Method and system for full state personnel and vehicle association based on intercept code device

Abstract

The application provides a method and system for full-state personnel and vehicle association based on a code detection device, comprising: collecting communication device data and vehicle data; selecting an association time period; performing data cleaning processing on the communication device data in the time period; performing piece-by-piece data analysis on the communication device data and the vehicle data after data cleaning through a time domain, a space domain and a data feature domain to obtain corresponding personnel and vehicle association results; repeating until association calculation of all communication device data is completed to obtain final information rate. The application performs analysis on the collected communication device data through a time domain, a space domain and a data feature domain, matches information with a target such as a ship, utilizes static data of the communication device and the personnel, and forms association of the personnel and the target such as the ship. The application fills the vacancy in intelligent management of association of the personnel and the target such as the ship, and improves association efficiency and coverage rate of the personnel and the ship and supervision efficiency.

Description

Technical Field

[0001] This invention relates to the field of code detection data analysis and fusion technology, specifically to a method and system for associating personnel and vehicles in all states based on code detection equipment. Background Technology

[0002] Code detection equipment is a type of device used for monitoring and eavesdropping on communications. This equipment is commonly used to monitor and eavesdrop on technologies such as radio broadcasts, mobile phones, and satellite communications. By capturing and analyzing communication signals, code detection equipment can identify the location, identity, and activity of communication devices. However, traditional code detection equipment can only determine the range of the information source, such as a fan-shaped area with an angle of 60° and a radius of 5 kilometers, making it difficult to pinpoint the location of the communication device. In the field of ship management, accurately associating communication devices with ships, and further associating personnel with ships, can provide crucial data support for relevant units. However, current technologies require significant manual intervention and the active cooperation of ship personnel, which allows uncooperative violators to take advantage of loopholes. Monitoring such individuals and ships remains extremely difficult for relevant units, and the efficiency of law enforcement personnel is low.

[0003] Therefore, there is a market need for a method and system based on detection equipment that can associate personnel and vehicles in all states, enabling intelligent management while providing important reference data for relevant law enforcement personnel, thereby improving regulatory efficiency. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the purpose of this invention is to provide a method and system for associating personnel and vehicles in all states based on a detection device.

[0005] A method for associating full-state personnel and vehicles based on a code detection device according to the present invention includes:

[0006] Step S1: Collect data from communication equipment and vehicles;

[0007] Step S2: Select the relevant time period;

[0008] Step S3: Perform data cleaning processing on the communication device data within the time period;

[0009] Step S4: Analyze the cleaned communication equipment data and vehicle data line by line through the time domain, spatial domain, and data feature domain to obtain the corresponding association results between personnel and vehicles;

[0010] Repeat steps S3 to S4 until the association calculation of all communication device data is completed, and the final information rate is obtained.

[0011] Preferably, the communication device data includes the communication device serial number, the communication device data acquisition time, the communication device data acquisition quantity, and the communication device data acquisition location;

[0012] The vehicle data includes vehicle location, vehicle distance, vehicle identification, and vehicle tracking time.

[0013] Preferably, the data cleaning process includes filtering interfering data features, which include low-frequency data features and short-range data features;

[0014] The low-frequency data characteristic refers to the number of data collected by the communication device being less than the quantity threshold H. count ;

[0015] The near-range data characteristics refer to communication device data that is evenly distributed in various directions, and the existence time of the communication device data is much longer than the data analysis time.

[0016] Preferably, the time domain refers to the degree of correlation calculated between communication device data and vehicle target data in the time dimension, and is determined by calculating the time correlation coefficient Coef. time The corresponding time correlation results are obtained, and the calculation formula is as follows:

[0017]

[0018] Among them, Coef time Represents the time correlation coefficient, t imsi-start Indicates the time period (t) start , t stop The time t is the time from which data collection of the corresponding communication device begins. imsi-stop Indicates the time period (t) start , t stop The last time data was collected from the communication device within t) target-start Represents the time period (t) imsi-start , t imsi-stop The time t is the time from which the corresponding target data is collected. target-stop Indicates the time period (t) imsi-start , t imsi-stop The time t is the last time the corresponding target data was collected within the specified period. start t represents the start time of the current time period. stop This indicates the end time for the current time period.

