Personnel filing management method and related device

Abstract

The embodiment of the present application discloses a personnel archiving management method and related devices, the method comprising: obtaining a data set of a first object, the data set comprising M data, each data comprising at least the identity information, location information and data sampling time point of the first object, wherein M is an integer greater than 1; dividing the M data into slices according to the time step and the space radius to obtain N slices, each slice comprising at least one data, wherein N is a positive integer less than M; and performing activity pattern analysis according to the N slices. The embodiment of the present application can realize accurate activity pattern analysis through personnel archiving.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a personnel filing management method and related devices. Background Art

[0002] In real life, in order to facilitate data mining and / or analysis of personnel images, the personnel images captured by each camera in the monitoring system can be classified according to the personnel they belong to, so that the personnel images of the same person are divided into the same category. This process is called personnel archiving. In the personnel archiving process, the person to whom the personnel image belongs is usually determined by face recognition or image matching. However, at present, personnel archiving is relatively rough, which makes it impossible to accurately analyze their activity patterns. Summary of the invention

[0003] The embodiments of the present application provide a personnel archiving management method and related devices, which can realize accurate activity pattern analysis through personnel archiving.

[0004] In a first aspect, an embodiment of the present application provides a personnel filing management method, the method comprising:

[0005] Acquire a data set of a first object, the data set including M data, each data including at least identity information, location information and a data sampling time point of the first object, and M is an integer greater than 1;

[0006] The M data are divided into slices according to the time step and the space radius to obtain N slices, each slice includes at least one data, and N is a positive integer less than M;

[0007] Activity pattern analysis is performed based on the N shards.

[0008] In a second aspect, an embodiment of the present application provides a personnel filing management device, the device comprising: an acquisition unit, a division unit and an analysis unit, wherein:

[0009] The acquisition unit is configured to acquire a data set of a first object, the data set comprising M data, each data comprising at least identity information, location information and a data sampling time point of the first object, and M is an integer greater than 1;

[0010] The partitioning unit is used to partition the M data into N slices according to the time step and the space radius, each slice including at least one data, where N is a positive integer less than M;

[0011] The analysis unit is used to analyze activity patterns based on the N shards.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0015] The implementation of the embodiments of the present application has the following beneficial effects:

[0016] It can be seen that the personnel archiving management method and related devices described in the embodiments of the present application obtain a data set of a first object, where the data set includes M data, each of which includes at least the identity information, location information and data sampling time point of the first object, M is an integer greater than 1, and the M data are sliced ​​according to the time step and the spatial radius to obtain N slices, each of which includes at least one data, N is a positive integer less than M, and activity pattern analysis is performed based on the N slices. Since the archiving process introduces time and space information, accurate activity pattern analysis can be achieved through personnel archiving combined with time and space information. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1A It is a flowchart of a personnel filing management method provided in an embodiment of the present application;

[0019] Figure 1B This is a schematic diagram showing a personnel filing management method provided in an embodiment of the present application;

[0020] Figure 1C This is another schematic diagram demonstrating a personnel filing management method provided by an embodiment of the present application;

[0021] Figure 1D This is another schematic diagram illustrating a personnel filing management method provided in an embodiment of the present application;

[0022] Figure 2 It is a flowchart of another personnel filing management method provided in an embodiment of the present application;

[0023] Figure 3 It is a flowchart of another personnel filing management method provided in an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In the embodiments of the present application, the electronic devices described may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptop computers, video matrices, mobile Internet devices (MIDs) or wearable devices, etc. The above are only examples, not exhaustive, and include but are not limited to the above devices. The electronic devices may also include cloud servers.

[0029] See also Figure 1A , Figure 1A : is a flow chart of a personnel filing management method provided in an embodiment of the present application. As shown in the figure, the personnel filing management method includes:

[0030] 101. Obtain a data set of a first object, where the data set includes M data, each data includes at least identity information, location information, and a data sampling time point of the first object, and M is an integer greater than 1.

[0031] The first object may be a person, an animal, a robot, a vehicle or other object, and the data set of the first object may include relevant data of the first object collected at different times. The location information may include at least one of the following: location name, longitude, latitude, etc., which are not limited here. The data sampling time point may be a time point. The data set of the first object may include M data, each of which includes at least the identity information, location information and data sampling time point of the first object, and the identity information may include at least one of the following: face image, license plate, card swiping record, etc., which are not limited here.

