Abnormal path behavior detection method and device

Abstract

The application discloses an abnormal path behavior detection method and device. The method comprises the following steps: acquiring first trajectory information of a first object in a target period; predicting second trajectory information of the first object in the target period according to a pre-determined path mapping function; determining a path error between the second trajectory information and the first trajectory information; and determining that the path behavior of the first object is abnormal when a difference between the path error and a fitting error of the path mapping function is greater than a first preset threshold. The application solves the technical problem that an abnormal path behavior event of an old person cannot be effectively detected in the related art.

Description

Technical Field

[0001] This application relates to the field of big data technology, and more specifically, to an abnormal path behavior detection method and apparatus. Background Technology

[0002] As the aging population deepens and the number of elderly people continues to increase, caring for the elderly is a social responsibility universally recognized by the whole society, within the cultural context of "respecting the elderly and caring for the young." Currently, incidents of elderly people getting lost or losing contact occur frequently, and to date, no effective method has been found to monitor abnormal behavior patterns among the elderly, making early prevention and resolution crucial before such incidents occur.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides an abnormal path behavior detection method and apparatus to at least solve the technical problem in the related art that it is impossible to effectively detect abnormal path behavior events of the elderly.

[0005] According to one aspect of the embodiments of this application, an abnormal path behavior detection method is provided, comprising: acquiring first trajectory information of a first object within a target period; predicting second trajectory information of the first object within the target period based on a predetermined path mapping function; determining the path error between the second trajectory information and the first trajectory information; and determining that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

[0006] Optionally, obtaining the first trajectory information of the first object within the target period includes: obtaining the first trajectory information of the mobile device of the first object within the target period from the operator, wherein the first trajectory information includes at least: the latitude and longitude, dwell time and dwell duration of each first path point traversed by the mobile device within the target period, and the dwell duration of the mobile device at each first path point exceeds a preset time threshold.

[0007] Optionally, the process of determining the path mapping function includes: obtaining the third trajectory information of the first object within a first time period; dividing the third trajectory information according to different time intervals to obtain multiple sets of trajectory information, wherein the time intervals corresponding to each subset of trajectory information in each set of trajectory information are the same; for each set of trajectory information, determining the activity range corresponding to each subset of trajectory information in the set of trajectory information, and determining the set of commercial entities within the activity range, and calculating the similarity of the sets of commercial entities corresponding to each subset of trajectory information; determining the time interval corresponding to the set of trajectory information with the highest similarity as the target period; and performing periodic function fitting based on the target period and the set of trajectory information with the highest similarity to obtain the path mapping function.

[0008] Optionally, determining the activity range corresponding to each subset of trajectory information in the trajectory information set includes: for each subset of trajectory information, determining the target centroid of all second path points in the subset of trajectory information; and determining the activity range corresponding to the subset of trajectory information with the target centroid as the center and the preset activity distance as the radius.

[0009] Optionally, determining the target centroid of all second path points in the trajectory information subset includes: calculating the first centroid of all second path points in the trajectory information subset using density; determining the midpoint of every two second path points in the trajectory information subset, calculating the second centroid of all midpoints using density; and determining the midpoint of the first centroid and the second centroid as the target centroid.

[0010] Optionally, determining the set of commercial entities within the activity range includes: determining the commercial entities corresponding to each second path point within the activity range, and counting the occurrence frequency of each type of commercial entity; filtering out commercial entities whose occurrence frequency is less than a second preset threshold, and taking all remaining commercial entities as the set of commercial entities.

[0011] Optionally, after determining that the path behavior of the first object is abnormal, the method further includes: obtaining the real-time location of the first object; and sending the real-time location and warning information to the mobile device of the second object associated with the first object, wherein the warning information is used to indicate that the first object has abnormal path behavior.

[0012] According to another aspect of the embodiments of this application, an abnormal path behavior detection device is also provided, comprising: an acquisition module, configured to acquire first trajectory information of a first object within a target period; a prediction module, configured to predict second trajectory information of the first object within a target period based on a predetermined path mapping function; a comparison module, configured to determine the path error between the second trajectory information and the first trajectory information; and a determination module, configured to determine that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

[0013] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein the device where the non-volatile storage medium is located executes the above-described abnormal path behavior detection method by running the program.

[0014] According to another aspect of the embodiments of this application, an electronic device is also provided, the electronic device including: a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described abnormal path behavior detection method through the computer program.