[0019] Preferably, the spatial domain includes both orientation correlation and distance correlation.

[0020] The degree of azimuth correlation is determined by calculating the azimuth correlation coefficient Coefa.zi The corresponding directional association results are obtained using the following calculation formula:

[0021]

[0022] Among them, Coef azi Azi represents the azimuth correlation coefficient. target-max Azi represents the maximum azimuth value of the target within the associated time period. target-min Azi represents the minimum azimuth value of the target within the associated time period. imsi-max Azi represents the maximum azimuth value of the serial number within the associated time period. imsi-min Indicates the minimum azimuth value of the serial number within the associated time period;

[0023] The distance correlation process is calculated by using the distance correlation coefficient Coefd. ist The corresponding distance association results are obtained, and the calculation formula is as follows:

[0024]

[0025] Among them, Coef dist H represents the distance correlation coefficient. dist-azi Represents the distance variance threshold, var dist This represents the variance between distance information in the communication device data and distance information in the target data closest to the time of data acquisition from the communication device.

[0026] Preferably, the data feature domain includes various factors obtained through correlation analysis between the time domain and the spatial domain, forming data domain features related to personnel and transportation vehicles. Further analysis of the data domain yields the overall correlation confidence score, calculated using the following formula:

[0027] score=f(Coef time Coef azi Coef dist )

[0028] Where, score represents the overall association confidence rate, and Coef time Coef represents the time correlation coefficient. azi Coef represents the azimuth correlation coefficient. dist represents the distance correlation coefficient, and f() represents the composite calculation function.

[0029] Preferably, the composite calculation results corresponding to the selected multiple time periods are superimposed to obtain the final information rate score. result The formula is as follows:

[0030] score result =α*score last+β*score current +γ*score before

[0031] Among them, 0≤α, β, γ≤1, and α+β+γ=1, score last The score represents the result of the calculation in the previous period. current The score represents the calculation result for the current period. before This indicates the result of a previous calculation.

[0032] A system for associating all-state personnel and vehicles based on a code detection device, according to the present invention, includes:

[0033] Module M1: Collects data from communication equipment and vehicles;

[0034] Module M2: Select the associated time period;

[0035] Module M3: Performs data cleaning processing on communication device data within the specified time period;

[0036] Module M4: Through time domain, spatial domain, and data feature domain, it performs data analysis on a data-by-data basis on the cleaned communication equipment data and vehicle data to obtain the corresponding association results between personnel and vehicles;

[0037] Repeatedly trigger modules M3 through M4 until the association calculation of all communication device data is completed, and the final information rate is obtained.

[0038] Preferably, the communication device data includes the communication device serial number, the communication device data acquisition time, the communication device data acquisition quantity, and the communication device data acquisition location;

[0039] The vehicle data includes vehicle location, vehicle distance, vehicle identification, and vehicle tracking time.

[0040] Preferably, the data cleaning process includes filtering interfering data features, which include low-frequency data features and short-range data features;

[0041] The low-frequency data characteristic refers to the number of data collected by the communication device being less than the quantity threshold H. count ;

[0042] The near-range data characteristics refer to communication device data that is evenly distributed in various directions, and the existence time of the communication device data is much longer than the data analysis time.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. This invention analyzes collected communication device data in the time domain, spatial domain, and data feature domain, and matches this data with targets such as ships to establish a connection between communication devices and these targets. By utilizing static data of communication devices and personnel, the invention associates communication devices with their owners, ultimately forming a link between personnel and targets such as ships. This fills the gap in intelligent management of the association between personnel and targets such as ships.

