records left by people continuously swiping their mobile phones at the same spatial location in a short time, which may interfere with the calculation results, identify the records with the same location for each user within a short time threshold, and retain the last one as valid data. Based on each level of block in the target research scope, divide the target area into blocks, perform spatial connection between the user trajectory points and the blocks, and identify the blocks visited by each mobile phone user ID. Assign 1 to the blocks visited by the user and 0 to the blocks not visited. Finally, construct multi-dimensional matrix data based on user ID, user profile and blocks.

[0045] In some possible embodiments, it is also possible to obtain the classification of each block within the target research scope.

[0046] In this embodiment, considering the two aspects of the load capacity and service function of the blocks, extract the corresponding indicators. Process the extracted indicator data to determine the standardized block function indicator data. Standardization refers to processing the original data related to the block function to make it conform to a certain standard range or distribution form for subsequent analysis and comparison. Standardization can ensure the comparability between different indicators and reduce the influence caused by differences in dimension or numerical range. Perform binary K-means clustering on the standardized block function indicators to obtain the first clustering result. Based on the load capacity indicator, perform secondary binary K-means clustering on the basis of the first clustering result to determine the second clustering result. Merge the first clustering result and the second clustering result to determine the final block classification.

[0047] S12: Based on the preprocessed data, construct a network structure.

[0048] In this embodiment, a traffic network is constructed using crowd movement trajectory data and block data. In the traffic network, blocks are used as nodes and user movement trajectories are used as edges to construct a crowd spatial behavior network. The analysis based on the network is mainly to discover the block nodes that play a key role in the structure and function of the block network based on the crowd movement spatial behavior. The evaluation indicators include Degree Centrality, Closeness Centrality, and Betweenness Centrality, which can measure the strength of the central role of block nodes from different perspectives, taking into account both the "center" and the "hub" aspects. Degree Centrality can characterize the centrality of block nodes in the block network analysis. The larger the Degree Centrality of a block node, the more important this block is in the network. Closeness Centrality reflects the degree of closeness between a certain block node and other nodes in the block network, describing the tightness between this block and other blocks. Blocks with a larger Closeness Centrality are usually located in the center of the network, while blocks with a smaller Closeness Centrality are usually located on the periphery or at the end of the network. Betweenness Centrality represents the mediating degree of block nodes, and it is an indicator that characterizes the importance of nodes based on the number of shortest paths passing through a certain block node. The higher the evaluation standard index, the more critical the node is.

[0049] In some possible embodiments, Degree Centrality is calculated according to the following formula:

[0050] C = deg(x) / N - 1

[0051] In the formula, C represents Degree Centrality, deg represents the degree of block node x, x represents a node in the block network based on crowd spatial behavior, N represents the number of nodes in the block network, and N > 1.

[0052] In some possible embodiments, Closeness Centrality is calculated according to the following formula:

[0053]

[0054] In the formula, C(u) represents Closeness Centrality, u represents the block network node for which Closeness Centrality is to be calculated, n represents the number of all block nodes, and d(u, v) represents the shortest distance, i.e., the shortest path, between block node v and block node u.

[0055] In some possible embodiments, Betweenness Centrality is calculated according to the following formula:

[0056]

[0057] In the formula, C(b) i represents Betweenness Centrality, σ mndenotes the number of shortest paths from block node m to block node n, σ mn (i) represents the number of shortest paths from block node m to block node n passing through node i, and G represents the set of all nodes.

[0058] S13: Based on the constructed network structure, obtain the indicators of block association rules.

[0059] In this embodiment, association rule analysis reflects the interdependence and relevance between one thing and other things, and is an important technology in data mining. Association rule calculation is used to mine the correlation relationships between valuable data items from a large amount of data, and rules such as "due to the occurrence of certain events, other events occur" can be associated and analyzed from the database. In this embodiment, support, confidence, and lift are used to mine block association rules. Using indicators such as support, confidence, and lift, the node pairs with the highest relevance are mined from the block association network constructed by the spatial behavior of the crowd, and their spatial connections and formation mechanisms are analyzed. Among them, those with both high support and high lift are strong association rules, those with the highest support are high-support nodes, and those with the highest lift are high-lift nodes. The form of the association rule is A and B are item sets located on the left and right sides of the rule respectively. The commonly used metrics for association rules are support, lift, and confidence. Among them, support is the percentage of cases where the selection of the crowd for the block contains both block item set A and block item set B. Confidence is the percentage of selections containing block item set A that also contain block item set B. Lift is the ratio of confidence to the percentage of cases where block item set B is selected. Based on the block association network constructed by the spatial behavior of the crowd, the node pairs with the highest relevance are mined using association rules, and the spatial connections and formation mechanisms between the node pairs are analyzed.

[0060] S14: Based on the obtained indicators, determine the spatial connections between blocks and the crowd behavior patterns.