[0015] In this embodiment, first trajectory information of a first object within a target period is obtained; second trajectory information of the first object within the target period is predicted based on a predetermined path mapping function; path error between the second trajectory information and the first trajectory information is determined; when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold, the abnormal path behavior of the first object is determined. Specifically, by statistically analyzing the first trajectory information of the first object within the target period, predicting the path trajectory of the first object using the path mapping function, and comparing the predicted second trajectory information with the actually observed first trajectory information to obtain relevant anomalies, abnormal path behavior of the first object can be detected in advance, thereby solving the technical problem in related technologies that cannot effectively detect abnormal path behavior events of the elderly. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a flowchart of an optional abnormal path behavior detection method according to an embodiment of this application;

[0018] Figure 2 This is a schematic diagram of an optional map display of an activity area according to an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of an optional abnormal path behavior detection device according to an embodiment of this application. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," etc., used in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] Example 1

[0023] According to an embodiment of this application, an abnormal path behavior detection method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] Figure 1 This is a flowchart illustrating an optional abnormal path behavior detection method according to an embodiment of this application, as shown below. Figure 1 As shown, the method includes at least steps S102-S108, wherein:

[0025] Step S102: Obtain the first trajectory information of the first object within the target period.

[0026] In the technical solution provided by step S102 of the present invention, the first subject can be an elderly person, and the target period can be one month, one week, etc. It should be noted that the target period is an observation period that reflects the travel habits of the first subject; therefore, the target period can be set according to actual circumstances, and no specific restrictions are imposed here. Furthermore, whether the first subject is elderly can be determined by, but is not limited to, the age or gender of the first subject. For example, an elderly person over 60 years old can be used as the first subject, and the first trajectory information of the first subject within one observation period can be obtained.

[0027] Step S104: Predict the second trajectory information of the first object within the target period based on the predetermined path mapping function.

[0028] In the technical solution provided by step S104 of the present invention, since the base station cannot accurately locate the specific location of the first object, and the positioning of the base station generally has a relatively fixed error, the second trajectory information of the first object within the target period can be predicted by a predetermined path mapping function. Thus, the path behavior abnormality of the first object can be determined by the actual observed first trajectory information and the predicted second trajectory information.

[0029] Step S106: Determine the path error between the second trajectory information and the first trajectory information.

[0030] In the technical solution provided by step S106 of the present invention, the path error between the second trajectory information and the first trajectory error of the first object in the target period can be predicted by the path mapping function, and used in turn to determine whether the first object has abnormal path behavior.

[0031] Step S108: When the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold, the path behavior of the first object is determined to be abnormal.

[0032] In the technical solution provided by step S108 of the present invention, the fitting error of the path mapping function obtained by the periodic function can be compared with the error between the path error between the second trajectory information and the first trajectory information to verify the behavior path of the first object.

[0033] Specifically, the time series corresponding to the first trajectory information can be represented as: (t m y′ m ), ..., (t m+T y′ m+T The time series corresponding to the second trajectory information can be represented as: (t m y m ), ..., (t m+T y m+T Therefore, the path error between the second trajectory information and the first trajectory information can be expressed as r. predict =∑(y m -y′ m ) 2 Furthermore, the fitting error of the path mapping function can be expressed as: r = ∑(yy n ) 2 Therefore, it can be determined by r predict The relationship between the size of r and the path behavior of the first object is used to determine whether the path behavior of the first object is abnormal.

[0034] In the technical solution provided by steps S102-S108 of this application, first trajectory information of a first object within a target period is obtained; second trajectory information of the first object within the target period is predicted based on a predetermined path mapping function; path error between the second trajectory information and the first trajectory information is determined; when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold, the abnormal path behavior of the first object is determined. Specifically, by statistically analyzing the first trajectory information of the first object within the target period, predicting the path trajectory of the first object using the path mapping function, and comparing the predicted second trajectory information with the actually observed first trajectory information to obtain relevant anomalies, abnormal path behavior of the first object can be detected in advance, thereby solving the technical problem in related technologies that cannot effectively detect abnormal path behavior events of the elderly.

[0035] The method described in this embodiment will be further described below.

[0036] As an optional implementation, in the technical solution provided by step S102 of the present invention, the method includes: obtaining first trajectory information of the mobile device of the first object within a target period from the operator, wherein the first trajectory information includes at least: the latitude and longitude, dwell time and dwell duration of each first path point traversed by the mobile device within the target period, and the dwell duration of the mobile device at each first path point exceeds a preset time threshold.