[0045] 2. In this invention, the detection device mainly works in the search and patrol state to monitor the entire area of ​​interest, collect communication device information indiscriminately within the monitored area, and perform indiscriminate correlation calculation, which is called conventional correlation calculation in this system. Under special circumstances, the detection device is in the target guidance state, and can perform key correlation calculation on the guided detection target, while performing conventional correlation calculation on other targets.

[0046] 3. This invention does not limit the working state of the detection equipment and is unaffected by changes in the working state of the detection equipment. It can still complete the target association analysis of personnel and vehicles with high accuracy, effectively improving the efficiency and coverage of personnel-vehicle association. It provides a more efficient solution for personnel-vehicle association based on detection technology and improves regulatory efficiency.

[0047] 4. This invention can associate communication equipment with any object equipped with communication equipment. It is not only applicable to the shipbuilding industry, but also to multiple water-related management industries such as public security, border inspection, maritime affairs, fishery administration, and water conservancy, improving monitoring effectiveness and having high applicability. Attached Figure Description

[0048] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0049] Figure 1 This is a system workflow diagram.

[0050] Figure 2 This is a diagram illustrating the time correlation coefficient.

[0051] Figure 3 This is a diagram illustrating the degree of spatial correlation. Detailed Implementation

[0052] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0053] This invention analyzes communication equipment information collected by the detection device from multiple dimensions, including time domain, spatial domain, and data characteristics. It then combines this analysis with dynamic and static data of the target vehicle to establish a correlation between humans and the vehicle. It should be noted that "all-state" in this invention means that it no longer distinguishes between whether the detection device is in search and patrol or target guidance mode; this invention can ignore differences in operational status and complete the correlation between humans and the vehicle.

[0054] According to the present invention, a method for associating full-state personnel and vehicles based on a code detection device is provided, such as... Figure 1 As shown, it includes:

[0055] Step S1: Collect communication equipment data and vehicle data. Communication equipment data includes the communication equipment serial number, data collection time, number of data items collected, and data collection location. The communication equipment serial number, also known as the IMSI code, serves as the identification information for the communication equipment. Communication equipment data is collected using a directional tracking detection device. This device can perform comprehensive monitoring and data collection across the deployment location monitoring area. Upon collecting communication equipment data, it assigns location information based on the system equipment's operating status, providing location reference values. Finally, based on the analysis results of the time and location distribution characteristics of each communication equipment's data, data analysis is performed. Combined with vehicle target data, the association between people and vehicle targets is ultimately achieved. Furthermore, this detection device primarily operates during search and patrol monitoring of the entire area of ​​interest, indiscriminately collecting communication equipment information within the monitored area and performing indiscriminate association calculations (referred to as conventional association calculations in this invention). Under special circumstances, the detection device is in a target-guided state, enabling focused association calculations on the guided detection target while performing conventional association calculations on other targets. Under target guidance, the serial code data and the ship target move together, with similar time and spatial spans, and the degree of correlation is determined based on the degree of similarity.

[0056] Vehicle data includes vehicle location, distance, identification information, and tracking time. This data can be collected via sensors, including vessels, vehicles, drones, and various base stations.

[0057] Step S2: Select the relevant time period.

[0058] Step S3: Perform data cleaning on the communication equipment data within the time period. Data cleaning includes filtering out interfering data features, which include low-frequency data features and short-range data features. Specifically, low-frequency data features refer to data collected from communication equipment with a quantity less than a threshold H. countThe data refers to communication equipment data. Short-range data characteristics refer to communication equipment data evenly distributed across various locations, with the data's existence time significantly exceeding the data analysis time. "significantly exceeding" means the data's existence time is greater than twice the data analysis time.

[0059] Step S4: Analyze the cleaned communication equipment data and vehicle data line by line through the time domain, spatial domain, and data feature domain to obtain the corresponding association results between personnel and vehicles.

