A method for recognizing aggregation behavior based on multi-trajectory conditional analysis

By using a multi-trajectory conditional analysis method, which integrates trajectory data from multiple time windows and sets aggregation behavior conditions, the problem of inaccurate aggregation behavior identification in traditional methods is solved. This enables accurate identification and rapid response to the aggregation of key personnel, and is suitable for lightweight implementation in the public security industry.

CN117688037BActive Publication Date: 2026-11-17WUHAN CITMS TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202311490432.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-08
Publication Date
2026-11-17
Estimated Expiration
2043-11-08

AI Technical Summary

Technical Problem

Traditional methods for identifying gathering behavior typically use only a small amount of trajectory data for analysis, which cannot fully determine the nature of the gathering behavior, making it difficult to achieve refined governance and effective protection of public safety.

Method used

A multi-trajectory conditional analysis method is adopted, which integrates trajectory data within multiple time windows, sets single-trajectory and multi-trajectory aggregation behavior conditions, including aggregation area type, interval between adjacent people, and aggregation number threshold, and performs comprehensive analysis using multiple trajectory data sources.

Benefits of technology

It achieves accurate identification and location of key personnel gatherings, with high accuracy and real-time performance, enabling rapid response and reduction of potential risks, and is suitable for lightweight implementation in the public security industry.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117688037B_ABST
    Figure CN117688037B_ABST
Patent Text Reader

Abstract

This invention relates to a method for recognizing aggregation behavior based on multi-trajectory condition analysis, comprising: collecting various types of trajectory information of key personnel; setting single-trajectory aggregation behavior conditions, including: the type of aggregation area, a maximum threshold for the interval between adjacent personnel, and a minimum threshold for the number of people in the aggregation area; determining single-trajectory aggregation behavior that meets the single-trajectory aggregation behavior conditions based on the trajectory information corresponding to the type of aggregation area in the single-trajectory aggregation behavior conditions; and using a multi-trajectory combination and different time windows to judge aggregation, the aggregation device can accurately identify different types of aggregation behavior by integrating trajectory data within multiple time windows.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of pattern analysis technology, and in particular to a method for recognizing aggregation behavior based on multi-trajectory condition analysis. Background Technology

[0002] The last mile of urban governance lies in the community. To optimize community governance, a new model of refined governance has been proposed. This model divides the community management area into unit grids according to certain standards. By statistically analyzing relevant governance indicators within each unit grid, layer-by-layer supervision is achieved, thus optimizing management. Among these indicators, population agglomeration and migration characteristics are important governance indicators that communities need to analyze, as they can provide reference information for social governance decisions.

[0003] Currently, the statistics of population data in communities have been managed through information technology. However, due to the lack of geographic information data and technical assistance, the division and changes of most grassroots grids are still based on paper documents. The analysis of population data in communities lacks spatial strategy analysis and visual early warning, making it difficult to intuitively reflect the changes of population governance indicators in relevant areas over time and space. This makes it impossible to achieve refined governance and affects higher-level decision-making.

[0004] Today, with technological advancements and social development, people have increasingly higher demands for grassroots social order management. In practice, it is necessary to pay close attention to the gathering behaviors of key individuals. However, focusing on these key individuals consumes a significant amount of manpower. Traditional methods for identifying gathering behaviors typically only analyze limited trajectory data, making it impossible to comprehensively determine the nature of the gathering behavior. Summary of the Invention

[0005] This invention addresses the technical problems existing in the prior art by providing a method for recognizing aggregation behavior based on multi-trajectory condition analysis. The aggregation device, which is based on multi-trajectory combination and different time windows, can accurately identify different types of aggregation behavior by integrating trajectory data within multiple time windows.

[0006] According to a first aspect of the present invention, a method for recognizing aggregation behavior based on multi-trajectory condition analysis is provided, comprising:

[0007] Step 1: Collect various types of trajectory information for key personnel;

[0008] Step 2: Set single-trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation area;

[0009] Step 3: Determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition.

[0010] Based on the above technical solution, the present invention can also be improved as follows.

[0011] Optionally, step 1 includes:

[0012] Step 101: Obtain various types of trajectory information of key personnel from the previous node via a message queue;

[0013] Step 102: Perform data processing on the trajectory information, including: data deduplication and filtering invalid data;

[0014] Step 103: Group the trajectory information according to the valid location field.

