A Diffusion Trajectory Analysis Method and System Based on a Double Screening Model

Abstract

The present invention discloses a diffusion trajectory analysis method and system based on a double screening model. Among them, the method includes: obtaining user terminal information; generating positioning data according to the user terminal information and hotspot area information; obtaining multivariate data through a big data platform according to the positioning data; and performing data screening and generation according to the summary result of the multivariate data and a first screening model to obtain the action trajectory result of the first target population and the result of the diffusion trajectory personnel. The present invention solves the technical problem in the prior art that the calculation process of the behavior trajectory only uses the information and data obtained in real time or collected by sensors for analysis, and calculates and generates the mathematical result of the behavior trajectory through certain analysis rules, but cannot summarize more data factors for the determination of the behavior trajectory, nor can it directly use the information collected by sensors or the information collected by the data platform as feature vectors through a neural network model for input and output a more accurate behavior trajectory result. At the same time, for people with diffusion trajectories, exclusion screening cannot be achieved, so the security effect of security technology cannot be increased.

Description

Technical Field

[0001] The present invention relates to the field of trajectory recognition, and in particular to a diffusion trajectory analysis method and system based on a double-screen model. Background Art

[0002] With the continuous development of artificial intelligence, many artificial intelligence related technologies have also been applied in the field of civil defense and security to assist in screening suspicious persons or potentially dangerous persons. By predicting and judging the trajectory of people in popular areas, idle people with diffuse irregular movements can be screened out. The presence of these people is the focus of security work. When predicting and analyzing behavioral trajectories, fixed rules of behavioral trajectories are usually used to analyze and calculate the existing trajectory parameter information, and the calculated results are processed to obtain the final behavioral trajectory map.

[0003] However, the behavior trajectory calculation process in the prior art only uses the information and data obtained in real time or collected by sensors for analysis, and calculates and generates the mathematical results of the behavior trajectory through certain analysis rules, but cannot aggregate more data factors to determine the behavior trajectory, nor can it use the neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector and output a more accurate behavior trajectory result. At the same time, it is impossible to achieve exclusionary screening for people with diffuse trajectories, and therefore it is impossible to increase the security effect of security technology.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiment of the present invention provides a diffuse trajectory analysis method and system based on a double screening model, so as to at least solve the problem that the behavior trajectory calculation process in the prior art only uses the information and data acquired in real time or collected by sensors for analysis, and calculates and generates the mathematical results of the behavior trajectory through certain analysis rules, but cannot summarize more data factors to determine the behavior trajectory, nor can it use a neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector and output a more accurate behavior trajectory result. At the same time, it is impossible to achieve exclusionary screening for people with diffuse trajectories, and therefore the technical problem that the security effect of security technology cannot be increased.

[0006] According to one aspect of an embodiment of the present invention, a diffusion trajectory analysis method based on a dual screening model is provided, including: obtaining user terminal information; generating positioning data based on the user terminal information and hot spot area information; obtaining multivariate data through a big data platform based on the positioning data; and performing data screening and generation based on the summary results of the multivariate data and a first screening model to obtain action trajectory results and diffusion trajectory personnel results of a first target population.

[0007] Optionally, after obtaining the user terminal information, the method further includes: determining hotspot area information and personnel information according to the user terminal information.

[0008] Optionally, obtaining multivariate data through a big data platform based on the positioning data includes: aggregating the positioning data and the multivariate data to obtain the aggregated result.

[0009] Optionally, the data is screened and generated according to the summary results of the multivariate data and the first screening model to obtain the action trajectory results and diffuse trajectory personnel results of the first target population, including: obtaining the action trajectory results of the first target population; inputting the action trajectory results of the first target population into a trajectory summary matrix module, and inputting the personnel information and the trajectory summary matrix module as input feature vector values ​​of the second screening model to obtain the screened diffuse trajectory personnel results.