[0060] The time domain refers to the degree of correlation between communication equipment data and vehicle target data calculated over time, and is determined by calculating the time correlation coefficient Coef. time The corresponding time correlation results are obtained, and the calculation formula is as follows:

[0061]

[0062] Among them, Coef time Represents the time correlation coefficient, t imsi-start Indicates the time period (t) start , t stop The time t is the time from which data collection of the corresponding communication device begins. imsi-stop Indicates the time period (t) start , t stop The last time data was collected from the communication device within t) target-start Represents the time period (t) imsi-start , t imsi-stop The time t is the time from which the corresponding target data is collected. target-stop Indicates the time period (t) imsi-start , t imsi-stop The time t is the last time the corresponding target data was collected within the specified period. start t represents the start time of the current time period. stop This indicates the end time for the current time period.

[0063] The spatial domain includes the degree of orientation correlation and the degree of distance correlation; the degree of orientation correlation is calculated by the orientation correlation coefficient Coef. azi The corresponding directional association results are obtained using the following calculation formula:

[0064]

[0065] Among them, Coef azi Azi represents the azimuth correlation coefficient. target-max Azi represents the maximum azimuth value of the target within the associated time period. target-min Azi represents the minimum azimuth value of the target within the associated time period. imsi-max Azi represents the maximum azimuth value of the serial number within the associated time period. imsi-minThis represents the minimum azimuth value of the serial number within the associated time period. The distance association period is calculated using the distance association coefficient Coef. dist The corresponding distance association results are obtained, and the calculation formula is as follows:

[0066]

[0067] Among them, Coef dist H represents the distance correlation coefficient. dist-azi Represents the distance variance threshold, var dist This represents the variance between distance information in the communication device data and distance information in the target data closest to the time of data acquisition from the communication device.

[0068] The data feature domain includes various factors obtained through correlation analysis between the time and spatial domains, forming data domain features related to personnel and transportation vehicles. Further analysis of the data domain yields the overall correlation confidence score, calculated as follows:

[0069] score=f(Coef time Coef azi Coef dist )

[0070] Where, score represents the overall association confidence rate, and Coef time Coef represents the time correlation coefficient. azi Coef represents the azimuth correlation coefficient. dist represents the distance correlation coefficient, and f() represents the composite calculation function.

[0071] Repeat steps S3 to S4 until the correlation calculation of all communication device data is completed, and the final information rate is obtained. The composite calculation results corresponding to the selected multiple time periods are then superimposed to obtain the final information rate score. result The formula is as follows:

[0072] score result =α*score last +β*score current +γ*score before

[0073] Among them, 0≤α, β, γ≤1, and α+β+γ=1, score last The score represents the result of the calculation in the previous period. current The score represents the calculation result for the current period. before This indicates the result of a previous calculation.

[0074] Furthermore, taking a ship as an example, the specific steps for implementing the method of associating all-state personnel with the vehicle based on the code detection device according to the present invention are described as follows:

[0075] First, communication equipment collects data, acquiring ship data through sensors such as radar and AIS. This invention automatically initiates a search and patrol of the monitored area, or provides target guidance for passing vessels, and collects information from communication equipment within the monitored area. The system records the location and time of data collection and stores the data in a database for future real-time or historical data analysis.

[0076] Furthermore, the distribution of communication device data exhibits statistical regularities. Therefore, the correlation results for the current time require historical data to complete the data correlation. This invention segments the data into time periods, setting a period T. The system will analyze the data from three time periods, assuming the current time is t. current The system started running at time t. init The three time periods are [t] current -T,t current ), [t current -2T, t current -T), [t init , t current -2T). In the calculation of some characteristic factors and results, the AHP (Analytic Hierarchy Process) concept is used to perform weighted summation of the calculation results to form the final calculation result.

