Method, device, equipment and medium for analyzing correlation relationships based on trajectory data

Abstract

The present invention relates to the field of relationship analysis technology, and discloses a method, apparatus, device, and medium for analyzing association relationships based on trajectory data. The method includes constructing preset data analysis rules, analyzing device information of a data set to be analyzed based on the preset data analysis rules, and obtaining a device relationship table; generating a one-to-one peer data set based on the preset data analysis rules and the device relationship table; performing statistics on the one-to-one peer data set based on the capture date to obtain a first peer data set; performing statistics on the first peer data set based on the characteristic value to obtain a second peer data set; sorting the second peer data set based on the number of days and times of peers to obtain an ordered peer data set; and analyzing the ordered peer data set based on the preset association relationship analysis rules to obtain an association relationship data set. In the present invention, association analysis is performed based on device information, time information, i.e., the capture date, and characteristic values, and the association relationships of different objects are quickly and accurately analyzed based on multiple types of trajectory data.

Description

Technical Field

[0001] The present invention relates to the technical field of relationship analysis, and in particular to a method, device, equipment and medium for analyzing association relationships based on trajectory data. Background Art

[0002] As informatization in all walks of life becomes more and more comprehensive, more and more data is collected. After analysis, a large amount of information can be obtained from it, such as the relationship between people, the relationship between people and cars, the relationship between people and mobile phones, the relationship between cars and mobile phones, the relationship between people, cars and mobile phones, etc.

[0003] However, in real life, manually browsing and searching for suspects is time-consuming, labor-intensive, and inefficient. Furthermore, the sheer volume of collected data makes it difficult to accurately analyze the relationships between numerous people, vehicles, and phone numbers. Furthermore, real-time analysis and query speeds are slow, making it impossible to accurately obtain crucial information about the relationships between people, vehicles, and phone numbers.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method, device, equipment and medium for analyzing association relationships based on trajectory data, aiming to solve the technical problems in existing investigative work such as slow, inefficient and inaccurate real-time queries due to the huge amount of data.

[0006] To achieve the above objectives, the present invention provides a method for analyzing association relationships based on trajectory data, the method comprising:

[0007] Get the data set to be analyzed;

[0008] Constructing a preset data analysis rule, and analyzing the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table;

[0009] Generate a one-to-one peer data set according to the preset data analysis rules and the device relationship table;

[0010] performing grouping statistics on the one-to-one peer dataset based on the capture date to obtain a first peer dataset;

[0011] performing grouping and statistics on the first peer data set according to the characteristic values ​​to obtain a second peer data set;

[0012] sorting the second peer data set based on the number of peer days and the number of peer times to obtain an ordered peer data set;

[0013] The ordered peer datasets are analyzed based on preset association relationship analysis rules to obtain an association relationship dataset.

[0014] In some embodiments, the constructing of preset data analysis rules includes:

[0015] Set vehicle data as the first category of data and face data as the second category of data;

[0016] Constructing a data type rule based on the first type of data and the second type of data;

[0017] Time rules are established based on whether the time difference between vehicle data and face data captured at the same site meets the time range;

[0018] Establish device relationship rules based on whether the latitude and longitude distance between the vehicle capture device and the face capture device meets the distance threshold;

[0019] Preset data analysis rules are constructed based on the data type rules, time rules and device relationship rules.

[0020] In some embodiments, analyzing the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table includes:

[0021] Extracting facial device information and vehicle device information of the data set to be analyzed;

[0022] Analyzing the facial device information and the vehicle device information according to the device relationship rule set by the preset data analysis rule, so as to determine the target facial device and the target vehicle device as devices at the same location according to the device relationship rule;

[0023] A device relationship table is constructed based on the target face device and the target vehicle device.

[0024] In some embodiments, generating a one-to-one peer data set according to the preset data analysis rule and the device relationship table includes:

[0025] According to the preset data analysis rules and the device relationship table, the face trajectory data and the vehicle trajectory data are associated through the device relationship to obtain an initial peer dataset;

[0026] The initial peer data set is filtered according to the time rule set by the preset data analysis rule to obtain a one-to-one peer data set.

[0027] In some embodiments, sorting the second peer data set based on the number of peer visits and the number of peer visits to obtain an ordered peer data set includes:

[0028] Arrange the second peer data set in reverse order based on the number of peer days to obtain an initial ordered data set;

[0029] The initial ordered data set is arranged in reverse order according to the number of times in the same row to obtain an ordered data set in the same row.

[0030] In some embodiments, the method further comprises:

[0031] The face trajectory data is set as the first category of data, and the vehicle trajectory data is set as the second category of data;

[0032] Constructing data rules based on the first and second types of data;

[0033] Establish a cycle rule based on whether the number of days traveling together meets the travel time rules and whether the person appears in the main driver's seat of the vehicle;

[0034] Establish relationship rules based on whether vehicles and personnel have a subordinate relationship;

[0035] Preset association relationship analysis rules are constructed based on the data rules, period rules and relationship rules.

[0036] In some embodiments, analyzing the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset includes:

[0037] Obtain data rules, cycle rules and relationship rules based on preset association relationship analysis rules;

[0038] Determining the ordered peer dataset according to the data rules, period rules, and relationship rules to obtain a target dataset that complies with the data rules, period rules, and relationship rules;

[0039] Generate an association relationship dataset based on the target dataset.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes a correlation analysis device based on trajectory data, comprising:

[0041] An acquisition module is used to obtain the data set to be analyzed;

[0042] A construction module, configured to construct a preset data analysis rule, and analyze the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table;

[0043] A generating module, configured to generate a one-to-one peer data set according to the preset data analysis rules and the device relationship table;

[0044] A first statistical module is used to group and count the one-to-one peer data set based on the capture date to obtain a first peer data set;

[0045] A second statistical module, configured to perform grouping statistics on the first same-same data set according to characteristic values ​​to obtain a second same-same data set;

[0046] a sorting module, configured to sort the second peer data set based on the number of peer days and the number of peer times to obtain an ordered peer data set;

[0047] The analysis module is used to analyze the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset.