[0010] According to another aspect of an embodiment of the present invention, a diffusion trajectory analysis system based on a dual screening model is also provided, including: an acquisition module for acquiring user terminal information; a generation module for generating positioning data based on the user terminal information and hot spot area information; a big data module for acquiring multivariate data through a big data platform based on the positioning data; a trajectory module for performing data screening and generation based on the summary results of the multivariate data and a first screening model to obtain action trajectory results and diffusion trajectory personnel results of the first target population.

[0011] Optionally, the system further includes: a determination module, configured to determine hotspot area information and personnel information based on the user terminal information.

[0012] Optionally, the big data module includes: a summary unit, used to summarize the positioning data and the multivariate data to obtain the summary result.

[0013] Optionally, the trajectory module includes: an acquisition unit, used to obtain the movement trajectory results of the first target population; a diffusion unit, used to input the movement trajectory results of the first target population into a trajectory summary matrix module, and input the personnel information and the trajectory summary matrix module as input feature vector values ​​of a second screening model to obtain the screened diffusion trajectory personnel results.

[0014] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute a diffusion trajectory analysis method based on a dual sieve model.

[0015] According to another aspect of an embodiment of the present invention, an electronic system is also provided, comprising a processor and a memory; the memory stores computer-readable instructions, and the processor is used to run the computer-readable instructions, wherein the computer-readable instructions execute a diffusion trajectory analysis method based on a dual-screening model when running.

[0016] Compared with the prior art, the beneficial effects of the present invention are: in the embodiment of the present invention, user terminal information is obtained; positioning data is generated according to the user terminal information and hot spot area information; multivariate data is obtained through a big data platform according to the positioning data; data is screened and generated according to the summary results of the multivariate data and the first screening model to obtain the action trajectory results of the first target population and the diffuse trajectory personnel results. This solves the problem that the behavior trajectory calculation process in the prior art only uses the information and data obtained in real time or collected by sensors for analysis, and calculates and generates the behavior trajectory mathematical results through certain analysis rules, but cannot summarize more data factors to determine the behavior trajectory, and cannot use a neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector, and output a more accurate behavior trajectory result. At the same time, it is impossible to achieve exclusionary screening for people with diffuse trajectories, and therefore the technical problem that the security effect of the security technology cannot be increased. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a diffusion trajectory analysis method based on a double sieve model according to an embodiment of the present invention;

[0019] Figure 2is a structural block diagram of a diffusion trajectory analysis system based on a double sieve model according to an embodiment of the present invention;

[0020] Figure 3 This is a trajectory prediction method in the prior art according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, a method embodiment of a diffusion trajectory analysis method based on a dual sieve model is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0024] Embodiment 1

[0025] Figure 1 is a flow chart of a diffusion trajectory analysis method based on a double sieve model according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining user terminal information.

[0027] Step S104: Generate positioning data according to the user terminal information and hot spot area information.

[0028] Step S106, obtaining multivariate data through a big data platform according to the positioning data.

[0029] Step S108, performing data screening and generation according to the summary results of the multivariate data and the first screening model to obtain the action trajectory results and the diffuse trajectory personnel results of the first target population.

[0030] Optionally, after obtaining the user terminal information, the method further includes: determining hotspot area information and personnel information according to the user terminal information.

[0031] Optionally, obtaining multivariate data through a big data platform based on the positioning data includes: aggregating the positioning data and the multivariate data to obtain the aggregated result.

[0032] Optionally, the data is screened and generated according to the summary results of the multivariate data and the first screening model to obtain the action trajectory results and diffuse trajectory personnel results of the first target population, including: obtaining the action trajectory results of the first target population; inputting the action trajectory results of the first target population into a trajectory summary matrix module, and inputting the personnel information and the trajectory summary matrix module as input feature vector values ​​of the second screening model to obtain the screened diffuse trajectory personnel results.