[0037] In this embodiment, the operator possesses a massive amount of customer data, and the mobile device carried by the first object interacts with the base station at a certain frequency. Therefore, the operator can record the location sequence of the mobile device carried by the first object at a certain frequency. Thus, in this embodiment, the first trajectory information of the mobile device carried by the first object within a target period can be obtained from the operator corresponding to the attributes of the mobile device carried by the first object. Specifically, the latitude and longitude information, dwell time, and dwell duration of the first path points through which the dwell time of the mobile device carried by the first object exceeds a preset time threshold are determined. Therefore, the activity range of the first object can be determined through the first trajectory information of the first object.

[0038] In addition, since the first object may visit different locations or make brief stops along the way during a period of observation, and these brief stops will also be recorded as the first object's visit locations, these stops are all noise points for subsequent abnormal path behavior analysis; or due to the drift of geographic location data, there will be data noise problems. In order to address the above problems, this application embodiment also needs to perform noise reduction processing on the trajectory information of the first object within the target period, so as to obtain the first trajectory information that truly reflects the activity range of the first object.

[0039] As an optional implementation, in the technical solution provided in step S104 of the present invention, the process of determining the path mapping function includes: obtaining the third trajectory information of the first object within a first time period; dividing the third trajectory information according to different time intervals to obtain multiple sets of trajectory information, wherein the time intervals corresponding to each subset of trajectory information in each set of trajectory information are the same; for each set of trajectory information, determining the activity range corresponding to each subset of trajectory information in the set of trajectory information, and determining the set of commercial entities within the activity range, and calculating the similarity of the set of commercial entities corresponding to each subset of trajectory information; determining the time interval corresponding to the set of trajectory information with the highest similarity as the target period; and performing periodic function fitting based on the target period and the set of trajectory information with the highest similarity to obtain the path mapping function.

[0040] In this embodiment, for ease of statistical analysis, the first time period (i.e., the observation period) T can be uniformly divided according to different time intervals, such as dividing a month into four weeks, thereby generating multiple sets of trajectory information for the mobile device carried by the first object within each of the four weeks; the commercial entity set includes, but is not limited to, convenience stores, hospitals, shopping malls, streets, train stations, coffee shops, etc. For example, if we define the commercial entity set B... t Includes B t = {Convenience store B1, shopping mall B2, coffee shop B3, street B4, train station B5, hospital B6}, when the geographical coordinates of the first object are (x, y), it can be identified that the set of commercial entities around the coordinates includes convenience store B1 and shopping mall B2; while when the geographical coordinates of the first object are (x1, y1), it can be identified that the set of commercial entities around the coordinates includes coffee shop B3 and hospital B6.

[0041] Specifically, taking the latitude and longitude set P(t) of a certain first object as an example, firstly, a fixed distance D is determined. Then, the activity range S(t) is determined with the point in P(t) as the center and D as the radius. It is then divided into four equal parts according to the time interval to obtain four sets with the same time interval, namely S0(t), S1(t), S2(t) and S3(t). Next, the second path points whose stay time within the range of sets S0(t), S1(t), S2(t) and S3(t) is less than the preset time threshold are eliminated to obtain S1(t).

[0042] Then, map S1(t) to Figure 2 In the map shown, and based on the data in the map, count the corresponding set of business entities B in S1(t). t ,in, Figure 2The entities with commercial attributes contained within the circled area constitute the set of commercial entities. Next, the Jaccard similarity coefficient is calculated for the set of commercial entities corresponding to each subset of trajectory information, and this coefficient is used as the similarity score. Output the data, then iterate through the similarity of the business entity sets corresponding to each subset of trajectory information within the multiple trajectory information sets, and take the time interval corresponding to the set of trajectory information with the highest similarity as the target period.

[0043] Finally, the minimum residual method is used to fit a periodic function to the set of trajectory information with the highest target period and similarity. The periodic function can be expressed as Asin(a*t+b)+M, and the fitting error index P can be set according to the actual situation. In this application, P is preferably 0.95, thus obtaining the path mapping function.

[0044] The fitting process will be further explained through the following steps.

[0045] If we denote the collected data point pairs as (t1, y1), ..., (t... n y n ), where t n Represents time series points, y n If the target point is represented, the fitting error can be defined using the following formula:

[0046] r=∑(yy n ) 2

[0047] Where y represents the value obtained using the periodic function Asin(a*t+b)+M, the amplitude A, the period-related constant a, and the phase b can be solved using the quasi-Newton method or the simplex method.