[0048] In addition, to achieve the above-mentioned purpose, the present invention also proposes a trajectory data-based association relationship analysis device, which includes: a memory, a processor, and a trajectory data-based association relationship analysis program stored in the memory and executable on the processor, wherein the trajectory data-based association relationship analysis program is configured to implement the trajectory data-based association relationship analysis method described above.

[0049] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, which stores a correlation relationship analysis program based on trajectory data, and the correlation relationship analysis program based on trajectory data is used to enable a processor to implement the correlation relationship analysis method based on trajectory data as described above when executed.

[0050] The present invention obtains a data set to be analyzed; constructs a preset data analysis rule, analyzes the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table; generates a one-to-one peer data set according to the preset data analysis rule and the device relationship table; performs grouping and statistics on the one-to-one peer data set based on the capture date to obtain a first peer data set; performs grouping and statistics on the first peer data set based on the characteristic value to obtain a second peer data set; sorts the second peer data set based on the number of days and the number of times of peers to obtain an ordered peer data set; analyzes the ordered peer data set based on the preset association relationship analysis rule to obtain an association relationship data set. In the present invention, based on device information, time information, i.e., capture date, and characteristic value, different types of devices are associated in view of the above characteristic data, and data can be associated and analyzed, thereby analyzing the association relationship of different objects based on multiple types of trajectory data, solving the technical problem of slow, inefficient and inaccurate real-time query speed in existing investigation work due to the huge amount of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of the structure of a device for analyzing association relationships based on trajectory data in a hardware operating environment according to an embodiment of the present invention;

[0052] Figure 2 This is a flow chart of a first embodiment of a method for analyzing association relationships based on trajectory data according to the present invention;

[0053] Figure 3 This is a flow chart of a second embodiment of a method for analyzing association relationships based on trajectory data according to the present invention;

[0054] Figure 4 This is a structural block diagram of the first embodiment of the trajectory data-based correlation analysis device of the present invention.

[0055] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0057] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0058] In addition, the descriptions of "first", "second", etc. in the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention. It should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0059] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a device for analyzing association relationships based on trajectory data in a hardware operating environment according to an embodiment of the present invention.

[0060] like Figure 1As shown, the trajectory data-based association analysis device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM memory) or a stable non-volatile memory (NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0061] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the device for analyzing association relationships based on trajectory data, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0062] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a correlation analysis program based on trajectory data.

[0063] exist Figure 1 In the trajectory data-based association relationship analysis device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the trajectory data-based association relationship analysis device of the present invention can be set in the trajectory data-based association relationship analysis device. The trajectory data-based association relationship analysis device calls the trajectory data-based association relationship analysis program stored in the memory 1005 through the processor 1001 and executes the trajectory data-based association relationship analysis method provided by the embodiment of the present invention.

[0064] The embodiment of the present invention provides a method for analyzing association relationships based on trajectory data. Figure 2 , Figure 2 This is a flow chart of a first embodiment of a method for analyzing association relationships based on trajectory data according to the present invention.

[0065] like Figure 2 As shown, the correlation relationship analysis method based on trajectory data includes:

[0066] Step S100: obtaining a data set to be analyzed;

[0067] Step S200: Constructing a preset data analysis rule, and analyzing the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table;

[0068] Step S300: generating a one-to-one peer data set according to the preset data analysis rules and the device relationship table;

[0069] Step S400: performing grouping statistics on the one-to-one peer dataset based on the capture date to obtain a first peer dataset;

[0070] Step S500: performing grouping and statistics on the first same-same data set according to the characteristic values ​​to obtain a second same-same data set;

[0071] Step S600: sorting the second peer data set based on the number of peer days and the number of peer times to obtain an ordered peer data set;

[0072] Step S700: Analyze the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset.

[0073] It should be noted that the execution subject in this embodiment may be a correlation analysis device based on trajectory data, and the correlation analysis device based on trajectory data may be a computer device with data processing capabilities, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for illustration.

[0074] It is understood that this embodiment is described by taking the analysis of association relationships based on trajectory data as an example. The data set to be analyzed includes but is not limited to trajectory data of multiple objects.

[0075] Specifically, trajectory data includes the following features: characteristic value information, such as license plate numbers, personnel profile codes, and mobile phone IMSIs; site information, such as the capture device code (i.e., the device code, longitude, and latitude at which the trajectory information was captured); and time information, such as the capture date and capture time (i.e., the moment the trajectory information was captured). This embodiment, taking into account the characteristics of trajectory data, associates different types of devices using longitude and latitude information, enabling correlation analysis between two or more types of data to determine different types of associations, such as acquaintances, colleagues, family members, the car belonging to a specific person, the car owner and passenger being familiar with each other, the phone belonging to a specific person, and the combination of person and vehicle codes.

[0076] In one embodiment, a data set to be analyzed is obtained; a preset data analysis rule is constructed, and device information of the data set to be analyzed is analyzed based on the preset data analysis rule to obtain a device relationship table. In one example, constructing the preset data analysis rule includes: setting vehicle data as a first type of data and facial data as a second type of data; constructing a data type rule based on the first and second types of data; constructing a time rule based on whether the time difference between vehicle data and facial data captured at the same site meets a time range; constructing a device relationship rule based on whether the latitude and longitude distance between the vehicle capture device and the facial capture device meets a distance threshold; and constructing the preset data analysis rule based on the data type rule, time rule, and device relationship rule.

[0077] Specifically, preset data analysis rules are set, and the device information is analyzed by the preset data analysis rules to obtain a device relationship table. Exemplarily, the preset data analysis rules include but are not limited to data type rules, time rules, and device relationship rules. The data type rules include which two types of data (or multiple types of data) to analyze, such as analyzing facial data and vehicle data, vehicle data and electronic fence data, or facial data and electronic fence data. The time rules include the time period of the current analysis and the time interval when the two types of data appear at the same site. The device relationship rules include different types of site distances, and the set distances exceeding the same site are not counted.