[0032] For example, the archive set aidN includes N data sets of objects, {aid1, aid2, aid3...aidN}, and each archive data set a in aidN n {a1,a2,a3,..a n}, which includes n objects. In order to increase the connection between data in time and space trajectory, for each a n Add longitude and latitude to form track p n ={p1,p2,p3,..p n}, p n =(lat i ,lon i ,t i ), where lat i Dimension, lat i Longitude, t i Capture time. Figure 1BAs shown, P1, P2, P3, P4, and P5 each correspond to a position and a time point, that is, only one position may appear at a time point.

[0033] 102. Slice the M data according to the time step and the space radius to obtain N slices, each slice includes at least one data, and N is a positive integer less than M.

[0034] In specific implementation, taking a person as an example, at a point in time, he will only be in one location, and at a time period, he will only be in one area.

[0035] Specifically, the time step and the space radius can be determined first. The time step can be determined first, and then the space radius is determined according to the location information of the data corresponding to the time step. Then, the M data are divided into N slices according to the time step and the space radius. Each slice may not have an intersection, and each slice includes at least one data, where N is a positive integer less than M. For example, when M is equal to n, the M data can form a trajectory p n , for the formed trajectory p n All points in the cluster are clustered based on R distance + T time range.

[0036] Optionally, the above step 102, dividing the M data into slices according to the time step and the space radius to obtain N slices, may include the following steps:

[0037] 21. Select a reference trajectory point as starting data, determine a preset time step and a preset space radius, and the reference trajectory point corresponds to at least one data among the M data;

[0038] 22. Slice the M data based on the reference trajectory point, the preset time step, and the preset space radius to obtain N reference slices;

[0039] 23. Eliminate abnormal data from the N reference slices to obtain the N slices.

[0040] Among them, the preset time step and the preset space radius can be pre-set or system default, the preset time step can be partially or completely equal, and the preset space radius can also be partially or completely equal. The number of reference trajectory points can be one or more, and the reference trajectory point corresponds to at least one data among the M data. For example, when there is one reference trajectory point, the reference trajectory point is the starting point, and when there are multiple reference trajectory points, each slice can correspond to a reference trajectory point. For example, the time period corresponding to the first slice is [0, T], and the time period corresponding to the second slice is [T, 2T], and so on.

[0041] In a specific implementation, a reference trajectory point may be selected as the starting data. For example, the M data may be divided into multiple time periods, and one or more time points within each time period may be selected as reference trajectory points.

[0042] Furthermore, the preset time step and the preset space radius can be determined. The preset time step and the preset space radius can be set in advance, or the two points with the farthest distance within a period of time can be selected as the radius, or the radius of the circumscribed circle within the time period can be determined as the preset space radius, and so on.

[0043] Furthermore, the M data can be divided into slices based on reference trajectory points, preset time steps and preset spatial radius to obtain N reference slices, and then the N reference slices are subjected to abnormal data exclusion to obtain N slices. In this way, N slices with accurate data can be obtained.

[0044] Optionally, when the reference trajectory point is data whose time among the M data is within a preset time range, the preset time range is a moment between the earliest time of the M data and a preset time step after the earliest moment;

[0045] The above step 22, dividing the M data into slices based on the reference trajectory points, the preset time step and the preset space radius to obtain N reference slices, may include the following steps:

[0046] 221. Determine a first slice of the M data according to the reference trajectory point, the preset time step, and the preset space radius;

[0047] 222. Divide the remaining slices according to the first slice, the preset time step, and the preset space radius to obtain the N reference slices.

[0048] Among them, when the reference trajectory point is data among M data whose time is within a preset time range, the preset time range is a moment between the earliest time of the M data and a preset time step after the earliest moment. The first slice of the M data is determined according to the reference trajectory point, the preset time step and the preset spatial radius. Then, subsequent slice divisions can be performed based on the first slice, and the remaining slice divisions are performed according to the first slice, the preset time step and the preset spatial radius to obtain N reference slices, and there is no intersection between each of the N reference slices.