[0033] Specifically, Figure 3 As shown, the behavior trajectory calculation process in the prior art only uses the information and data acquired in real time or collected by sensors for analysis, and calculates and generates the mathematical results of the behavior trajectory through certain analysis rules, but cannot summarize more data factors to determine the behavior trajectory, nor can it use the neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector, and output the behavior trajectory result. The present invention increases the diversity in the generation process of the behavior trajectory through the collection and processing of big data diversified data, so that the analysis results of the behavior trajectory are more accurate and reliable. Further, not only the real-time behavior parameters can be obtained through the big data platform, but also the behavior trajectory route of the behavior trajectory object that is about to occur can be analyzed through historical data, and the route can be used as the basis for predicting the behavior trajectory. By utilizing the user terminal information, the historical navigation trajectory and historical walking data of the navigation map APP in the user terminal can also be obtained, and the motion data in the user terminal can also be obtained. Through the motion data and historical navigation data, it can be obtained what kind of walking trajectory the user may take when passing through this area, such as going to a barber shop, going to a library, going to an office building, etc. After the behavioral trajectory is screened by the first screening model, the screening model of the diffuse trajectory personnel can also be used for diffuse screening of the remaining personnel, thereby obtaining suspicious people for security.

[0034] With respect to the embodiment of the present invention, in the specific implementation, the embodiment of the present invention must first obtain user terminal information; specifically, in order to detect and analyze the user's movement trajectory, it is necessary to obtain the user terminal information, and the user terminal information includes the user terminal's hardware address code, networking information, the total number of user terminals, etc., which is used to determine the operation status of the user terminal within a fixed area, so as to perform the user movement trajectory analysis operation according to the user terminal information.

[0035] The hotspot area information is determined based on the user terminal information; specifically, the hotspot area information is determined based on the user terminal information and the required information of the motion trajectory, wherein the hotspot area information is used to define the range within which the user terminal motion trajectory analysis is performed, to avoid technical problems such as unclear areas and inaccurate motion trajectory analysis.

[0036] Generate positioning data based on the user terminal information and the hotspot area information; specifically, in order to determine the trajectory of the user terminal in real time through the positioning service, it is necessary to combine the networking information in the user terminal information with the hotspot area information, calculate the trajectory movement route of all user terminals through the calculation method of A=αF(b), and use the trajectory movement route as a prerequisite for the final trajectory analysis result.

[0037] In addition, the above-mentioned user terminal information can be utilized by obtaining the historical navigation trajectory and historical walking data of the navigation map APP in the user terminal, and the motion data in the user terminal can also be obtained. The motion data and historical navigation data can be used to obtain what kind of walking trajectory the user may take when passing through the area, such as going to a barber shop, a library, an office building, etc. Through the analysis of the daily data of the users in the above-mentioned user terminals, the trajectory movement routes of all user terminals can be further calculated, and summarized as positioning data for subsequent prediction of the user's final behavior trajectory in combination with the big data content.

[0038] According to the positioning data, multivariate data is obtained through a big data platform, wherein the multivariate data includes target data, action data, other data, etc., such as a user's ordering, taxi-hailing, historical location movement information, etc.; the positioning data and the multivariate data are aggregated and processed to obtain an aggregated result, and the aggregated result is optimized to filter out erroneous data; specifically, according to the positioning data, multivariate data is obtained through a big data platform, wherein the multivariate data includes target data, action data, other data, etc., such as a user's ordering, taxi-hailing, historical location movement information, etc.; specifically, in order to combine positioning service data with big data information To predict and analyze the action trajectory, it is necessary to obtain and collect relevant information of user terminals involved in the hot spots in the big data platform. The multivariate data includes target data, action data, and other data, such as the user's ordering, taxi-hailing, and historical location movement information. Another example is the ordering service information of user terminals in hot spots, which can include where the user terminal is about to move to pick up the meal and bring the picked-up food back to the starting point of the user terminal. This process can determine the movement trajectory of the user terminal that sent the ordering information from time a to time b. Time a to time b is the estimated time for the user terminal to wait for the meal, pick up the meal, and return.