[0015] Optionally, the various types of trajectory information come from data associated with various set types of areas, including: internet access data, hotel accommodation data, train ticket purchase data, bus ticket purchase data, air ticket purchase data, and facial recognition alerts.

[0016] Optionally, step 3 includes:

[0017] Step 301: Determine the corresponding trajectory information based on the type of the aggregation region in the aggregation behavior conditions;

[0018] Step 302: Based on the trajectory information, construct a table association between key personnel and the type of clustered areas;

[0019] Step 303: Set an aggregation operator based on the aggregation behavior conditions, and output a list containing all single-trajectory aggregation behaviors that meet the conditions based on the aggregation operator and the table association.

[0020] Optionally, the identification method further includes:

[0021] Step 4: Set multi-track aggregation behavior conditions, and determine multi-track aggregation behaviors that satisfy the multi-track aggregation behavior conditions based on each of the single-track aggregation behaviors.

[0022] Optionally, the multi-track aggregation behavior conditions include: a minimum threshold for the number of people in the aggregation, a minimum threshold for the number of single-track aggregation behaviors that meet the conditions, and a maximum threshold for the single-track interval duration.

[0023] Optionally, step 4 includes:

[0024] Step 401: Calculate and mark the aggregation time of each of the single trajectory aggregation behaviors obtained in step 3, and determine and cache each of the single trajectory aggregation behaviors that satisfies the highest threshold of single trajectory interval duration in the multi-trajectory aggregation behavior conditions.

[0025] Step 402: Calculate the Cartesian product of each of the single-track aggregation behaviors in the cache, iterate through each result sequentially, and obtain the result based on the number of existing track types m and the minimum threshold n of the number in the multi-track aggregation behavior conditions. A permutation and combination of multiple trajectory aggregation behaviors;

[0026] Step 403: Iterate through the permutations and combinations to find the intersection. If the number of intersection results is greater than or equal to the minimum threshold of the number of people in the multi-track aggregation behavior condition, then output the result of the multi-track aggregation behavior condition.

[0027] According to a second aspect of the present invention, a clustering behavior recognition system based on multi-trajectory condition analysis is provided, comprising: a trajectory information acquisition module, a single-trajectory clustering behavior condition module, and a determination unit;

[0028] The trajectory information acquisition module is used to collect various types of trajectory information of key personnel;

[0029] The single-track aggregation behavior condition module is used to set single-track aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation.

[0030] The determination unit is used to determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition.

[0031] According to a third aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the processor is configured to implement a method for recognizing aggregation behavior based on multi-trajectory condition analysis when executing a computer management program stored in the memory.

[0032] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having a computer management program stored thereon, which, when executed by a processor, implements the steps of a method for recognizing aggregation behavior based on multi-trajectory condition analysis.

[0033] This invention provides a method, system, electronic device, and storage medium for recognizing aggregation behavior based on multi-trajectory condition analysis. It first processes the data of a single trajectory to obtain a list of single trajectory data, and then aggregates and analyzes the obtained list data of multiple trajectories. Its beneficial effects include:

[0034] 1. High Accuracy: Through multi-trajectory condition analysis, this processing device can accurately identify and locate key groups of people. It can utilize multiple trajectory data sources and comprehensively consider multiple factors to provide more accurate results and avoid false alarms or missed alarms.

[0035] 2. Real-time monitoring: This device can collect and analyze trajectory data in real time to quickly detect gatherings of key personnel. This allows relevant departments or security personnel to understand the situation in real time and take appropriate measures to ensure public safety and order.

[0036] The processing device based on multi-trajectory condition analysis can quickly issue alarms or notifications to enable timely action. Its high response speed allows emergency response teams to quickly arrive on-site and handle cluster incidents, minimizing potential risks and losses.

[0037] 3. Rapid Response: The processing device based on multi-trajectory condition analysis can quickly issue alarms or notifications to enable timely action. Its high reaction speed allows emergency response teams to quickly arrive on-site and handle cluster incidents, minimizing potential risks and losses.