[0049] For example, Figure 1C As shown, in the specific implementation, p is used n The longitude and latitude of the first point p1 in the trajectory is (lat1, lon1), the radius of the circle is R, and the time of p1 (ti ) is the time range of the midpoint before and after the step length T to divide the time and space range into the first segment RT1. The second segment RT2 uses the boundary of the first segment RT1, and then divides the time and space range by 2 times R + 2 times T. In the figure, each circle represents a segment. In this way, we know the segment RT n .

[0050] Further, the shard boundary division: the first shard RT1 is divided into the time and space center range based on the trajectory point of the first archived data p1 in the archive aidN. The second shard requires the starting trajectory point p x , after the spatiotemporal aggregation of shard RT1, the remaining trajectory p n The data in the collection is sorted according to the archiving time. Due to the error of the archived data in the sorting, the second fragmentation appears and the first starting trajectory point p is selected. x , a verification mechanism needs to be added. For the subsequent selection of the starting trajectory point, the remaining p can be calculated n The starting point is the point in the middle of the set with the smallest time and space range with the last track point in the RT1 slice:

[0051] disance(p x ,p y )≤β,|t x -t y |≤T,|(lat x ,lon x )-(lat y ,lon y )|≤R.

[0052] Where y represents the starting point of another shard, disance(p x ,p y ) indicates p x 、p y The distance between x 、p y Respectively represent trajectory points, lat x ,lon x Indicates p x The longitude and latitude of the y ,lon y Indicates p y represents the longitude and latitude, and β represents an empirical parameter which can be set in advance.

[0053] In the specific implementation, shard RT n Direction judgment can be based on the (Point of Interest, POI) map information to obtain RT n-1 The last multiple trajectories p in the shard n The location information is provided by pn The data direction and POI information are calculated to determine the next RT when multiple directions appear. n The starting data of the fragment. In the specific implementation, when the starting p in different directions appears at an intersection n point, then according to multiple p n Calculate the time and space range. The heap with the most data within the time and space range is considered to be RT. n Each POI contains four pieces of information: name, category, longitude, and latitude.

[0054] Optionally, the above step 23, eliminating abnormal data from the N reference slices to obtain the N slices, may include the following steps:

[0055] 231. Obtain a first data sampling time point and corresponding first position information of data j in reference slice i, where the reference slice i is any reference slice among the N reference slices, and the data j is any data in the reference slice i;

[0056] 232. Obtain second data sampling time points and corresponding second position information of k data that are temporally adjacent to the data j, where k is a positive integer;

[0057] 233. Eliminate abnormal data according to the first data sampling time point and the corresponding first position information of the data j in the reference slice i, and the second data sampling time point and the corresponding second position information of the k data, to obtain the reference slice i after the abnormal data is eliminated.

[0058] In the specific implementation, taking reference slice i as an example, the reference slice i is any reference slice among the N reference slices, and the data j is any data in the reference slice i, then the first data sampling time point and the corresponding first position information of the data j in the reference slice i can be obtained, and the second data sampling time point and the corresponding second position information of the k data adjacent to the data j in time can be obtained, k is a positive integer, then the abnormal data can be eliminated according to the first data sampling time point and the corresponding first position information of the data j in the reference slice i, and the second data sampling time point and the corresponding second position information of the k data, to obtain the reference slice i after the abnormal data is eliminated, that is, the corresponding positions of two adjacent data should be within a reasonable distance.

[0059] In the specific implementation, Figure 1D As shown, for each shard, abnormal data can also be excluded. For data in the spatiotemporal trajectory, due to errors in longitude and latitude and the presence of erroneous archived data in the archive aidN, it is necessary to exclude data that is not in the shard RT. n The data in the time and space range are eliminated.

[0060] In the specific implementation, RT n Each trajectory p in the shard n The longitude and latitude are verified using the geographical information of the Point of Interest (POI). If any data has an abnormal geographical location, it will be removed. When the continuous trajectory p n In the middle, the trajectory point before and after The time-space distance is greater than Then remove it.

[0061] 103. Analyze activity patterns based on the N shards.

[0062] Among them, the activity pattern analysis may include at least one of the following: activity location statistics, activity itinerary, etc., which are not limited here.

[0063] Optionally, the above step 103, analyzing the activity pattern according to the N shards, may include the following steps:

[0064] 31. Perform location type statistics on each of the N slices to obtain statistical results;

[0065] 32. Divide each of the N shards into time ranges according to the statistical results to obtain a division result;

[0066] 33. According to the division result, a weight value is configured for each position in each of the N slices, wherein the greater the number, the smaller the weight value.