[0061] In this embodiment, after obtaining the indicators of the block association rules, the urban functional area division (such as commercial areas and residential areas) can be analyzed based on the obtained indicators. In the analysis of the association rules of typical nodes, mainly focus on strongly associated rule nodes, high-support nodes, and high-lift nodes. Nodes with both high support and high lift are strongly associated rules, the node with the highest support is the high-support node, and the node with the highest lift is the high-lift node. Strongly associated rules can reveal which blocks have frequent movement relationships. In order to analyze the heterogeneity of block associations based on the spatial behavior characteristics of different groups, it is necessary to construct a network with both blocks and individuals with different attributes as nodes. Select a two-mode network for heterogeneity analysis. Set one type of node as people with different attributes and the second type of node as blocks. Construct a two-mode network according to the spatial behavior of different groups to reflect the tendency of node selection. The two-mode network mainly reflects the association between people and blocks. After constructing this type of network, select the block nodes with the highest selection degree for different groups for comparative analysis. Combine user portrait data to analyze the spatial behavior characteristics of different populations (such as gender, age, etc.) and the heterogeneity of block association rules. Combine road network and trajectory data to analyze the urban functional area division (such as commercial areas and residential areas).

[0062] The above is an introduction to the crowd movement trajectory analysis method provided by the embodiment of the present application. Based on the crowd movement trajectory data, the complex network and association rule algorithm are used to spatially couple the crowd spatial behavior with the block, discover the association characteristics between blocks from the perspective of spatial behavior, and deeply analyze the differences in association characteristics caused by different population characteristics. The "complex network + association rule" algorithm can explore the hidden laws in the random behavior of the crowd, effectively analyze the explicit and implicit association rules between blocks, discover strong association elements that are difficult to directly observe, refine the spatial behavior preferences of various groups of people, and provide decision-making references for land integration, structural optimization and line adjustment in the context of urban renewal. In the spatial behavior trajectory network, each block has both "center" and "hub" functions. Crowd movement is manifested as a multi-node, chain-like spatial behavior pattern. Nodes with strong centrality include popular attractions, popular catering and accommodation, and blocks with high traffic rates. The selection of attractions and facilities located in marginal areas is low. Crowds are mostly manifested as short-distance, adjacent blocks. In this way, it is helpful for urban planning, such as optimizing public resource allocation, adjusting traffic routes, etc. It can also help make business decisions, such as identifying high-traffic blocks and assisting in business site selection. In addition, it can also help with social governance, such as analyzing the flow of people and improving the efficiency of emergency management. It is understandable that the size of the sequence number of each step in the above-mentioned embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. In addition, in some possible implementation methods, the steps in the above-mentioned embodiments can be selectively executed according to actual conditions, and can be partially executed or fully executed, which is not limited here. All or part of any features of any embodiment of the present application can be freely and arbitrarily combined without contradiction. The combined technical solution is also within the scope of the present application.

[0063] Based on the method in the above embodiment, the embodiment of the present application also provides a crowd movement trajectory analysis device. For example, Figure 2 A crowd movement trajectory analysis device 200 is shown, which is deployed in a computing device. The crowd movement trajectory analysis device 200 includes: an acquisition module 201 and a processing module 202 .

[0064] The acquisition module 201 is used to acquire the spatiotemporal location information of the user in the target research area and perform data preprocessing on the acquired information.

[0065] The processing module 202 is used to construct a network structure based on the preprocessed data; the nodes of the network structure are the blocks in the target research area, and the edges are the movement trajectories of the users; the weights of the edges are based on the user movement frequency or spatiotemporal correlation.

[0066] The processing module 202 is further configured to obtain the metrics of the block association rules based on the constructed network structure.

[0067] The processing module 202 is further configured to determine the spatial connection and population behavior pattern between blocks based on the obtained metrics.

[0068] It should be understood that the above device is used to execute the method in the above embodiment. For the corresponding program module in the device, its implementation principle and technical effect are similar to those described in the above method. The working process of the device can refer to the corresponding process in the above method, which will not be elaborated here.

[0069] This application also provides a computing device 300. As Figure 3 shown, the computing device 300 includes: a bus 302, a processor 304, a memory 306, and a communication interface 308. The processor 304, the memory 306, and the communication interface 308 communicate with each other through the bus 302. The computing device 300 can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 300.

[0070] The bus 302 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 3 only one line is shown in the figure, but it does not mean that there is only one bus or one type of bus. The bus 304 can include a path for transmitting information between various components of the computing device 300 (for example, the memory 306, the processor 304, and the communication interface 308).

[0071] The processor 304 can include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP), etc.

[0072] The memory 306 may include volatile memory, such as random access memory (RAM). The processor 304 may also include non-volatile memory, such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0073] The executable program code is stored in the memory 306, and the processor 304 executes the executable program code to respectively implement the functions of the foregoing obtaining module 201 and processing module 203, thereby implementing all or part of the steps of the method in the foregoing embodiments. That is, instructions for executing all or part of the steps of the method in the foregoing embodiments are stored on the memory 306.

