Resident migration data mining method and device, computing equipment and storage medium
By acquiring the spatiotemporal trajectory information of the main cluster and establishing a spatial index using quadtrees and R-trees, the distribution of the main's active areas is determined. This solves the problem of inaccurate residence and migration information in existing technologies, and enables accurate calculation of residence and migration, meeting the application needs of smart logistics, smart cities, and smart transportation.
Patent Information
- Application Number
- CN202310558404.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-17
- Publication Date
- 2024-11-22
AI Technical Summary
Existing technologies cannot systematically and accurately monitor and calculate the number of residents and migrants in a region, resulting in inaccurate resident and migration information that cannot meet the needs of application scenarios such as smart logistics and smart cities.
By acquiring the spatiotemporal trajectory information of the main cluster, using quadtrees and R-trees to establish spatial indexes, the distribution of active regions of the main body is determined, and the residence and migration information is calculated based on the changes in active status, so as to accurately determine the association between the main body and the target region and achieve the accuracy of residence and migration.
It improves the accuracy of residency and migration information, and can be effectively applied to scenarios such as smart logistics, smart cities, and smart transportation, providing accurate data on residency, inflow, and outflow.
Smart Images

Figure CN119003607A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data analysis and processing, and in particular to a method and apparatus for resident migration data mining, a computing device, a computer-readable storage medium, and a computer program product. Background Art
[0002] At present, the development of Internet technology has achieved the precise positioning of the target subject. When the subject cluster is equipped with a positioning device, the residence and migration information of each subject in a certain space can be mined based on the confirmation information provided by each subject. Many application scenarios (such as smart logistics, smart cities, smart transportation, etc.) require residence and migration information of the target area. However, there is currently a lack of solutions that can systematically and self-consistently monitor and calculate the residence and migration volume of a region (such as an administrative division).
[0003] In the related technologies, it is impossible to mine the residence volume of each subject based on the spatiotemporal trajectory of each subject, or the time dimension of mining the residence migration information of the subject cluster is too long (for example, within one to three years), and the statistical process and calculation method of the related technical solutions are very rough. For example, only the subjects who reside in the target area on that day are regarded as the residence volume of the target area, or only the number of subjects that appeared in another area the day before and appeared in the target area on that day is regarded as the migration volume, resulting in the statistical residence migration information being inaccurate and not having sufficient reference value. Summary of the invention
[0004] In view of this, the present application provides a resident migration data mining method and apparatus, a computing device, a computer-readable storage medium, and a computer program product, which are expected to alleviate or overcome some or all of the above-mentioned defects and other possible defects.
[0005] According to a first aspect of the present application, a resident migration data mining method is provided, comprising: obtaining confirmation information of a subject cluster in each time unit of a preset time unit sequence, wherein the subject cluster includes multiple subjects; based on the confirmation information of the subject cluster in each time unit of the preset time unit sequence, determining the active area distribution of the subject cluster in each time unit from a predetermined area set, wherein the predetermined area set includes a target area; according to the active area distribution of the subject cluster in each time unit, determining a first target active state and a second target active state of the subject cluster, wherein the first target active state indicates a change in the active area distribution of the subject cluster in the first target time unit relative to at least one adjacent previous time unit and its association with the target area, and the second target active state indicates a change in the active area distribution of the subject cluster in the second target time unit relative to at least one adjacent previous time unit and its association with the target area, wherein the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is the previous time unit adjacent to the first target time unit in the preset time unit sequence; according to the first target active state and the second target active state of the subject cluster, determining the resident migration information of the target area in the first target time unit.
[0006] According to a second aspect of the present application, a resident migration data mining device is provided, which comprises: an acquisition module, which is configured to acquire confirmation information of a subject cluster in each time unit of a preset time unit sequence, wherein the subject cluster comprises a plurality of subjects; an active area determination module, which is configured to determine the active area distribution of the subject cluster in each time unit from a predetermined area set based on the confirmation information of the subject cluster in each time unit of the preset time unit sequence, wherein the predetermined area set comprises a target area; a target active state determination module, which is configured to determine a first target active state and a second target active state of the subject cluster according to the active area distribution of the subject cluster in each time unit, wherein the first target active state Indicates the change in the active area distribution of the main cluster in the first target time unit relative to at least one adjacent previous time unit and its association with the target area, the second target active state indicates the change in the active area distribution of the main cluster in the second target time unit relative to at least one adjacent previous time unit and its association with the target area, the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is the previous time unit adjacent to the first target time unit in the preset time unit sequence; a statistical module is configured to determine the resident migration information of the target area in the first target time unit based on the first target active state and the second target active state of the main cluster.
[0007] According to a third aspect of the present application, a computing device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor is prompted to perform the steps of the resident migration data mining method according to some embodiments of the present application.
[0008] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed, the resident migration data mining method according to some embodiments of the present application is implemented.
[0009] According to a fifth aspect of the present application, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the resident migration data mining method according to some embodiments of the present application.
[0010] In the resident migration data mining method and device according to some embodiments of the present application, in the resident migration data mining process, the active area distribution of the main cluster is first accurately determined based on the confirmation information, and then the target active state of the main cluster related to the target area is determined using the active area distribution, and the resident migration information of the target area is calculated based on the transfer of the target active state of each spatial subject between adjacent time units, thereby ensuring the accuracy of the obtained resident volume and migration volume and effectively applying them to respective application scenarios (such as smart logistics, smart cities, smart transportation, etc.).
[0011] These and other advantages of the present application will become apparent from and be elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Embodiments of the present application will now be described in more detail and with reference to the accompanying drawings, in which:
[0013] Figure 1 It is an exemplary application scenario of the resident migration data mining method according to some embodiments of the present application;
[0014] Figure 2 is a flowchart of a resident migration data mining method according to some embodiments of the present application;
[0015] Figure 3 is a flow chart of determining an active area according to some embodiments of the present application;
[0016] Figure 4 is a schematic diagram of determining active areas of a subject in various time windows according to some embodiments of the present application;
[0017] Figure 5 is a schematic diagram of changing the active state according to some embodiments of the present application;
[0018] Figure 6 is a flow chart for determining the resident migration information of the target area in the first target time unit;
[0019] Figure 7 is a schematic diagram of a state transition mode according to some embodiments of the present application;
[0020] Figure 8 is an exemplary structural block diagram of a resident migration data mining device according to some other embodiments of the present application;
[0021] Fig. 9 An example system is shown that includes an example computing device that represents one or more systems and / or devices that may implement the various methods described herein. DETAILED DESCRIPTION
[0022] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.
[0023] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0024] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0025] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0026] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the concepts of the present application. As used herein, the term "and / or" and similar terms include all combinations of any, multiple, and all of the associated listed items.
[0027] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present application, and therefore cannot be used to limit the scope of protection of the present application.
[0028] Before describing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.
[0029] Spatiotemporal trajectory information: refers to information representing temporal content and spatial content, where the temporal content can be a timestamp and the spatial content can be spatial coordinates. In this application, it is actively provided by the subject.
[0030] Subject: refers to the terminal or device to which the corresponding confirmation information can point, such as a vehicle that can collect positioning information (such as a car), goods in transit, identification devices, communication equipment, etc.
[0031] Region: refers to a certain spatial scope, such as a county, city or provincial administrative division.
[0032] Resident behavior: refers to the behavior of a subject staying in a certain area for a specific time unit.
[0033] Migration behavior: refers to the behavior of a subject moving out of one area and into another area in a specific time unit.
[0034] Quadtree: Quadtree is a tree-like data structure with four sub-blocks on each node. Quadtree is often used for the analysis and classification of two-dimensional spatial data. It divides the data into four quadrants, each of which can be a square, rectangle or other arbitrary shape. For example, the entire data area is divided into many small rectangles, each of which represents a node of a quadtree. The largest rectangle is the root node of the quadtree. Some rectangles are divided into four small rectangles of equal size. These small rectangles are the four sub-nodes of the node. The smaller the rectangle, the greater the depth of the node.
[0035] R-tree: R-tree is a data structure used to process multidimensional data. There are two types of nodes on the tree: leaf nodes and non-leaf nodes. Each node is composed of several index items. For leaf nodes, the index item is in the form of (Index, Obj_ID). Among them, Index represents the minimum bounding rectangle MBR surrounding the spatial data body, and Obi ID identifies a spatial data body. For a non-leaf node, its index item is in the form of (Index, Child Pointer), Child Pointer points to the child node of the node, and Index still refers to a rectangular area, which surrounds the minimum rectangular area of all index item MBRs on the child node.
[0036] Figure 1 An exemplary application scenario 100 of the resident migration data mining method according to some embodiments of the present application is shown. The application scenario 100 may include a client 101, a network 102, and a service unit 103, and the service unit 103 is communicatively coupled with the client 101 through the network 102. The network 102 may be, for example, a wide area network (WAN), a local area network (LAN), a wireless network, a public telephone network, an intranet, and any other type of network known to those skilled in the art.
[0037] In this embodiment, the resident migration data mining method is executed by the service unit 103 .
[0038] First, the service unit 103 obtains confirmation information of the subject cluster in each time unit of the preset time unit sequence. It should be noted that the confirmation information can be pre-stored in a local database (not shown) or a storage module of the service unit 103, or can be obtained in real time from other parties. When the confirmation information is pre-stored in the local database or the storage module of the service unit 103, the subsequent steps for the confirmation information can be pre-processed offline, which can save a lot of computing resources and improve processing efficiency.
[0039] Then, the service unit 103 determines the active area of each subject in each time unit from a predetermined area set based on the confirmation information of the subject in each time unit of the preset time unit sequence for each subject in the subject cluster, and the predetermined area set includes an empty area and at least one non-empty area, and the at least one non-empty area includes the target area. As described above, when the confirmation information is pre-stored in the local database or the storage module of the service unit 103, this step can be pre-executed in the service unit 103. The active areas of each subject in each time unit determined in this step can be stored in the form of a table for the client 101 to query on demand, which helps the client 101 understand the active areas of a single individual.
[0040] Then, the service unit 103 determines the first active state and the second active state of each subject in the subject cluster according to the active area of each time unit in the preset time unit sequence, wherein the first active state indicates the change of the active area of the subject in the first target time unit relative to at least one adjacent previous time unit, and the second active state indicates the change of the active area of the subject in the second target time unit relative to at least one adjacent previous time unit, wherein the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is the previous time unit adjacent to the first target time unit in the preset time unit sequence. Similarly, the first active state and the second active state of the subject determined in this step can be stored in the form of a table for the client 101 to query on demand, which helps the client 101 understand the resident migration information of a single individual.
[0041] Next, the service unit 103 determines the first target active state of the subject according to the first active state of the subject and determines the second target active state of the subject according to the second active state of the subject for each subject in the subject cluster, wherein the first target active state of the subject includes the first active state of the subject and its association with the target area, and the second target active state of the subject includes the second active state of the subject and its association with the target area. In this step, the service unit 103 only needs to determine the first target active state corresponding to the first target time unit and the second target active state corresponding to the second target time unit, and does not need to determine the target active states corresponding to other time units.