[0039] According to the optimized summary results and the first screening model, data screening and generation are performed to obtain the action trajectory results of the first target population; the positioning data and the multivariate data are aggregated and processed to obtain the summary results, and the summary results are optimized to filter out erroneous data. Specifically, the positioning data of the user terminal and the multi-source data obtained by the big data platform are aggregated to obtain the movement parameters of the user terminal, wherein the above movement parameters include the user's real-time movement location and the user's possible movement location points, that is, accurate predictions are made through big data, which improves the efficiency and accuracy of action trajectory analysis. In addition, in order to further optimize the aggregated data and reduce the situation of data errors and confusion, it is also necessary to eliminate missing data and delete erroneous data according to the optimization rules. Among them, the first screening model can be a mathematical model obtained by training the DNN deep neural network model, which can input the above-mentioned optimized summary results as feature vectors, and obtain the final action trajectory data according to the algorithm of the historical data training results, and feed it back to the server.

[0040] The action trajectory results of the first target population are input into a trajectory summary matrix module, and the personnel information and the trajectory summary matrix module are input as input feature vector values ​​of a second screening model to obtain the screened diffuse trajectory personnel results.

[0041] The algorithm logic of the above-mentioned DNN deep learning model can adopt the DLSS computing function in the Nv computing chip, and perform planning input and planning input of feature vectors for various behavior trajectories of personnel in the first screening model, and obtain known trajectory data based on the personnel information. Then in the second screening model, the above-mentioned screening algorithm can be used to exclude the screening operator in the product module. Then, after the characteristic vector input of the behavior trajectory results and the personnel information, the final value result of the remaining diffuse crowd can be obtained. For the diffuse personnel, it can be used as the suspicious crowd range of the security system, and further screening work can be carried out according to manual screening rules.

[0042] Through the above embodiments, the problem that the behavior trajectory calculation process in the prior art only uses the information and data obtained in real time or collected by sensors for analysis, and calculates and generates the mathematical results of the behavior trajectory through certain analysis rules, but cannot aggregate more data factors to determine the behavior trajectory, nor can it use the neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector and output a more accurate behavior trajectory result, and at the same time, it is impossible to achieve exclusionary screening for people with diffuse trajectories, and therefore the technical problem that the security effect of the security technology cannot be increased.

[0043] Embodiment 2

[0044] Figure 2 is a structural block diagram of a diffusion trajectory analysis system based on a double sieve model according to an embodiment of the present invention, such as Figure 2 As shown, the system includes:

[0045] The acquisition module 20 is used to acquire user terminal information.

[0046] The generating module 22 is used to generate positioning data according to the user terminal information and the hot spot area information.

[0047] The big data module 24 is used to obtain multivariate data through a big data platform according to the positioning data.

[0048] The trajectory module 26 is used to screen and generate data according to the summary results of the multivariate data and the first screening model to obtain the action trajectory results and diffuse trajectory personnel results of the first target population.

[0049] Optionally, the system further includes: a determination module, configured to determine hotspot area information and personnel information based on the user terminal information.

[0050] Optionally, the big data module includes: a summary unit, used to summarize the positioning data and the multivariate data to obtain the summary result.

[0051] Optionally, the trajectory module includes: an acquisition unit, used to obtain the movement trajectory results of the first target population; a diffusion unit, used to input the movement trajectory results of the first target population into a trajectory summary matrix module, and input the personnel information and the trajectory summary matrix module as input feature vector values ​​of a second screening model to obtain the screened diffusion trajectory personnel results.