[0038] Furthermore, this device is more focused on the public security sector, and parameters can be adjusted according to actual conditions to obtain more accurate results. Apart from caching relying on Redis, there are no other third-party dependent components, making it relatively lightweight and requiring only general server resources, with a lower cost. Attached Figure Description

[0039] Figure 1 A flowchart illustrating a method for recognizing aggregation behavior based on multi-trajectory condition analysis provided by this invention;

[0040] Figure 2 This invention provides a schematic diagram of the arrival timeline of key personnel at a hotel.

[0041] Figure 3 A flowchart for determining single-trajectory aggregation behavior is provided in an embodiment of the present invention;

[0042] Figure 4 A schematic diagram illustrating a single-trajectory aggregation behavior condition provided in an embodiment of the present invention.

[0043] Figure 5 A schematic diagram illustrating a multi-track aggregation behavior condition provided in an embodiment of the present invention;

[0044] Figure 6 A flowchart for determining multi-track aggregation behavior is provided in an embodiment of the present invention;

[0045] Figure 7 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0046] Figure 8 This is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. Detailed Implementation

[0047] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0048] Figure 1 A flowchart of a clustering behavior recognition method based on multi-trajectory conditional analysis provided by the present invention is shown below. Figure 1 As shown, the identification method includes:

[0049] Step 1: Collect various types of trajectory information for key personnel.

[0050] Step 2: Set single-trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation.

[0051] Step 3: Determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition.

[0052] This invention provides a method for recognizing aggregation behavior based on multi-trajectory condition analysis. The aggregation device, which is based on multi-trajectory combination and different time windows, can accurately identify different types of aggregation behavior by integrating trajectory data within multiple time windows.

[0053] Example 1

[0054] Embodiment 1 provided by this invention is an embodiment of a clustering behavior recognition method based on multi-trajectory condition analysis provided by this invention, combined with... Figure 1 It can be seen that embodiments of this identification method include:

[0055] Step 1: Collect various types of trajectory information for key personnel.

[0056] In one possible embodiment, step 1 includes:

[0057] Step 101: Obtain various types of trajectory information of key personnel from the previous node through a message queue.

[0058] Step 102: Perform data processing on the trajectory information, including data deduplication and filtering invalid data.

[0059] Step 103: Group the trajectory information according to the valid location field.

[0060] In one possible implementation, various types of trajectory information come from data associated with various defined types of areas, including: internet access data, hotel accommodation data, train ticket purchase data, bus ticket purchase data, air ticket purchase data, and facial recognition alerts.

[0061] Step 2: Set single-trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation.

[0062] Step 3: Determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition.

[0063] In one possible embodiment, step 3 includes:

[0064] Step 301: Determine the corresponding trajectory information based on the type of clustered area in the clustering behavior conditions; for example, when the type of clustered area in the clustering behavior conditions is a hotel, select hotel accommodation data as the trajectory information.

[0065] Step 302: Construct a table association between key personnel and cluster areas of this type based on trajectory information.

[0066] Step 303: Set the aggregation operator based on the aggregation behavior conditions, and output a list containing all single-trajectory aggregation behaviors that meet the conditions based on the aggregation operator and table association.

[0067] In specific implementation, the area can be set as such as: internet cafe, railway, and hotel, etc. In one embodiment provided by this invention, such as... Figure 2 The diagram shown is a schematic representation of the arrival timeline of key personnel at a hotel according to an embodiment of the present invention. Figure 3 The diagram shown is a flowchart for determining single-trajectory aggregation behavior according to an embodiment of the present invention. Figure 4 The diagram shown is a schematic representation of a single-trajectory aggregation behavior condition provided by an embodiment of the present invention. Figure 2 The timeline can illustrate the logical judgment of the clustering; the three trajectories of internet cafes, hotels, and accommodations all follow... Figure 3 The flowchart in the document is processed in the same way for the three trajectories before the "output list". That is, the table association and aggregation operators are universal.

[0068] Figure 4 In the given embodiment, the type of clustering area is hotel accommodation, the maximum threshold for the interval is 5 minutes, and the minimum threshold for the clustering score is 4 minutes. That is, trajectory information is obtained from the hotel accommodation information of each key person, and it is determined whether there are more than 4 key persons clustering in a certain hotel, and the time interval between the current person and the next person is less than or equal to 5 minutes, which is determined to be a single trajectory clustering behavior.