[0042] Finally, the service unit 103 determines the resident migration information of the target area in the first target time unit according to the first target active state and the second target active state of each subject in the subject cluster, and the resident migration information indicates the number of subjects in the subject cluster that have at least one of the resident behavior and the migration behavior related to the target area in the first target time unit. For example, the service unit 103 can then use the network 102 to transmit the resident migration information of the target area in the first target time unit to the client 101.
[0043] exist Figure 1 In the application scenario shown, the resident migration data mining method according to some embodiments of the present application is implemented on the service unit 103, but this is only illustrative and not restrictive. The resident migration data mining method according to some embodiments of the present application can also be implemented on other entities with sufficient computing resources and computing capabilities, for example, it can be implemented on the client 101 with sufficient computing resources and computing capabilities. Of course, it can also be partially implemented on the service unit 103 and partially implemented on the client 101, which is not restrictive.
[0044] As understood by those skilled in the art, an instance of the service unit 103 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The servers may be directly or indirectly connected via wired or wireless communications, which is not limited in this application.
[0045] The client 101 may be any type of mobile computing device, including a mobile computer (e.g., a personal digital assistant (PDA), a laptop computer, a notebook computer, a tablet computer, a netbook, etc.), a mobile phone (e.g., a cellular phone, a smart phone, etc.), a wearable computing device (e.g., a smart watch, a head-mounted device, including smart glasses, etc.), or other types of mobile devices. In some embodiments, the client 101 may also be a stationary computing device, such as a desktop computer, a game console, a smart TV, etc.
[0046] like Figure 1 As shown, the client 101 may include a display screen and a terminal application that can interact with the terminal user via the display screen. The terminal application can be a local application, a web page (Web) application, or a small program (Lite App, such as a mobile phone small program, WeChat small program) as a lightweight application. In the case where the terminal application is a local application that needs to be installed, the terminal application can be installed on the client 101. In the case where the terminal application is a Web application, the terminal application can be accessed through a browser. In the case where the terminal application is a small program, the terminal application can be directly opened on the client 101 by searching for relevant information of the terminal application (such as the name of the terminal application, etc.), scanning a graphic code (such as a barcode, a QR code, etc.) of the terminal application, etc., without installing the terminal application.
[0047] Figure 2 is a flowchart of a resident migration data mining method according to some embodiments of the present application. The method 200 shown can be performed in a service unit (for example, in Figure 1 In some embodiments, when the client 101 has sufficient computing resources and computing power, the resident migration data mining method according to some embodiments of the present application can be directly executed on the client 101. In other embodiments, the resident migration data mining method according to some embodiments of the present application can also be executed by the service unit 103 and the client 101 in combination. Figure 2 As shown, according to some embodiments of the present application, the resident migration data mining method may include steps S201-S205. In step S201, confirmation information of the subject cluster in each time unit of the preset time unit sequence is obtained, and the subject cluster includes multiple subjects. In various embodiments of the present application, the confirmation information may include spatiotemporal trajectory information. A time unit is a time of preset length, for example, a time unit can be a day, a month, a quarter, an hour, etc. The preset time unit sequence includes multiple time units, which may be continuous or discontinuous. For example, in the case where a time unit is a time period of one day, the preset time unit sequence may be a sequence including fifteen consecutive days (i.e., fifteen consecutive time units).
[0048] In an embodiment of the resident migration data mining method according to the present application, the basic data for mining the resident migration information is confirmation information, so the confirmation information of each subject (such as spatiotemporal trajectory information) should be obtained first. Since when inferring the resident migration information of the target time unit, it is mainly affected by the confirmation information of the target time unit and the confirmation information of the previous time unit of the target time unit, in order to improve the accuracy of the finally determined resident migration information, the confirmation information of the subject cluster in the preset time unit sequence can be obtained. When the more confirmation information is used for mining, the more accurate the finally determined resident migration information is. In addition, the length of the time unit can be set in advance, which helps to improve the flexibility of the time unit.
[0049] In step S202, based on the confirmation information of the subject cluster in each time unit of the preset time unit sequence, the active area distribution of the subject cluster in each time unit is determined from the predetermined area set, and the predetermined area set includes the target area. The confirmation information of a subject in a time unit may include multiple areas, which means that the subject appears in multiple areas in the time unit. At this time, it is necessary to select one area from them as the active area of the subject in the time unit, excluding the interference of inactive areas. The active area indicates the most active area of a subject in a time unit. For example, if subject A appears 5 times in area 1 and 1 time in area 2, area 1 can be used as the active area of subject A. The active area distribution reflects the distribution of active areas of each subject in the subject cluster. The confirmation information can be a trajectory curve composed of multiple ternary coordinate information containing time content and spatial content. The ternary coordinate information can be, for example, (13:21, 80, 100), which means that subject A appears at position (80, 100) at 13:21. Therefore, one objective according to an embodiment of the present application is to determine the resident migration information of a target area, so the target area should be included in the predetermined area set.
[0050] This step can realize the transitional processing of the confirmation information to obtain the active area distribution of the main cluster.
[0051] In step S203, according to the active area distribution of the main cluster in each time unit, the first target active state and the second target active state of the main cluster are determined, the first target active state indicates the change of the active area distribution of the main cluster in the first target time unit relative to at least one adjacent previous time unit and its association with the target area, the second target active state indicates the change of the active area distribution of the main cluster in the second target time unit relative to at least one adjacent previous time unit and its association with the target area, the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is the previous time unit adjacent to the first target time unit in the preset time unit sequence. Because in this embodiment, it is only necessary to determine the resident migration information of the target area in the first target time unit, and it is not necessary to determine the resident migration information of other areas in the first target time unit, so in this step, it is only necessary to distinguish the main cluster with respect to the target area and determine the association between the main cluster and the target area, thereby saving computing resources.
[0052] In step S204, the resident migration information of the target area in the first target time unit is determined according to the first target active state and the second target active state of the subject cluster. In various embodiments of the present application, the resident migration information indicates the number of subjects in the subject cluster that have at least one of the resident behavior and the migration behavior related to the target area in the first target time unit. In the previous steps, the resident migration situation of each subject and the association with the target area have been determined, so the resident migration information of the target area in the first target time unit can be determined directly according to the first target active state and the second target active state of each subject in the subject cluster. In some embodiments, the resident migration information includes the subject resident amount, the subject migration amount and the subject migration amount. The subject resident amount indicates the number of subjects with resident behavior related to the target area in the first target time unit. The subject migration amount indicates the number of subjects with migration behavior related to the target area and the migration place is the target area in the first target time unit. The subject migration amount indicates the number of subjects with migration behavior related to the target area and the migration place is the target area in the first target time unit.
[0053] In the residence migration data mining method according to some embodiments of the present application, in the residence migration data mining process, the active area distribution of the main cluster is first accurately determined based on the confirmation information, and then the target activity state of the main cluster related to the target area is determined using the active area distribution, and the residence migration information of the target area is calculated based on the transfer of the target activity state of each spatial subject between adjacent time units, thereby ensuring the accuracy of the residence volume and migration volume obtained and effectively applying them to respective application scenarios (such as smart logistics, smart cities, smart transportation, etc.).
[0054] Table 1 - Example table of migration information.
[0055] Region Name Retention Migration Migration Region 1 1000 1022 275 Area 2 2163 745 198
[0056] According to some embodiments of the present application, the migration information table shown in Table 1 may be obtained to provide a reference for other applications.
[0057] More detailed embodiments are provided below from various perspectives.
[0058] Figure 3 is a flow chart of determining an active area according to some embodiments of the present application. Figure 3 As shown, in this embodiment, the predetermined area set includes an empty area and at least one non-empty area, because not every subject has confirmation information in each time unit. If not, the active area of the object in the time unit can be determined as an empty area. In this embodiment, for each subject in the subject cluster, based on the confirmation information of the subject in each time unit of the preset time unit sequence, the active area of the subject in each time unit is determined from the predetermined area set, including steps S301-S306.
[0059] In step S301, a spatial index corresponding to the predetermined area set is constructed based on the contour information of at least one non-empty area in the predetermined area set. Because confirmation information such as spatiotemporal trajectory information is often embodied in the form of coordinates, in order to determine the active area of the subject in each time unit, the indexing method of the predetermined area set should be determined first. To this end, a spatial index can be established based on the contour information of each area. For example, a spatial index of the predetermined area set is established based on a quadtree or an R-tree.
[0060] In step S302, for each subject in the subject cluster and each time unit in the preset time unit sequence, in response to the confirmation information of the subject in the time unit being not empty, at least one space-time stop point is extracted from the confirmation information and the position information and corresponding timestamp of each space-time stop point are obtained. In this embodiment, if the confirmation information (such as space-time trajectory information) is the trajectory curve of the subject, the space-time point information can be one of the points, that is, the ternary coordinate information. The space-time point information indicates the position where the subject stays at a certain moment. Because a subject may have multiple space-time point information in a time unit, it is necessary to select valuable space-time point information from it as the space-time stop point of the subject, for example, the space-time point in the smoothing stage of the entire trajectory curve can be used as the space-time stop point. Alternatively, the space-time point in the space-time trajectory can be directly used as the space-time stop point.
[0061] In step S303, for each spatiotemporal stay point of each subject in each time unit in the subject cluster, based on the position information and spatial index of the spatiotemporal stay point, the non-empty area where the spatiotemporal stay point is located is determined from the predetermined area set. As described above, the index can be completed based on the spatial index of the predetermined area set established by the quadtree or R-tree, so as to determine the non-empty area where each spatiotemporal stay point is located.
[0062] In step S304, for each time unit in the predetermined time unit sequence, the time unit is divided into a plurality of time windows to form a time window sequence. A more detailed division is performed for each time unit, so that the area where the subject is located can be determined more accurately. For example, when the length of a time unit is one day, each time unit can be divided into 24 time windows to form a time window sequence for the time unit.
[0063] In step S305, for each subject in the subject cluster, based on the non-empty area at each spatiotemporal stop point of the subject in each time unit and the corresponding timestamp, the non-empty area at which the subject is located in each time window in the time window sequence of the time unit is determined from the predetermined area set. In this embodiment, the non-empty area at which the subject is located in each time window can be determined based on the time window sequence of the time unit formed in step S304, and the non-empty area at which each spatiotemporal stop point is located and the timestamp determined in step S303. For example, based on the timestamp, the non-empty area at which each spatiotemporal stop point is located can be associated with the time window.
[0064] In step S306, for each subject in the subject cluster, the active region of the subject in the time unit is determined from the predetermined region set according to the non-empty region where the subject is located in each time window in the time window sequence of each time unit. In this step, there are many ways to determine the active region of the subject in the time unit, such as taking the most appearing non-empty region as the active region, or taking the latest appearing non-empty region as the active region, etc., which are not limited here.