[0077] Next, before data analysis, it is necessary to identify and clean the interference data. This is because detection equipment generates a lot of interference data when monitoring communication devices. For example, due to reflections during transmission of electromagnetic waves emitted by communication devices, signals from communication devices not in the detection antenna's monitoring direction can also be detected. For instance, due to the sidelobes of the electromagnetic waves emitted by the detection antenna, when communication devices close to the detection equipment are detected by sidelobes, there is a significant deviation between the actual location of the communication device and the direction of the detection antenna, leading to inaccurate data. For example, due to the influence of the antenna's back lobe, communication devices with opposite antenna orientations may also be detected.

[0078] The interference data characteristics mainly include low-frequency data characteristics and short-range data characteristics. Since the number of communication device data detected by reflection and back lobe is generally low, referred to as low-frequency data in this invention, and its data distribution is irregular, to avoid filtering out detection data from distant communication devices that also exhibit low quantity characteristics, the low-frequency data needs to satisfy a variance greater than a certain value when filtering the number of communication devices. That is, within the data analysis time, the number of communication device data must be less than a quantity threshold H.count The data from the communication device is considered low-frequency and needs to be filtered out as interference. The communication device data detected by the sidelobes is uniformly distributed across all directions, and its existence time is much longer than the data analysis time. Therefore, communication device data meeting these conditions needs to be filtered out as short-range serial data received by the sidelobes. The detected communication device exists before the ship target appears in the system; therefore, filtering data meeting the above conditions can further remove the aforementioned interference data.

[0079] Next, after data cleaning, data analysis and processing begin. This primarily involves analyzing each piece of collected communication equipment data in the time domain, spatial domain, and data feature domain to arrive at the final human-ship correlation result. Specifically, the time domain refers to the degree of correlation calculated between communication equipment data and ship target data over time. In a full-state analysis scenario, the time correlation coefficient Coef... time Used to measure the compatibility between a ship and its communication acquisition equipment, as mentioned above, under different time periods, assuming the start and end times of that period are denoted by t... start t stop The time correlation coefficient Coef represents... time The calculation formula is:

[0080]

[0081] Among them, t imsi-start For the time period (t) start , t stop Within ) the time when data collection of the corresponding communication device begins, t imsi-stop For the time period (t) start , t stop Within ) the time when the last data was collected from the communication device; t target-start For the time period (t) imsi-start , t imsi-stop Within ) the time when the corresponding target data begins to be collected, t target-stop For the time period (t) imsi-start , t imsi-stop Within a given timeframe, the time at which the corresponding target data was last collected. The working principle of the time correlation coefficient is as follows: Figure 2 As shown, the results can be divided into four main categories:

[0082] (1) is a complete match association, that is, at time (t) imsi-start , t imsi-stop Within this range, the target exists throughout the entire process, and the time correlation coefficient is calculated as Coef. time =1;

[0083] (2), (3), and (4) are incomplete matching states, that is, at time (t)imsi-start , t imsi-stop Within this range, if the target is not present throughout the entire process, the time correlation coefficient calculation result is 0 ≤ Coef. time ≤1.

[0084] The spatial domain includes two dimensions: the degree of orientational correlation and the degree of distance correlation. The orientational correlation method is calculated similarly to the time correlation coefficient and is called the orientational correlation coefficient (Coef). azi The calculation formula is:

[0085]

[0086] Among them, Coef azi The value range is [0, 1]. The calculation of distance correlation first uses time alignment to calculate the variance between the distance information in the communication device data and the distance information in the target data closest to the communication device data acquisition time, obtaining the result var. dist ,like Figure 3 As shown. Let the distance correlation coefficient be Coef. dist The calculation method is as follows:

[0087]

[0088] Among them, H dist-azi This is the distance variance threshold, which can be adaptively selected based on different scenario characteristics and needs. (Coef) dist The value range is [0, 1].

[0089] By analyzing the correlation between the time and spatial domains, various factors are obtained, forming the data domain characteristics of the human-ship correlation. Further analysis within the data domain yields the overall correlation confidence score. The confidence score is calculated by combining the time and spatial characteristic factors, using the following formula:

[0090] score=f(Coef time Coef azi Coef dist )

[0091] f(Coef time Coef azi Coef dist ) is a calculation function, such as weighted average, maximum likelihood estimation function, maximum a posteriori estimation function, etc.