[0069] Right now Figure 2The criteria for determining the single-track clustering behavior are whether the time interval between the current person and the next person is less than or equal to 5 minutes. The intervals between A and B are 1 minute, B and C are 1 minute, and C and D are 3 minutes, all within 5 minutes. However, the interval between D and E is 12 minutes, so they are disconnected. Since A, B, C, and D meet the number requirement, they are determined to be a single-track clustering behavior involving the same accommodation. The time intervals of J, K, and M meet the single-track clustering behavior condition, but since there are only 3 people, they do not meet the single-track clustering behavior condition.

[0070] To more accurately determine the clustering of certain key individuals, it's important to understand that relying on a single trajectory isn't very precise. If, within a certain timeframe, n out of m trajectories (n <= m) meet certain criteria, then it can be determined that these key individuals are clustering. For example... Figure 5 The diagram shown is a schematic representation of a multi-track aggregation behavior condition provided by an embodiment of the present invention. Figure 6 The diagram shown is a flowchart for determining multi-trajectory aggregation behavior according to an embodiment of the present invention.

[0071] In one possible embodiment, the identification method further includes:

[0072] Step 4: Set multi-track aggregation behavior conditions, and determine the multi-track aggregation behavior that meets the multi-track aggregation behavior conditions based on each single-track aggregation behavior.

[0073] In one possible embodiment, the multi-track aggregation behavior conditions include: a minimum threshold for the number of people in the aggregation, a minimum threshold for the number of single-track aggregation behaviors that meet the conditions, and a maximum threshold for the single-track interval duration.

[0074] Specifically, the minimum threshold for the number of people in a cluster is as follows: the number of people in multiple trajectories is further filtered. For example, if there are three people (A, B, C) in the internet browsing cluster, three people (A, B, C) in the hotel accommodation cluster, and three people (A, B, C) in the railway ticket purchase cluster, then the result of merging is two people (A, B, and C) in a cluster, which does not meet the condition that the number of people in a cluster is 3, so there is no output result.

[0075] Minimum threshold for the number of single-trajectory clustering behaviors that meet the conditions: at least n conditions must be met in m.

[0076] Maximum threshold for single trajectory interval: Suppose there are three people (A, B, C) gathering online and three people (A, B, C) gathering at a hotel. However, if the time difference between the time of the online gathering and the time of the hotel gathering exceeds 4 hours, no result will be output.

[0077] In one possible embodiment, step 4 includes:

[0078] Step 401: Calculate and mark the aggregation time of each single trajectory aggregation behavior obtained in step 3, and determine and cache each single trajectory aggregation behavior that satisfies the highest threshold of single trajectory interval duration in the multi-trajectory aggregation behavior conditions.

[0079] Step 402: Calculate the Cartesian product of each single-track aggregation behavior in the cache. Iterate through each result sequentially, and based on the number of existing track types m and the minimum threshold n of the number in the multi-track aggregation behavior condition, obtain... A permutation and combination of multiple trajectory aggregation behaviors.

[0080] Step 403: Iterate through the permutations and combinations to find the intersection. If the number of intersection results is greater than or equal to the minimum threshold of the number of people in the multi-track aggregation behavior condition, then output the result of the multi-track aggregation behavior condition and trigger an early warning.

[0081] Example 2

[0082] Embodiment 2 of the present invention is an embodiment of a clustering behavior recognition system based on multi-trajectory condition analysis provided by the present invention. The embodiment of the recognition system includes: a trajectory information acquisition module, a single trajectory clustering behavior condition module, and a judgment unit.

[0083] The trajectory information collection module is used to collect various types of trajectory information of key personnel.

[0084] The Single Trajectory Aggregation Behavior Conditions module is used to set single trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation.

[0085] The determination unit is used to determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition.

[0086] It is understood that the aggregation behavior recognition system based on multi-trajectory condition analysis provided by the present invention corresponds to the aggregation behavior recognition method based on multi-trajectory condition analysis provided in the foregoing embodiments. The relevant technical features of the aggregation behavior recognition system based on multi-trajectory condition analysis can be referred to the relevant technical features of the aggregation behavior recognition method based on multi-trajectory condition analysis, and will not be repeated here.