[0065] In this embodiment, by further dividing the time unit and respectively determining the non-empty area where each time window is located, it helps to more accurately determine the active area of the subject in a specific time unit, laying a good foundation for accurately determining the resident migration information.
[0066] Regarding step S306, in some embodiments, for each subject in the subject cluster, based on the non-empty area where the subject is located in each time window in the time window sequence of each time unit, the active area of the subject in the time unit is determined from a predetermined area set, including the following steps.
[0067] First, for each time window sequence of each time unit, the activity weight corresponding to each time window in the time window sequence is determined in chronological order, wherein for at least a portion of the time windows of the time window sequence, the activity weight corresponding to the previous time window is less than the activity weight corresponding to the later time window. In this embodiment, an activity weight is determined for each time window of the time window sequence of each time unit, and the activity weight indicates the importance of determining the area corresponding to the time window as an active area. Therefore, the higher the activity weight, the more likely the area under the time window is to become an active area. Because in general, the later the time indicated by the time window, the more likely the subject is to reside in the area corresponding to the time window, and the area is more representative of the active area, so the later time window can be assigned a higher activity weight.
[0068] Then, for each subject in the subject cluster and in each time unit, the activity weights of each different time window of the time unit corresponding to the same non-empty area where the subject is located are added together to calculate the activity of each non-empty area where the subject is located in each time window in the time window sequence of the time unit. In this step, in order to integrate the regional information of each time window, for each non-empty area, the sum of the activity weights of each different time window corresponding to the same non-empty area is taken as the activity of the non-empty area.
[0069] For example, when the time unit is 1 day, which is divided into 3 time windows, and each time window is 8 hours long, if the non-empty area where subject A is located from point 0 to point 7 is area 1, the activity weight of the time window is 0.2, and the non-empty area where subject A is located from point 8 to point 15 is area 2, the activity weight of the time window is 0.3, and the subject A is in an empty area from point 16 to point 23, the activity weight of the time window is 0.5, then the activity of area 1 is 0.1, and the activity of area 2 is 0.3.
[0070] Finally, for each subject in the subject cluster, the active area of the subject in the time unit is determined from each non-empty area according to the activity of each non-empty area where the subject is located in each time window of the time window sequence of each time unit. In this step, in order to improve the accuracy of the resident migration information of the target area in the first target time unit, the area with the highest activity can be selected as the active area. As in the example in the previous step, area 2 can be used as the active area of subject A in the time unit. The active area of the subject in the time unit can also be determined by other means.
[0071] In this embodiment, the later time window is assigned a higher activity weight, which helps to improve the accuracy of determining the active area and lays a good foundation for accurately determining the resident migration information of the target area in the first target time unit.
[0072] In some embodiments, a time unit is divided into M time windows, where M is a positive integer greater than 1. In order to process the activity weight more finely, the activity weight of each time window may be determined according to formula (1).
[0073]
[0074] Among them, j is a non-negative integer, w j is the weight of the jth time window, e is the natural logarithm, and β is a custom parameter. Here, the active weight of the Mth time window is the active weight of the first time window multiplied by e. β For example, when p = 1, the activity weight of the Mth time window is e times the activity weight of the first time window. When β = 2, the activity weight of the Mth time window is e times the activity weight of the first time window. 2 times.
[0075] After determining the active weight of each time window, the score of each area in the predetermined area set can be calculated. The calculation method can refer to formula (2).
[0076]
[0077] Where i indicates the region identifier, k is a non-negative integer, and w k is the weight of the kth time window, Ci is the set of time windows when the subject is in region i. Finally, in each region, the region with the highest score is determined as the active region of the subject in that time unit.
[0078] In some cases, the subject does not provide confirmation information (such as spatiotemporal trajectory information) in some time units, and the active areas of these time units need to be processed. In some embodiments, for each subject in the subject cluster, based on the non-empty area where the subject is located at each spatiotemporal stop point of each time unit and the corresponding timestamp, the non-empty area where the subject is located in each time window in the time window sequence of the time unit is determined from a predetermined area set, including the following steps.
[0079] For each subject in the subject cluster and each time unit in the time unit sequence, perform the following steps:
[0080] First, based on the non-empty area where each spatiotemporal stop point is located and the corresponding timestamp, at least one matching time window that matches one or more spatiotemporal stop points and the one or more non-empty areas where each of them is located is determined from the time window sequence. In this step, the matching time window indicates the time window that matches the non-empty area in the time window sequence. Because the subject may have multiple spatiotemporal stop points in a time window, a matching time window may match multiple non-empty areas. Because each spatiotemporal stop point has a corresponding timestamp, the matching time window that matches each spatiotemporal stop point can be directly determined based on the timestamp.
[0081] Then, for each matching time window in at least one matching time window, the non-empty area where the subject is located in the matching time window is determined from one or more non-empty areas according to the number of spatiotemporal stay points corresponding to each non-empty area in the one or more non-empty areas that match it. As mentioned above, because the subject may have multiple spatiotemporal stay points in a time window, a matching time window may match multiple non-empty areas. At this time, in a matching time window, for example, the non-empty area with the most appearances is more suitable as the non-empty area matched by the matching time window. For another example, since the later the subject appears in a certain area, the more likely it is to reside in the area, the non-empty area with the latest appearance time can be used as the non-empty area matched by the matching time window according to the corresponding timestamp among the one or more non-empty areas matched by the matching time window. These methods are helpful to improve the accuracy of determining active areas.
[0082] Finally, in response to the time window sequence including at least one non-matching time window other than at least one matching time window, for each non-matching time window, the non-empty area where the subject is located in the non-matching time window is determined according to the non-empty area corresponding to the matching time window adjacent to the non-matching time window in the time window sequence. The non-matching time window indicates the time window that does not match the non-empty area in the time window sequence, that is, the time window that matches the empty area. For the convenience of subsequent calculations, the area where the subject is located in the non-matching time window can be filled. In this step, the non-empty area corresponding to the matching time window is used to fill the area where the subject is located in the non-matching time window, that is, according to the non-empty area corresponding to the matching time window adjacent to the non-matching time window, the non-empty area corresponding to the non-matching time window is determined. In this way, each time window in the entire time window sequence has a corresponding non-empty area. In this step, the adjacent matching time window can be a matching time window closest to the non-matching time window.
[0083] Figure 4It is a schematic diagram of determining the active area of the subject in each time window according to some embodiments of the present application. In this embodiment, a time unit is divided into 24 time windows and forms a time window sequence. The length of a time unit is one day, and the length of a time window is one hour. According to the time and space stop point of the subject in the time unit, it can be determined that the subject is in area 1 in the 5th time window, in area 2 in the 6th time window, in area 3 in the 19th time window, and in area 4 in the 21st time window.
[0084] like Figure 4 As shown, the 1st to 4th time windows are non-matching time windows, and the 5th time window is closest to them, so the area corresponding to the 1st to 4th time windows is determined as area 1.
[0085] The 7th to 12th time windows are non-matching time windows, and the 6th time window is closest to them, so the area corresponding to the 7th to 12th time windows is determined to be area 2.
[0086] The 13th to 18th time windows are non-matching time windows, and the 19th time window is closest to them, so the area corresponding to the 13th to 18th time windows is determined to be area 3.
[0087] The 20th time window is a non-matching time window. Although the 19th time window and the 21st time window are both closest to it, the 21st time window is later and should have a higher active weight. Therefore, the area corresponding to the 20th time window can be determined as area 4.
[0088] The 22nd to 24th time windows are non-matching time windows, and the 21st time window is closest to them, so the area corresponding to the 22nd to 24th time windows is determined to be area 4.
[0089] In some embodiments, a first target active state and a second target active state of a subject cluster are determined based on the distribution of active areas of the subject cluster in each time unit, including: first, for each subject in the subject cluster, the first active state and the second active state of the subject are determined based on the active area of the subject in each time unit in a preset time unit sequence; then, for each subject in the subject cluster, the first target active state of the subject is determined based on the first active state of the subject and the second target active state of the subject is determined based on the second active state of the subject.
[0090] In this embodiment, the process of determining the first and second target active states is further divided into two stages: first determining the first and second active states, and then determining the first and second target active states. The first active state indicates the change of the active area of the subject in the first target time unit relative to at least one adjacent previous time unit, and the second active state indicates the change of the active area of the subject in the second target time unit relative to at least one adjacent previous time unit. In this embodiment, because the confirmation information of a subject does not necessarily have data in each time unit, in order to improve the accuracy of the resident migration information, the first active state can indicate the change of the active area of the subject in the first target time unit relative to at least one adjacent previous time unit. For example, the preset time unit sequence includes 15 time units. If subject A has an active area in the first target time unit (i.e., the 15th time unit), does not have an active area in the second target time unit (i.e., the 14th time unit), and has an active area in the 13th time unit, then the first active state of the subject can be determined based on the active area in the first target time unit (i.e., the 15th time unit) and the active area in the 13th-14th time unit.
[0091] In this embodiment, the active state of each individual (i.e., subject) can be predetermined, and the active state reflects the individual's resident migration situation, and then the resident migration information of the target area in the first target time unit is determined according to the active state of each individual. Therefore, in this step, the first active state and the second active state of each subject are determined according to the active area of each time unit in the preset time unit sequence. The first target time unit is the time unit corresponding to the final determination of the resident migration information, so the first active state of the subject corresponding to the first target time unit can be predetermined in this step. The resident migration information (especially the migration behavior) is also affected by the confirmation information of the second target time unit, so the second active state of the subject corresponding to the second target time unit can be determined. Therefore, determining the resident migration information of the target area in the first target time unit according to the first active state and the second active state of each subject can improve the accuracy. In addition, in this step, the active state of each subject in other time units of the preset time unit sequence is not determined, so a lot of computing resources can be saved.
[0092] In addition, by first determining the first and second active states, the relationship between the corresponding subject and the predetermined area set can be determined. In this way, when determining the first and second target active states in the second step, it is only necessary to perform a simple comparison on the target area based on the results of the first step. This embodiment provides a simple and easy implementation method for determining the first and second target active states.
[0093] In some other embodiments, specific implementation methods for determining the first active state and the second active state of a subject are provided. Each of the first active state and the second active state includes an active resident state, an active migration state, and an inactive state. And for each subject in the subject cluster, the first active state and the second active state of the subject are determined according to the active area of each time unit of the subject in a preset time unit sequence, including: for each subject in the subject cluster, the following steps are performed.