[0067] In a specific implementation, location type statistics can be performed on each of the N shards to obtain statistical results, that is, each data has a location. Then, statistics can be performed and time ranges can be divided for each of the N shards based on the statistical results to obtain division results, that is, which time point is at which location. Finally, weight values ​​can be configured for each location in each of the N shards based on the division results, where the more times, the smaller the weight value.

[0068] For example, for shard RT n Shard the collection to divide the behavior and activity patterns. n The latitude and longitude of each data in the POI information obtains detailed geographic information, and counts the number of occurrences of each location type, and ranges the number of occurrences τ{t start ,t end}Time range division. The data format of the division is W i {(school, {(τ1,10), (τ2,2), (τ n,18)})}, {(shop, {(τ1, 2), (τ2, 21), (τ n ,13)})},{(residence,{(τ1,22),(τ2,2),(τ n , 1)})}, etc. (address name, time period, number of occurrences). i Perform statistics and set different calculation weight values ​​δ for frequently occurring geographical locations i {δ1, δ2...δ i}, the higher the probability of occurrence, the lower the weight value, such as the weight of school appears δ1 = 1-total school / total all , where total all Indicates the total number of all school The statistical number of occurrences of school locations.

[0069] Furthermore, the following steps may be included:

[0070] A1. Obtain X shards corresponding to the data set of the second object, where X is an integer greater than 1;

[0071] A2. Compare the N fragments with the X fragments to obtain a similarity comparison result;

[0072] A3. Determine a target relationship attribute between the first object and the second object according to the similarity comparison result.

[0073] In a specific implementation, the similarity of the behavior rules between the two files can be calculated. The second object can be a person, an animal, a robot, a vehicle or other objects. Obtain X slices corresponding to the data set of the second object, where X is an integer greater than 1, and then compare the similarity of the N slices with the X slices to obtain a similarity comparison result. Specifically, the intersection of the two files can be compared for similarity. If there is no intersection, the similarity is 0. Then, the target relationship attribute between the first object and the second object can be determined according to the similarity comparison result. In the embodiment of the present application, the relationship attribute can include at least one of the following: peers, classmates, colleagues, business partners, etc., which are not limited here.

[0074] For example, compare the trajectory shard data in any two aid1 and aid2 in the aidN set, and compare the data similarity of the intersection of the time and space range. When the shards between two archives intersect across different shards, the similarity is calculated separately and then summed. The cosine calculation method can be combined with the active address δ i The weighted similarity is calculated as follows:

[0075]

[0076]

[0077] Among them, aid x ,aid y Represents a file of two objects (object x, object y), similar (aid x ,aid y ) represents the similarity between object x and object y, aid xRTn represents the nth shard corresponding to x, The corresponding nth shard, δ represents the weight value, RTx numi Represents the characteristics of the i-th data, RTy numi Represents the feature of the i-th data, and the feature may include at least one of the following: feature points, feature vectors, etc., which are not limited here.

[0078] Furthermore, we can compare the similarities between different archive aids. Those with high similarity can be considered as peers, accompanying communities, and groups with the same activity patterns. We can also mine basic community information based on statistical population density in time and space. In this way, we can improve the accuracy of activity patterns such as community discovery and behavioral analysis.

[0079] Optionally, when the first object is a target person, the above step 101 of obtaining a data set of the first object may include the following steps:

[0080] 11. Obtain facial images collected during a preset time period to obtain multiple facial images;

[0081] 12. Obtain a preset face template of the target person;

[0082] 13. Match the multiple face images with the preset face template to obtain at least one face image that successfully matches the preset face template;

[0083] 14. Obtain relevant information of the at least one facial image to obtain at least one relevant information;

[0084] 15. Determine a data set of the first object based on the at least one facial image and the at least one related information.

[0085] Among them, the preset time period can be preset or the system defaults, and the preset face template can be saved in advance. In a specific implementation, the face images collected in the preset time period can be obtained to obtain multiple face images, and the preset face template of the target person can also be obtained. Then, the multiple face images can be matched with the preset face template to obtain at least one face image that successfully matches the preset face. The relevant information of at least one face image can also be obtained to obtain at least one relevant information, which can include the collection time point, location information, etc. Then, the data set of the first object can be determined based on the at least one face image and the at least one relevant information, so that the personnel file can be quickly completed.