[0048] Next, the following fitting performance metrics can be used to determine the final optimized fitting error:

[0049]

[0050] Among them, Y i , These represent the true predicted value and the mean of the sequence, respectively. Additionally, R... 2 The closer the value is to 1, the better the curve fit. Additionally, R can be set... 2 When the value is greater than 0.4, the curve fitting effect is considered good.

[0051] As an optional implementation, in the technical solution provided by step S104 of the present invention, the method includes: determining the commercial entities corresponding to each second path point within the activity range, and counting the occurrence frequency of each type of commercial entity; filtering out commercial entities whose occurrence frequency is less than a second preset threshold, and taking all remaining commercial entities as a set of commercial entities.

[0052] In this embodiment, the commercial entities at each second path point within the activity range of the first object include, but are not limited to, convenience stores, hospitals, shopping malls, streets, train stations, coffee shops, etc. To accurately determine whether the first object frequently visits a commercial entity or infrequently visits it, the frequency of the first object's visits to the commercial entity can also be used for judgment. When the frequency of the first object's appearance exceeds a second preset threshold, the commercial entity is determined to be frequently visited by the first object; otherwise, it is considered infrequently visited by the first object.

[0053] Specifically, if the observation set of the first object during the first time period is {T1, T2, T3, ..., T...} n}, thus the observation sequence for statistically analyzing the access frequency of a set of business entities is as follows By extracting the statistical frequency of specific business entities, we can obtain the observation sequence. Specifically, based on the access frequency of the first object, if the access frequency exceeds the second preset threshold Y1, the first object is considered to frequently access the business entity; while if the access frequency is less than the second preset threshold Y1, the first object is considered to not frequently access the business entity.

[0054] As an optional implementation, in the technical solution provided by step S106 of the present invention, the method includes: for each subset of trajectory information, determining the target centroid of all second path points; taking the target centroid as the center and the preset activity distance as the radius, determining the activity range corresponding to the subset of trajectory information.

[0055] In this embodiment, in order to further improve the accuracy of the data in the trajectory information set of the first object, the target centroid of all second path points in each trajectory information subset can be determined, where the target centroid is the path point in the trajectory information subset, and the activity range corresponding to the trajectory information subset is determined with the target centroid as the center and the preset activity distance as the radius.

[0056] Specifically, taking the latitude and longitude set P(t) of a certain first object as an example, it can be divided into four equal parts according to the time interval, resulting in four sets with the same time interval, namely S0(t), S1(t), S2(t), and S3(t). Then, path points whose dwell time within the range of sets S0(t), S1(t), S2(t), and S3(t) is less than a preset time threshold can be eliminated, resulting in four trajectory information subsets. For each trajectory information subset, the target centroid of its second path point can be determined, and the activity range corresponding to the trajectory information subset can be determined with the target centroid as the center and the preset activity distance D as the radius.

[0057] As an optional implementation, in the technical solution provided by step S106 of the present invention, the method includes: calculating the first centroid of all second path points in the trajectory information subset using density; determining the midpoint of every two second path points in the trajectory information subset, calculating the second centroid of all midpoints using density; and determining the midpoint of the first centroid and the second centroid as the target centroid.

[0058] In this embodiment, in order to further improve the accuracy of the data in the trajectory information set of the first object, this application embodiment provides the idea of ​​determining the centroid by distance and the idea of ​​determining the centroid by density. By combining the overlap of the two centroids, the target centroid is finally determined.

[0059] Specifically, the data in set S0(t) is first split according to the daily splitting criteria to obtain M. 01 ~M 07 A subset of trajectory information; then, the density is used to calculate the set M respectively. 01 ~M 07 First centroid of all second path points Then each trajectory information subset M 01 ~M 07 Find the midpoint between every two second path points, and use density to calculate the second centroid of all midpoints. Therefore, based on the first mass center Second center of mass Determine the target centroid.

[0060] It should be noted that during the comparison of the centers of mass, if and If they coincide, then any one of the centroids can be chosen as the target centroid; if and Since they do not coincide, the midpoint of the line connecting the two centroids can be taken as the average centroid, and denoted as . The obtained average centroid The target centroid is determined by density calculation, as well as the target centroid of each subset of trajectory information.