[0078] It is understood that this embodiment uses the analysis of the human-vehicle association relationship, i.e., the analysis of facial data and vehicle data, as an example for explanation. The rules defining peers, i.e., the preset data analysis rules, include but are not limited to data type rules, time rules, and device relationship rules.

[0079] For example, data type rules include setting the first type of data to be personnel trajectory information and the second type of data to be vehicle trajectory data. Time rules include setting the query time interval to 5 seconds for each hour of data, and analyzing the previous day's data daily. Vehicle data and facial data captured at the same site that are within 5 seconds of each other are considered valid data. Device relationship rules include setting the latitude and longitude calculated distance to be within 10 meters for the same site. This means that if the latitude and longitude distance between the vehicle capture device and the facial capture device is less than 10 meters, they are considered to be the same site. It should be noted that the above 5 seconds and 10 meters are for illustrative purposes only, and this embodiment does not impose any restrictions on specific time and distance.

[0080] Specifically, the device information of the data set to be analyzed is analyzed based on the preset data analysis rules to obtain a device relationship table, including: extracting the facial device information and vehicle device information of the data set to be analyzed; analyzing the facial device information and vehicle device information according to the device relationship rules set according to the preset data analysis rules to determine the target facial device and target vehicle device as devices at the same location according to the device relationship rules; and constructing a device relationship table based on the target facial device and target vehicle device.

[0081] For example, a device relationship rule in a preset data analysis rule can be set, such as calculating by longitude and latitude that a distance of less than 10 meters is considered the same site. Based on the facial device information and vehicle device information of the data set to be analyzed, the facial devices and vehicle devices that are considered the same device are calculated and recorded in the device relationship table, indicating that a facial device and a vehicle device are devices at the same site.

[0082] It should be noted that the structure of the device relationship table may be B{type, siteA, siteB}, where type is the device type, siteA is the site code of the first type of data device, and siteB is the site code of the second type of data device.

[0083] Specifically, the basic information (e.g., longitude and latitude) of the vehicle device table (as shown in Table 1) and the face device table (as shown in Table 2) is queried. The distance between the face device and the vehicle device is calculated using the longitude and latitude information of the vehicle device and the face device. For example, based on the device relationship rule in the preset data analysis rules, if the calculated distance between the face device and the vehicle device is less than 10 meters, the face device and the vehicle device are considered to be at the same site and recorded in the device relationship table. The device relationship table for the face device and the vehicle device is shown in Table 3. The device relationship table in Table 3 includes the face device code, the vehicle device code, and the distance between the two.

[0084] Table 1

[0085] Vehicle equipment coding longitude latitude C0001 132.123445 39.123412 C0002 132.222325 39.123546 C0003 132.698745 39.685741 C0004 132.658974 39.563287 C0005 132.852147 39.521463 C0006 132.589632 39.874521 … … …

[0086] Table 2

[0087] Face device encoding longitude latitude F0001 132.123455 39.123422 F0002 132.222315 39.123536 F0003 132.963258 39.123654 F0004 132.258741 39.963258 F0005 132.741258 39.456321 F0006 132.852147 39.521463 … … …

[0088] Table 3

[0089] Vehicle equipment coding Face device encoding Distance (meters) C0001 F0001 1.5 C0002 F0002 1.2 C0005 F0006 0 … … …

[0090] In one embodiment, a one-to-one peer data set is generated according to the preset data analysis rules and the device relationship table, including: according to the preset data analysis rules and the device relationship table, associating the face trajectory data with the vehicle trajectory data through the device relationship to obtain an initial peer data set; and filtering the initial peer data set according to the time rule set by the preset data analysis rules to obtain a one-to-one peer data set.

[0091] Specifically, based on the preset data analysis rules and the device relationships in the device relationship table, the two types of trajectory data are compared to obtain a one-to-one peer dataset. For example, by associating facial trajectory data with vehicle trajectory data through the device relationship, and then filtering according to the time interval in the time rule, a one-to-one peer dataset can be obtained, that is, a person and a car appear at a certain place at a certain time on a certain day. In one example, the structure of the one-to-one peer dataset is T{rtarget, rsite, rtime, ttarget, tsite, ttime}, where rtarget is the first type of data feature value, rsite is the first type of data device site code, rtime is the first type of data capture time, ttarget is the second type of data feature value, tsite is the second type of data device site code, and ttime is the second type of data capture time.

[0092] For example, one-to-one peer data is stored in the database based on rule queries. To reduce the pressure of large data queries, a day's data can be divided into 24 queries, each querying one hour of data. Vehicle data and facial data within the same hour are linked by device code through the device relationship table for correlation queries. This yields a one-to-one peer relationship set between the vehicle data and facial data, i.e., a one-to-one peer data set. The one-to-one peer data set is shown in Table 4.

[0093] Table 4

[0094]

[0095]

[0096]

[0097] It should be noted that in this embodiment, to reduce the pressure of large data queries, one day's data can be divided into 24 queries, each querying one hour of data. By splitting the time period, querying in small time periods, and recording intermediate results, query efficiency is improved and the problem of slow real-time queries is solved.

[0098] In one embodiment, the one-to-one peer data set is grouped and counted based on the capture date to obtain a first peer data set. Specifically, according to preset data analysis rules and the one-to-one peer data set, the peer data sets of two objects (e.g., a person and a vehicle) are counted on a daily basis to obtain the first peer data set. The structure of the first peer data set is S{rtarget, ttarget, passday, num}, where rtarget is a first-category data feature value, ttarget is a second-category data feature value, passday is the capture date, and num is the current number of peers.

[0099] For example, the one-to-one travel dataset is grouped and counted based on the capture date to obtain a daily travel dataset (i.e., the first travel dataset), which shows how many times a person and a vehicle appeared together at a certain location on a certain day. For example, the number of times each subject traveled together was counted on a daily basis. The one-to-one travel dataset was grouped based on vehicle and facial landmarks, and the number of daily travels was counted to obtain a daily travel dataset. The daily travel dataset is shown in Table 5.