[0087] Example 3

[0088] Embodiment 3 of this invention is a specific application embodiment of the aggregation behavior recognition method based on multi-trajectory condition analysis provided by this invention. The data processing of the aggregation behavior recognition method is divided into the following steps: obtaining hotel accommodation information data / internet cafe access data / railway traffic data of key personnel from the previous node through a message queue; data processing (data deduplication, filtering invalid data, etc.); grouping according to the effective location field; merging a batch of data after the last disconnection time of the last analysis; analyzing whether each group of data has the same aggregation person; caching a batch of data after the last disconnection time; and outputting to the next node.

[0089] To more accurately determine the clustering of several key individuals, but relying on a single trajectory is not very accurate, if we can determine that if n (n <= m) out of m trajectories meet certain conditions within a certain time period, then we can conclude that these key individuals are clustering. The data processing for multi-trajectory clustering behavior conditions involves the following steps:

[0090] Step 1: Obtain the data input to the upstream node's aggregation operator (the above image shows the aggregated data from internet cafes, railways, and hotels; at least one of these three types of data must be present for the node to be triggered).

[0091] Assume the data obtained is aggregated data from internet cafes, and the data is: [

[0092] {“People gathered”: “a, b, c”, “Gathering time”: “2023-08-30 14:30:00”},

[0093] {“People who gathered”:“g,h,i”,“Gathering time”:“2023-08-30 14:40:00”} ]

[0095] Step two: Obtain the latest time value from the upstream node data (this involves finding the latest time from the clustered data of internet cafes, railways, and hotels).

[0096] The latest time obtained in this step is: 2023-08-30 14:40:00

[0097] Step 3: Retrieve the data from the cache for the three types of trajectory aggregations mentioned above, and remove data where the latest time value - aggregation time (the time contained in the aggregation data) > trajectory interval (the value here is the configuration parameter in the multi-condition operator in the above figure).

[0098] Assume the following data is retrieved from the cache:

[0099] Data aggregated from internet cafes, and the data is: [

[0100] {“People who gathered”:“w,z,y”,“Gathering time”:“2023-08-30 09:20:00”} ]

[0102] Railway ticket purchase aggregated data, and the data is: [

[0103] {“People gathered”: “a, b, c”, “Gathering time”: “2023-08-30 13:50:00”},

[0104] {“People gathered”:“d, e, h”,“Gathering time”:“2023-08-30 12:40:00”} ]

[0106] Hotel accommodation cluster data, and the data is as follows: [

[0107] {“People gathered”: “a, b, c”, “Gathering time”: “2023-08-30 14:00:00”} ]

[0109] The result after removing those that do not meet the conditions is:

[0110] Data aggregated from internet cafes, and the data is: [

[0111] {“People gathered”: “a, b, c”, “Gathering time”: “2023-08-30 14:30:00”},

[0112] {“People who gathered”:“g,h,i”,“Gathering time”:“2023-08-30 14:40:00”} ]

[0114] Railway ticket purchase aggregated data, and the data is: [

[0115] {“People gathered”: “a, b, c”, “Gathering time”: “2023-08-30 13:50:00”},

[0116] {“People gathered”:“d, e, h”,“Gathering time”:“2023-08-30 12:40:00”} ]

[0118] Hotel accommodation cluster data, and the data is as follows: [

[0119] {“People who gathered”: “h, j, y”, “Gathering time”: “2023-08-30 14:00:00”} ]

[0121] Step 4: Cache all trajectory aggregation data (cache the results of the previous step).

[0122] Step 5: Calculate the Cartesian product of all trajectories that satisfy the conditions (i.e., the results of Step 3) (the goal is to list all combinations).