[0061] As an optional implementation, in the technical solution provided in step S108 of the present invention, after determining that the path behavior of the first object is abnormal, the method further includes: obtaining the real-time location of the first object; sending the real-time location and warning information to the mobile device of the second object associated with the first object, wherein the warning information is used to indicate that the first object has abnormal path behavior.

[0062] In this embodiment, once the path behavior of the first object is determined to be abnormal, it can be preliminarily determined that the first object is lost or missing. At this time, the real-time location of the first object can be obtained, and the real-time location and warning information can be sent to the mobile devices of the second object associated with the first object. For example, the real-time location and warning information can be sent to the mobile devices of the first object's family members or other relatives. The warning information is used to indicate that the first object has abnormal path behavior.

[0063] In the above steps, the accuracy of the trajectory information of the first object is improved by denoising the data; the centroid is determined by distance and density, and the overlap of the centroids determined by the two methods is combined to obtain the final target centroid, making the determination of the activity range of the first object more accurate; in addition, the set of business entities frequently visited by the first object is determined by statistically analyzing the frequency of occurrence of the business entities corresponding to each second path point visited by the first object within its activity range, thereby more accurately reflecting the trajectory information of the first object.

[0064] Example 2

[0065] According to an embodiment of this application, an abnormal path behavior detection device is also provided for implementing the abnormal path behavior detection method in Embodiment 1. Figure 3 This is a schematic diagram of the structure of an optional abnormal path behavior detection device according to an embodiment of this application, as shown below. Figure 3 As shown, the abnormal path behavior detection device includes at least an acquisition module 31, a prediction module 32, a comparison module 33, and a determination module 33, wherein:

[0066] The acquisition module 31 is used to acquire the first trajectory information of the first object within the target period.

[0067] The primary target group can be elderly individuals, and the target period can be one month, one week, etc. It should be noted that the target period is an observation period that reflects the primary target group's travel habits; therefore, the target period can be set according to actual circumstances, and no specific restrictions are imposed here. Furthermore, the primary target group's age or gender can be used to determine whether it is elderly, but is not limited to this. For example, individuals over 60 years old can be used as the primary target group, and their initial trajectory information within one observation period can be obtained.

[0068] As an optional implementation, the acquisition module 31 acquires the first trajectory information of the mobile device of the first object within the target period from the operator. The first trajectory information includes at least the latitude and longitude, dwell time and dwell duration of each first path point traversed by the mobile device within the target period, and the dwell duration of the mobile device at each first path point exceeds a preset time threshold.

[0069] In this embodiment, the operator possesses a massive amount of customer data, and the mobile device carried by the first object interacts with the base station at a certain frequency. Therefore, the operator can record the location sequence of the mobile device carried by the first object at a certain frequency. Thus, in this embodiment, the first trajectory information of the mobile device carried by the first object within a target period can be obtained from the operator corresponding to the attributes of the mobile device carried by the first object. Specifically, the latitude and longitude information, dwell time, and dwell duration of the first path points through which the dwell time of the mobile device carried by the first object exceeds a preset time threshold are determined. Therefore, the activity range of the first object can be determined through the first trajectory information of the first object.

[0070] In addition, since the first object may visit different locations or make brief stops along the way during a period of observation, and these brief stops will also be recorded as the first object's visit locations, these stops are all noise points for subsequent abnormal path behavior analysis; or due to the drift of geographic location data, there will be data noise problems. In order to address the above problems, this application embodiment also needs to perform noise reduction processing on the trajectory information of the first object within the target period, so as to obtain the first trajectory information that truly reflects the activity range of the first object.

[0071] The prediction module 32 is used to predict the second trajectory information of the first object within the target period based on a predetermined path mapping function.

[0072] Since the base station cannot accurately locate the specific location of the first object, and the positioning of the base station generally has a relatively fixed error, in this embodiment of the application, the second trajectory information of the first object within the target period can also be predicted by the path mapping function predetermined by the prediction module 32. In this way, the path behavior abnormality of the first object can be determined by the actual observed first trajectory information and the predicted second trajectory information.

[0073] As an optional implementation, the process of determining the path mapping function includes: obtaining the third trajectory information of the first object within a first time period; dividing the third trajectory information according to different time intervals to obtain multiple sets of trajectory information, wherein the time intervals corresponding to each subset of trajectory information in each set of trajectory information are the same; for each set of trajectory information, determining the activity range corresponding to each subset of trajectory information in the set of trajectory information, and determining the set of commercial entities within the activity range, and calculating the similarity of the sets of commercial entities corresponding to each subset of trajectory information; determining the time interval corresponding to the set of trajectory information with the highest similarity as the target period; and performing periodic function fitting based on the target period and the set of trajectory information with the highest similarity to obtain the path mapping function.