[0100] Table 5

[0101] Vehicle signs Face landmark date Number of trips Hubei A12345 Zhang San 2023-01-01 3 Hubei A12345 Zhang San 2023-01-02 3 Hubei A12345 Zhang San 2023-01-03 3 Hubei A12345 Zhang San 2023-01-04 3 Hubei A12345 Zhang San 2023-01-05 3 Hubei A12345 Zhang San 2023-01-06 3 Hubei A12345 Zhang San 2023-01-07 3 Hubei A12345 Zhang San 2023-01-08 3 Hubei A12345 Zhang San 2023-01-09 3 Hubei A12345 Zhang San 2023-01-10 3 Hubei A12345 Zhang San 2023-01-11 3 Hubei A12345 Zhang San 2023-01-12 3 … … … …

[0102] In one embodiment, the first travel data set is grouped and counted according to the characteristic value to obtain the second travel data set. According to the first travel data set, all travel data sets between each object are counted to obtain the second travel data set. Specifically, the above-mentioned daily travel data set (i.e., the first travel data set) is grouped and counted according to the characteristic value to obtain the entire travel data set (i.e., the second travel data set), that is, how many days a certain car has traveled with a certain person and how many times they have traveled together. The structure of the entire travel data set (i.e., the second travel data set) is R{rtarget, ttarget, dayNum, totalNum}, where rtarget is the first type of data characteristic value, ttarget is the second type of data characteristic value, dayNum is the number of days of travel, and totalNum is the total number of travel times.

[0103] For example, the number of days and times each object has traveled together are counted. Based on the daily travel data set, the number of days and times the vehicle signs and face signs have traveled together are counted again to obtain the entire travel data set (i.e., the second travel data set). The entire travel data set is shown in Table 6.

[0104] Table 6

[0105] Vehicle signs Face landmark Number of days Number of trips Hubei A77777 Zhao Liu 4 12 Hubei A12345 Zhang San 28 84 Hubei A54321 Li Si 30 120 Hubei A55555 Wang Wu 20 60 Hubei A99999 Panax notoginseng 10 33 … … … …

[0106] In one embodiment, the second peer data set is sorted based on the number of peer days and the number of peer times to obtain an ordered peer data set, including: arranging the second peer data set in reverse order based on the number of peer days to obtain an initial ordered data set; and arranging the initial ordered data set in reverse order according to the number of peer times to obtain an ordered peer data set.

[0107] Specifically, by sorting all peer data sets (i.e., the second peer data set), an ordered peer data set is obtained. This embodiment uses the example of sorting all peer data sets (i.e., the second peer data set) by the number of days of peer interaction and the number of times of peer interaction as an example for explanation, and this embodiment does not limit the specific sorting rules.

[0108] In one example, all peer data sets (i.e., the second peer data set) are sorted by the number of peer days and the number of peer times to obtain an ordered peer data set. The structure of the ordered peer data set is R{rtarget, ttarget, dayNum, totalNum}, where rtarget is the first type of data feature value, ttarget is the second type of data feature value, dayNum is the number of peer days, and totalNum is the total number of peer times.

[0109] For example, the peer result set (i.e., the second peer data set) is sorted in reverse order by the number of days of peer interaction and the number of times of peer interaction to obtain an ordered peer result set (i.e., an ordered peer data set). For example, all peer data sets (i.e., the second peer data set) are sorted in reverse order by the number of days of peer interaction and then sorted in reverse order by the number of times of peer interaction to obtain an ordered peer data set. The ordered peer result set is shown in Table 7.

[0110] It should be noted that this embodiment does not limit the order of sorting operations for the number of days and times of traveling together.

[0111] Table 7

[0112] Vehicle signs Face landmark Total days Number of days Number of trips Hubei A54321 Li Si 30 30 120 Hubei A12345 Zhang San 30 28 84 Hubei A55555 Wang Wu 30 20 60 Hubei A99999 Panax notoginseng 30 10 33 Hubei A77777 Zhao Liu 30 4 12 … … … … …

[0113] In one embodiment, the ordered peer data set is analyzed based on preset association relationship analysis rules to obtain an association relationship data set, including: obtaining data rules, period rules and relationship rules according to the preset association relationship analysis rules; judging the ordered peer data set according to the data rules, period rules and relationship rules to obtain a target data set that complies with the data rules, period rules and relationship rules; and generating an association relationship data set based on the target data set.

[0114] Exemplarily, the preset association relationship analysis rules include but are not limited to data rules, cycle rules, and relationship rules, wherein data rules refer to data types, such as face data, vehicle data, electronic fence data, etc.; cycle rules refer to the minimum number of days of the same peer and the proportion of the days; relationship rules refer to the relationship between the two.

[0115] Specifically, a preset association analysis rule is set. Based on the preset association analysis rule and the ordered peer dataset, the association dataset between each object is analyzed. The structure of the association dataset is R1{rtarget, ttarget, gx}, where rtarget is the first-category data feature value, ttarget is the second-category data feature value, and gx is the association relationship.

[0116] It should be noted that the trajectory data-based association analysis method proposed in this embodiment has a wider scope of application. Any eligible trajectory data can be used for association analysis, not limited to vehicle data, facial data, and mobile phone data, thereby increasing the number of association schemes between different data types. The association relationships in this embodiment can support the mutual association of multiple types of data, ultimately deriving association relationships between multiple objects, not limited to pairwise relationships.

[0117] This embodiment obtains a data set to be analyzed; constructs a preset data analysis rule, analyzes the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table; generates a one-to-one peer data set according to the preset data analysis rule and the device relationship table; performs grouping and statistics on the one-to-one peer data set based on the capture date to obtain a first peer data set; performs grouping and statistics on the first peer data set based on the characteristic value to obtain a second peer data set; sorts the second peer data set based on the number of days and times of peers to obtain an ordered peer data set; analyzes the ordered peer data set based on the preset association relationship analysis rule to obtain an association relationship data set. In this embodiment, based on the device information, time information, i.e., the capture date, and characteristic value information, different types of devices are associated in view of the above characteristic data, and the data can be subjected to association analysis, thereby analyzing the association relationship of different objects based on multiple types of trajectory data, solving the technical problem of slow, inefficient and inaccurate real-time query speed in existing investigation work due to the huge amount of data.