[0094] In response to the subject's active area in the first target time unit and the subject's active area in the second target time unit being the same non-empty area, the subject's first active state is determined as an active resident state, and the active resident state includes resident location information indicating the same non-empty area as the resident area. For example, if the subject A's active area in the first target time unit is area 1, and the active area in the second target time unit is area 1, then the subject's first active state can be determined as an active resident state, and the active resident state includes resident location information indicating area 1 as the resident area. When the subject's active area in the first target time unit and the subject's active area in the second target time unit are the same non-empty area, since the first active state is for the first target time unit, what may happen is that the subject has been resident in the same non-empty area in these two time units, so it is more accurate to determine the subject's first active state as an active resident state.
[0095] In response to the subject's active area in the first target time unit and the subject's active area in the second target time unit being different non-empty areas, the subject's first active state is determined as an active migration state, and the active migration state includes migration location information indicating that the non-empty area corresponding to the first target time unit is a migration-in area and the non-empty area corresponding to the second target time unit is a migration-out area. For example, if the subject A's active area in the first target time unit is area 1 and the active area in the second target time unit is area 2, the subject's first active state can be determined as an active migration state, and the active migration state includes migration location information indicating that area 1 is a migration-in area and area 2 is a migration-out area. When the subject's active area in the first target time unit and the subject's active area in the second target time unit are different non-empty areas, since the first active state is for the first target time unit, what may happen is that the subject migrates from the active area in the second target time unit to the active area in the first target time unit, so it is more accurate to determine the subject's first active state as an active migration state.
[0096] In response to the subject's active area being an empty area in the first target time unit and being a non-empty area in the second target time unit, the subject's first active state is determined as an active resident state, and the active resident state includes residence information indicating that the non-empty area corresponding to the second target time unit is the residence area. For example, if the subject A's active area in the first target time unit is an empty area and the active area in the second target time unit is area 1, the subject's first active state can be determined as an active resident state, and the active resident state includes residence information indicating that area 1 is the residence area. When the subject's active area in the first target time unit is an empty area and the active area in the second target time unit is a non-empty area, since the first active state is for the first target time unit, it may happen that the subject has been resident from the second target time unit to the first target time unit, so it is more accurate to determine the subject's first active state as an active resident state.
[0097] In response to the subject's active area in the second target time unit being an empty area, the subject's active area in the first target time unit being a non-empty area, at least one time unit corresponding to the non-empty active area exists in the preset time unit sequence before the second target time unit, and the active area corresponding to the last time unit in at least one time unit is the same non-empty area as the active area corresponding to the first target time unit, the subject's first active state is determined as an active resident state, and the active resident state includes resident location information indicating the same non-empty area as the resident area. In this step, at least one time unit corresponding to the non-empty active area exists in the preset time unit sequence before the second target time unit, and the active area corresponding to the last time unit in at least one time unit refers to the last time unit corresponding to the non-empty area in the preset time unit sequence except the first target time unit. For example, the preset time unit sequence includes 15 time units, the active area of subject A in the first target time unit is area 1, the active area in the third time unit is area 2, the active area in the fifth time unit is area 1, and the active areas in other time units are all empty areas. Then, the first active state of subject A can be determined as the active residence state, and the active residence state includes residence location information indicating area 1 as the residence area.
[0098] When the active area of the subject in the second target time unit is an empty area, the active area of the subject in the first target time unit is a non-empty area, there is at least one time unit corresponding to the non-empty active area before the second target time unit in the preset time unit sequence, and the active area corresponding to the last time unit in at least one time unit is the same non-empty area as the active area corresponding to the first target time unit, since the first active state is for the first target time unit, it may happen that the subject has been residing in the same non-empty area from the last time unit in the at least one time unit to the first target time unit, so it is more accurate to determine the first active state of the subject as the active resident state.
[0099] In response to the subject's active area in the second target time unit being an empty area, the subject's active area in the first target time unit being a non-empty area, at least one time unit corresponding to the non-empty active area existing before the second target time unit in the preset time unit sequence, and the active area corresponding to the last time unit in the at least one time unit and the active area corresponding to the first target time unit being mutually different non-empty areas, the subject's first active state is determined as an active migration state, and the active migration state includes migration location information indicating that the non-empty area corresponding to the first target time unit is used as an in-region and the non-empty area corresponding to the last time unit is used as an out-region. As in one case, in this step, at least one time unit corresponding to the non-empty active area exists before the second target time unit in the preset time unit sequence, and the active area corresponding to the last time unit in the at least one time unit refers to the last time unit corresponding to the non-empty area in the preset time unit sequence except the first target time unit. For example, the preset time unit sequence includes 15 time units, the active area of subject A in the first target time unit is area 1, the active area in the third time unit is area 1, the active area in the fifth time unit is area 2, and the active areas in other time units are all empty areas. Then, the first active state of subject A can be determined as the active migration state, and the active residence state includes migration destination information indicating area 1 as the migration-in area and area 2 as the migration-out area.
[0100] When the active area of the subject in the second target time unit is an empty area, the active area of the subject in the first target time unit is a non-empty area, there is at least one time unit corresponding to the non-empty active area before the second target time unit in the preset time unit sequence, and the active area corresponding to the last time unit in at least one time unit and the active area corresponding to the first target time unit are non-empty areas different from each other, since the first active state is for the first target time unit, what may happen is that the area corresponding to the last time unit of the subject in the at least one time unit migrates to the area corresponding to the first target time unit, so it is more accurate to determine the first active state of the subject as an active migration state.
[0101] In response to the subject's active area in the first target time unit and the active area in the second target time unit being both empty areas, and there being at least one time unit corresponding to a non-empty area before the second target time unit in the preset time unit sequence, the subject's first active state is determined to be an active resident state, and the active resident state includes residence information indicating that the non-empty area corresponding to the last time unit in at least one unit is used as the residence area. In this case, it may happen that the subject has always been resident in the non-empty area corresponding to the at least one time unit, so it is more accurate to determine the subject's first active state as an active resident state. For example, the preset time unit sequence includes 15 time units, the subject A's active area in the 5th time unit is area 1, and the active areas in other time units are all empty areas, then the subject A's first active state can be determined as an active resident state, and the active resident state includes residence information indicating area 1 as the residence area.
[0102] In response to the subject's active area in the first target time unit being a non-empty area, and the active areas corresponding to each time unit except the first target time unit in the preset time unit sequence are all empty areas, the subject's first active state is determined to be an active resident state, and the active resident state includes residence information indicating that the non-empty area corresponding to the first target time unit is used as the residence area. In this case, it may happen that the subject has always been resident in the non-empty area corresponding to the first target time unit, so it is more accurate to determine the subject's first active state as an active resident state. For example, the preset time unit sequence includes 15 time units, the subject A's active area in the first target time unit is area 1, and the active areas in other time units are all empty areas, then the subject A's first active state can be determined as an active resident state, and the active resident state includes residence information indicating area 1 as the residence area.
[0103] In response to the subject's active area in each time unit in the preset time unit sequence being an empty area, the subject's first active state is determined to be an inactive state. If the subject's active area in each time unit is an empty area, it means that there is no confirmation information of the subject, so its first active state can be determined to be an inactive state.
[0104] Combined with the above analysis, determining the accurate first active state of the subject is a very important foundation, which can significantly affect the accuracy of the resident migration information of the target area in the first target time unit. In this embodiment, a comprehensive analysis and accurate speculation are conducted on various possible situations of the subject's active area in the preset time unit sequence, so the determined first active state of the subject is relatively accurate, which helps to improve the accuracy of the resident migration information of the target area in the first target time unit.
[0105] Table 2 - Example table of active states.
[0106]
[0107] In Table 2, "specific time unit" indicates the last time unit in the preset time unit sequence that has at least one time unit corresponding to a non-empty area before the second target time unit. When the active area corresponding to the second target unit is a non-empty area (for example, area 1), the area corresponding to the last time unit in the preset time unit sequence that has at least one time unit corresponding to a non-empty area before the second target time unit must be the same (i.e., area 1). In Table 2, "area 1" and "area 2" are both exemplary, indicating that the two areas are different from each other and can be replaced by any area in the predetermined area set.
[0108] Figure 5 It is a schematic diagram of changing the active state according to some embodiments of the present application. The starting point of the arrow represents the active state in the second target time unit, and the end point of the arrow represents the active state in the first target time unit. Two active states connected by an arrow constitute a change in the active state. For example, if the active state of the subject in the second target time unit is an active resident state, then the subject can be changed to an inactive state or an active migrating state in the first target time unit according to the above embodiment, or it can still remain in an active resident state; if the active state of the subject in the second target time unit is an active migrating state, then the subject can be changed to an active resident state in the first target time unit according to the above embodiment, or it can still remain in an active migrating state; if the active state of the subject in the second target time unit is an inactive state, then the subject can be changed to an active resident state in the first target time unit according to the above embodiment, or it can still remain in an inactive state.
[0109] After the first active state is determined according to the above method, the first target active state may be determined accordingly. In some embodiments, each of the first target active state and the second target active state includes a target active resident state, a target active migration state, a target active migration state, a non-target active state, and an inactive state, and for each subject in the subject cluster, the first target active state of the subject is determined according to the first active state of the subject, including: for each subject in the subject cluster, performing the following steps: in response to the first active state of the subject being an active resident state and the corresponding resident area being the same as the target area, determining the first target active state of the subject as the target active resident state; in response to the first active state of the subject being an active migration state and the corresponding migration area being the same as the target area, determining the first target active state of the subject as the target active migration state; in response to the first active state of the subject being an active migration state and the corresponding migration area being the same as the target area, determining the first target active state of the subject as the target active migration state; in response to the first active state of the subject being an active resident state or an active migration state, and the first active state is not related to the target area, determining the first target active state of the subject as a non-target active state; in response to the first active state of the subject being an inactive state, determining the first target active state of the subject as an inactive state. It should be noted that the non-target active state does not mean that the subject's first active state is an inactive state, but that its first active state has no relationship with the target area.
[0110] In this embodiment, the first target activity state indicates the association of the first activity state in one of the four aspects of residence, migration, non-target activity, and inactivity. Because the residence migration information of the target area in the first target time unit depends on this association, this comprehensive analysis of the first activity state and the target area can improve the accuracy of the residence migration information of the target area in the first target time unit.
[0111] Similarly, the second target activity state is determined according to the second activity state in the same manner.
[0112] like Figure 6 As shown, combined with the implementation method of determining the first target active state and the second target active state in the above embodiments, in some embodiments, the residence migration information of the target area in the first target time unit is determined based on the first target active state and the second target active state of each subject in the subject cluster, including steps S601-S603.
[0113] In step S601, for each subject in the subject cluster, according to the subject's first target active state and second target active state, the state transition mode of the subject from the second target time unit to the first target time unit is determined from a predetermined state transition mode set. The predetermined state transition mode set includes a number of state transition modes, each state transition mode indicates the change between two target active states, that is, the subject transfers from the previous target active state in the state transition mode to the latter target active state. This change is an important indicator to distinguish whether the subject has adopted a resident behavior or a migratory behavior.