[0092] Finally, through the above calculation process, the confidence rate for a single period was calculated. Then, by superimposing the calculation results from multiple time periods, the final information rate score was obtained. result The calculation formula is as follows:

[0093] score result =α*score last +β*score current +γ*score before

[0094] Among them, 0≤α, β, γ≤1, and α+β+γ=1. score last The score is the result of the previous period's calculation. current The score is the result calculated for the current period. before This is the result of previous calculations.

[0095] This invention analyzes collected communication device data in the time, spatial, and data feature domains, and matches this data with targets such as ships to establish a connection between communication devices and these targets. By utilizing static data on communication devices and personnel, the invention links communication devices to their owners, ultimately establishing a connection between personnel and targets such as ships, thus filling a gap in the intelligent management of such connections. While establishing the connection between people and ships, this invention also provides a confidence rate for this connection, offering crucial reference data for law enforcement personnel and effectively improving regulatory efficiency.

[0096] The present invention also provides a system for associating personnel and vehicles in all states based on a code detection device. Those skilled in the art can implement the system by executing the steps of the method for associating personnel and vehicles in all states based on a code detection device. That is, the method for associating personnel and vehicles in all states based on a code detection device can be understood as a preferred embodiment of the system for associating personnel and vehicles in all states based on a code detection device.

[0097] A system for associating all-state personnel and vehicles based on a code detection device, according to the present invention, includes:

[0098] Module M1: Collects data from communication equipment and vehicles. Communication equipment data includes the communication equipment serial number, data collection time, number of data points collected, and data collection location. Vehicle data includes the vehicle's location, distance, identification information, and tracking time.

[0099] Module M2: Select the associated time period.

[0100] Module M3: Performs data cleaning on communication equipment data within a given time period. Data cleaning includes filtering out interfering data features, which include low-frequency and short-range data features. Low-frequency data features refer to data collected from communication equipment where the number of data points is less than a threshold H. countThe data refers to communication equipment data that is evenly distributed across various locations, and whose existence time is much longer than the data analysis time.

[0101] Module M4: This module analyzes the cleaned communication equipment and transportation vehicle data line by line through time, space, and data feature domains to obtain the corresponding correlation results between personnel and transportation vehicles. The time domain refers to the degree of correlation calculated between communication equipment data and target transportation vehicle data over time, and this is achieved by calculating the time correlation coefficient, Coef. time The corresponding time correlation results are obtained, and the calculation formula is as follows:

[0102]

[0103] Among them, Coef time Represents the time correlation coefficient, t imsi-start Indicates the time period (t) start , t stop The time t is the time from which data collection of the corresponding communication device begins. imsi-stop Indicates the time period (t) start , t stop The last time data was collected from the communication device within t) target-start Represents the time period (t) imsi-start , t imsi-stop The time t is the time from which the corresponding target data is collected. target-stop Indicates the time period (t) imsi-start , t imsi-stop The time t is the last time the corresponding target data was collected within the specified period. start t represents the start time of the current time period. stop This indicates the end time for the current time period.

[0104] The spatial domain includes the degree of orientation correlation and the degree of distance correlation; the degree of orientation correlation is calculated by the orientation correlation coefficient Coef. azi The corresponding directional association results are obtained using the following calculation formula:

[0105]

[0106] Among them, Coef azi Azi represents the azimuth correlation coefficient. target-max Azi represents the maximum azimuth value of the target within the associated time period. target-min Azi represents the minimum azimuth value of the target within the associated time period. imsi- m ax Azi represents the maximum azimuth value of the serial number within the associated time period. imsi-min This represents the minimum azimuth value of the serial number within the associated time period, calculated using the distance correlation coefficient Coef.dist The corresponding distance association results are obtained, and the calculation formula is as follows:

[0107]

[0108] Among them, Coef dist H represents the distance correlation coefficient. dist-azi Represents the distance variance threshold, var dist This represents the variance between distance information in the communication device data and distance information in the target data closest to the time of data acquisition from the communication device.