[0086] Furthermore, the above step 13, matching the multiple face images with the preset face template, may include the following steps:

[0087] 131. Obtain a first feature point set of a facial image y, where the facial image y is any facial image among the multiple facial images;

[0088] 132. Match the first feature point set with the second feature point set of the preset face template;

[0089] 133. When the matching value between the first feature set and the second feature point set is greater than a first preset threshold, it is determined that the face image j is successfully matched with the preset face template;

[0090] 134. When the matching value between the first feature set and the second feature point set is less than or equal to the first preset threshold and greater than the second preset threshold, select three pairs of feature points with the largest matching values ​​according to the matching result, wherein the three pairs of feature points with the largest matching values ​​include three first feature points in the face image y and three second feature points in the preset face template;

[0091] 135. Construct a first triangle according to the three first feature points in the facial image y, and construct a second triangle according to the three second feature points in the preset facial template. When the first triangle is similar to the second triangle, determine that the facial image j is successfully matched with the preset facial template.

[0092] The first preset threshold and the second preset threshold can both be preset or set by the system by default, and the second preset threshold is smaller than the first preset threshold.

[0093] Specifically, the first feature point set can be matched with the second feature point set of the preset face template. When the matching value between the first feature set and the second feature point set is greater than a first preset threshold, it is determined that the face image j successfully matches the preset face template. When the matching value between the first feature set and the second feature point set is less than or equal to a second preset threshold, it can be determined that the match fails. A high threshold can be set to achieve accurate face recognition.

[0094] Further, when the matching value between the first feature set and the second feature point set is less than or equal to the first preset threshold and greater than the second preset threshold, three pairs of feature points with the largest matching values ​​are selected according to the matching results, and the three pairs of feature points with the largest matching values ​​include three first feature points in the face image y and three second feature points in the preset face template, and then a first triangle is constructed according to the three first feature points in the face image y, and a second triangle is constructed according to the three second feature points in the preset face template. When the first triangle is similar to the second triangle, it is determined that the face image j successfully matches the preset face template, otherwise, it is determined that the face image j fails to match the preset face template, so that face matching can be performed accurately. Since the matching value may be misidentified or missed when it is between the second preset threshold and the first preset threshold, and because the image quality is sometimes poor, the feature point significance is low, and the feature points are used to form a triangle to compare similarities, which can reduce the threshold of feature significance, and further identify and distinguish through the "similar shape" of the feature points, which helps to improve the accuracy of face recognition and ensure the accuracy of personnel filing.

[0095] It can be seen that the personnel archiving management method described in the embodiment of the present application obtains a data set of the first object, and the data set includes M data, each data includes at least the identity information, location information and data sampling time point of the first object, M is an integer greater than 1, and the M data are sliced ​​according to the time step and the spatial radius to obtain N slices, each slice includes at least one data, N is a positive integer less than M, and activity pattern analysis is performed based on the N slices. Since the archiving process introduces time and space information, accurate activity pattern analysis can be achieved through personnel archiving combined with time and space information.

[0096] With the above Figure 1A For the embodiments shown, please refer to Figure 2 , Figure 2 : is a flow chart of a personnel filing management method provided in an embodiment of the present application, and the personnel filing management method includes:

[0097] 201. Obtain a data set of a first object, where the data set includes M data, each data includes at least identity information, location information, and a data sampling time point of the first object, and M is an integer greater than 1.

[0098] 202. Slice the M data according to the time step and the space radius to obtain N slices, each slice including at least one data, and N is a positive integer less than M.

[0099] 203. Perform activity pattern analysis based on the N shards.

[0100] 204. Obtain X shards corresponding to the data set of the second object, where X is an integer greater than 1.

[0101] 205. Perform a similarity comparison between the N slices and the X slices to obtain a similarity comparison result.

[0102] 206. Determine a target relationship attribute between the first object and the second object according to the similarity comparison result.

[0103] The specific description of the above steps 201 to 206 can refer to the above Figure 1A The corresponding steps of the described personnel archive management method will not be repeated here.