[0114] Whether calculating the subject residence amount or the subject embedding amount and subject migration amount, it is necessary to calculate according to the target active state corresponding to the first target time unit and the second target time unit, otherwise the accuracy cannot be guaranteed. If the number of subjects with residence behavior related to the target area is calculated only according to the first target active state corresponding to the first target unit, for example, the number of subjects with active residence state in the first target active state is taken as the number of subjects with residence behavior in the target area in the first target time unit, then the subjects who migrated to the target area in the first target time unit are likely to be counted, but these subjects should be counted as the number of subjects with migration behavior in the target area in the first target time unit, so this will lead to inaccurate calculation. Therefore, in this step, the state transition mode of each subject from the second target time unit to the first target time unit is calculated.
[0115] Step S602, according to the state transition mode of each subject in the subject cluster from the second target time unit to the first target time unit, determine the number of subjects corresponding to at least one state transition mode in the predetermined state transition mode set. After determining the state transition mode of each subject from the second target time unit to the first target time unit, the number of subjects corresponding to the at least one state transition mode can be counted by a summation operation.
[0116] Step S603, according to the number of subjects corresponding to at least one state transition mode in the predetermined state transition mode set, determine the resident migration information of the target area in the first target time unit. The subject resident quantity, subject migration quantity and subject migration quantity correspond to different state transition modes respectively and can be calculated separately as needed.
[0117] In this embodiment, by analyzing the target activity status of each subject in the first target time unit and the second target time unit in detail, the accurate control of the resident migration information of each subject is achieved, which can greatly improve the accuracy of the resident migration information of the target area in the first target time unit. At the same time, there is no need to calculate the target activity status of other time units, so the amount of calculation is reduced to a minimum.
[0118] In order to more accurately determine the resident migration information of the target area in the first target time unit, at least the target activity state corresponding to the first target time unit and the target activity state corresponding to the second target time unit need to be known. As mentioned above, the change of the target activity state from the second target time unit to the first target time unit is a very important influencing factor, and it is necessary to make a comprehensive analysis in this regard.
[0119] The previous embodiment provides a total of 5 types of target active states, so they can be combined into 25 different combinations, each of which is a state transition mode, as shown in Table 3.
[0120] Table 3 - Example table of state transition patterns.
[0121]
[0122]
[0123] Although there are 25 state transition modes in total, some state transition modes are impossible to occur. For example, the state transition mode from active resident state to active input state is theoretically impossible to occur. This state transition mode indicates that the subject in this mode has already resided in the target area in the second target time unit, so it is obviously impossible to migrate to the target area from other areas in the predetermined area set in the first target time unit. The rationality column in Table 3 indicates whether each state transition mode is possible. A rational state transition mode may occur in reality, and an irrational state transition mode may not occur in reality.
[0124] From Table 3, we can find that there are 13 reasonable state transition modes. Figure 7 Shown in. Figure 7 is a schematic diagram of a state transition mode according to some embodiments of the present application.
[0125] like Figure 7 As shown, the starting point of the arrow represents the second target active state, and the end point of the arrow represents the first target active state. The two target active states connected by an arrow constitute a reasonable state transition pattern. For example, the target active migration state and the target active residence state connected by arrow 1 constitute a state transition pattern from the target active migration state to the target active residence state, and the state transition pattern is reasonable. Other state transition patterns are not listed one by one.
[0126] but Figure 7Not all of the state transition modes shown in the figure can be used to determine the resident migration information of the target area in the first target time unit. For example, the state transition mode from the non-target active state to the non-target active state has no value in determining the resident migration information of the target area in the first target time unit, and does not involve the determination of the resident amount, nor does it involve the determination of the in-migration amount and the out-migration amount. It is necessary to screen these 13 state transition modes.
[0127] In some embodiments, the predetermined state transition pattern set includes a first state transition pattern, a second state transition pattern, a third state transition pattern, a fourth state transition pattern, a fifth state transition pattern, a sixth state transition pattern, a seventh state transition pattern, and an eighth state transition pattern, and for each subject in the subject cluster, according to the first target active state and the second target active state of the subject, determining the state transition pattern of the subject from the second target time unit to the first target time unit from the predetermined state transition pattern set, comprising: for each subject in the subject cluster, performing the following steps:
[0128] In response to the subject's first target active state and second target active state both being the target active resident state, the subject's state transition mode from the second target time unit to the first target time unit is determined as the first state transition mode, i.e., the state transition mode from the target active resident state to the target active resident state, which can be used to determine the resident amount of the target area in the first target time unit.
[0129] In response to the first target active state of the subject being the target active outgoing state and the second target active state being the target active resident state, the state transition mode of the subject from the second target time unit to the first target time unit is determined as the second state transition mode, i.e., the state transition mode from the target active resident state to the target active outgoing state, which can be used to determine the outgoing amount of the target area in the first target time unit.
[0130] In response to the first target active state of the subject being the inactive state and the second target active state being the target active resident state, the state transition mode of the subject from the second target time unit to the first target time unit is determined as a third state transition mode, i.e., a state transition mode from the target active resident state to the inactive state, which can be used to determine the migration amount of the target area in the first target time unit.
[0131] In response to the first target activity state of the subject being the target activity resident state and the second target activity state being the target activity migration state, the state transition mode of the subject from the second target time unit to the first target time unit is determined as a fourth state transition mode, i.e., a state transition mode from the target activity migration state to the target activity resident state, which can be used to determine the residence amount of the target area in the first target time unit.
[0132] In response to the first target activity state of the subject being the target activity migration-out state and the second target activity state being the target activity migration-in state, the state transition mode of the subject from the second target time unit to the first target time unit is determined as a fifth state transition mode, i.e., a state transition mode from the target activity migration-in state to the target activity migration-out state, which can be used to determine the migration-out amount of the target area in the first target time unit.
[0133] In response to the first target activity state of the subject being the target activity migration-in state and the second target activity state being the target activity migration-out state, the state transition mode of the subject from the second target time unit to the first target time unit is determined as a sixth state transition mode, i.e., a state transition mode from the target activity migration-out state to the target activity migration-in state, which can be used to determine the migration amount of the target area in the first target time unit.
[0134] In response to the subject's first target active state being the target active migration state and the second target active state being the non-target active state, the subject's state transition mode from the second target time unit to the first target time unit is determined as a seventh state transition mode, i.e., a state transition mode from the non-target active state to the target active migration state, which can be used to determine the migration amount of the target area in the first target time unit.
[0135] In response to the subject's first target active state being the target active resident state and the subject's second target active state being the inactive state, the subject's state transition mode from the second target time unit to the first target time unit is determined as an eighth state transition mode, i.e., a state transition mode from the inactive state to the target active resident state, which can be used to determine the amount of migration into the target area in the first target time unit.
[0136] In this embodiment, 8 state transition modes are selected, and these state transition modes are all necessary data for determining the resident migration information of the target area in the first target time unit. This embodiment provides a reasonable, valuable, and comprehensive method for determining the state transition mode, which helps to improve the accuracy of the resident migration information of the target area in the first target time unit.
[0137] On this basis, the resident migration information of the target area in the first target time unit can be determined based on the eight state transition data. In some embodiments, the resident migration information of the target area in the first target time unit is determined based on the number of entities corresponding to at least one state transition mode in the predetermined state transition mode set, including at least one of the following steps (1)-(3).
[0138] (1) Calculate the sum of the number of subjects corresponding to the first state transition mode and the number of subjects corresponding to the fourth state transition mode to determine the subject residence amount of the target area in the first target time unit. The first state transition mode is a state transition mode from the target active residence state to the target active residence state, indicating that the subject resides in the target area in both the second target time unit and the first target time unit, and can be used to determine the subject residence amount of the target area in the first target unit; the fourth state transition mode is a state transition mode from the target active migration state to the target active residence state, indicating that the subject migrates into the target area in the second target time unit and resides in the target area in the first target time unit, and can also be used to determine the subject residence amount of the target area in the first target unit. Therefore, it is accurate to determine the residence amount of the target area in the first target unit based on the number of subjects corresponding to these two state transition modes. The number of subjects corresponding to the first state transition mode is denoted by N S→S To represent, the number of entities corresponding to the fourth state transition mode is N I→S The main residence time of the target area in the first target time unit is expressed as F S To represent, where S represents the active resident state of the target, and I represents the active migration state of the target, then F S =N S→S +N I→S .
[0139] (2) Calculate the sum of the number of subjects corresponding to the sixth state transition mode, the number of subjects corresponding to the seventh state transition mode, and the number of subjects corresponding to the eighth state transition mode to determine the amount of subject migration in the target area in the first target time unit. The subject migration amount includes a real subject migration amount part and a virtual subject migration amount part. The sixth state transition mode is a state transition mode from the target active migration-out state to the target active migration-in state, indicating that the subject migrates out of the target area in the second target time unit and migrates into the target area in the first target time unit, which can be used as the real subject migration amount part to determine the amount of subject migration in the target area in the first target unit; the seventh state transition mode is a state transition mode from the non-target active state to the target active migration-in state, indicating that the subject is in the active state in the second target time unit but has nothing to do with the target area, and migrates into the target area in the first target time unit, which can be used as the real subject migration amount part to determine the amount of subject migration in the target area in the first target unit; therefore, the sum of the number of subjects corresponding to the sixth state transition mode and the number of subjects corresponding to the seventh state transition mode can be used as the real subject migration amount part. The eighth state transition mode is the state transition mode from the non-target active state to the target active resident state, indicating that the subject is in the active state but has nothing to do with the target area in the second target time unit, and resides in the target area in the first target time unit. It can be used as a virtual subject migration amount part to determine the subject migration amount of the target area in the first target unit. Therefore, it is accurate to determine the subject migration amount of the target area in the first target unit based on the number of subjects corresponding to these three state transition modes. If the number of subjects corresponding to the sixth state transition mode is represented by N o→I To represent, the number of entities corresponding to the seventh state transition mode is N X→I To represent, the number of entities corresponding to the eighth state transition mode is N L→S The amount of main body migration in the target area in the first target time unit is represented by F in To represent, where S represents the active resident state of the target, I represents the active incoming state of the target, O represents the active outgoing state of the target, and L represents the inactive incoming state, then F in =N o→I +N x→I +N L→s .