[0109] The data feature domain includes various factors obtained through correlation analysis between the time and spatial domains, forming data domain features related to personnel and transportation vehicles. Further analysis of the data domain yields the overall correlation confidence score, calculated as follows:

[0110] score=f(Coef time Coef azi Coef dist )

[0111] Where, score represents the overall association confidence rate, and Coef time Coef represents the time correlation coefficient. azi Coef represents the azimuth correlation coefficient. dist represents the distance correlation coefficient, and f() represents the composite calculation function.

[0112] Modules M3 through M4 are repeatedly triggered until the correlation calculation of all communication device data is completed, yielding the final information rate. The composite calculation results corresponding to the selected multiple time periods are then superimposed to obtain the final information rate score. result The formula is as follows:

[0113] score result =α*score last +β*score current +γ*score before

[0114] Among them, 0≤α, β, γ≤1, and α+β+γ=1, score last The score represents the result of the calculation in the previous period. current The score represents the calculation result for the current period. before This indicates the result of a previous calculation.

[0115] Those skilled in the art will understand that, in addition to implementing the system, apparatus, and their modules provided by this invention in purely computer-readable program code, the same program can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system, apparatus, and their modules provided by this invention can be considered a hardware component, and the modules included therein for implementing various programs can also be considered structures within the hardware component; alternatively, modules for implementing various functions can be considered both software programs implementing the method and structures within the hardware component.

[0116] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for full state person-vehicle association based on a snooping device, characterized in that, include: Step S1: Collect data from communication equipment and vehicles; Step S2: Select the relevant time period; Step S3: Perform data cleaning processing on the communication device data within the time period; Step S4: Analyze the cleaned communication equipment data and vehicle data line by line through the time domain, spatial domain, and data feature domain to obtain the corresponding association results between personnel and vehicles; Repeat steps S3 to S4 until the association calculation of all communication device data is completed, and the final information rate is obtained. The time domain refers to the correlation degree calculated in the time dimension between the communication device data and the vehicle target data by calculating the time correlation coefficient The corresponding time correlation result is obtained, and the calculation formula is as follows: in, Indicates the time correlation coefficient. Indicates the time period The time when data collection from the corresponding communication device begins. Indicates the time period The time when the last data was collected from the communication device. Indicates time period The time when the corresponding target data was first collected. Indicates the time period The time when the corresponding target data was last collected. Indicates the start time of the current time period. Indicates the end time of the current time period; The spatial domain includes the degree of orientation correlation and the degree of distance correlation; The degree of orientation correlation is calculated by an orientation correlation coefficient The corresponding orientation correlation result is obtained, and the calculation formula is as follows: in, Represents the azimuth correlation coefficient. This indicates the maximum azimuth value of the target within the associated time period. This represents the minimum azimuth value of the target within the associated time period. This indicates the maximum azimuth value of the serial number within the associated time period. Indicates the minimum azimuth value of the serial number within the associated time period; The distance correlation process is calculated by the distance correlation coefficient. The corresponding distance association results are obtained, and the calculation formula is as follows: wherein, denotes a distance correlation coefficient, denotes a distance variance threshold, denotes a variance between distance information in the communication device data and distance information in the target data closest in time to the communication device data collection time; The data domain characteristic includes the analysis of the correlation degree between the time domain and the space domain, each factor is obtained, the data domain characteristic of the correlation between the personnel and the carrier is formed, and the total correlation confidence rate is obtained by further analyzing the data domain The calculation formula is as follows: wherein, represents the total correlation confidence rate, represents the time correlation coefficient, represents the orientation correlation coefficient, represents the distance correlation coefficient, represents the composite calculation function.