[0123] The Cartesian product yields the following four results:

[0124] Internet cafe: {"People gathered": "a, b, c", "Gathering time": "2023-08-30 14:30:00"}

[0125] Railway: {"People Gathered": "a, b, c", "Gathering Time": "2023-08-30 13:50:00"}

[0126] Hotel: {"People Gathering": "h, j, y", "Gathering Time": "2023-08-30 14:00:00"}

[0127] Internet cafe: {"People gathered": "a, b, c", "Gathering time": "2023-08-30 14:30:00"}

[0128] Railway: {"Gathering People": "d, e, h", "Gathering Time": "2023-8-30 12:40:00"}

[0129] Hotel: {"People Gathering": "h, j, y", "Gathering Time": "2023-08-30 14:00:00"}

[0130] Internet cafe: {"People gathered": "g, h, i", "Gathering time": "2023-08-30 14:40:00"}

[0131] Railway: {"People Gathered": "a, b, c", "Gathering Time": "2023-08-30 13:50:00"}

[0132] Hotel: {"People Gathering": "h, j, y", "Gathering Time": "2023-08-30 14:00:00"}

[0133] Internet cafe: {"People gathered": "g, h, i", "Gathering time": "2023-08-30 14:40:00"}

[0134] Railway: {"Gathering People": "d, e, h", "Gathering Time": "2023-8-30 12:40:00"}

[0135] Hotel: {"People Gathering": "h, j, y", "Gathering Time": "2023-08-30 14:00:00"}

[0136] Step 6: Iterate through each result from the previous step, calculating the permutations and combinations based on the number of existing trajectory types (m, 3 in this case) and the number of conditions to be met (n, as shown in the configuration-conditional matching above, 2 in this case).

[0137] The permutations and combinations of the above results are as follows:

[0138] Internet cafes and railways: a, b, c and a, b, c

[0139] Internet cafes and hotels: a, b, c and h, j, y

[0140] Hotels and railways: h, j, y and a, b, c

[0141] Internet cafes and railways: a, b, c and d, e, h

[0142] Internet cafes and hotels: a, b, c and h, j, y

[0143] Hotels and railways: d, e, h and h, j, y

[0144] ...

[0145] Step 7: Iterate through the data and find the intersection. If the number of intersection results is greater than or equal to the number of people in the cluster (the number of people in the cluster is configured as shown in the figure above - conditional matching, and is 3 in this case), then output the result and trigger an alert.

[0146] The result of the intersection is: only the intersection of the first line is not empty, and the result is a, b, c. The number of people in the cluster is 3, which meets the conditions. The final output result is a, b, c.

[0147] Please see Figure 7 , Figure 7 This is a schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 7 As shown, this embodiment of the invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, it performs the following steps: collecting various types of trajectory information of key personnel; setting single-trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent personnel, and the minimum threshold for the number of people in the aggregation area; and determining single-trajectory aggregation behavior that meets the single-trajectory aggregation behavior conditions based on the trajectory information corresponding to the type of aggregation area in the single-trajectory aggregation behavior conditions.

[0148] Please see Figure 8 , Figure 8 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by the present invention. (See diagram below.) Figure 8As shown, this embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, it performs the following steps: collecting various types of trajectory information of key personnel; setting single trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold of the interval between adjacent personnel, and the minimum threshold of the number of people in the aggregation area; and determining the single trajectory aggregation behavior that meets the single trajectory aggregation behavior conditions based on the trajectory information corresponding to the type of aggregation area in the single trajectory aggregation behavior conditions.

[0149] This invention provides a method, system, electronic device, and storage medium for recognizing aggregation behavior based on multi-trajectory condition analysis. It first processes the data of a single trajectory to obtain a list of single trajectory data, and then aggregates and analyzes the obtained list data of multiple trajectories. Its beneficial effects include:

[0150] 1. High Accuracy: Through multi-trajectory condition analysis, this processing device can accurately identify and locate key groups of people. It can utilize multiple trajectory data sources and comprehensively consider multiple factors to provide more accurate results and avoid false alarms or missed alarms.

[0151] 2. Real-time monitoring: This device can collect and analyze trajectory data in real time to quickly detect gatherings of key personnel. This allows relevant departments or security personnel to understand the situation in real time and take appropriate measures to ensure public safety and order.

[0152] The processing device based on multi-trajectory condition analysis can quickly issue alarms or notifications to enable timely action. Its high response speed allows emergency response teams to quickly arrive on-site and handle cluster incidents, minimizing potential risks and losses.

[0153] 3. Rapid Response: The processing device based on multi-trajectory condition analysis can quickly issue alarms or notifications to enable timely action. Its high reaction speed allows emergency response teams to quickly arrive on-site and handle cluster incidents, minimizing potential risks and losses.