[0118] In some embodiments, as Figure 4 As shown, based on the first embodiment, a second embodiment of the method for analyzing association relationships based on trajectory data of the present invention is proposed. Step S700 includes:

[0119] Step S701: obtaining data rules, cycle rules, and relationship rules according to preset association relationship analysis rules;

[0120] Step S702: determining the ordered peer data set according to the data rule, period rule, and relationship rule to obtain a target data set that meets the data rule, period rule, and relationship rule;

[0121] Step S703: Generate an association relationship dataset based on the target dataset.

[0122] In one embodiment, the method further includes: setting the face trajectory data as the first category of data and the vehicle trajectory data as the second category of data; constructing data rules based on the first category of data and the second category of data; constructing period rules based on whether the number of days of travel meets the travel time rules and whether the person appears in the main driver's seat of the vehicle; constructing relationship rules based on whether the vehicle and the person have a subordinate relationship; and constructing preset association relationship analysis rules based on the data rules, period rules and relationship rules.

[0123] Specifically, the preset association relationship analysis rules include but are not limited to data rules, cycle rules, and relationship rules, where data rules refer to data types, such as face data, vehicle data, electronic fence data, etc.; cycle rules refer to the minimum number of days and the proportion of days; relationship rules refer to the relationship between the two.

[0124] In one example, a preset association analysis rule is set. Based on the preset association analysis rule and an ordered peer dataset, the association dataset between objects is analyzed. Based on the ordered peer dataset and the preset association analysis rule, a relationship dataset is obtained, i.e., a result set indicating that a certain car belongs to a certain person. The structure of the relationship dataset is R1{rtarget, ttarget, gx}, where rtarget is the first-category data feature value, ttarget is the second-category data feature value, and gx is the association relationship.

[0125] Exemplarily, preset association relationship analysis rules are defined: data rule, the first type of data is face trajectory data, and the second type of data is vehicle trajectory data; period rule, at least 5 days of travel together, the proportion of travel days is 90%, and the person appears in the main driver's seat of the car; relationship rule, this car belongs to this person.

[0126] Specifically, a preset association analysis rule is set. Days with fewer than two daily trips are not counted. Then, based on the ratio of the number of trips to the total number of days (the trip-day ratio), the relationship between the person and the vehicle is determined: if the trip-day ratio does not exceed 20%, the person and the vehicle are considered passengers or temporary users; if the trip-day ratio exceeds 20% but does not exceed 60%, the person and the vehicle are considered short-term users; if the trip-day ratio exceeds 60% but does not exceed 90%, the person and the vehicle are considered long-term users; and if the trip-day ratio reaches 90%, the person and the vehicle are considered owners. The trip-day ratio results can be obtained by calculating the preset association analysis rule. The results of the trip-day ratio are shown in Table 8.

[0127] Table 8

[0128] Vehicle signs Face landmark Comparison of days between peers Hubei A54321 Li Si 100％ Hubei A12345 Zhang San 93％ Hubei A55555 Wang Wu 67％ Hubei A99999 Panax notoginseng 33％ Hubei A77777 Zhao Liu 13％ … … …

[0129] In one example, an association relationship data set is obtained according to the association relationship analysis result set, and the association relationship data set is shown in Table 9.

[0130] Table 9

[0131] Vehicle signs Face landmark Association Hubei A54321 Li Si car owner Hubei A12345 Zhang San car owner Hubei A55555 Wang Wu Long-term car use Hubei A99999 Panax notoginseng Short-term car use Hubei A77777 Zhao Liu Temporary car … … …

[0132] In this embodiment, by analyzing the data to obtain the association relationship data set, a useful relationship between people, vehicles, and codes is obtained to help police find clues. It can be used as an important reference when the exact relationship between people, vehicles, and codes cannot be obtained in real life.

[0133] In this embodiment, data rules, periodic rules, and relationship rules are obtained based on preset association relationship analysis rules; the ordered peer dataset is judged based on the data rules, periodic rules, and relationship rules to obtain a target dataset that conforms to the data rules, periodic rules, and relationship rules; and an association relationship dataset is generated based on the target dataset. In this embodiment, based on device information, time information, i.e., the capture date, and feature value information, different types of devices are associated with each other in view of the above-mentioned feature data, and association analysis can be performed on the data, thereby analyzing the association relationships between different objects based on multiple types of trajectory data. This solves the technical problem in existing investigation work that real-time queries are slow, inefficient, and inaccurate due to the large amount of data.

[0134] In addition, an embodiment of the present invention further provides a storage medium storing a trajectory data-based association relationship analysis program. When the trajectory data-based association relationship analysis program is executed by a processor, the steps of the trajectory data-based association relationship analysis method described above are implemented.

[0135] Reference Figure 4 , Figure 4This is a structural block diagram of the first embodiment of the trajectory data-based correlation analysis device of the present invention.

[0136] like Figure 4 As shown, the trajectory data-based correlation analysis device includes:

[0137] An acquisition module 10 is used to acquire a set of data to be analyzed;

[0138] A construction module 20 is configured to construct a preset data analysis rule, and analyze the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table;

[0139] A generating module 30, configured to generate a one-to-one peer data set according to the preset data analysis rules and the device relationship table;

[0140] A first statistical module 40 is configured to perform group statistics on the one-to-one peer dataset based on the capture date to obtain a first peer dataset;

[0141] A second statistical module 50 is configured to perform grouping statistics on the first same-same data set according to characteristic values ​​to obtain a second same-same data set;

[0142] A sorting module 60 is configured to sort the second peer data set based on the number of peer days and the number of peer times to obtain an ordered peer data set;

[0143] The analysis module 70 is configured to analyze the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset.