[0140] (3) Calculate the sum of the number of subjects corresponding to the second state transfer mode, the number of subjects corresponding to the third state transfer mode, and the number of subjects corresponding to the fifth state transfer mode to determine the subject migration volume of the target area in the first target time unit. The subject migration volume also includes the real subject migration volume part and the virtual subject migration volume part. The second state transition mode is a state transition mode from the target active resident state to the target active emigration state, indicating that the subject resides in the target area in the second target time unit and migrates out of the target area in the first target time unit, which can be used as a real subject migration amount part to determine the subject migration amount of the target area in the first target unit; the third state transition mode is a state transition mode from the target active resident state to the inactive state, indicating that the subject resides in the target area in the second target time unit and has no active area in the first target time unit, which can be used as a virtual subject migration amount part to determine the subject migration amount of the target area in the first target unit; the fifth state transition mode is a state transition mode from the target active migration state to the target active migration state, indicating that the subject migrates into the target area in the second target time unit and migrates out of the target area in the first target time unit, which can be used as a real subject migration amount part to determine the subject migration amount of the target area in the first target unit. That is, the sum of the number of subjects corresponding to the second state transition mode and the number of subjects corresponding to the fifth state transition mode can be used as the real subject migration amount part. Therefore, it is accurate to determine the subject migration amount of the target area in the first target unit according to the number of subjects corresponding to these three state transition modes. If the number of entities corresponding to the second state transition mode is N S→O To represent, the number of entities corresponding to the third state transition mode is N S→L To represent, the number of entities corresponding to the fifth state transition mode is N I→o The amount of main migration out of the target area in the first target time unit is expressed as F out To represent, where S represents the active resident state of the target, I represents the active incoming state of the target, O represents the active outgoing state of the target, and L represents the inactive incoming state, then F out =N S→O +N I→O +N S→L .
[0141] In addition, based on the embodiments of the present application, the resident migration information of the target area in the first target unit can also be determined in other ways. In some embodiments, the resident migration information of the target area in the first target time unit is determined according to the number of entities corresponding to at least one state transition mode in a predetermined state transition mode set, including the following steps.
[0142] First, the subject migration amount and subject residence amount of the target area in the second target time unit are obtained. In this step, the subject migration amount and subject residence amount of the target area in the second target time unit are determined in the same way as the subject migration amount and subject residence amount of the target area in the first target time unit.
[0143] Then, the sum of the number of subjects corresponding to the second state transfer mode, the number of subjects corresponding to the third state transfer mode, and the number of subjects corresponding to the fifth state transfer mode is calculated to determine the amount of subjects migrating out of the target area in the first target time unit.
[0144] Finally, the subject residence amount of the target area in the first target time unit is determined by subtracting the subject migration amount of the target area in the first target time unit from the sum of the subject migration amount and the subject residence amount of the target area in the second target time unit.
[0145] In this embodiment, the subject migration amount and subject residence amount of the target area in the first target time unit can be determined according to the subject migration amount and subject residence amount of the target area in the second target time unit because of the following reasons.
[0146] First, for the time unit before the second target time unit and the second target time unit (denoted by T-1), the number of subjects in the first state transition mode (i.e., from the target active resident state to the target active resident state) (denoted by ), the number of subjects in the fourth state transition mode (i.e., from the target active migration state to the target active residence state) (denoted by ), the number of subjects in the eighth state transition mode (i.e., from the inactive state to the target active resident state) (denoted by The sum of the number of subjects (denoted by ) in the first state transition mode (i.e., from the target active resident state to the target active resident state) for the second target time unit and the first target time unit (denoted by T) should be equal to the number of subjects (denoted by ), the number of subjects in the second state transition mode (i.e., from the target active resident state to the target active exit state) (denoted by ), the number of subjects in the third state transition mode (i.e., from the target active resident state to the inactive state) (denoted by represents the sum of ), see formula (3).
[0147]
[0148] That is, the number of subjects that transfer from the non-target active outgoing state to the target active resident state in the second target time unit should be equal to the number of subjects that transfer from the target active resident state to the non-target active incoming state in the first target time unit.
[0149] Secondly, for the time unit before the second target time unit and the second target time unit, the number of subjects in the sixth state transition mode (i.e., from the target active migration-out state to the target active migration-in state) (in terms of ), the number of subjects in the seventh state transition mode (i.e., from the non-target active state to the target active migration state) (denoted by denoted by ), should be equal to the number of subjects (expressed by ) in the fourth state transition mode (i.e., from the target active migration state to the target active residence state) for the second target time unit and the first target time unit. ), the number of subjects in the fifth state transition mode (i.e., from the target active migration state to the target active migration state) (denoted by represents the sum of ), see formula (4).
[0150]
[0151] That is to say, the number of subjects that transfer from the target active migration-out state and the non-target active state to the active migration-in state in the second target time unit should be equal to the number of subjects that transfer from the target active migration-in state to the target active resident state and the target active migration-out state in the first target time unit.
[0152] use represents the residence time of the target area in the first target time unit, then there is formula (5):
[0153]
[0154] Formula (5) can be decomposed as follows.
[0155]
[0156]
[0157]
[0158]
[0159]
[0160] That is, the resident amount of the first target time unit = the resident amount of the second target data unit + the migration amount of the second target data unit - the migration amount of the first target time unit. The accuracy of the calculation steps in this embodiment has been proved.
[0161] In this embodiment, firstly, when knowing the resident amount, the in-migration amount of the target area in the second target time unit and the out-migration amount of the target area in the first target time unit, when determining the resident amount of the target area in the first target time unit, there is no need to calculate the sum of the number of subjects corresponding to the first state transfer mode and the number of subjects corresponding to the fourth state transfer mode, and the resident amount of the target area in the first target time unit can be directly derived based on the three known quantities, thereby saving a lot of computing resources and ensuring accuracy at the same time; secondly, because the resident migration information of the subject cluster in the first target time unit is partially calculated based on the second target active state of the subject cluster, that is, there is a certain correlation between the resident migration information of the subject cluster in the first target time unit and the resident migration information of the subject cluster in the second target time unit, which means that the resident migration information in the second target time unit can theoretically be partially applied to calculate the resident migration information in the first target time unit. In fact, this association relationship is actually the association relationship embodied by formula (3) and formula (4). This embodiment makes full use of this association relationship in the above-mentioned recursive process, which shows that there is no conflict or contradiction in the logical process of calculating the resident migration information according to the embodiment of the present application. Therefore, it is possible to recursively infer the data of the first target time unit based on the data of the second target time unit, which shows that this embodiment and other embodiments are logically self-consistent.
[0162] In addition, according to some embodiments of the present application, a method for calculating the migration amount between regions is also provided. In some embodiments, the method further includes the following steps.
[0163] First, a set of migrating subjects is selected from the subject cluster, wherein the first active state of each subject in the migrating subject set is an active migratory state. Then, a set of migration area pairs is determined based on a predetermined area set, wherein each area in the migration area pair set includes a first non-empty area and a second non-empty area that are different from each other in the predetermined area set. Then, for each area pair in the migration area pair set, according to the active migration state of each subject in the migration subject set, a subset of migrating subjects corresponding to the area pair is screened from the migration subject set, wherein the incoming area in the migration state of each subject in the migration subject subset is the first non-empty area and the outgoing area is the second non-empty area. Finally, for each area pair in the migration area pair set, the number of subjects in the migration subject subset corresponding to the area pair is counted as the amount of subject migration from the first non-empty area to the second non-empty area in the first target time unit.
[0164] Because the above embodiment has determined the first active state of each subject, when counting the migration amount between regions, it is only necessary to query the subjects in the subject cluster that migrated from the first non-empty region to the second non-empty region and add them up.
[0165] Table 4 - Example statistics of migration volumes.
[0166] Place of migration Place of migration Migration Region 1 Area 2 1245 Area 3 Region 4 1236
[0167] According to some embodiments of the present application, the migration volume statistics table shown in Table 4 can be obtained to provide a reference for other applications.
[0168] Figure 8 It is an exemplary structural block diagram of a resident migration data mining device 800 according to some embodiments of the present application. The resident migration data mining device 800 includes: an acquisition module 801, an active area determination module 802, a target active state determination module 803, and a statistical module 804. The acquisition module 801 is configured to acquire confirmation information of a subject cluster in each time unit of a preset time unit sequence, and the subject cluster includes multiple subjects; the active area determination module 802 is configured to determine the active area distribution of the subject cluster in each time unit from a predetermined area set based on the confirmation information of the subject cluster in each time unit of the preset time unit sequence, and the predetermined area set includes a target area; the target active state determination module 803 is configured to determine the first target active state and the second target active state of the subject cluster according to the active area distribution of the subject cluster in each time unit, and the first target active state indicates that the subject cluster is in the first target time unit. Relative to the changes in the distribution of active areas of at least one adjacent previous time unit and its association with the target area, the second target active state indicates the changes in the distribution of active areas of the main cluster in the second target time unit relative to at least one adjacent previous time unit and its association with the target area, the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is the previous time unit adjacent to the first target time unit in the preset time unit sequence; a statistical module 804 is configured to determine the resident migration information of the target area in the first target time unit based on the first target active state and the second target active state of the main cluster.
[0169] It should be noted that the various modules described above can be implemented in software or hardware or a combination of the two. Multiple different modules can be implemented in the same software or hardware structure, or one module can be implemented by multiple different software or hardware structures.
[0170] In the resident migration data mining device according to some embodiments of the present application, in the resident migration data mining process, the active area distribution of the main cluster is first accurately determined based on the confirmation information, and then the target active state of the main cluster related to the target area is determined using the active area distribution, and the resident migration information of the target area is calculated based on the transfer of the target active state of each spatial subject between adjacent time units, thereby ensuring the accuracy of the resident volume and migration volume obtained and effectively applying them to respective application scenarios (such as smart logistics, smart cities, smart transportation, etc.).
[0171] Fig. 9 An example system 900 is illustrated, which includes an example computing device 910 that represents one or more systems and / or devices that can implement the various methods described herein. Computing device 910 can be, for example, a server of a service provider, a device associated with a server, a system on a chip, and / or any other suitable computing device or computing system. Figure 7 The depicted resident migration data mining apparatus 800 may take the form of a computing device 910. Alternatively, the resident migration data mining apparatus 800 may be implemented as a computer program in the form of an application 916.
[0172] The example computing device 910 as shown includes a processing system 911, one or more computer-readable media 912, and one or more I / O interfaces 913 that are communicatively coupled to each other. Although not shown, the computing device 910 may also include a system bus or other data and command transmission system that couples various components to each other. The system bus may include any one or combination of different bus structures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and / or a processor or local bus utilizing any one of a variety of bus architectures. Various other examples are also contemplated, such as control and data lines.
[0173] Processing system 911 represents the function of performing one or more operations using hardware. Therefore, processing system 911 is illustrated as including hardware elements 914 that can be configured as processors, functional blocks, etc. This can include other logic devices implemented in hardware as application-specific integrated circuits or formed using one or more semiconductors. Hardware elements 914 are not limited by the materials from which they are formed or the processing mechanisms used therein. For example, a processor can be composed of (multiple) semiconductors and / or transistors (e.g., electronic integrated circuits (ICs)). In such a context, processor executable instructions can be electronic executable instructions.