2. The method of full state person-vehicle association based on a device of a snooping code according to claim 1, characterized in that, The communication device data includes the communication device serial number, communication device data acquisition time, communication device data acquisition quantity, and communication device data acquisition location; The vehicle data includes vehicle location, vehicle distance, vehicle identification, and vehicle tracking time.

3. The method of full state person-vehicle association based on a device of a probe code according to claim 1, characterized in that, The data cleaning process includes filtering out interfering data features, which include low-frequency data features and short-range data features. The low-frequency data feature refers to that the quantity of data collection of the communication device is less than a quantity threshold ; The near-range data characteristics refer to communication device data that is evenly distributed in various directions, and the existence time of the communication device data is much longer than the data analysis time.

4. The method of full state person-vehicle association based on a device of a snooping code according to claim 1, characterized in that, The final information rate is obtained by superimposing the composite calculation results corresponding to the selected time periods , as follows: wherein , and , denotes the result of the calculation of the previous period, denotes the result of the calculation of the current period, denotes the result of the previous calculation.

5. A system for associating personnel and vehicles in all states based on a code detection device, characterized in that, include: Module M1: Collects data from communication equipment and vehicles; Module M2: Select the associated time period; Module M3: Performs data cleaning processing on communication device data within the specified time period; Module M4: Through time domain, spatial domain, and data feature domain, it performs data analysis on a data-by-data basis on the cleaned communication equipment data and vehicle data to obtain the corresponding association results between personnel and vehicles; Repeatedly trigger modules M3 to M4 until the association calculation of all communication device data is completed, and the final information rate is obtained; The time domain refers to the correlation degree calculated in the time dimension between the communication device data and the vehicle target data by calculating the time correlation coefficient The corresponding time correlation result is obtained, and the calculation formula is as follows: in, Indicates the time correlation coefficient. Indicates the time period The time when data collection from the corresponding communication device begins. Indicates the time period The time when the last data was collected from the communication device. Indicates time period The time when the corresponding target data was first collected. Indicates the time period The time when the corresponding target data was last collected. Indicates the start time of the current time period. Indicates the end time of the current time period; The spatial domain includes the degree of orientation correlation and the degree of distance correlation; The degree of orientation correlation is calculated by an orientation correlation coefficient The corresponding orientation correlation result is obtained, and the calculation formula is as follows: in, Represents the azimuth correlation coefficient. This indicates the maximum azimuth value of the target within the associated time period. This represents the minimum azimuth value of the target within the associated time period. This indicates the maximum azimuth value of the serial number within the associated time period. Indicates the minimum azimuth value of the serial number within the associated time period; The distance correlation program calculates the distance correlation coefficient The corresponding distance correlation result is obtained, and the calculation formula is as follows: wherein, denotes a distance correlation coefficient, denotes a distance variance threshold, denotes a variance between distance information in the communication device data and distance information in the target data closest in time to the communication device data collection time; The data domain characteristic includes the analysis of the correlation degree between the time domain and the space domain, each factor is obtained, the data domain characteristic of the correlation between the personnel and the carrier is formed, and the total correlation confidence rate is obtained by further analyzing the data domain The calculation formula is as follows: wherein, represents the total correlation confidence rate, represents the time correlation coefficient, represents the azimuth correlation coefficient, represents the distance correlation coefficient, represents the composite calculation function.

6. The system for full state person-vehicle association based on a code device according to claim 5, characterized in that, The communication device data includes the communication device serial number, communication device data acquisition time, communication device data acquisition quantity, and communication device data acquisition location; The vehicle data includes vehicle location, vehicle distance, vehicle identification, and vehicle tracking time.

7. The system for full state person-vehicle association based on a code device according to claim 5, wherein, The data cleaning process includes filtering out interfering data features, which include low-frequency data features and short-range data features. The low-frequency data feature refers to that the quantity of data collection of the communication device is less than a quantity threshold ; The near-range data characteristics refer to communication device data that is evenly distributed in various directions, and the existence time of the communication device data is much longer than the data analysis time.

Images