[0052] Specifically, Figure 3 As shown, the behavior trajectory calculation process in the prior art only uses the information and data acquired in real time or collected by sensors for analysis, and calculates and generates the mathematical results of the behavior trajectory through certain analysis rules, but cannot summarize more data factors to determine the behavior trajectory, nor can it use the neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector, and output the behavior trajectory result. The present invention increases the diversity in the generation process of the behavior trajectory through the collection and processing of big data diversified data, so that the analysis results of the behavior trajectory are more accurate and reliable. Further, not only the real-time behavior parameters can be obtained through the big data platform, but also the behavior trajectory route of the behavior trajectory object that is about to occur can be analyzed through historical data, and the route can be used as the basis for predicting the behavior trajectory. By utilizing the user terminal information, the historical navigation trajectory and historical walking data of the navigation map APP in the user terminal can also be obtained, and the motion data in the user terminal can also be obtained. Through the motion data and historical navigation data, it can be obtained what kind of walking trajectory the user may take when passing through this area, such as going to a barber shop, going to a library, going to an office building, etc. After the behavioral trajectory is screened by the first screening model, the screening model of the diffuse trajectory personnel can also be used for diffuse screening of the remaining personnel, thereby obtaining suspicious people for security.

[0053] With respect to the embodiment of the present invention, in the specific implementation, the embodiment of the present invention must first obtain user terminal information; specifically, in order to detect and analyze the user's movement trajectory, it is necessary to obtain the user terminal information, and the user terminal information includes the user terminal's hardware address code, networking information, the total number of user terminals, etc., which is used to determine the operation status of the user terminal within a fixed area, so as to perform the user movement trajectory analysis operation according to the user terminal information.

[0054] The hotspot area information is determined based on the user terminal information; specifically, the hotspot area information is determined based on the user terminal information and the required information of the motion trajectory, wherein the hotspot area information is used to define the range within which the user terminal motion trajectory analysis is performed, to avoid technical problems such as unclear areas and inaccurate motion trajectory analysis.

[0055] Generate positioning data based on the user terminal information and the hotspot area information; specifically, in order to determine the trajectory of the user terminal in real time through the positioning service, it is necessary to combine the networking information in the user terminal information with the hotspot area information, calculate the trajectory movement route of all user terminals through the calculation method of A=αF(b), and use the trajectory movement route as a prerequisite for the final trajectory analysis result.

[0056] In addition, the above-mentioned user terminal information can be utilized by obtaining the historical navigation trajectory and historical walking data of the navigation map APP in the user terminal, and the motion data in the user terminal can also be obtained. The motion data and historical navigation data can be used to obtain what kind of walking trajectory the user may take when passing through the area, such as going to a barber shop, a library, an office building, etc. Through the analysis of the daily data of the users in the above-mentioned user terminals, the trajectory movement routes of all user terminals can be further calculated, and summarized as positioning data for subsequent prediction of the user's final behavior trajectory in combination with the big data content.

[0057] According to the positioning data, multivariate data is obtained through a big data platform, wherein the multivariate data includes target data, action data, other data, etc., such as a user's ordering, taxi-hailing, historical location movement information, etc.; the positioning data and the multivariate data are aggregated and processed to obtain an aggregated result, and the aggregated result is optimized to filter out erroneous data; specifically, according to the positioning data, multivariate data is obtained through a big data platform, wherein the multivariate data includes target data, action data, other data, etc., such as a user's ordering, taxi-hailing, historical location movement information, etc.; specifically, in order to combine positioning service data with big data information To predict and analyze the action trajectory, it is necessary to obtain and collect relevant information of user terminals involved in the hot spots in the big data platform. The multivariate data includes target data, action data, and other data, such as the user's ordering, taxi-hailing, and historical location movement information. Another example is the ordering service information of user terminals in hot spots, which can include where the user terminal is about to move to pick up the meal and bring the picked-up food back to the starting point of the user terminal. This process can determine the movement trajectory of the user terminal that sent the ordering information from time a to time b. Time a to time b is the estimated time for the user terminal to wait for the meal, pick up the meal, and return.