[0104] It can be seen that the personnel archiving management method described in the embodiment of the present application obtains a data set of the first object, the data set includes M data, each data includes at least the identity information, location information and data sampling time point of the first object, M is an integer greater than 1, and the M data are sliced ​​according to the time step and the spatial radius to obtain N slices, each slice includes at least one data, N is a positive integer less than M, and activity pattern analysis is performed according to the N slices, and X slices corresponding to the data set of the second object are obtained, X is an integer greater than 1, and the N slices are compared with the X slices for similarity to obtain a similarity comparison result, and the target relationship attribute between the first object and the second object is determined according to the similarity comparison result. On the one hand, since the archiving process introduces time and space information, through personnel archiving, combined with time and space information, accurate activity pattern analysis can be achieved. On the other hand, the similarity between the two archives can also be compared to determine the relationship between the two objects.

[0105] In accordance with the above embodiment, please refer to Figure 3 , Figure 3: is a schematic diagram of the structure of a smart street lamp provided in an embodiment of the present application. As shown in the figure, the smart street lamp includes a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor. In the embodiment of the present application, the program includes instructions for executing the following steps:

[0106] Acquire a data set of a first object, the data set including M data, each data including at least identity information, location information and a data sampling time point of the first object, and M is an integer greater than 1;

[0107] The M data are divided into slices according to the time step and the space radius to obtain N slices, each slice includes at least one data, and N is a positive integer less than M;

[0108] Activity pattern analysis is performed based on the N shards.

[0109] Optionally, in the aspect of dividing the M data into slices according to the time step and the space radius to obtain N slices, the program includes instructions for executing the following steps:

[0110] Selecting a reference trajectory point as starting data, determining a preset time step and a preset space radius, wherein the reference trajectory point corresponds to at least one of the M data;

[0111] Slice the M data based on the reference trajectory point, the preset time step, and the preset space radius to obtain N reference slices;

[0112] Abnormal data is eliminated from the N reference slices to obtain the N slices.

[0113] Optionally, when the reference trajectory point is data whose time among the M data is within a preset time range, the preset time range is a moment between the earliest time of the M data and a preset time step after the earliest moment;

[0114] In terms of dividing the M data into slices based on the reference trajectory points, the preset time step, and the preset spatial radius to obtain N reference slices, the program includes instructions for executing the following steps:

[0115] Determine a first slice of the M data according to the reference trajectory point, the preset time step, and the preset space radius;

[0116] The remaining slices are divided according to the first slice, the preset time step, and the preset space radius to obtain the N reference slices.

[0117] Optionally, in the aspect of eliminating abnormal data from the N reference slices to obtain the N slices, the program includes instructions for executing the following steps:

[0118] Acquire a first data sampling time point and corresponding first position information of data j in reference slice i, wherein the reference slice i is any reference slice among the N reference slices, and the data j is any data in the reference slice i;

[0119] Obtain second data sampling time points and corresponding second position information of k data that are temporally adjacent to the data j, where k is a positive integer;

[0120] Abnormal data is eliminated according to the first data sampling time point and the corresponding first position information of the data j in the reference slice i, and the second data sampling time point and the corresponding second position information of the k data, to obtain the reference slice i after the abnormal data is eliminated.

[0121] Optionally, in the aspect of performing activity pattern analysis according to the N shards, the program includes instructions for executing the following steps:

[0122] Performing location type statistics on each of the N slices to obtain a statistical result;

[0123] Divide each of the N shards into time ranges according to the statistical results to obtain a division result;

[0124] A weight value is configured for each position in each of the N slices according to the division result, wherein the greater the number, the smaller the weight value.

[0125] Optionally, the program further includes instructions for executing the following steps:

[0126] Get X shards corresponding to the data set of the second object, where X is an integer greater than 1;

[0127] Compare the N slices with the X slices for similarity to obtain a similarity comparison result;

[0128] A target relationship attribute between the first object and the second object is determined according to the similarity comparison result.

[0129] It can be seen that the electronic device described in the embodiment of the present application obtains a data set of a first object, and the data set includes M data, each data includes at least identity information, location information and data sampling time point of the first object, M is an integer greater than 1, and the M data are sliced ​​according to the time step and the spatial radius to obtain N slices, each slice includes at least one data, N is a positive integer less than M, and activity pattern analysis is performed based on the N slices. Since the archiving process introduces time and space information, accurate activity pattern analysis can be achieved through personnel archiving combined with time and space information.