[0174] Computer-readable media 912 is illustrated as including memory / storage 915. Memory / storage 915 represents memory / storage capacity associated with one or more computer-readable media. Memory / storage 915 may include volatile media (such as random access memory (RAM)) and / or non-volatile media (such as read-only memory (ROM), flash memory, optical disks, magnetic disks, etc.). Memory / storage 915 may include fixed media (e.g., RAM, ROM, fixed hard drives, etc.) and removable media (e.g., flash memory, removable hard drives, optical disks, etc.). Computer-readable media 912 may be configured in various other ways as further described below.
[0175] One or more I / O interfaces 913 represent functionality that allows a user to input commands and information to the computing device 910 using various input devices and optionally also allows information to be presented to the user and / or other components or devices using various output devices. Examples of input devices include a keyboard, a cursor control device (e.g., a mouse), a microphone (e.g., for voice input), a scanner, touch functionality (e.g., a capacitive or other sensor configured to detect physical touch), a camera (e.g., which can use visible or invisible wavelengths (such as infrared frequencies) to detect motion that does not involve touch as gestures), and the like. Examples of output devices include a display device, a speaker, a printer, a network card, a tactile response device, and the like. Thus, the computing device 910 can be configured in various ways as further described below to support user interaction.
[0176] The computing device 910 also includes an application 916. The application 916 may be, for example, a software instance that hosts the migration data mining apparatus 800 and, in combination with other elements in the computing device 910, implements the techniques described herein.
[0177] Various techniques may be described herein in the general context of software hardware elements or program modules. Generally, these modules include routines, programs, objects, elements, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The terms "module", "function" and "component" as used herein generally represent software, firmware, hardware or a combination thereof. The features of the techniques described herein are platform-independent, meaning that these techniques can be implemented on a variety of computing platforms with a variety of processors.
[0178] An implementation of the described modules and techniques may be stored on or transmitted across some form of computer-readable media. Computer-readable media may include a variety of media accessible by computing device 910. By way of example and not limitation, computer-readable media may include “computer-readable storage media” and “computer-readable signal media.”
[0179] In contrast to a simple signal transmission, carrier wave, or signal itself, "computer-readable storage medium" refers to a medium and / or device capable of persistently storing information, and / or a tangible storage device. Therefore, a computer-readable storage medium refers to a non-signal-bearing medium. Computer-readable storage media include hardware such as volatile and non-volatile, removable and non-removable media and / or storage devices implemented in a method or technology suitable for storing information (such as computer-readable instructions, data structures, program modules, logic elements / circuits, or other data). Examples of computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage device, hard disk, cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or other storage device, tangible medium, or article of manufacture suitable for storing desired information and accessible by a computer.
[0180] "Computer-readable signal media" refers to signal-bearing media that is configured to send instructions to the hardware of the computing device 910, such as via a network. Signal media typically can embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, data signal, or other transport mechanism. Signal media also include any information transfer media. The term "modulated data signal" refers to a signal that has one or more of its characteristics set or changed so as to encode information into the signal. By way of example and not limitation, communication media include wired media such as a wired network or direct connection and wireless media such as acoustic, RF, infrared, and other wireless media.
[0181] As before, hardware elements 914 and computer-readable media 912 represent instructions, modules, programmable device logic and / or fixed device logic implemented in hardware form, which can be used to implement at least some aspects of the technology described herein in some embodiments. Hardware elements can include integrated circuits or systems on a chip, application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs) and other implementations in silicon or components of other hardware devices. In this context, hardware elements can be used as processing devices for executing program tasks defined by instructions, modules and / or logic embodied by hardware elements, and hardware devices for storing instructions for execution, such as the computer-readable storage media described previously.
[0182] The aforementioned combination may also be used to implement various techniques and modules herein. Therefore, software, hardware or program modules and other program modules may be implemented as one or more instructions and / or logic embodied on some form of computer-readable storage medium and / or by one or more hardware elements 914. The computing device 910 may be configured to implement specific instructions and / or functions corresponding to the software and / or hardware modules. Therefore, for example, by using a computer-readable storage medium and / or hardware element 914 of a processing system, a module may be implemented as a module executable by the computing device 910 as software, at least in part, in hardware. Instructions and / or functions may be executable / operable by one or more articles (e.g., one or more computing devices 910 and / or processing systems 911) to implement the techniques, modules and examples described herein.
[0183] In various embodiments, computing device 910 can adopt various different configurations. For example, computing device 910 can be implemented as a computer-type device including a personal computer, a desktop computer, a multi-screen computer, a laptop computer, a netbook, etc. Computing device 910 can also be implemented as a mobile device-type device including mobile devices such as mobile phones, portable music players, portable game devices, tablet computers, multi-screen computers, etc. Computing device 910 can also be implemented as a television-type device, which includes a device with or connected to a generally larger screen in a casual viewing environment. These devices include televisions, set-top boxes, game consoles, etc.
[0184] The techniques described herein may be supported by these various configurations of computing device 910 and are not limited to the specific examples of the techniques described herein. Functionality may also be implemented in whole or in part on the "cloud" 920 by using a distributed system, such as through a platform 922 as described below.
[0185] Cloud 920 includes and / or represents a platform 922 for resources 924. Platform 922 abstracts the underlying functionality of the hardware (e.g., servers) and software resources of cloud 920. Resources 924 may include applications and / or data that may be used when executing computer processing on a server remote from computing device 910. Resources 924 may also include services provided over the Internet and / or over a subscriber network such as a cellular or Wi-Fi network.
[0186] The platform 922 may abstract resources and functionality to connect the computing device 910 with other computing devices. The platform 922 may also be used to abstract hierarchies of resources to provide hierarchies of corresponding levels of demand encountered for resources 924 implemented via the platform 922. Thus, in an interconnected device embodiment, the implementation of the functionality described herein may be distributed throughout the system 900. For example, functionality may be implemented in part on the computing device 910 and through the platform 922 that abstracts the functionality of the cloud 920.
[0187] It should be understood that, for the sake of clarity, embodiments of the present application are described with reference to different functional units. However, it will be apparent that, without departing from the present application, the functionality of each functional unit can be implemented in a single unit, in multiple units or as a part of other functional units. For example, the functionality that is described as being performed by a single unit can be performed by multiple different units. Therefore, reference to a specific functional unit is only considered as a reference to the appropriate unit for providing the described functionality, rather than indicating a strict logical or physical structure or organization. Therefore, the present application can be implemented in a single unit, or can be physically and functionally distributed between different units and circuits.
[0188] Although the present application has been described in conjunction with some embodiments, it is not intended to be limited to the specific form set forth herein. On the contrary, the scope of the present application is limited only by the appended claims. Additionally, although individual features may be included in different claims, these may possibly be advantageously combined, and the inclusion in different claims does not imply that the combination of features is not feasible and / or advantageous. The order of features in the claims does not imply any specific order in which the features must work. In addition, in the claims, the word "comprising" does not exclude other elements, and the term "one" or "an" does not exclude a plurality. The figure marks in the claims are provided only as clear examples and should not be interpreted as limiting the scope of the claims in any way.
[0189] It is understandable that in the specific implementation of this application, the subject's confirmation information (such as spatiotemporal trajectory information) and other related data are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.
Claims
1. A method for mining resident migration data. include: Acquire confirmation information of a subject cluster in each time unit of a preset time unit sequence, wherein the subject cluster includes a plurality of subjects; Based on confirmation information of the subject cluster in each time unit of a preset time unit sequence, determining the active area distribution of the subject cluster in each time unit from a predetermined area set, wherein the predetermined area set includes a target area; According to the active area distribution of the main cluster in each time unit, determine the first target active state and the second target active state of the main cluster, the first target active state indicates the change of the active area distribution of the main cluster in the first target time unit relative to at least one adjacent previous time unit and its association with the target area, the second target active state indicates the change of the active area distribution of the main cluster in the second target time unit relative to at least one adjacent previous time unit and its association with the target area, the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is the previous time unit adjacent to the first target time unit in the preset time unit sequence; The resident migration information of the target area in the first target time unit is determined according to the first target active state and the second target active state of the subject cluster.
2. The method according to claim 1, wherein the predetermined area set includes an empty area and at least one non-empty area, And for each subject in the subject cluster, based on the confirmation information of the subject in each time unit of the preset time unit sequence, the active area of the subject in each time unit is determined from a predetermined area set, include: Based on the contour information of the at least one non-empty area in the predetermined area set, construct a spatial index corresponding to the predetermined area set; For each subject in the subject cluster and each time unit in the preset time unit sequence, in response to the confirmation information of the subject in the time unit being not empty, extract at least one spatiotemporal stay point from the confirmation information and obtain the position information and corresponding timestamp of each of the spatiotemporal stay points; For each spatiotemporal stay point of each subject in the subject cluster in each time unit, based on the position information of the spatiotemporal stay point and the spatial index, determine the non-empty area where the spatiotemporal stay point is located from the predetermined area set; For each time unit in the predetermined time unit sequence, dividing the time unit into a plurality of time windows to form a time window sequence; For each subject in the subject cluster, based on the non-empty region where the subject is located at each spatiotemporal stop point of each time unit and the corresponding timestamp, determine the non-empty region where the subject is located in each time window in the time window sequence of the time unit from the predetermined region set; For each subject in the subject cluster, the active area of the subject in the time unit is determined from the predetermined area set according to the non-empty area where the subject is located in each time window in the time window sequence of each time unit.
3. The method according to claim 2, wherein for each subject in the subject cluster, the active area of the subject in the time unit is determined from the predetermined area set according to the non-empty area where the subject is located in each time window in the time window sequence of each time unit, include: For each time window sequence of each time unit, determine the activity weight corresponding to each time window in the time window sequence in chronological order, wherein for at least a portion of the time windows in the time window sequence, the activity weight corresponding to the previous time window is less than the activity weight corresponding to the subsequent time window; For each subject and each time unit in the subject cluster, the activity weights of different time windows of the time unit corresponding to the same non-empty area where the subject is located are added together to calculate the activity of each non-empty area where the subject is located in each time window in the time window sequence of the time unit; For each subject in the subject cluster, according to the activity of each non-empty area where the subject is located in each time window of the time window sequence of each time unit, the active area of the subject in the time unit is determined from the non-empty areas.
4. The method according to claim 2, wherein for each subject in the subject cluster, based on the non-empty area where the subject is located at each spatiotemporal stop point of each time unit and the corresponding timestamp, the non-empty area where the subject is located in each time window in the time window sequence of the time unit is determined from the predetermined area set, include: For each subject in the subject cluster and each time unit in the time unit sequence, perform the following steps: Based on the non-empty region where each spatiotemporal stop point is located and the corresponding timestamp, determining at least one matching time window from the time window sequence that matches one or more spatiotemporal stop points and the one or more non-empty regions where each of the spatiotemporal stop points is located; For each matching time window in the at least one matching time window, according to the number of spatiotemporal stay points corresponding to each of the one or more non-empty regions matched therewith, determine the non-empty region where the subject is located in the matching time window from the one or more non-empty regions; In response to the time window sequence including at least one non-matching time window other than the at least one matching time window, for each non-matching time window, the non-empty area where the subject is located in the non-matching time window is determined based on the non-empty area corresponding to the matching time window adjacent to the non-matching time window in the time window sequence.