[0144] It should be noted that this embodiment is described by taking the analysis of association relationships based on trajectory data as an example. The data set to be analyzed includes but is not limited to trajectory data of multiple objects.

[0145] Specifically, trajectory data includes the following features: characteristic value information, such as license plate numbers, personnel profile codes, and mobile phone IMSIs; site information, such as the capture device code (i.e., the device code, longitude, and latitude at which the trajectory information was captured); and time information, such as the capture date and capture time (i.e., the moment the trajectory information was captured). This embodiment, taking into account the characteristics of trajectory data, associates different types of devices using longitude and latitude information, enabling correlation analysis between two or more types of data to determine different types of associations, such as acquaintances, colleagues, family members, the car belonging to a specific person, the car owner and passenger being familiar with each other, the phone belonging to a specific person, and the combination of person and vehicle codes.

[0146] In one embodiment, a data set to be analyzed is obtained; a preset data analysis rule is constructed, and device information of the data set to be analyzed is analyzed based on the preset data analysis rule to obtain a device relationship table. In one example, constructing the preset data analysis rule includes: setting vehicle data as a first type of data and facial data as a second type of data; constructing a data type rule based on the first and second types of data; constructing a time rule based on whether the time difference between vehicle data and facial data captured at the same site meets a time range; constructing a device relationship rule based on whether the latitude and longitude distance between the vehicle capture device and the facial capture device meets a distance threshold; and constructing the preset data analysis rule based on the data type rule, time rule, and device relationship rule.

[0147] Specifically, preset data analysis rules are set, and the device information is analyzed by the preset data analysis rules to obtain a device relationship table. Exemplarily, the preset data analysis rules include but are not limited to data type rules, time rules, and device relationship rules. The data type rules include which two types of data (or multiple types of data) to analyze, such as analyzing facial data and vehicle data, vehicle data and electronic fence data, or facial data and electronic fence data. The time rules include the time period of the current analysis and the time interval when the two types of data appear at the same site. The device relationship rules include different types of site distances, and the set distances exceeding the same site are not counted.

[0148] It is understood that this embodiment uses the analysis of the human-vehicle association relationship, i.e., the analysis of facial data and vehicle data, as an example for explanation. The rules defining peers, i.e., the preset data analysis rules, include but are not limited to data type rules, time rules, and device relationship rules.

[0149] For example, data type rules include setting the first type of data to be personnel trajectory information and the second type of data to be vehicle trajectory data. Time rules include setting the query time interval to 5 seconds for each hour of data, and analyzing the previous day's data daily. Vehicle data and facial data captured at the same site that are within 5 seconds of each other are considered valid data. Device relationship rules include setting the latitude and longitude calculated distance to be within 10 meters for the same site. This means that if the latitude and longitude distance between the vehicle capture device and the facial capture device is less than 10 meters, they are considered to be the same site. It should be noted that the above 5 seconds and 10 meters are for illustrative purposes only, and this embodiment does not impose any restrictions on specific time and distance.

[0150] Specifically, the device information of the data set to be analyzed is analyzed based on the preset data analysis rules to obtain a device relationship table, including: extracting the facial device information and vehicle device information of the data set to be analyzed; analyzing the facial device information and vehicle device information according to the device relationship rules set according to the preset data analysis rules to determine the target facial device and target vehicle device as devices at the same location according to the device relationship rules; and constructing a device relationship table based on the target facial device and target vehicle device.

[0151] For example, a device relationship rule in a preset data analysis rule can be set, such as calculating by longitude and latitude that a distance of less than 10 meters is considered the same site. Based on the facial device information and vehicle device information of the data set to be analyzed, the facial devices and vehicle devices that are considered the same device are calculated and recorded in the device relationship table, indicating that a facial device and a vehicle device are devices at the same site.

[0152] It should be noted that the structure of the device relationship table may be B{type, siteA, siteB}, where type is the device type, siteA is the site code of the first type of data device, and siteB is the site code of the second type of data device.

[0153] Specifically, the basic information (e.g., longitude and latitude) of the vehicle device table (as shown in Table 1 in the embodiment of the association relationship analysis method based on trajectory data) and the face device table (as shown in Table 2 in the embodiment of the association relationship analysis method based on trajectory data) is queried, and the distance between the face device and the vehicle device is calculated using the longitude and latitude information of the vehicle device and the face device. For example, according to the device relationship rule in the preset data analysis rule, if the calculated distance between the face device and the vehicle device is less than 10 meters, the face device and the vehicle device are considered to be the same site and recorded in the device relationship table. The device relationship table is shown in Table 3 in the embodiment of the association relationship analysis method based on trajectory data. The device relationship table in Table 3 includes the face device code, the vehicle device code, and the distance between the two.

[0154] In one embodiment, a one-to-one peer data set is generated according to the preset data analysis rules and the device relationship table, including: according to the preset data analysis rules and the device relationship table, associating the face trajectory data with the vehicle trajectory data through the device relationship to obtain an initial peer data set; and filtering the initial peer data set according to the time rule set by the preset data analysis rules to obtain a one-to-one peer data set.

[0155] Specifically, based on the preset data analysis rules and the device relationships in the device relationship table, the two types of trajectory data are compared to obtain a one-to-one peer dataset. For example, by associating facial trajectory data with vehicle trajectory data through the device relationship, and then filtering according to the time interval in the time rule, a one-to-one peer dataset can be obtained, that is, a person and a car appear at a certain place at a certain time on a certain day. In one example, the structure of the one-to-one peer dataset is T{rtarget, rsite, rtime, ttarget, tsite, ttime}, where rtarget is the first type of data feature value, rsite is the first type of data device site code, rtime is the first type of data capture time, ttarget is the second type of data feature value, tsite is the second type of data device site code, and ttime is the second type of data capture time.