[0130] Figure 4 4 is a functional unit composition block diagram of a personnel filing management device 400 involved in an embodiment of the present application, which is applied to an electronic device. The device 400 includes: an acquisition unit 401, a division unit 402 and an analysis unit 403, wherein:

[0131] The acquisition unit 401 is used to acquire a data set of a first object, the data set includes M data, each data includes at least identity information, location information and data sampling time point of the first object, and M is an integer greater than 1;

[0132] The partitioning unit 402 is used to partition the M data into N slices according to the time step and the space radius, each slice including at least one data, where N is a positive integer less than M;

[0133] The analysis unit 403 is used to analyze activity patterns according to the N slices.

[0134] Optionally, in the aspect of dividing the M data into slices according to the time step and the space radius to obtain N slices, the dividing unit 402 is specifically used for:

[0135] Selecting a reference trajectory point as starting data, determining a preset time step and a preset space radius, wherein the reference trajectory point corresponds to at least one of the M data;

[0136] Slice the M data based on the reference trajectory point, the preset time step, and the preset space radius to obtain N reference slices;

[0137] Abnormal data is eliminated from the N reference slices to obtain the N slices.

[0138] Optionally, when the reference trajectory point is data whose time among the M data is within a preset time range, the preset time range is a moment between the earliest time of the M data and a preset time step after the earliest moment;

[0139] In the aspect of dividing the M data into slices based on the reference trajectory points, the preset time step and the preset space radius to obtain N reference slices, the dividing unit 402 is specifically used to:

[0140] Determine a first slice of the M data according to the reference trajectory point, the preset time step, and the preset space radius;

[0141] The remaining slices are divided according to the first slice, the preset time step, and the preset space radius to obtain the N reference slices.

[0142] Optionally, in the aspect of eliminating abnormal data from the N reference slices to obtain the N slices, the dividing unit 402 is specifically configured to:

[0143] Acquire a first data sampling time point and corresponding first position information of data j in reference slice i, wherein the reference slice i is any reference slice among the N reference slices, and the data j is any data in the reference slice i;

[0144] Obtain second data sampling time points and corresponding second position information of k data that are temporally adjacent to the data j, where k is a positive integer;

[0145] Abnormal data is eliminated according to the first data sampling time point and the corresponding first position information of the data j in the reference slice i, and the second data sampling time point and the corresponding second position information of the k data, to obtain the reference slice i after the abnormal data is eliminated.

[0146] Optionally, in the aspect of performing activity pattern analysis according to the N shards, the analyzing unit 403 is specifically configured to:

[0147] Performing location type statistics on each of the N slices to obtain a statistical result;

[0148] Divide each of the N shards into time ranges according to the statistical results to obtain a division result;

[0149] A weight value is configured for each position in each of the N slices according to the division result, wherein the greater the number, the smaller the weight value.

[0150] Optionally, the device 400 is further specifically used for:

[0151] Get X shards corresponding to the data set of the second object, where X is an integer greater than 1;

[0152] Compare the N slices with the X slices for similarity to obtain a similarity comparison result;

[0153] A target relationship attribute between the first object and the second object is determined according to the similarity comparison result.

[0154] It can be seen that the personnel archiving management device described in the embodiment of the present application obtains a data set of a first object, and the data set includes M data, each data includes at least the identity information, location information and data sampling time point of the first object, M is an integer greater than 1, and the M data are sliced ​​according to the time step and the spatial radius to obtain N slices, each slice includes at least one data, N is a positive integer less than M, and activity pattern analysis is performed based on the N slices. Since the archiving process introduces time and space information, accurate activity pattern analysis can be achieved through personnel archiving combined with time and space information.

[0155] It can be understood that the functions of each program module of the personnel filing management device of this embodiment can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0156] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes a control platform.

[0157] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes a control platform.

[0158] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0159] In the above embodiments, 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.

[0160] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as 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, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0161] The units described above 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or software functional unit.