5. The method according to claim 1, wherein the first target active state and the second target active state of the subject cluster are determined according to the active area distribution of the subject cluster in each time unit, include: for each subject in the subject cluster, determining a first active state and a second active state of the subject according to an active area of the subject in each time unit in a preset time unit sequence; For each subject in the subject cluster, a first target activity state of the subject is determined according to the first activity state of the subject, and a second target activity state of the subject is determined according to the second activity state of the subject.
6. The method according to claim 5, wherein each of the first active state and the second active state comprises an active resident state, an active migrating state, and an inactive state; And for each subject in the subject cluster, determining the first active state and the second active state of the subject according to the active area of each time unit in the preset time unit sequence of the subject, includes: for each subject in the subject cluster, performing the following steps: In response to the active area of the subject in the first target time unit and the active area in the second target time unit being the same non-empty area, determining the first activity state of the subject as an active residency state, the active residency state including residency location information indicating the same non-empty area as a residency area; In response to the active area of the subject in the first target time unit and the active area in the second target time unit being different non-empty areas, determining the first active state of the subject as an active migration state, the active migration state including migration location information indicating that the non-empty area corresponding to the first target time unit is used as a migration-in area and the non-empty area corresponding to the second target time unit is used as a migration-out area; In response to the active area of the subject in the first target time unit being an empty area and the active area in the second target time unit being a non-empty area, determining the first active state of the subject as an active resident state, the active resident state including resident location information indicating that the non-empty area corresponding to the second target time unit is a resident area; In response to the active area of the subject in the second target time unit being an empty area, the active area of the subject in the first target time unit being a non-empty area, there being at least one time unit corresponding to the non-empty active area before the second target time unit in the preset time unit sequence, and the active area corresponding to the last time unit in the at least one time unit and the active area corresponding to the first target time unit being the same non-empty area, the first active state of the subject is determined as an active resident state, the active resident state including resident location information indicating the same non-empty area as a resident area; In response to the active area of the subject in the second target time unit being an empty area, the active area of the subject in the first target time unit being a non-empty area, there being at least one time unit corresponding to the non-empty active area before the second target time unit in the preset time unit sequence, and the active area corresponding to the last time unit in the at least one time unit and the active area corresponding to the first target time unit being non-empty areas different from each other, the first active state of the subject is determined as an active migration state, the active migration state including migration location information indicating that the non-empty area corresponding to the first target time unit is a migration-in area and the non-empty area corresponding to the last time unit is a migration-out area; In response to the active area of the subject in the first target time unit and the active area in the second target time unit being both empty areas, and there being at least one time unit corresponding to a non-empty active area before the second target time unit in the preset time unit sequence, the first active state of the subject is determined as an active resident state, the active resident state including resident location information indicating that the non-empty area corresponding to the last time unit in the at least one unit is used as a resident area; In response to the active area of the subject in the first target time unit being a non-empty area, and the active areas corresponding to each time unit in the preset time unit sequence except the first target time unit being an empty area, determining the first active state of the subject as an active resident state, the active resident state including resident location information indicating that the non-empty area corresponding to the first target time unit is a resident area; In response to the active area of the subject in each time unit in the preset time unit sequence being an empty area, the first active state of the subject is determined to be an inactive state.
7. The method according to claim 6, in, Each of the first target active state and the second target active state includes a target active resident state, a target active migrated state, a target active migrated state, a non-target active state, and an inactive state, and The step of determining the first target active state of each subject in the subject cluster according to the first active state of the subject includes: performing the following steps for each subject in the subject cluster: In response to the first activity state of the subject being an active dwell state and the corresponding dwell area being the same as the target area, determining the first target activity state of the subject as a target active dwell state; In response to the first activity state of the subject being an active migration state and the corresponding migration-in region being the same as the target region, determining the first target activity state of the subject as a target active migration-in state; In response to the first activity state of the subject being an active migration state and the corresponding migration-out region being the same as the target region, determining the first target activity state of the subject as a target active migration-out state; In response to the first activity state of the subject being an active resident state or an active migratory state, and the first activity state being irrelevant to the target area, determining the first target activity state of the subject as a non-target activity state; In response to the first activity state of the subject being an inactive state, the first target activity state of the subject is determined to be an inactive state.
8. The method according to claim 7, wherein the resident migration information of the target area in the first target time unit is determined according to the first target active state and the second target active state of each subject in the subject cluster, include: For each subject in the subject cluster, determining a state transition mode of the subject from a second target time unit to a first target time unit from a predetermined state transition mode set according to a first target active state and a second target active state of the subject; Determine the number of subjects corresponding to at least one state transition mode in the predetermined state transition mode set according to the state transition mode of each subject in the subject cluster from the second target time unit to the first target time unit; The resident migration information of the target area in the first target time unit is determined according to the number of entities corresponding to at least one state transition mode in the predetermined state transition mode set.
9. The method according to claim 8, wherein the predetermined state transfer mode set includes a first state transfer mode, a second state transfer mode, a third state transfer mode, a fourth state transfer mode, a fifth state transfer mode, a sixth state transfer mode, a seventh state transfer mode and an eighth state transfer mode, and in, The step of determining, for each subject in the subject cluster, a state transition mode of the subject from the second target time unit to the first target time unit from a predetermined state transition mode set according to the first target active state and the second target active state of the subject, comprises: For each subject in the subject cluster, perform the following steps: In response to the first target active state and the second target active state of the subject both being the target active resident state, determining the state transition mode of the subject from the second target time unit to the first target time unit as the first state transition mode; In response to the first target activity state of the subject being the target activity-emigration state and the second target activity state being the target activity-residence state, determining the state transition mode of the subject from the second target time unit to the first target time unit as the second state transition mode; In response to the first target activity state of the subject being an inactive state and the second target activity state being a target active resident state, determining a state transition mode of the subject from the second target time unit to the first target time unit as a third state transition mode; In response to the first target activity state of the subject being the target active resident state and the second target activity state being the target active migrated state, determining the state transition mode of the subject from the second target time unit to the first target time unit as a fourth state transition mode; In response to the first target activity state of the subject being a target activity transition-out state and the second target activity state being a target activity transition-in state, determining a state transition mode of the subject from the second target time unit to the first target time unit as a fifth state transition mode; In response to the first target activity state of the subject being the target activity migration-in state and the second target activity state being the target activity migration-out state, determining the state transition mode of the subject from the second target time unit to the first target time unit as a sixth state transition mode; In response to the first target active state of the subject being the target active transition state and the second target active state being the non-target active state, determining the state transition mode of the subject from the second target time unit to the first target time unit as a seventh state transition mode; In response to the first target activity state of the subject being the target active stay state and the second target activity state being the inactive state, a state transition mode of the subject from the second target time unit to the first target time unit is determined as an eighth state transition mode.
10. The method according to claim 9, in, The resident migration information includes the subject resident volume, subject migration volume and subject migration volume.
11. The method according to claim 10, in, The step of determining the resident migration information of the target area in the first target time unit according to the number of entities corresponding to at least one state transition mode in the predetermined state transition mode set includes at least one of the following steps: Calculating the sum of the number of subjects corresponding to the first state transition mode and the number of subjects corresponding to the fourth state transition mode to determine the subject residence amount of the target area in the first target time unit; Calculating the sum of the number of subjects corresponding to the sixth state transfer mode, the number of subjects corresponding to the seventh state transfer mode, and the number of subjects corresponding to the eighth state transfer mode to determine the amount of subject migration to the target area in the first target time unit; The sum of the number of subjects corresponding to the second state transfer mode, the number of subjects corresponding to the third state transfer mode and the number of subjects corresponding to the fifth state transfer mode is calculated to determine the amount of subjects migrating out of the target area in the first target time unit.
12. The method according to claim 10, in, The determining, according to the number of entities corresponding to at least one state transition mode in the predetermined state transition mode set, the resident migration information of the target area in the first target time unit includes: Obtaining the subject migration volume and subject residence volume of the target area in the second target time unit; Calculating the sum of the number of subjects corresponding to the second state transfer mode, the number of subjects corresponding to the third state transfer mode, and the number of subjects corresponding to the fifth state transfer mode to determine the amount of subjects moving out of the target area in the first target time unit; The subject residence amount of the target area in the first target time unit is determined by subtracting the subject migration amount of the target area in the first target time unit from the sum of the subject migration amount and the subject residence amount of the target area in the second target time unit.
13. The method according to claim 6, further comprising: include: Selecting a migration subject set from the subject cluster, wherein the first active state of each subject in the migration subject set is an active migration state; Determine a migration region pair set according to the predetermined region set, wherein each region in the migration region pair set includes a first non-empty region and a second non-empty region that are different from each other in the predetermined region set; For each region pair in the migration region pair set, according to the active migration state of each subject in the migration subject set, a migration subject subset corresponding to the region pair is selected from the migration subject set, wherein the migration state of each subject in the migration subject subset has an incoming region as the first non-empty region and an outgoing region as the second non-empty region; For each region pair in the migration region pair set, the number of subjects in the migration subject subset corresponding to the region pair is counted as the subject migration amount from the first non-empty region to the second non-empty region in the first target time unit.
14. A resident migration data mining device, include: an acquisition module configured to acquire confirmation information of a subject cluster in each time unit of a preset time unit sequence, wherein the subject cluster includes a plurality of subjects; an active area determination module, configured to determine the active area distribution of the subject cluster in each time unit from a predetermined area set based on confirmation information of the subject cluster in each time unit of a preset time unit sequence, wherein the predetermined area set includes a target area; a target active state determination module, configured to determine a first target active state and a second target active state of the subject cluster according to the active area distribution of the subject cluster in each time unit, wherein the first target active state indicates a change in the active area distribution of the subject cluster in the first target time unit relative to at least one adjacent previous time unit and its association with the target area, and the second target active state indicates a change in the active area distribution of the subject cluster in the second target time unit relative to at least one adjacent previous time unit and its association with the target area, the first target time unit is the last time unit in the preset time unit sequence, and the second target time unit is a previous time unit adjacent to the first target time unit in the preset time unit sequence; The statistical module is configured to determine the resident migration information of the target area in the first target time unit according to the first target activity state and the second target activity state of the subject cluster.
15. A computing device, include: a memory configured to store computer-executable instructions; A processor configured to perform a method according to any one of claims 1-13 when the computer executable instructions are executed by the processor.
16. A computer-readable storage medium storing computer-executable instructions, which when executed implement the method according to any one of claims 1 to 13.
17. A computer program product comprising a computer program which, when executed, implements the steps of the method according to any one of claims 1 to 13.