[0074] Alternatively, executable code is stored in the memory 306, and the processor 304 executes the executable code to respectively implement the functions of the foregoing crowd movement trajectory analysis device 200, thereby implementing all or part of the steps of the method in the foregoing embodiments. That is, instructions for executing all or part of the steps of the method in the foregoing embodiments are stored on the memory 306.

[0075] The communication interface 308 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 300 and other devices or a communication network.

[0076] Based on the method in the foregoing embodiments, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when running on a processor, causes the processor to execute the methods in the foregoing embodiments.

[0077] Based on the method in the foregoing embodiments, an embodiment of the present application provides a computer program product, which, when running on a processor, causes the processor to execute the methods in the foregoing embodiments.

[0078] It can be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0079] The method steps in the embodiments of the present application may be implemented in a hardware manner or by a processor executing software instructions. The software instructions may be composed of corresponding software modules, and the software modules may be stored in a random access memory (RAM), flash memory, read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), registers, hard disks, removable hard disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an ASIC.

[0080] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0081] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application.

Claims

1. A method for analyzing crowd movement trajectories, characterized in that: The method comprises: Obtain the user's spatiotemporal location information in the target research area and perform data preprocessing on the acquired information; Based on the preprocessed data, a network structure is constructed; the nodes of the network structure are the blocks in the target research area, and the edges are the movement trajectories of the users; the weights of the edges are based on the user movement frequency or spatiotemporal correlation; Based on the constructed network structure, the indicators of neighborhood association rules are obtained; Based on the obtained indicators, the spatial connections between blocks and crowd behavior patterns are determined.

2. The method according to claim 1, characterized in that The obtaining of the user's spatiotemporal location information in the target research area and the data preprocessing of the obtained information are specifically as follows: Get the user ID, as well as the timestamp and longitude and latitude information of the user in the target study area; The acquired information is pre-processed, including deleting the information of indigenous people whose place of residence is local, removing duplicate records of the same spatial location within a preset time period, and retaining the last piece of data as valid data.

3. The method according to claim 1, characterized in that The indicators of the block association rule include: at least one of support, confidence and lift, and the indicators are used to measure the strength and pattern of association between nodes to analyze the spatial behavior pattern of the crowd.

4. The method according to claim 1, characterized in that The constructed network structure is used to confirm the key nodes among the nodes, and the confirmation is performed through a judgment indicator, and the judgment indicator includes at least one of point degree centrality, proximity centrality and betweenness centrality.

5. The method according to claim 4, characterized in that The point degree centrality is calculated according to the following formula: C=deg(x) / N-1 In the formula, C represents the point degree centrality, deg represents the degree of node x, x represents a node in the network structure, N represents the number of nodes in the network structure, and N>1.

6. The method according to claim 4, characterized in that The closeness center is calculated according to the following formula: In the formula, C(u) represents the closeness centrality, u represents the node whose closeness centrality is to be calculated, n represents the number of all nodes, and d(u,v) represents the shortest distance between node v and node u.

7. The method according to claim 4, characterized in that The betweenness centrality is calculated according to the following formula: In the formula, C(b) i Characterizes the betweenness centrality, σ mn represents the number of shortest paths from node m to node n, σ mn (i) represents the number of shortest paths from node m to node n through node i, and G represents the node set.

8. The method according to claim 1, characterized in that The method further includes: performing hierarchical clustering on the blocks in the target study area, including: Performing hierarchical clustering on the blocks in the target study area to determine a first clustering result; Based on the first clustering result, a second-level binary K-means clustering is performed based on the block load capacity index to determine a second clustering result; The first clustering result and the second clustering result are combined to determine a final block classification.

9. The method according to claim 1, characterized in that: The method further comprises: Construct a 2-mode heterogeneous network, where one type of node is individuals with different attributes, and the other type of node is the neighborhood; Based on the 2-mode network, the block selection preferences of different groups of people are analyzed, including: extracting the block nodes with the highest selection degree of different groups, and comparing and analyzing the heterogeneity of spatial behavior of groups under the attributes of gender, age, and source of tourists.

10. A crowd movement trajectory analysis device, characterized in that: The device comprises: The acquisition module is used to obtain the user's spatiotemporal location information in the target research area and perform data preprocessing on the acquired information; A processing module, used to construct a network structure based on the preprocessed data; the nodes of the network structure are the blocks in the target research area, and the edges are the movement trajectories of the users; the weights of the edges are based on the user movement frequency or spatiotemporal correlation; The processing module is also used to obtain indicators of block association rules based on the constructed network structure; The processing module is also used to determine the spatial connections and crowd behavior patterns between blocks based on the acquired indicators.

Images