[0074] As an optional implementation, the prediction module 32 can also determine the business entities corresponding to each second path point within the activity range, and count the frequency of occurrence of each type of business entity; filter out business entities whose frequency of occurrence is less than a second preset threshold, and take all remaining business entities as a set of business entities.

[0075] In this embodiment, the commercial entities at each second path point within the activity range of the first object include, but are not limited to, convenience stores, hospitals, shopping malls, streets, train stations, coffee shops, etc. To accurately determine whether the first object frequently visits a commercial entity or infrequently visits it, the frequency of the first object's visits to the commercial entity can also be used for judgment. When the frequency of the first object's appearance exceeds a second preset threshold, the commercial entity is determined to be frequently visited by the first object; otherwise, it is considered infrequently visited by the first object.

[0076] The comparison module 33 is used to determine the path error between the second trajectory information and the first trajectory information.

[0077] Specifically, the comparison module 33 can predict the path error between the second trajectory information of the first object and the first trajectory error within the target period through the path mapping function, and use this as a basis to determine whether the first object has abnormal path behavior.

[0078] As an optional implementation, for each subset of trajectory information, the target centroid of all second path points is determined; with the target centroid as the center and the preset activity distance as the radius, the activity range corresponding to the subset of trajectory information is determined.

[0079] In this embodiment, in order to further improve the accuracy of the data in the trajectory information set of the first object, the target centroid of all second path points in each trajectory information subset can be determined, where the target centroid is the path point in the trajectory information subset, and the activity range corresponding to the trajectory information subset is determined with the target centroid as the center and the preset activity distance as the radius.

[0080] As an optional implementation, the comparison module 33 can also use density to calculate the first centroid of all second path points in the trajectory information subset; determine the midpoint of every two second path points in the trajectory information subset; use density to calculate the second centroid of all midpoints; and determine the midpoint of the first centroid and the second centroid as the target centroid.

[0081] In this embodiment, in order to further improve the accuracy of the data in the trajectory information set of the first object, this application embodiment provides the idea of ​​determining the centroid by distance and the idea of ​​determining the centroid by density. By combining the overlap of the two centroids, the target centroid is finally determined.

[0082] The determination module 34 is used to determine that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

[0083] As an optional implementation, after determining that the path behavior of the first object is abnormal, the determining module 34 can also obtain the real-time location of the first object; and send the real-time location and warning information to the mobile device of the second object associated with the first object. The warning information is used to indicate that the first object has abnormal path behavior.

[0084] In this embodiment, once the path behavior of the first object is determined to be abnormal, it can be preliminarily determined that the first object is lost or missing. At this time, the real-time location of the first object can be obtained, and the real-time location and warning information can be sent to the mobile devices of the second object associated with the first object. For example, the real-time location and warning information can be sent to the mobile devices of the first object's family members or other relatives. The warning information is used to indicate that the first object has abnormal path behavior.

[0085] It should be noted that each module in the abnormal path behavior detection device in this application embodiment corresponds one-to-one with each implementation step of the abnormal path behavior detection method in embodiment 1. Since embodiment 1 has been described in detail, some details not shown in this embodiment can be referred to embodiment 1, and will not be elaborated further here.

[0086] Example 3

[0087] According to an embodiment of this application, a non-volatile storage medium is also provided, which includes a stored program, wherein the device where the non-volatile storage medium is located executes the abnormal path behavior detection method in Embodiment 1 by running the program.

[0088] Optionally, the device containing the non-volatile storage medium executes the following steps by running the program: acquiring first trajectory information of the first object within a target period; predicting second trajectory information of the first object within a target period based on a predetermined path mapping function; determining the path error between the second trajectory information and the first trajectory information; and determining that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

[0089] According to an embodiment of this application, a processor is also provided for running a program, wherein the abnormal path behavior detection method in embodiment 1 is executed during program execution.

[0090] Optionally, the program executes the following steps during runtime: obtaining first trajectory information of the first object within the target period; predicting second trajectory information of the first object within the target period based on a pre-determined path mapping function; determining the path error between the second trajectory information and the first trajectory information; and determining that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

[0091] According to an embodiment of this application, an electronic device is also provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the abnormal path behavior detection method of embodiment 1 through the computer program.