[0058] According to the optimized summary results and the first screening model, data screening and generation are performed to obtain the action trajectory results of the first target population; the positioning data and the multivariate data are aggregated and processed to obtain the summary results, and the summary results are optimized to filter out erroneous data. Specifically, the positioning data of the user terminal and the multi-source data obtained by the big data platform are aggregated to obtain the movement parameters of the user terminal, wherein the above movement parameters include the user's real-time movement location and the user's possible movement location points, that is, accurate predictions are made through big data, which improves the efficiency and accuracy of action trajectory analysis. In addition, in order to further optimize the aggregated data and reduce the situation of data errors and confusion, it is also necessary to eliminate missing data and delete erroneous data according to the optimization rules. Among them, the first screening model can be a mathematical model obtained by training the DNN deep neural network model, which can input the above-mentioned optimized summary results as feature vectors, and obtain the final action trajectory data according to the algorithm of the historical data training results, and feed it back to the server.

[0059] The action trajectory results of the first target population are input into a trajectory summary matrix module, and the personnel information and the trajectory summary matrix module are input as input feature vector values ​​of a second screening model to obtain the screened diffuse trajectory personnel results.

[0060] The algorithm logic of the above-mentioned DNN deep learning model can adopt the DLSS computing function in the Nv computing chip, and perform planning input and planning input of feature vectors for various behavior trajectories of personnel in the first screening model, and obtain known trajectory data based on the personnel information. Then in the second screening model, the above-mentioned screening algorithm can be used to exclude the screening operator in the product module. Then, after the characteristic vector input of the behavior trajectory results and the personnel information, the final value result of the remaining diffuse crowd can be obtained. For the diffuse personnel, it can be used as the suspicious crowd range of the security system, and further screening work can be carried out according to manual screening rules.

[0061] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute a diffusion trajectory analysis method based on a dual sieve model.

[0062] Specifically, the above-mentioned diffusion trajectory analysis method based on the double screening model includes: obtaining user terminal information; generating positioning data according to the user terminal information and hot spot area information; obtaining multivariate data through a big data platform according to the positioning data; screening and generating data according to the summary result of the multivariate data and the first screening model to obtain the action trajectory result and the diffusion trajectory personnel result of the first target population. Optionally, after obtaining the user terminal information, the method further includes: determining the hot spot area information and the personnel information according to the user terminal information. Optionally, obtaining multivariate data through a big data platform according to the positioning data includes: summarizing the positioning data and the multivariate data to obtain the summary result. Optionally, screening and generating data according to the summary result of the multivariate data and the first screening model to obtain the action trajectory result and the diffusion trajectory personnel result of the first target population includes: obtaining the action trajectory result of the first target population; inputting the action trajectory result of the first target population into a trajectory summary matrix module, and inputting the personnel information and the trajectory summary matrix module as input feature vector values ​​of the second screening model to obtain the filtered diffusion trajectory personnel result.

[0063] According to another aspect of an embodiment of the present invention, an electronic system is also provided, comprising a processor and a memory; the memory stores computer-readable instructions, and the processor is used to run the computer-readable instructions, wherein the computer-readable instructions execute a diffusion trajectory analysis method based on a dual-screening model when running.

[0064] Specifically, the above-mentioned diffusion trajectory analysis method based on the double screening model includes: obtaining user terminal information; generating positioning data according to the user terminal information and hot spot area information; obtaining multivariate data through a big data platform according to the positioning data; screening and generating data according to the summary result of the multivariate data and the first screening model to obtain the action trajectory result and the diffusion trajectory personnel result of the first target population. Optionally, after obtaining the user terminal information, the method further includes: determining the hot spot area information and the personnel information according to the user terminal information. Optionally, obtaining multivariate data through a big data platform according to the positioning data includes: summarizing the positioning data and the multivariate data to obtain the summary result. Optionally, screening and generating data according to the summary result of the multivariate data and the first screening model to obtain the action trajectory result and the diffusion trajectory personnel result of the first target population includes: obtaining the action trajectory result of the first target population; inputting the action trajectory result of the first target population into a trajectory summary matrix module, and inputting the personnel information and the trajectory summary matrix module as input feature vector values ​​of the second screening model to obtain the filtered diffusion trajectory personnel result.