[0156] For example, one-to-one peer data is stored in the database based on rule queries. To reduce the pressure of large data queries, a day's data can be divided into 24 queries, each querying one hour of data. Vehicle data and facial data within the same hour are linked by device code through a device relationship table for correlation query. This yields a one-to-one peer relationship set between the vehicle data and facial data, i.e., a one-to-one peer data set. This one-to-one peer data set is shown in Table 4 of the embodiment of the trajectory data-based correlation relationship analysis method.

[0157] It should be noted that in this embodiment, to reduce the pressure of large data queries, one day's data can be divided into 24 queries, each querying one hour of data. By splitting the time period, querying in small time periods, and recording intermediate results, query efficiency is improved and the problem of slow real-time queries is solved.

[0158] In one embodiment, the one-to-one peer data set is grouped and counted based on the capture date to obtain a first peer data set. Specifically, according to preset data analysis rules and the one-to-one peer data set, the peer data sets of two objects (e.g., a person and a vehicle) are counted on a daily basis to obtain the first peer data set. The structure of the first peer data set is S{rtarget, ttarget, passday, num}, where rtarget is a first-category data feature value, ttarget is a second-category data feature value, passday is the capture date, and num is the current number of peers.

[0159] For example, the one-to-one peer data set is grouped and counted based on the capture date to obtain a daily peer data set (i.e., the first peer data set), which shows how many times a person and a vehicle appear at the same place on a certain day. For example, the number of times each object appears together is counted on a daily basis. The one-to-one peer data set is grouped based on vehicle and facial markers, and the number of times each object appears together is counted each day to obtain a daily peer data set, as shown in Table 5 of the embodiment of the above-mentioned trajectory data-based correlation relationship analysis method.

[0160] In one embodiment, the first travel data set is grouped and counted according to the characteristic value to obtain the second travel data set. According to the first travel data set, all travel data sets between each object are counted to obtain the second travel data set. Specifically, the above-mentioned daily travel data set (i.e., the first travel data set) is grouped and counted according to the characteristic value to obtain the entire travel data set (i.e., the second travel data set), that is, how many days a certain car has traveled with a certain person and how many times they have traveled together. The structure of the entire travel data set (i.e., the second travel data set) is R{rtarget, ttarget, dayNum, totalNum}, where rtarget is the first type of data characteristic value, ttarget is the second type of data characteristic value, dayNum is the number of days of travel, and totalNum is the total number of travel times.

[0161] Exemplarily, the number of days and the number of times each object has traveled together are counted. Based on the daily travel data set, the number of days and the number of times the vehicle signs and face signs have traveled together are counted again to obtain the entire travel data set (i.e., the second travel data set). The entire travel data set is shown in Table 6 in the embodiment of the above-mentioned correlation relationship analysis method based on trajectory data.

[0162] In one embodiment, the second peer data set is sorted based on the number of peer days and the number of peer times to obtain an ordered peer data set, including: arranging the second peer data set in reverse order based on the number of peer days to obtain an initial ordered data set; and arranging the initial ordered data set in reverse order according to the number of peer times to obtain an ordered peer data set.

[0163] Specifically, by sorting all peer data sets (i.e., the second peer data set), an ordered peer data set is obtained. This embodiment uses the example of sorting all peer data sets (i.e., the second peer data set) by the number of days of peer interaction and the number of times of peer interaction as an example for explanation, and this embodiment does not limit the specific sorting rules.

[0164] In one example, all peer data sets (i.e., the second peer data set) are sorted by the number of peer days and the number of peer times to obtain an ordered peer data set. The structure of the ordered peer data set is R{rtarget, ttarget, dayNum, totalNum}, where rtarget is the first type of data feature value, ttarget is the second type of data feature value, dayNum is the number of peer days, and totalNum is the total number of peer times.

[0165] For example, the peer result set (i.e., the second peer data set) is sorted in reverse order by the number of days of peer interaction and the number of times of peer interaction to obtain an ordered peer result set (i.e., an ordered peer data set). For example, all peer data sets (i.e., the second peer data set) are sorted in reverse order by the number of days of peer interaction and then sorted in reverse order by the number of times of peer interaction to obtain an ordered peer data set. The ordered peer data set is shown in Table 7 of the embodiment of the above-mentioned method for analyzing association relationships based on trajectory data.

[0166] It should be noted that this embodiment does not limit the order of sorting operations for the number of days and times of traveling together.

[0167] In one embodiment, the ordered peer data set is analyzed based on preset association relationship analysis rules to obtain an association relationship data set, including: obtaining data rules, period rules and relationship rules according to the preset association relationship analysis rules; judging the ordered peer data set according to the data rules, period rules and relationship rules to obtain a target data set that complies with the data rules, period rules and relationship rules; and generating an association relationship data set based on the target data set.

[0168] Exemplarily, the preset association relationship analysis rules include but are not limited to data rules, cycle rules, and relationship rules, wherein data rules refer to data types, such as face data, vehicle data, electronic fence data, etc.; cycle rules refer to the minimum number of days of the same peer and the proportion of the days; relationship rules refer to the relationship between the two.

[0169] Specifically, a preset association analysis rule is set. Based on the preset association analysis rule and the ordered peer dataset, the association dataset between each object is analyzed. The structure of the association dataset is R1{rtarget, ttarget, gx}, where rtarget is the first-category data feature value, ttarget is the second-category data feature value, and gx is the association relationship.

[0170] It should be noted that the trajectory data-based association analysis device proposed in this embodiment has a wider scope of application. Any qualified trajectory data can be used for association analysis, not limited to vehicle data, facial data, and mobile phone data, thereby increasing the number of association schemes between different data types. The association relationship of this embodiment can support the mutual association of multiple types of data, ultimately deriving association relationships between multiple objects, not limited to relationships between two objects.

[0171] In this embodiment, based on device information, time information, i.e., the capture date, and feature value information, different types of devices are associated in view of the above feature data, and data can be associated and analyzed, thereby analyzing the association relationship between different objects based on multiple types of trajectory data, solving the technical problem of slow, inefficient, and inaccurate real-time query speed in existing investigation work due to the huge amount of data.