[0163] If the above-mentioned 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 memory. Based on this understanding, the technical solution of the present application is essentially 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 memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0164] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0165] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A personnel filing management method, characterized in that: The method comprises: Acquire a data set of a first object, the data set including M data, each data including at least identity information, location information and a data sampling time point of the first object, and M is an integer greater than 1; The M data are divided into slices according to the time step and the space radius to obtain N slices, each slice includes at least one data, and N is a positive integer less than M; Performing activity pattern analysis according to the N shards; The performing activity pattern analysis according to the N shards includes: Performing location type statistics on each of the N slices to obtain a statistical result; Divide each of the N shards into time ranges according to the statistical results to obtain a division result; According to the division result, a weight value is configured for each position in each of the N slices, wherein the greater the number, the smaller the weight value; The method further comprises: Get X shards corresponding to the data set of the second object, where X is an integer greater than 1; Compare the N slices with the X slices for similarity to obtain a similarity comparison result, where the similarity is a behavior rule similarity; Determine a target relationship attribute between the first object and the second object according to the similarity comparison result; The comparing the N slices with the X slices to obtain a similarity comparison result includes: When the shards between N shards and X shards intersect across different shards, the cosine calculation method is used separately in combination with the active address weight to calculate the similarity, and finally the sum is calculated.

2. The method according to claim 1, characterized in that The M data are divided into pieces according to the time step and the space radius to obtain N pieces, including: Selecting a reference trajectory point as starting data, determining a preset time step and a preset space radius, wherein the reference trajectory point corresponds to at least one of the M data; Slice the M data based on the reference trajectory point, the preset time step, and the preset space radius to obtain N reference slices; Abnormal data is eliminated from the N reference slices to obtain the N slices.

3. The method according to claim 2, characterized in that When the reference trajectory point is data in the M data whose time is within a preset time range, the preset time range is a moment between the earliest time of the M data and a preset time step after the earliest time; The step of slicing the M data based on the reference trajectory point, the preset time step, and the preset space radius to obtain N reference slices includes: Determine a first slice of the M data according to the reference trajectory point, the preset time step, and the preset space radius; The remaining slices are divided according to the first slice, the preset time step, and the preset space radius to obtain the N reference slices.

4. The method according to claim 2, characterized in that: The step of eliminating abnormal data from the N reference slices to obtain the N slices includes: Obtain a first data sampling time point and corresponding first position information of data j in reference slice i, wherein the reference slice i is any reference slice among the N reference slices, and the data j is any data in the reference slice i; Obtain second data sampling time points and corresponding second position information of k data that are temporally adjacent to the data j, where k is a positive integer; Abnormal data is eliminated according to the first data sampling time point and the corresponding first position information of the data j in the reference slice i, and the second data sampling time point and the corresponding second position information of the k data, to obtain the reference slice i after the abnormal data is eliminated.

5. A personnel filing management device, characterized in that: The device comprises: an acquisition unit, a division unit and an analysis unit, wherein the acquisition unit is used to acquire a data set of a first object, the data set includes M data, each data includes at least identity information, location information and data sampling time point of the first object, and M is an integer greater than 1; The partitioning unit is used to partition the M data into N slices according to the time step and the space radius, each slice including at least one data, where N is a positive integer less than M; The analysis unit is used to analyze activity patterns according to the N shards; The analysis unit is specifically used for: Performing location type statistics on each of the N slices to obtain a statistical result; Divide each of the N shards into time ranges according to the statistical results to obtain a division result; According to the division result, a weight value is configured for each position in each of the N slices, wherein the greater the number, the smaller the weight value; The device is also specifically used for: Get X shards corresponding to the data set of the second object, where X is an integer greater than 1; Compare the N slices with the X slices for similarity to obtain a similarity comparison result, where the similarity is a behavior rule similarity; Determine a target relationship attribute between the first object and the second object according to the similarity comparison result; The device is also specifically used for: When the shards between N shards and X shards intersect across different shards, the cosine calculation method is used separately in combination with the active address weight to calculate the similarity, and finally the sum is calculated.

6. The device according to claim 5, characterized in that In the aspect of dividing the M data into slices according to the time step and the space radius to obtain N slices, the dividing unit is specifically used for: Selecting a reference trajectory point as starting data, determining a preset time step and a preset space radius, wherein the reference trajectory point corresponds to at least one of the M data; Slice the M data based on the reference trajectory point, the preset time step, and the preset space radius to obtain N reference slices; Abnormal data is eliminated from the N reference slices to obtain the N slices.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program comprises instructions for executing the steps in the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 4.

Images