[0092] Optionally, the processor is configured to execute the following steps via a computer program: acquiring first trajectory information of a first object within a target period; predicting second trajectory information of the first object within a target period based on a predetermined path mapping function; determining the path error between the second trajectory information and the first trajectory information; and determining that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

[0093] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0094] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0096] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0098] If the integrated unit is implemented as 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 this application, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0099] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An abnormal path behavior detection method, characterized in that, include: Obtain the first trajectory information of the first object within the target period; Predict the second trajectory information of the first object within the target period based on a predetermined path mapping function; Determine the path error between the second trajectory information and the first trajectory information; When the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold, the path behavior of the first object is determined to be abnormal. The process of determining the path mapping function includes: acquiring the third trajectory information of the first object within a first time period; dividing the third trajectory information according to different time intervals to obtain multiple sets of trajectory information, wherein the time intervals corresponding to each subset of trajectory information in each set of trajectory information are the same; for each set of trajectory information, determining the activity range corresponding to each subset of trajectory information in the set of trajectory information, and determining the set of commercial entities within the activity range, and calculating the similarity of the set of commercial entities corresponding to each subset of trajectory information; determining the time interval corresponding to the set of trajectory information with the highest similarity as the target period; and performing periodic function fitting based on the target period and the set of trajectory information with the highest similarity to obtain the path mapping function.

2. The method according to claim 1, characterized in that, Obtain the first trajectory information of the first object within the target period, including: The first trajectory information of the mobile device of the first object within the target period is obtained from the operator, wherein the first trajectory information includes at least: the latitude and longitude, dwell time and dwell time of each first path point traversed by the mobile device within the target period, and the dwell time of the mobile device at each first path point exceeds a preset time threshold.

3. The method according to claim 1, characterized in that, Determining the activity range corresponding to each subset of trajectory information in the trajectory information set includes: For each subset of trajectory information, determine the target centroid of all second path points in the subset of trajectory information; Using the target centroid as the center and a preset activity distance as the radius, the activity range corresponding to the trajectory information subset is determined.

4. The method according to claim 3, characterized in that, Determining the target centroid of all second path points in the subset of trajectory information includes: Calculate the first centroid of all second path points in the subset of trajectory information using density; Determine the midpoint of every two second path points in the subset of trajectory information, and calculate the second centroid of all midpoints using density; The midpoint between the first centroid and the second centroid is determined as the target centroid.

5. The method according to claim 1, characterized in that, Determine the set of business entities within the scope of the activity, including: Identify the business entities corresponding to each second path point within the activity area, and count the frequency of occurrence of each type of business entity; Filter out commercial entities that appear less than a second preset threshold, and include all remaining commercial entities as the set of commercial entities.

6. The method according to claim 1, characterized in that, After determining that the path behavior of the first object is abnormal, the method further includes: Obtain the real-time position of the first object; The real-time location and warning information are sent to the mobile device of the second object associated with the first object. The warning information is used to indicate that the first object has abnormal path behavior.

7. An abnormal path behavior detection device, characterized in that, include: The acquisition module is used to acquire the first trajectory information of the first object within the target period; The prediction module is used to predict the second trajectory information of the first object within the target period based on a pre-determined path mapping function. The process of determining the path mapping function includes: acquiring the third trajectory information of the first object within a first time period; dividing the third trajectory information according to different time intervals to obtain multiple sets of trajectory information, wherein the time intervals corresponding to each subset of trajectory information in each set are the same; for each set of trajectory information, determining the activity range corresponding to each subset of trajectory information, and determining the set of commercial entities within the activity range, calculating the similarity between the sets of commercial entities corresponding to each subset of trajectory information; determining the time interval corresponding to the set of trajectory information with the highest similarity as the target period; and performing periodic function fitting based on the target period and the set of trajectory information with the highest similarity to obtain the path mapping function. The comparison module is used to determine the path error between the second trajectory information and the first trajectory information; The determination module is used to determine that the path behavior of the first object is abnormal when the difference between the path error and the fitting error of the path mapping function is greater than a first preset threshold.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein the device containing the non-volatile storage medium executes the abnormal path behavior detection method according to any one of claims 1 to 6 by running the program.

9. An electronic device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the abnormal path behavior detection method of any one of claims 1 to 6 through the computer program.

Images