[0172] In addition, for technical details not fully described in the embodiment of the trajectory data-based association relationship analysis device, reference can be made to the trajectory data-based association relationship analysis method described above provided in any embodiment of the present invention, and will not be repeated here.

[0173] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0174] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0175] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0176] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0177] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0178] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for analyzing association relationships based on trajectory data, characterized in that: The method comprises: Get the data set to be analyzed; Constructing a preset data analysis rule, and analyzing the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table; Generate a one-to-one peer data set according to the preset data analysis rules and the device relationship table; performing grouping statistics on the one-to-one peer dataset based on the capture date to obtain a first peer dataset; performing grouping and statistics on the first peer data set according to the characteristic values ​​to obtain a second peer data set; sorting the second peer data set based on the number of peer days and the number of peer times to obtain an ordered peer data set; Analyzing the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset; The construction of preset data analysis rules includes: setting vehicle data as the first type of data and facial data as the second type of data; constructing data type rules based on the first and second types of data; constructing time rules based on whether the time difference between vehicle data and facial data captured at the same site meets the time range; constructing device relationship rules based on whether the latitude and longitude distance between the vehicle capture device and the facial capture device meets the distance threshold; and constructing preset data analysis rules based on the data type rules, time rules, and device relationship rules. Analyzing the device information of the data set to be analyzed based on the preset data analysis rules to obtain a device relationship table, including: extracting facial device information and vehicle device information of the data set to be analyzed; analyzing the facial device information and vehicle device information according to device relationship rules set by the preset data analysis rules to determine target facial devices and target vehicle devices that are devices at the same location according to the device relationship rules; and constructing a device relationship table based on the target facial devices and target vehicle devices; Generating a one-to-one peer data set according to the preset data analysis rules and the device relationship table includes: associating face trajectory data with vehicle trajectory data through device relationships according to the preset data analysis rules and the device relationship table to obtain an initial peer data set; filtering the initial peer data set according to a time rule set by the preset data analysis rules to obtain a one-to-one peer data set.

2. The method for analyzing association relationships based on trajectory data according to claim 1, wherein: The step of sorting the second peer data set based on the number of peer encounter days and the number of peer encounter times to obtain an ordered peer data set includes: Arrange the second peer data set in reverse order based on the number of peer days to obtain an initial ordered data set; The initial ordered data set is arranged in reverse order according to the number of times in the same row to obtain an ordered data set in the same row.

3. The method for analyzing association relationships based on trajectory data according to claim 1, wherein: The method further comprises: The face trajectory data is set as the first category of data, and the vehicle trajectory data is set as the second category of data; Constructing data rules based on the first and second types of data; Establish a cycle rule based on whether the number of days traveling together meets the travel time rules and whether the person appears in the main driver's seat of the vehicle; Establish relationship rules based on whether vehicles and personnel have a subordinate relationship; Preset association relationship analysis rules are constructed based on the data rules, period rules and relationship rules.

4. The method for analyzing association relationships based on trajectory data according to claim 3, wherein: The step of analyzing the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset includes: Obtain data rules, cycle rules and relationship rules based on preset association relationship analysis rules; Determining the ordered peer dataset according to the data rules, period rules, and relationship rules to obtain a target dataset that complies with the data rules, period rules, and relationship rules; Generate an association relationship dataset based on the target dataset.

5. A correlation analysis device based on trajectory data, characterized in that: The device comprises: An acquisition module is used to obtain the data set to be analyzed; A construction module, configured to construct a preset data analysis rule, and analyze the device information of the data set to be analyzed based on the preset data analysis rule to obtain a device relationship table; A generating module, configured to generate a one-to-one peer data set according to the preset data analysis rules and the device relationship table; A first statistical module is used to group and count the one-to-one peer data set based on the capture date to obtain a first peer data set; A second statistical module, configured to perform grouping statistics on the first same-same data set according to characteristic values ​​to obtain a second same-same data set; a sorting module, configured to sort the second peer data set based on the number of peer days and the number of peer times to obtain an ordered peer data set; An analysis module, configured to analyze the ordered peer dataset based on preset association relationship analysis rules to obtain an association relationship dataset; The construction of preset data analysis rules includes: setting vehicle data as the first type of data and facial data as the second type of data; constructing data type rules based on the first and second types of data; constructing time rules based on whether the time difference between vehicle data and facial data captured at the same site meets the time range; constructing device relationship rules based on whether the latitude and longitude distance between the vehicle capture device and the facial capture device meets the distance threshold; and constructing preset data analysis rules based on the data type rules, time rules, and device relationship rules. Analyzing the device information of the data set to be analyzed based on the preset data analysis rules to obtain a device relationship table, including: extracting facial device information and vehicle device information of the data set to be analyzed; analyzing the facial device information and vehicle device information according to device relationship rules set by the preset data analysis rules to determine target facial devices and target vehicle devices that are devices at the same location according to the device relationship rules; and constructing a device relationship table based on the target facial devices and target vehicle devices; Generating a one-to-one peer data set according to the preset data analysis rules and the device relationship table includes: associating face trajectory data with vehicle trajectory data through device relationships according to the preset data analysis rules and the device relationship table to obtain an initial peer data set; filtering the initial peer data set according to a time rule set by the preset data analysis rules to obtain a one-to-one peer data set.

6. A device for analyzing association relationships based on trajectory data, characterized in that: The trajectory data-based association relationship analysis device includes: a memory, a processor, and a trajectory data-based association relationship analysis program stored in the memory and executable on the processor, wherein the trajectory data-based association relationship analysis program is configured to implement the trajectory data-based association relationship analysis method according to any one of claims 1 to 4.

7. A storage medium, characterized in that: The storage medium stores a trajectory data-based correlation analysis program, which is configured to enable a processor to implement the trajectory data-based correlation analysis method according to any one of claims 1 to 4 when executed.

Images