[0154] Furthermore, this device is more focused on the public security sector, and parameters can be adjusted according to actual conditions to obtain more accurate results. Apart from caching relying on Redis, there are no other third-party dependent components, making it relatively lightweight and requiring only general server resources, with a lower cost.

[0155] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0156] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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, etc.) containing computer-usable program code.

[0157] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, 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, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0158] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0159] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0160] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0161] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for recognizing collective behavior based on multi-trajectory conditional analysis, characterized in that, The identification method includes: Step 1: Collect various types of trajectory information for key personnel; Step 2: Set single-trajectory aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation area; Step 3: Determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition; Step 4: Set multi-track aggregation behavior conditions, and determine multi-track aggregation behaviors that satisfy the multi-track aggregation behavior conditions based on each of the single-track aggregation behaviors. The conditions for multi-track aggregation behavior include: a minimum threshold for the number of people in the aggregation, a minimum threshold for the number of single-track aggregation behaviors that meet the conditions, and a maximum threshold for the single-track interval duration. Step 4 includes: Step 401: Calculate and mark the aggregation time of each of the single trajectory aggregation behaviors obtained in step 3, and determine and cache each of the single trajectory aggregation behaviors that satisfies the highest threshold of single trajectory interval duration in the multi-trajectory aggregation behavior conditions. Step 402, calculating the results of the Cartesian product of each of the single-track aggregation behaviors in the cache, sequentially traversing each result, and obtaining a permutation combination of the multi-track aggregation behaviors according to the number m of existing track categories and the minimum threshold n of the number in the multi-track aggregation behavior condition. Step 403: Iterate through the permutations and combinations to find the intersection. If the number of intersection results is greater than or equal to the minimum threshold of the number of people in the multi-track aggregation behavior condition, then output the result of the multi-track aggregation behavior condition.

2. The identification method according to claim 1, characterized in that, Step 1 includes: Step 101: Obtain various types of trajectory information of key personnel from the previous node via a message queue; Step 102: Perform data processing on the trajectory information, including: data deduplication and filtering invalid data; Step 103: Group the trajectory information according to the valid location field.

3. The identification method according to claim 1 or 2, characterized in that, The various types of trajectory information come from data associated with various defined types of areas, including: internet access data, hotel accommodation data, train ticket purchase data, bus ticket purchase data, air ticket purchase data, and facial recognition alerts.

4. The identification method according to claim 1, characterized in that, Step 3 includes: Step 301: Determine the corresponding trajectory information based on the type of the clustering region in the clustering behavior conditions; Step 302: Based on the trajectory information, construct a table association between key personnel and the type of clustered areas; Step 303: Set an aggregation operator based on the aggregation behavior conditions, and output a list containing all single-trajectory aggregation behaviors that meet the conditions based on the aggregation operator and the table association.

5. A clustering behavior recognition system based on multi-trajectory conditional analysis using the method described in any one of claims 1-4, characterized in that, The recognition system includes: a trajectory information acquisition module, a single trajectory aggregation behavior condition module, and a judgment unit; The trajectory information acquisition module is used to collect various types of trajectory information of key personnel; The single-track aggregation behavior condition module is used to set single-track aggregation behavior conditions, including: the type of aggregation area, the maximum threshold for the interval between adjacent people, and the minimum threshold for the number of people in the aggregation. The determination unit is used to determine the single trajectory aggregation behavior that satisfies the single trajectory aggregation behavior condition based on the trajectory information corresponding to the type of aggregation region in the single trajectory aggregation behavior condition.

6. An electronic device, characterized in that, It includes a memory and a processor, wherein the processor is used to implement the steps of the aggregation behavior recognition method based on multi-trajectory condition analysis as described in any one of claims 1-4 when executing a computer management program stored in the memory.

7. A computer-readable storage medium, characterized in that, It stores a computer management program, which, when executed by a processor, implements the steps of the aggregation behavior recognition method based on multi-trajectory condition analysis as described in any one of claims 1-4.

Citation Information

Patent Citations

  • Aggregation risk determination method and device, computer readable medium and electronic equipment

    CN115188488A