[0065] Through the above embodiments, the problem that the behavior trajectory calculation process in the prior art only uses the information and data obtained in real time or collected by sensors for analysis, and calculates and generates the mathematical results of the behavior trajectory through certain analysis rules, but cannot aggregate more data factors to determine the behavior trajectory, nor can it use the neural network model to directly input the information collected by the sensor or the information collected by the data platform as a feature vector and output a more accurate behavior trajectory result, and at the same time, it is impossible to achieve exclusionary screening for people with diffuse trajectories, and therefore the technical problem that the security effect of the security technology cannot be increased.

[0066] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0067] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0069] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0070] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0071] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0072] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for analyzing diffusion trajectories based on a double screening model, characterized in that, it includes: Obtain user terminal information; Generate positioning data according to the user terminal information and hotspot area information; Obtain multi-source data through a big data platform according to the positioning data; Perform data screening and generation according to the summary result of the multi-source data and the first screening model to obtain the action trajectory result of the first target population and the result of the diffusion trajectory personnel; After obtaining the user terminal information, the method further includes: Determine hotspot area information and personnel information according to the user terminal information; The obtaining multi-source data through a big data platform according to the positioning data includes: Perform summary processing on the positioning data and the multi-source data to obtain the summary result; The performing data screening and generation according to the summary result of the multi-source data and the first screening model to obtain the action trajectory result of the first target population and the result of the diffusion trajectory personnel includes: Obtain the action trajectory result of the first target population; Input the action trajectory result of the first target population into the trajectory summary matrix module, and input the personnel information and the trajectory summary matrix module as the input feature vector values of the second screening model to obtain the screened result of the diffusion trajectory personnel; Among them, the user terminal information at least includes: the hardware address code of the user terminal, the networking information, and the total number of user terminals; Generating positioning data according to the user terminal information and hotspot area information includes: combining the networking information in the user terminal information with the hotspot area information, calculating the trajectory movement routes of all user terminals, and using the trajectory movement routes as the prerequisite for the final trajectory analysis result.

2. A system for analyzing diffusion trajectories based on a double screening model, characterized in that, it includes: An obtaining module for obtaining user terminal information; A generating module for generating positioning data according to the user terminal information and hotspot area information; A big data module for obtaining multi-source data through a big data platform according to the positioning data; A trajectory module for performing data screening and generation according to the summary result of the multi-source data and the first screening model to obtain the action trajectory result of the first target population and the result of the diffusion trajectory personnel; The system further includes: A determining module for determining hotspot area information and personnel information according to the user terminal information; The big data module includes: A summarizing unit for performing summary processing on the positioning data and the multi-source data to obtain the summary result; The trajectory module includes: An obtaining unit for obtaining the action trajectory result of the first target population; A diffusion unit for inputting the action trajectory result of the first target population into the trajectory summary matrix module, and inputting the personnel information and the trajectory summary matrix module as the input feature vector values of the second screening model to obtain the screened result of the diffusion trajectory personnel; Among them, the user terminal information at least includes: the hardware address code of the user terminal, the networking information, and the total number of user terminals; Generate positioning data based on the user terminal information and hotspot area information, including: combining the networking information in the user terminal information with the hotspot area information, calculating the trajectory movement routes of all user terminals, and using the trajectory movement routes as a prerequisite for the final trajectory analysis result.

3. A non-volatile storage medium, characterized in that, the non-volatile storage medium includes a stored program, wherein when the program runs, it controls the device where the non-volatile storage medium is located to execute the method described in claim 1.

4. An electronic system, characterized in that, it includes a processor and a memory; computer-readable instructions are stored in the memory, and the processor is used to run the computer-readable instructions, wherein when the computer-readable instructions run, they execute the method described in claim 1.

Images